Zhuosheng Zhang

Selected Publications

• MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft
  Tianjie Ju, Yueqing Sun, Zheng Wu, Wei Zhang, Yaqi Huo, Xi Su, Qi Gu*, Xunliang Cai, Gongshen Liu, Zhuosheng Zhang*.
  EMNLP, 2026
  [PDF] [Abstract]
  MineExplorer

  Multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and action generation. However, their ability to sustain exploration in dynamic open worlds remains unclear. Existing embodied and game-based benchmarks often compress interaction into short-horizon tasks or entangle success with domain-specific game mechanics. In this paper, we introduce MineExplorer benchmark for evaluating open-world exploration capabilities of MLLM agents in Minecraft. We first filter atomic tasks whose solutions rely heavily on Minecraft-specific knowledge to better reflect general open-world reasoning. Then we organize the benchmark around a ReAct-style capability formulation and compose atomic tasks into implicit multi-hop tasks. To further construct reliable instances, MineExplorer uses a multi-agent synthesis workflow that jointly designs task graphs, sandbox scenes, and rule-based milestone evaluators. Human evaluation shows that the multi-agent synthesis workflow produces significantly more reliable instances than a single-agent baseline. Experiments with advanced MLLM agents show that open-world exploration remains challenging, as strong models can handle many single-hop tasks but degrade sharply when hidden prerequisites must be coordinated over longer trajectories. Further analysis finds that task difficulty tracks agent completion, and larger models or thinking modes do not consistently translate into better performance.

• GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
  Haodong Zhao, Tianyi Xu, Tianhang Zhao, Zhuosheng Zhang*, Gongshen Liu*.
  EMNLP, 2026
  [PDF] [Abstract]
  GradSentry

  Fine-tuning Large Language Models with untrusted data exposes models to backdoor attacks, where poisoned samples cause targeted misbehavior. Existing sample-filtering defenses rely on clustering, which requires sufficient data and can fail at extreme poison ratios. We propose GradSentry({Grad}ient {Sentry}), a backdoor sample filtering method based on the spectral entropy of per-sample gradients. Our key finding is that poisoned samples produce gradients with higher spectral entropy compared to clean samples. GradSentry captures output-altering backdoor signatures using per-sample gradient spectra, avoiding pairwise sample comparisons and clustering during feature construction. Importantly, our method is training-agnostic: it works for both parameter-efficient fine-tuning methods like LoRA and full-parameter tuning, as the gradient analysis operates independently of which parameters are being updated during training. GradSentry requires no clustering, operates effectively across all poison ratios (1%--90%), and introduces minimal computational overhead (20--50ms per sample for a 7B model). Evaluation on four QA datasets and four attack types demonstrates the effectiveness of spectral entropy for backdoor detection.

• Causal Probing for Internal Visual Representations in Multimodal Large Language Models
  Zehao Deng, Tianjie Ju, Zheng Wu, Liangbo He, Jun Lan*, Huijia Zhu, Weiqiang Wang, Zhuosheng Zhang*.
  EMNLP, 2026
  [PDF] [Abstract]

  Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode and ground distinct visual concepts remain poorly understood. To bridge this gap, we propose a causal framework based on activation steering to actively probe and manipulate internal visual representations. Through systematic intervention across four visual concept categories, our results reveal a divergence in concept encoding: entities exhibit distinct localized memorization, whereas abstract concepts are globally distributed across the network. Critically, this divergence uncovers a mechanistic driver of scaling laws: increasing model depth is indispensable for encoding distributed and complex abstract concepts, whereas entity localization remains remarkably invariant to scale. Furthermore, reverse steering uncovers that blocking explicit output triggers a surge in latent activations, exposing a compensatory mechanism between perception and generation. Finally, extending our analysis to visual reasoning, we expose a disconnect between perception and reasoning although MLLMs successfully recognize geometric relations, they treat them merely as static visual features, failing to trigger the procedural execution necessary for abstract problem-solving.

• Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents
  Zhaoyuan Huang, Tianjie Ju, Pengzhou Cheng, Zheng Wu, Yansi Li, Chuanbiao Song, Jun Lan*, Huijia Zhu, Weiqiang Wang, Zhuosheng Zhang*.
  EMNLP, 2026
  [PDF] [Abstract]
  ConflictGuard

  Graphical user interface (GUI) agents are increasingly used to execute natural-language instructions on user interfaces, yet real users may issue infeasible instructions due to benign mistakes. A reliable agent should not only know how to act, but also when not to act. In this work, we introduce ConflictGUI, a benchmark covering instruction-internal conflicts and instruction-GUI context conflicts to study conflict-aware termination. Our evaluation reveals severe execution-biased over-compliance: agents that perform well on feasible tasks often continue to execute blindly under conflicting instructions. To mitigate this behavior, we propose ConflictGuard, an inference-time framework that aligns an agent's feasibility awareness with its action generation. ConflictGuard contains two coupled components: a feasibility verification protocol that guides the agent to assess instruction logic and GUI-side evidence before acting, and a conditional action modulation mechanism that steers agent's over-compliance into termination-oriented behavior. Experiments across five widely-used agents demonstrate that ConflictGuard improves average conflict task success rate significantly, while preserving normal GUI-task performance. These results validate that a lightweight inference-time intervention can substantially boost GUI Agent's competence to identify inappropriate execution scenarios and refrain from unnecessary actions.

• Communication Policy Evolution for Proactive LLM Agents
  Xinbei Ma, Jiyang Qiu, Yao Yao, Zheng Wu, Yijie Lu, Xiangmou Qu, Jiaxin Yin, Xingyu Lou*, Jun Wang*, Weiwen Liu, Weinan Zhang, Zhuosheng Zhang*, Hai Zhao*.
  EMNLP, 2026
  [PDF] [Abstract]
  GenUI

  LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.

• First Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves
  Tianjie Ju, Xinyue Xu, Wanxuan Sun, Lingxiao Diao, Gongshen Liu, Zhuosheng Zhang*, Cheng Yang*.
  EMNLP, 2026
  [PDF] [Abstract]
  FTF-RL

  Recent progress in multimodal large language models (MLLMs) has fueled significant enthusiasm in their potential to act as autonomous agents for real-world tasks. However, scenarios requiring agents to fulfill users’ complex, structured requirements remain largely underexplored. In this work, we examine reasoning tasks under three distinct requirement scenarios, each defined by the feasible solution set delineated by must-have and nice-to-have requirements: (i) Must-have requirements uniquely determine a unique feasible solution; (ii) Multiple candidate solutions satisfy the must-have requirements and are prioritized via the nice-to-have requirements; and (iii) No candidate solution satisfies the must-have requirements, in which case the agent should abstain from generating a response. We evaluate state-of-the-art MLLMs on 3,649 carefully constructed problems that reflect realistic service scenarios, including e-commerce platforms, booking systems, and map-based or ride-hailing applications. Our evaluation reveals that existing MLLMs exhibit catastrophic failures in all scenarios. Specifically, these models frequently misinterpret task requirements, violate must-have requirements, and produce invalid solutions. To address this critical gap, we propose First Things First Reinforcement Learning (FTF-RL) that explicitly optimizes reasoning over multi-priority user requirements. Experimental results show that our method substantially improves the task success rate compared to strong baselines. Moreover, FTF-RL yields general effectiveness on popular logical and mathematical reasoning tasks, including LogicVista, MathVision, and MathVista. Our finding suggests that enhancing requirement comprehension provides a simple yet effective pathway toward improving the broad generalization of MLLMs.

• Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion
  Haodong Zhao, Jidong Li, Zhaomin Wu*, Tianjie Ju, Zhuosheng Zhang*, Bingsheng He, Gongshen Liu*.
  EMNLP, 2026
  [PDF] [Abstract]

  Understanding persuasion is critical for the safety and reliability of multi-agent systems built on large language models (LLMs). This paper studies persuasion dynamics by contrasting general LLMs with Large Reasoning Models (LRMs) that employ explicit “thinking” processes. Through large-scale experiments on objective (MMLU) and subjective (PersuasionBench and Perspectrum) tasks, we identify Persuasion Duality: reasoning enhances an agent’s persuasive power while simultaneously increasing its resistance to persuasion. For LRMs, adding thinking content increases persuasion rates by 21 pp on average, yet reduces susceptibility to incorrect persuasion by up to 10 pp on objective tasks. Despite these gains, we uncover a critical vulnerability: persuasiveness often stems from superficial cues such as response length and repetition rather than logical validity. Non-semantic padding or repeated conclusions can match or exceed the persuasive effect of coherent reasoning, revealing a strong length bias in agents’ judgments. We further show that persuasion propagates non-linearly in multi-hop agent chains, where intermediate agents may amplify or attenuate influence depending on task subjectivity. Finally, guided by attention analysis, we propose a promptlevel adversarial argument detection method that consistently improves agent robustness

• Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness
  Jiyang Qiu, Xinbei Ma, Yunqing Xu, Zhuosheng Zhang, Hai Zhao*.
  EMNLP, 2026
  [PDF] [Abstract]
  CoTri

  The rapid deployment of large language model (LLM)-based agents in real-world applications has raised serious concerns about their trustworthiness. In this work, we reveal the security and robustness vulnerabilities of these agents through backdoor attacks. Distinct from traditional backdoors limited to single-step control, we propose the Chain-of-Trigger Backdoor (CoTri), a multi-step backdoor attack designed for long-horizon agentic control. CoTri relies on an ordered sequence. It starts with an initial trigger, and subsequent ones are drawn from the environment, allowing multi-step manipulation that diverts the agent from its intended task. Experimental results show that CoTri achieves a near-perfect attack success rate (ASR) while maintaining a near-zero false trigger rate (FTR). Due to training data modeling the stochastic nature of the environment, the implantation of CoTri paradoxically enhances the agent's performance on benign tasks and even improves its robustness against environmental distractions. We further validate CoTri on vision-language models (VLMs), confirming its scalability to multimodal agents. Our work highlights that CoTri achieves stable, multi-step control within agents, improving their inherent robustness and task capabilities, which ultimately makes the attack more stealthy and raises potential safty risks.

• Post-quantum Cryptography in the Wild: Assessing the Readiness of Open-Source Ecosystems
  Tongxin Yuan, Zhanpeng Liu, Jiashuo Liang, Zhuosheng Zhang*, Gongshen Liu, Yang Yu, Guancheng Li*.
  ASE, 2026
  [PDF] [Abstract]

  The threat of cryptographically relevant quantum computers, compounded by harvest now, decrypt later attacks, has made migration to post-quantum cryptography (PQC) urgent. With PQC standards finalized and transition guidance phasing out quantum-vulnerable algorithms, the readiness of the open-source supply chain, through which cryptographic vulnerabilities propagate, remains unclear. To fill this gap, we present the first crossecosystem empirical study of sourcelevel PQC readiness. PQC Scanner is a twostage pipeline in which (i) crypto detection identifies packages with cryptographic functionality, and (ii) PQC detection produces a binary support label and sourcederived structured readiness record at the repository level using commit history, source analysis, and agent postverification. Applied to 1,117,913 packages, Stage 1 identifies 55,654 cryptorelated packages. Stage 2 evaluates their repositories for sourcelevel PQC support. A separate audit of 219 Stage 2negative repositories gives a Stage 2 recall lower bound of ≥97.48%. On a 247repository deploymentvalidation sample, agent post-verification eliminated all false positives, yielding precision of 1.000. The pipeline scales to million-package scans: at concurrency 10, it analyzes over one million packages in just over two weeks, with a median LLM cost of $0.0010 per package. Across 8 ecosystems, we find a migration gap: only 1.88% of crypto-related packages show source-level PQC support, and the repository-deduplicated rate is 1.72%. Rust leads by both counts, while NuGet/Ruby/PHP remain near zero. Source derived structured readiness records show partial support: among PQC-supporting repositories, only 19.2% satisfy the full-support criterion, with a mean migration coverage of 36%. Adoption accelerates sharply after FIPS publication (August 2024), but migration This work is licensed under a Creative Commons AttributionNonCommercialNoDerivatives 4.0 International License. ASE ’26, Munich, Germany © 2026 Copyright held by the owner/author(s). ACM ISBN 979-8-4007-2882-2/2026/10 https://doiorg/101145/38327833837461 remains infrastructure-gated: key libraries such as Python’s cryptography (581M downloads/month) and framework integration layers in Java/npm still lack deployable PQC pathways, blocking downstream packages regardless of developer intent. We characterize adoption timing, bottlenecks, and community response strategies, deriving recommendations for maintainers, registry operators, and policy makers.

• DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance
  Yansi Li, Zhuosheng Zhang*.
  IJCAI, 2026
  [PDF] [Abstract]

  Generating executable tool plans requires selecting appropriate subsets from tool libraries, a combinatorial search problem with an exponentially large solution space. However, we identify a critical misalignment in predominant approaches: standard autoregressive (AR) decoding suffers from early commitment, where initial token choices rigidly constrain the search trajectory. We quantify this limitation through a controlled study, demonstrating that masked denoising achieves substantially higher solution coverage than AR sampling (Pass@10: 0.943 vs. 0.320) under matched compute. Motivated by this, we propose DiG-Plan, a framework that decouples combinatorial exploration from structural refinement. DiG-Plan employs a diffusion-based proposer to generate diverse tool sets via iterative refinement, followed by an AR refiner for dependency prediction. Experiments on TaskBench and API-Bank show that DiG-Plan outperforms AR baselines by a 10% relative margin, with the largest gains on complex compositional tasks.

• Faithful Mobile GUI Agents with Guided Advantage Estimator
  Haowen Hu, Pengzhou Cheng, Zheng Wu, Lingzhong Dong, Gongshen Liu, Zhuosheng Zhang*.
  ICML, 2026
  [PDF] [Abstract]
  Faithful-Agent

  Vision-language model based graphical user interface (GUI) agents have shown strong interaction capabilities. However, they often behave unfaithfully, relying on memorized shortcuts rather than grounding actions in displayed screen evidence or user instructions. To address this, we propose Faithful-Agent, a faithfulness-first framework that reformulates GUI interaction to prioritize evidence groundedness and internal consistency. Faithful-Agent employs a two-stage pipeline: (i) a faithfulness-oriented SFT stage to instill abstainment behaviors under evidence perturbations; (ii) an RFT stage that further amplifies faithfulness by introducing the guided advantage estimator (GuAE), an anchor-based and variance-adaptive advantage tempering mechanism built upon GRPO. GuAE prevents advantage collapse in low-variance rollout groups under sparse GUI rewards, and with a thought-action consistency reward, Faithful-Agent (Stage II) elevates the Trap SR from 13.88\% to 80.21\% relative to the baseline, while preserving robust general instruction-following performance.

• Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
  Lai Wei, Liangbo He, Jun Lan, Lingzhong Dong, Yutong Cai, Siyuan Li, Huijia Zhu, Weiqiang Wang, Linghe Kong, Yue Wang, Zhuosheng Zhang, Weiran Huang.
  ICML, 2026
  [PDF] [Abstract]
  Zooming-without-Zooming

  Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global context. Recent "Thinking-with-Images" methods alleviate this by iteratively zooming in and out regions of interest during inference, but incur high latency due to repeated tool calls and visual re-encoding. To address this, we propose Region-to-Image Distillation, which transforms zooming from an inference-time tool into a training-time primitive, thereby internalizing the benefits of agentic zooming into a single forward pass of an MLLM. In particular, we first zoom in to micro-cropped regions to let strong teacher models generate high-quality VQA data, and then distill this region-grounded supervision back to the full image. After training on such data, the smaller student model improves "single-glance" fine-grained perception without tool use. To rigorously evaluate this capability, we further present ZoomBench, a hybrid-annotated benchmark of 845 VQA data spanning six fine-grained perceptual dimensions, together with a dual-view protocol that quantifies the global--regional "zooming gap". Experiments show that our models achieve leading performance across multiple fine-grained perception benchmarks, and also improve general multimodal cognition on benchmarks such as visual reasoning and GUI agents. We further discuss when "Thinking-with-Images" is necessary versus when its gains can be distilled into a single forward pass. Our code is available at this https://github.com/inclusionAI/Zooming-without-Zooming.

• SE-GA: Memory-Augmented Self-Evolution for GUI Agents
  Shilong Jin, Lanjun Wang, Zhuosheng Zhang.
  ICML, 2026
  [PDF] [Abstract]

  Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail to adapt to dynamic environments. To address these limitations, this work proposes the Self-Evolving GUI Agent (SE-GA), a novel framework that integrates hierarchical memory structures with an iterative self-improvement mechanism. At the core of our approach is Test-Time Memory Extension (TTME), which facilitates long-term planning by dynamically retrieving episodic, semantic, and experiential memories to provide salient contexts during inference. To ensure continuous learning, we introduce Memory-Augmented Self-Evolution (MASE), which is a training pipeline that adopts the data collected by TTME to stabilize and enhance the agent's foundational policy. Extensive evaluations across both offline and online benchmarks demonstrate SE-GA achieves state-of-the-art performance, reaching success rates of 89.0\% on ScreenSpot and 75.8\% on the challenging AndroidControl-High dataset. Furthermore, significant improvements on the AndroidWorld benchmark highlight the superior generalization to dynamic environments.

• Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning
  Zheng Wu, Xingyu Lou, Xinbei Ma, Yansi Li, Weiwen Liu, Weinan Zhang, Jun Wang*, Zhuosheng Zhang*.
  ACL, 2026
  [PDF] [Abstract]
  Agent-Dice

  Large Language Model (LLM)-based agents significantly extend the utility of LLMs by interacting with dynamic environments. However, enabling agents to continually learn new tasks without catastrophic forgetting remains a critical challenge, known as the stability-plasticity dilemma. In this work, we argue that this dilemma fundamentally arises from the failure to explicitly distinguish between common knowledge shared across tasks and conflicting knowledge introduced by task-specific interference. To address this, we propose Agent-Dice, a parameter fusion framework based on directional consensus evaluation. Concretely, Agent-Dice disentangles knowledge updates through a two-stage process: geometric consensus filtering to prune conflicting gradients, and curvature-based importance weighting to amplify shared semantics. We provide a rigorous theoretical analysis that establishes the validity of the proposed fusion scheme and offers insight into the origins of the stability-plasticity dilemma. Extensive experiments on GUI agents and tool-use agent domains demonstrate that Agent-Dice exhibits outstanding continual learning performance with minimal computational overhead and parameter updates.

• ParaCook: On Time-Efficient Planning for Multi-Agent Systems
  Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang*, Hai Zhao*, Ming-Hsuan Yang*
  ACL, 2026
  [PDF] [Abstract]
  ParaCook

  Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks, yet existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. To address this, we present ParaCook, a benchmark for time-efficient collaborative planning. Inspired by the Overcooked game, ParaCook provides an environment for various challenging interaction planning of multi-agent systems that are instantiated as cooking tasks, with a simplified action space to isolate the core challenge of strategic parallel planning. Through a comprehensive evaluation of state-of-the-art LLMs, we find that current approaches achieve suboptimal plans, which struggle with parallel actions or coordination. Our analysis also reveals LLMs' potential on abstract tasks where they can focus on high-level parallel optimization. ParaCook provides a scalable evaluation framework with adjustable complexity, establishing a foundation for developing and assessing time efficiency-aware multi-agent planning.

• The Confidence Paradox: Unveiling the Latent Discriminative Power of Diffusion Large Language Models in Mathematical Reasoning
  Yansi Li, Gongshen Liu, Zhuosheng Zhang*
  ACL, 2026
  [PDF] [Abstract]

  Diffusion large language models (DLLMs) have emerged as a promising alternative to autoregressive (AR) generation, uniquely offering token-level probabilities under bidirectional context. However, the semantics of their native uncertainty estimates remain underexplored. In this work, we uncover a calibration paradox inherent to the bidirectional generation mechanism of state-of-the-art DLLMs. Concretely, we demonstrate that diffusion confidence is structurally distinct from AR likelihood. Notably, LLaDA-8B is highly miscalibrated (31.2% ECE) on mathematical reasoning benchmarks, yet possesses superior discriminative power (0.826 AUROC), significantly outperforming comparable AR baselines in single-pass settings (0.611 AUROC). We diagnose that this paradox arises because diffusion confidence functions less like a probability of correctness and more like a proxy for structural consistency enabled by the model’s bidirectional access to the entire solution path. We further show that lightweight post-hoc calibration can reconcile this gap, reducing ECE by over 60% while preserving the strong ranking signal. Our findings suggest that DLLMs offer a unique, cost-efficient uncertainty signal for reasoning tasks that complements expensive AR approaches.

• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
  Qiushi_Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong
  ACL, 2026
  Best Paper Award at AIWILD @ ICLR2026 🏆
  [PDF] [Abstract]
  OS-Sentinel

  Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their potential for unsafe operations, such as system compromise and privacy leakage, is raising significant concerns. Detecting these safety concerns across the vast and complex operational space of mobile environments presents a formidable challenge that remains critically underexplored. To establish a foundation for mobile agent safety research, we introduce MobileRisk-Live, a dynamic sandbox environment accompanied by a safety detection benchmark comprising realistic trajectories with fine-grained annotations. Built upon this, we propose OS-Sentinel, a novel hybrid safety detection framework that synergistically combines a Formal Verifier for detecting explicit system-level violations with a VLM-based Contextual Judge for assessing contextual risks and agent actions. Experiments show that \ours achieves 10%–30% improvements over existing approaches across multiple metrics. Further analysis provides critical insights that foster the development of safer and more reliable autonomous mobile agents. Our code, environment, and data are available at https://qiushisun.github.io/OS-Sentinel-Home/.

• EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks
  Yijie Lu, Manman Zhao, Tianjie Ju, Zihe Yan, Xinbei Ma, Yuan Guo, Daizong Ding, Gongshen Liu*, Zhuosheng Zhang*
  ACL, 2026
  [PDF] [Abstract]

  As multimodal agents are increasingly trained to operate graphical user interfaces (GUIs) to complete user tasks, they face a growing threat from indirect prompt injection, attacks in which misleading instructions are embedded into the agent's visual environment, such as popups or chat messages, and misinterpreted as part of the intended task. A typical example is environmental injection, in which GUI elements are manipulated to influence agent behavior without directly modifying the user prompt. To address these emerging attacks, we propose EVA, a red teaming framework for indirect prompt injection which transforms the attack into a closed loop optimization by continuously monitoring an agent's attention distribution over the GUI and updating adversarial cues, keywords, phrasing, and layout, in response. Compared with prior one shot methods that generate fixed prompts without regard for how the model allocates visual attention, EVA dynamically adapts to emerging attention hotspots, yielding substantially higher attack success rates and far greater transferability across diverse GUI scenarios. We evaluate EVA on six widely used generalist and specialist GUI agents in realistic settings such as popup manipulation, chat based phishing, payments, and email composition. Experimental results show that EVA substantially improves success rates over static baselines. Under goal agnostic constraints, where the attacker does not know the agent's task intent, EVA still discovers effective patterns. Notably, we find that injection styles transfer well across models, revealing shared behavioral biases in GUI agents. These results suggest that evolving indirect prompt injection is a powerful tool not only for red teaming agents, but also for uncovering common vulnerabilities in their multimodal decision making.

• ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution
  Jihong Wang, Jiamu Zhou, Weiming Zhang, Teng Wang, Weiwen Liu, Zhuosheng Zhang, Xingyu Lou, Weinan Zhang, Huarong Deng, Jun Wang.
  ACL, 2026
  [PDF] [Abstract]

  With the advancement of vision-language models, web automation has made significant progress. However, deploying autonomous agents in real-world settings remains challenging, primarily due to site heterogeneity, where generalist models lack domain-specific priors for diverse interfaces, and long-horizon instability, characterized by the accumulation of decision drift over extended interactions. To address these challenges, we introduce ColorBrowserAgent (Complex Long-Horizon Browser Agent), a knowledge-evolving agent for robust web automation. Our approach addresses these challenges through two synergistic mechanisms: human-in-the-loop knowledge adaptation that transforms sparse human feedback into reusable domain knowledge, and knowledge-aligned progressive summarization that stabilizes long interactions through memory compression. Extensive experiments on WebArena, WebChoreArena and industrial deployment show that ColorBrowserAgent consistently outperforms strong baselines. It achieves a state-of-the-art success rate of 71.2% on WebArena and maintains 47.4% performance under zero-shot transfer setting on WebChoreArena. In commercial deployment, it improves user satisfaction by 19.3% relatively, verifying its robustness in real-world scenarios.

• ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks
  Yuanyi Song, Heyuan Huang, Qiqiang Lin, Yin Zhao, Xiangmou Qu, Jun Wang, Xingyu Lou, Weiwen Liu, Zhuosheng Zhang, Jun Wang, Yong Yu, Weinan Zhang, Zhaoxiang Wang.
  WWW, 2026
  [PDF] [Abstract]
  ColorBench

  The rapid advancement of multimodal large language models has enabled agents to operate mobile devices by directly interacting with graphical user interfaces, opening new possibilities for mobile automation. However, real-world mobile tasks are often complex and allow for multiple valid solutions. This contradicts current mobile agent evaluation standards: offline static benchmarks can only validate a single predefined "golden path", while online dynamic testing is constrained by the complexity and non-reproducibility of real devices, making both approaches inadequate for comprehensively assessing agent capabilities. To bridge the gap between offline and online evaluation and enhance testing stability, this paper introduces a novel graph-structured benchmarking framework. By modeling the finite states observed during real-device interactions, it achieves static simulation of dynamic behaviors. Building on this, we develop ColorBench, a benchmark focused on complex long-horizon tasks. It supports evaluation of multiple valid solutions, subtask completion rate statistics, and atomic-level capability analysis. ColorBench contains 175 tasks (74 single-app, 101 cross-app) with an average length of over 13 steps. Each task includes at least two correct paths and several typical error paths, enabling quasi-dynamic interaction. By evaluating ColorBench across various baselines, we discover limitations of existing models and propose improvement directions and feasible technical pathways to enhance agents' performance on complex, long-horizon problems based on experimental results.

• See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
  Zongru Wu, Rui Mao, Zhiyuan Tian, Pengzhou Cheng, Tianjie Ju, Zheng Wu, Lingzhong Dong, Haiyue Sheng, Zhuosheng Zhang*, Gongshen Liu*.
  CVPR, 2026
  [PDF] [Abstract]
  StaR

  The advent of multimodal agents facilitates effective interaction within graphical user interface (GUI), especially in ubiquitous GUI control. However, their inability to reliably execute toggle control instructions remains a key bottleneck. To investigate this, we construct a state control benchmark with binary toggle instructions from public datasets. Evaluations of existing agents demonstrate their unreliability, particularly when the current toggle state already matches the desired state. To address the challenge, we propose State-aware Reasoning (StaR), a training method that teaches agents to perceive the current toggle state, analyze the desired state from the instruction, and act accordingly. Experiments on three multimodal agents demonstrate that StaR can improve toggle instruction execution accuracy by over 30\%. Further evaluations on three public benchmarks show that StaR also enhances general task performance. Finally, evaluations on a dynamic environment highlight the potential of StaR for real-world applications.

• Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation
  Zehao Deng, Tianjie Ju, Zheng Wu, Zhuosheng Zhang*, Gongshen Liu.
  CVPR, 2026
  [PDF] [Abstract]
  CES

  The rapid development of large vision-language model (VLM) has greatly promoted the research of GUI agent. However, GUI agents still face significant challenges in handling long-horizon tasks. First, single-agent models struggle to balance high-level capabilities and low-level execution capability, facing prevalent issues of responsibility coupling and capability conflicts. Second, agents lack awareness of the task state, leading to progress loss in long-horizon tasks. To address these challenges, we propose a staged execution-feedback reinforcement learning algorithm. Unlike training a unified policy model, we focus on training high-level scheduling models. Specifically, we propose and train two agents: a Coordinator, responsible for the strategic planning and task decomposition; and a State Tracker, responsible for context compression and information management to maintain the task's state and coherence. Based on this, we built the Coordinator-Executor-State Tracker (CES) multi-agent framework, which can be integrated with any low-level Executor model, assisting the Executor in solving long-horizon tasks through task scheduling and state management. Experiments on long-horizon task benchmarks demonstrate that CES significantly enhances the system's planning and state management capabilities. Furthermore, analysis confirms that our trained high-level scheduling module is a generalizable, plug-and-play module that significantly enhances the long-horizon capabilities of various Executors.

• LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents
  Zihe Yan, Zhuosheng Zhang*, Jiaping Gui, Gongshen Liu.
  CVPR, 2026
  [PDF] [Abstract]

  Graphical user interface (GUI) agents built on multimodal large language models (MLLMs) have recently demonstrated strong decision-making abilities in screen-based interaction tasks. However, they remain highly vulnerable to pop-up-based environmental injection attacks, where malicious visual elements divert model attention and lead to unsafe or incorrect actions. Existing defense methods either require costly retraining or perform poorly under inductive interference. In this work, we systematically study how such attacks alter the attention behavior of GUI agents and uncover a layer-wise attention divergence pattern between correct and incorrect outputs. Based on this insight, we propose \textbf{LaSM}, a \textit{Layer-wise Scaling Mechanism} that selectively amplifies attention and MLP modules in critical layers. LaSM improves the alignment between model saliency and task-relevant regions without additional training. Extensive experiments across 12 types of pop-up perturbations and 4 different model backbones show that LaSM consistently enhances the defense success rate. When combined with prompt-level alerts, LaSM achieves over 98\% robustness even under strong inductive attacks. Our findings reveal that attention misalignment is a core vulnerability in MLLM agents and can be effectively addressed through selective layer-wise modulation.

• DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
  Zhiwei He, Tian Liang, Jiahao Xu, Qiuzhi Liu, Xingyu Chen, Yue Wang, Linfeng Song, Dian Yu, Zhenwen Liang, Wenxuan Wang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu.
  ICLR, 2026
  [PDF] [Abstract]
  

  Reinforcement learning (RL) with large language models shows promise in complex reasoning. However, its progress is hindered by the lack of large-scale training data that is sufficiently challenging, contamination-free and verifiable. To this end, we introduce DeepMath-103K, a large-scale mathematical dataset designed with high difficulty (primarily levels 5-9), rigorous decontamination against numerous benchmarks, and verifiable answers for rule-based RL reward. It further includes three distinct R1 solutions adaptable for diverse training paradigms such as supervised fine-tuning (SFT). Spanning a wide range of mathematical topics, DeepMath-103K fosters the development of generalizable and advancing reasoning. Notably, models trained on DeepMath-103K achieve leading results on challenging mathematical benchmarks and demonstrate generalization beyond math such as biology, physics and chemistry, underscoring its broad efficacy.

• Auditing Partial Dataset Usage in Large Language Models Via Fuzzy Membership Aggregation
  Hongyu Zhu, Sichu Liang, Bofan Chen, Shilin Wang, Zhuosheng Zhang, Weiping Ding.
  IEEE Transactions on Fuzzy Systems, 2026
  [PDF] [Abstract]
  

  The remarkable capabilities of Large Language Models (LLMs) are fueled by massive internet-scale corpora. However, scraped data owners often do not consent to its use for training, raising significant legal and ethical concerns over copyright and privacy. Data auditing techniques seek to verify whether a protected dataset was used in training a target LLM, typically framing the task as membership inference: estimating binary sample-level membership and aggregating to a dataset-level decision. In this paper, we identify a fundamental limitation of this crisp binary paradigm: in realistic training pipelines, datasets are rarely used in full. Instead, models are trained on mixtures of partial subsets drawn from multiple sources. Existing auditing techniques, built upon an all-or-none assumption—declaring a dataset either entirely present or absent from training—collapse in partial dataset usage scenarios. Their predictions fluctuate unpredictably with the member ratio, causing unstable performance and high false-negative rates. Inspired by fuzzy set theory, we relax the crisp notion of binary membership to a continuous fuzzy membership in [0,1], quantifying each sample's degree of inclusion in the model's training set. We establish a theoretical bridge between sample-level fuzzy memberships and the dataset-level usage ratio, facilitating inference of the proportion of a protected dataset used during training. A neural network fuzzifier first estimates sample-level fuzzy memberships from binary labels in a reference set, then refines them using dataset-level member ratios as higher-order supervision. Finally, a defuzzification stage aggregates calibrated memberships to determine partial usage. Across LLMs of varying scales and multiple auditing datasets, our Fuzzy Auditor substantially outperforms state-of-the-art crisp binary techniques in detecting partial usage, estimating member proportions, and identifying individual member samples.

• Generalizable and Adaptive Continual Learning Framework for AI-generated Image Detection
  Hanyi Wang, Jun Lan, Yaoyu Kang, Huijia Zhu, Weiqiang Wang, Zhuosheng Zhang, Shilin Wang.
  IEEE Transactions on Multimedia, 2026
  [PDF] [Abstract]
  

  The malicious misuse and widespread dissemination of AI-generated images pose a significant threat to the authenticity of online information. Current detection methods often struggle to generalize to unseen generative models, and the rapid evolution of generative techniques continuously exacerbates this challenge. Without adaptability, detection models risk becoming ineffective in real-world applications. To address this critical issue, we propose a novel three-stage domain continual learning framework designed for continuous adaptation to evolving generative models. In the first stage, we employ a strategic parameter-efficient fine-tuning approach to develop a transferable offline detection model with strong generalization capabilities. Building upon this foundation, the second stage integrates unseen data streams into a continual learning process. To efficiently learn from limited samples of novel generated models and mitigate overfitting, we design a data augmentation chain with progressively increasing complexity. Furthermore, we leverage the Kronecker-Factored Approximate Curvature (K-FAC) method to approximate the Hessian and alleviate catastrophic forgetting. Finally, the third stage utilizes a linear interpolation strategy based on Linear Mode Connectivity, effectively capturing commonalities across diverse generative models and further enhancing overall performance. We establish a comprehensive benchmark of 27 generative models, including GANs, deepfakes, and diffusion models, chronologically structured up to August 2024 to simulate real-world scenarios. Extensive experiments demonstrate that our initial offline detectors surpass the leading baseline by +5.51% in terms of mean average precision. Our continual learning strategy achieves an average accuracy of 92.20%, outperforming state-of-the-art methods.

• GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents
  Zheng Wu, Pengzhou Cheng, Zongru Wu, Lingzhong Dong, Zhuosheng Zhang*
  AAAI, 2026
  [PDF] [Abstract]
  GEM-OODforGUIagents

  Graphical user interface (GUI) agents have recently emerged as an intriguing paradigm for human-computer interaction, capable of automatically executing user instructions to operate intelligent terminal devices. However, when encountering out-of-distribution (OOD) instructions that violate environmental constraints or exceed the current capabilities of agents, GUI agents may suffer task breakdowns or even pose security threats. Therefore, effective OOD detection for GUI agents is essential. Traditional OOD detection methods perform suboptimally in this domain due to the complex embedding space and evolving GUI environments. In this work, we observe that the in-distribution input semantic space of GUI agents exhibits a clustering pattern with respect to the distance from the centroid. Based on the finding, we propose GEM, a novel method based on fitting a Gaussian mixture model over input embedding distances extracted from the GUI agent that reflect its capability boundary. Evaluated on eight datasets spanning smartphones, computers, and web browsers, our method achieves an average accuracy improvement of 23.70\% over the best-performing baseline while only increasing training time by 4.9\% and testing time by 6.5\%. We also experimentally demonstrate that GEM can improve the step-wise success rate by 9.40\% by requesting assistance from the cloud model when encountering OOD samples. Analysis verifies the generalization ability of our method through experiments on nine different backbones.

• An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains
  Zihe Yan, Kai Luo, Haoyu Yang, Yang Yu, Zhuosheng Zhang*, Guancheng Li*
  AAAI, 2026
  [PDF] [Abstract]
  HSBRiskEvaluator

  In modern software development workflows, the open-source software supply chain contributes significantly to efficient and convenient engineering practices. With increasing system complexity, using open-source software as third-party dependencies has become a common practice. However, the lack of maintenance for underlying dependencies and insufficient community auditing create challenges in ensuring source code security and the legitimacy of repository maintainers, especially under high-stealthy backdoor attacks exemplified by the XZ-Util incident. To address these problems, we propose a fine-grained project evaluation framework for backdoor risk assessment in open-source software. The framework models stealthy backdoor attacks from the viewpoint of the attacker and defines targeted metrics for each attack stage. In addition, to overcome the limitations of static analysis in assessing the reliability of repository maintenance activities such as irregular committer privilege escalation and limited participation in reviews, the framework uses large language models (LLMs) to conduct semantic evaluation of code repositories without relying on manually crafted patterns. The framework is evaluated on sixty six high-priority packages in the Debian ecosystem. The experimental results indicate that the current open-source software supply chain is exposed to various security risks.

[2025 & Before]
• Multimodal Chain-of-Thought Reasoning in Language Models
  Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, Alex Smola.
  TMLR, 2024
  "Imagine learning a textbook with no figures: Multimodal-CoT surpasses humans on ScienceQA."
  Featured in Dive into Deep Learning (Adopted at 500 universities from 70 countries)
  [Top Trending Research on paperswithcode] [Idea Inspiration] [PDF] [Abstract]
  
  MM-CoT

  Large language models (LLMs) have shown impressive performance on complex reasoning by leveraging chain-of-thought (CoT) prompting to generate intermediate reasoning chains as the rationale to infer the answer. However, existing CoT studies are mostly isolated in the language modality with LLMs, where LLMs are hard to deploy. To elicit CoT reasoning in multimodality, a possible solution is to fine-tune small language models by fusing the vision and language features to perform CoT reasoning. The key challenge is that those language models tend to generate hallucinated reasoning chains that mislead the answer inference. To mitigate the effect of such mistakes, we propose Multimodal-CoT that incorporates vision features in a decoupled training framework. The framework separates the rationale generation and answer inference into two stages. By incorporating the vision features in both stages, the model is able to generate effective rationales that contribute to answer inference. With Multimodal-CoT, our model under 1 billion parameters outperforms the previous state-of-the-art LLM (GPT-3.5) by 16% (75.17%->91.68%) on the ScienceQA benchmark and even surpasses human performance. Code is publicly available at https://github.com/amazon-science/mm-cot.

• Automatic Chain of Thought Prompting in Large Language Models
  Zhuosheng Zhang, Aston Zhang, Mu Li, Alex Smola.
  ICLR, 2023
  "Let's think not just step by step, but also one by one."
  Featured in Dive into Deep Learning (Adopted at 400 universities from 60 countries)
  [PDF] [Abstract] [bilibili] [slides]
  
  Auto-CoT

  Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One leverages a simple prompt like "Let's think step by step" to facilitate step-by-step thinking before answering a question. The other uses a few manual demonstrations one by one, each composed of a question and a reasoning chain that leads to an answer. The superior performance of the second paradigm hinges on the hand-crafting of task-specific demonstrations one by one. We show that such manual efforts may be eliminated by leveraging LLMs with the "Let's think step by step" prompt to generate reasoning chains for demonstrations one by one, i.e., let's think not just step by step, but also one by one. However, these generated chains often come with mistakes. To mitigate the effect of such mistakes, we find that diversity matters for automatically constructing demonstrations. We propose an automatic CoT prompting method: Auto-CoT. It samples questions with diversity and generates reasoning chains to construct demonstrations. On ten public benchmark reasoning tasks with GPT-3, Auto-CoT consistently matches or exceeds the performance of the CoT paradigm that requires manual designs of demonstrations. Code is available at https://github.com/amazon-research/auto-cot

• You Only Look at Screens: Multimodal Chain-of-Action Agents
  Zhuosheng Zhang, Aston Zhang.
  ACL, 2024
  "Perform a task on smart phones? Train an agent using screenshots."
  [PDF] [Abstract] [slides]
  
  Auto-GUI

  Autonomous graphical user interface (GUI) agents aim to facilitate task automation by interacting with the user interface without manual intervention. Recent studies have investigated eliciting the capabilities of large language models (LLMs) for effective engagement in diverse environments. To align with the input-output requirement of LLMs, most existing approaches are developed under a sandbox setting where they rely on external tools and application-specific APIs to parse the environment into textual elements and interpret the predicted actions. Consequently, those approaches often grapple with inference inefficiency and error propagation risks. To mitigate the challenges, we introduce Auto-GUI, a multimodal solution that directly interacts with the interface, bypassing the need for environment parsing or reliance on application-dependent APIs. Moreover, we propose a chain-of-action technique -- leveraging a series of intermediate previous action histories and future action plans -- to help the agent decide what action to execute. We evaluate our approach on a new device-control benchmark AITW with 30K unique instructions, spanning multi-step tasks such as application operation, web searching, and web shopping. Experimental results show that Auto-GUI achieves state-of-the-art performance with an action type prediction accuracy of 90\% and an overall action success rate of 74\%. Code is publicly available at https://github.com/cooelf/Auto-GUI.

• Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy
  Xiangru Tang, Qiao Jin, Kunlun Zhu, Tongxin Yuan, Yichi Zhang, Wangchunshu Zhou, Meng Qu, Yilun Zhao, Jian Tang, Zhuosheng Zhang, Arman Cohan, Zhiyong Lu, Mark Gerstein.
  Nature Communications, 2025
  [PDF] [Abstract]
  

  Intelligent agents powered by large language models (LLMs) have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, they also introduce novel vulnerabilities that demand careful consideration for safety. However, there exists a notable gap in the literature, as there has been no comprehensive exploration of these vulnerabilities. This position paper fills this gap by conducting a thorough examination of vulnerabilities in LLM-based agents within scientific domains, shedding light on potential risks associated with their misuse and emphasizing the need for safety measures. We begin by providing a comprehensive overview of the potential risks inherent to scientific LLM agents, taking into account user intent, the specific scientific domain, and their potential impact on the external environment. Then, we delve into the origins of these vulnerabilities and provide a scoping review of the limited existing works. Based on our analysis, we propose a triadic framework involving human regulation, agent alignment, and an understanding of environmental feedback (agent regulation) to mitigate these identified risks. Furthermore, we highlight the limitations and challenges associated with safeguarding scientific agents and advocate for the development of improved models, robust benchmarks, and comprehensive regulations to address these issues effectively.

• Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents
  Zhuosheng Zhang#, Yao Yao#, Aston Zhang, Xiangru Tang, Xinbei Ma, Zhiwei He, Yiming Wang, Mark Gerstein, Rui Wang, Gongshen Liu, Hai Zhao.
  ACM Computing Surveys, 2025
  "Join us on an exciting journey from chain-of-thought reasoning to language agent!"
  [PDF] [Abstract]
  
  CoT-Igniting-Agent

  Large language models (LLMs) have dramatically enhanced the field of language intelligence, as demonstrably evidenced by their formidable empirical performance across a spectrum of complex reasoning tasks. Additionally, theoretical proofs have illuminated their emergent reasoning capabilities, providing a compelling showcase of their advanced cognitive abilities in linguistic contexts. Critical to their remarkable efficacy in handling complex reasoning tasks, LLMs leverage the intriguing chain-of-thought (CoT) reasoning techniques, obliging them to formulate intermediate steps en route to deriving an answer. The CoT reasoning approach has not only exhibited proficiency in amplifying reasoning performance but also in enhancing interpretability, controllability, and flexibility. In light of these merits, recent research endeavors have extended CoT reasoning methodologies to nurture the development of autonomous language agents, which adeptly adhere to language instructions and execute actions within varied environments. This survey paper orchestrates a thorough discourse, penetrating vital research dimensions, encompassing: (i) the foundational mechanics of CoT techniques, with a focus on elucidating the circumstances and justification behind its efficacy; (ii) the paradigm shift in CoT; and (iii) the burgeoning of language agents fortified by CoT approaches. Prospective research avenues envelop explorations into generalization, efficiency, customization, scaling, and safety. We hope to offer readers a comprehensive understanding of prevalent research areas such as CoT reasoning and language agents and illuminate the interconnections weaving through these areas. This paper caters to a wide audience, including beginners seeking comprehensive knowledge of CoT reasoning and language agents, as well as experienced researchers interested in foundational mechanics and engaging in cutting-edge discussions on these topics. A repository for the related papers is available at https://github.com/Zoeyyao27/CoT-Igniting-Agent.

• Do NOT Think That Much for 2+ 3=? On the Overthinking of o1-Like LLMs
  Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu.
  ICML, 2025
  [PDF] [Abstract]
  

  The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. These models employ extended chain-of-thought (CoT) processes, exploring multiple strategies to enhance problem-solving capabilities. However, a critical question remains: How to intelligently and efficiently scale computational resources during testing. This paper presents the first comprehensive study on the prevalent issue of overthinking in these models, where excessive computational resources are allocated for simple problems with minimal benefit. We introduce novel efficiency metrics from both outcome and process perspectives to evaluate the rational use of computational resources by o1-like models. Using a self-training paradigm, we propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy. Experimental results show that our approach successfully reduces computational overhead while preserving model performance across a range of testsets with varying difficulty levels, such as GSM8K, MATH500, GPQA, and AIME.

Shared Tasks

[May 2022] HellaSwag Leaderboard on Commonsense Reasoning

• The best among all submissions.
[Leaderboard] [Paper]
[January 2021] ShARC Leaderboard on Conversational Question Answering

• The best among all submissions.
[Leaderboard] [Paper]
[September 2020] MuTual Leaderboard on Dialogue Reasoning Challenge

• The best among all submissions.
[Leaderboard] [Paper]
[July 2019] SQuAD2.0 Leaderboard on Machine Reading Comprehension

• The best models for both single and ensemble settings among all submissions (2020.01).
• The first to surpass human benchmark on both EM and F1 scores with a single model (from 2019.07-09).
• The first time to exceed 90% F1 score with ensemble models.
  [Leaderboard] [Paper] [Report]
[March 2019] RACE Leaderboard on Machine Reading Comprehension

• The best among all submissions.
• The best among all academic submissions.
  [Leaderboard] [Paper] [Report]
[April 2019] SNLI Leaderboard on Language Inference
• The best among all submissions.
  [Leaderboard] [Paper]
[March 2019] GLUE Leaderboard on Language Understanding
• The 3rd best among all submissions.
• The best among all academic submissions.
  [Leaderboard] [Paper]
[August 2017] Chinese Machine Reading Comprehension (CCL-CMRC 2017)
• The best single system and the second ensemble system (Silver Medal).
  [Leaderboard] [Paper] [Source]

Awards & Honors

• 2024: WAIC Youth Outstanding Paper Award, World Artificial Intelligence Conference.

• 2024: WAIC YunFan Award: Bright Star, World Artificial Intelligence Conference.

• 2023: Excellent Doctoral Thesis of Chinese Information Processing Society (CIPS).

• 2023: Shanghai Outstanding Doctoral Graduate.

• 2022: Academic Stars of Graduate Students (10 recipients), Shanghai Jiao Tong University.

• 2021: Global Top 100 Chinese Rising Stars in Artificial Intelligence (Top 10 recommended), Baidu Research.

• 2021: Baidu Scholarship (10 recipients, worldwide), Baidu.

• 2020: National Scholarship of China, Ministry of Education of the P.R. China.

• 2019: Yang Yuanqing Education Fund, The foundation of Class 1988 in CS @ Shanghai Jiao Tong University.

• 2018: Academic Stars of Graduate Students (The only master student awardee), Shanghai Jiao Tong University.

• 2016: National Figures Nomination of College Students (20 total recipients), Ministry of Education of the P.R. China.

• 2015: CCF Elite Collegiate Award, China Computer Federation.

Academic Service

Organization:
• Organizing Committee Member of CJNLP 2025
• Co-chair of Hot Paper Session at CCL 2025
• Session Chair at RL China 2024
• Session Chair at CJNLP 2024
• Session Chair at IJCNLP-AACL 2023
• Co-chair of Student Seminar at CCL 2022
• President of IBM Tech Club at Wuhan University, 2014-2015
(Senior) Area Chair / Action Editor/ SPC:
• AAAI 2026
• ACL Rolling Review
• NeurIPS 2025
• EMNLP 2025
• ACL 2025
• LREC-COLING 2024
• IJCAI 2024
• ICLR 2023 TinyPapers
Program Committee Member:
• ML/AI conferences: ICLR, ICML, NeurIPS, AAAI, IJCAI, etc.
• CL/NLP conferences: ARR, ACL, EMNLP, COLING, NAACL, AACL, NLPCC, CCL, etc.

Journal Reviewer:
• Artificial Intelligence, IEEE/ACM TASLP, IEEE TNNLS, IEEE TETCI, IEEE Communications Magazine, ACM TALLIP, ACM TOIS, TMLR, Neurocomputing, Multimedia Systems, Neural Computing and Applications, Expert Systems With Applications.

Experience

• Jul. 2022 - Aug. 2023, Amazon Web Services AI, CA, USA.
  Applied Scientist Intern, advised by Dr. Aston Zhang, Mu Li, Alex Smola.
• Feb. 2022 - June. 2022, Microsoft Cognitive Services Research Group, WA, USA.
  Research Intern, advised by Dr. Shuohang Wang.
• Mar. 2021 - Dec. 2021, Langboat Tech, Beijing, China.
  Research Intern, advised by Prof. Ming Zhou.
• Jun. 2019 - Jul. 2020, NICT, Kyoto, Japan.
  Internship Research Fellow, advised by Prof. Rui Wang, Kehai Chen, Masao Utiyama, and Eiichiro Sumita.

Education

• Sept. 2020 - Sept. 2023
  Ph.D., Dept. of Computer Science and Engineering, Shanghai Jiao Tong University, advised by Prof. Hai Zhao.
• Sept. 2016 - Mar. 2020
  M.S., Dept. of Computer Science and Engineering, Shanghai Jiao Tong University, advised by Prof. Hai Zhao.
• Sept. 2012 - Jun. 2016
  B.S., Dept. of Computer Science and Engineering, Wuhan University, advised by Prof. Haojun Ai.
Research Team
PhD Students:
• 2026: Yijie Lu
• 2025: Yansi Li
• 2024: Zihe Yan
• 2023: Yiming Wang (co-advising with Prof. Rui Wang)
• 2022: Zongru Wu (co-advising with Prof. Gongshen Liu), Pengzhou Cheng (co-advising with Prof. Gongshen Liu)
• 2021: Xinbei Ma (co-advising with Prof. Hai Zhao, → Postdoc @ NUS), Zhiwei He (co-advising with Prof. Rui Wang, → MiniMax), Tianjie Ju (co-advising with Prof. Gongshen Liu, → Postdoc @ NUS), Haodong Zhao (co-advising with Prof. Gongshen Liu, 入选中国科协青年科技人才培育工程博士生专项计划、腾讯犀牛鸟精英人才计划，→ Postdoc @ NUS)
Master Students:
• 2026: Haowen Hu
• 2025: Zheng Wu (获评上海交通大学2025届优异学士学位论文）, Lingxiao Diao, Zhuzuoken Xuan
• 2024: Lingzhong Dong
• 2023: Tongxin Yuan, co-advising with Prof. Gongshen Liu ( → Tencent Xuanwu Lab)
• 2022: Anni Zou, co-advising with Prof. Hai Zhao ( → Alibaba Tongyi Lab)
Alumni:
• 2026: Yuan Guo
• 2025: Yiting Wang ( → MS at UCSD), Xuanchang Zhang ( → RA at UIUC)
• 2024: Yexin Wu ( → MS at UIUC)
• 2023: Sizhe Zhou ( → MS at UIUC)
• 2022: Siru Ouyang ( → PhD at UIUC), Jialin Chen ( → PhD at Yale University), Junlong Li ( → MS at SJTU), Dongjie Yang ( → PhD at SJTU), Yuchen He ( → MS at SJTU)
• 2021: Longxiang Liu ( → MS at ICT/CAS)
• 2020: Yuwei Wu ( → MS at CMU)