Yujun Zhou

Yue Huang, Chujie Gao, Siyuan Wu et al.

Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, as well as industry practices and standards. Based on this analysis, we propose a set of guiding principles for GenFMs, developed through extensive multidisciplinary collaboration that integrates technical, ethical, legal, and societal perspectives. Second, we introduce TrustGen, the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods. Using TrustGen, we reveal significant progress in trustworthiness while identifying persistent challenges. Finally, we provide an in-depth discussion of the challenges and future directions for trustworthy GenFMs, which reveals the complex, evolving nature of trustworthiness, highlighting the nuanced trade-offs between utility and trustworthiness, and consideration for various downstream applications, identifying persistent challenges and providing a strategic roadmap for future research. This work establishes a holistic framework for advancing trustworthiness in GenAI, paving the way for safer and more responsible integration of GenFMs into critical applications. To facilitate advancement in the community, we release the toolkit for dynamic evaluation.

Suliu Qin, Haomin Zhuang, Yujun Zhou et al.

Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful step is often not an obviously forbidden output, but an ordinary executable action that becomes unsafe because attacker-controlled context steers authorized access against the user's interest. We identify this failure mode as authority confusion: untrusted resources may inform reasoning, but they must not authorize side effects. We present AIRGuard, a runtime guard that operationalizes least privilege as action-time authorization. AIRGuard normalizes heterogeneous tool calls, derives task authority into step-level authority, tracks source and target trust, simulates sensitive side effects, audits cross-step risk, and enforces decisions before actions execute. On AgentTrap, AIRGuard reduces Sonnet 4.6 attack success from 36.3% without defense to 5.5%. On DTAP-150, AIRGuard preserves 76.0% benign utility with Haiku 4.5, compared with 52.0% for ARGUS and 42.0% for MELON. An ablation further shows that prompt-only policy helps only modestly, whereas a dedicated runtime authority-control layer gives the agent system direct control over tool-mediated side effects. Code and data are available at https://github.com/Sophie508/AIRGuard.

Haomin Zhuang, Hanwen Xing, Yujun Zhou et al.

Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also introduces a new security problem: a malicious skill does not need to ask the model to perform an obviously harmful action. Instead, it can disguise the harmful behavior as part of a routine workflow, relying on the agent to execute that workflow with high-value permissions and limited human supervision. We introduce AgentTrap, a dynamic benchmark for evaluating whether LLM agents can use third-party skills while resisting malicious runtime behavior. AgentTrap contains 141 tasks: 91 malicious tasks and 50 benign utility tasks, covering 16 security-impact dimensions grounded in agent-skill supply-chain threats. In each task, the agent receives an ordinary user request, runs with installed skills that may contain malicious workflow elements, and is executed in a sandboxed environment. AgentTrap then judges complete trajectories for attack success, blocked or refused behavior, attack-not-triggered cases, and no-attack-evidence outcomes. Our central finding is that the most informative failures are not simple jailbreaks. Models often complete the visible user task while treating unsafe side effects introduced by the skill as part of the normal workflow. This motivates runtime evaluation of the concrete model--framework--workspace environment in which users actually delegate work. Code and data are available at https://github.com/zhmzm/AgentTrap and https://huggingface.co/datasets/zhmzm/AgentTrap.

Yujun Zhou, Zhenwen Liang, Haolin Liu et al.

Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR), yet real-world deployment demands models that can self-improve without labels or external judges. Existing self-improvement approaches primarily rely on self-confirmation signals (e.g., confidence, entropy, or consistency) to generate rewards. This reliance drives models toward over-confident, majority-favored solutions, causing an entropy collapse that degrades pass@n and reasoning complexity. To address this, we propose EVOL-RL, a label-free framework that mirrors the evolutionary principle of balancing selection with variation. Concretely, EVOL-RL retains the majority-voted answer as an anchor for stability, but adds a novelty-aware reward that scores each sampled solution by how different its reasoning is from other concurrently generated responses. This majority-for-stability + novelty-for-exploration rule mirrors the variation-selection principle: selection prevents drift, while novelty prevents collapse. Evaluation results show that EVOL-RL consistently outperforms the majority-only baseline; e.g., training on label-free AIME24 lifts Qwen3-4B-Base AIME25 pass@1 from baseline's 4.6% to 16.4%, and pass@16 from 18.5% to 37.9%. EVOL-RL not only prevents in-domain diversity collapse but also improves out-of-domain generalization (from math reasoning to broader tasks, e.g., GPQA, MMLU-Pro, and BBEH). The code is available at: https://github.com/YujunZhou/EVOL-RL.

Zixiang Xu, Yanbo Wang, Yue Huang et al.

Large language models (LLMs) are increasingly applied to socially grounded tasks, such as online community moderation, media content analysis, and social reasoning games. Success in these contexts depends on a model's social reasoning ability - the capacity to interpret social contexts, infer others' mental states, and assess the truthfulness of presented information. However, there is currently no systematic evaluation framework that comprehensively assesses the social reasoning capabilities of LLMs. Existing efforts often oversimplify real-world scenarios and consist of tasks that are too basic to challenge advanced models. To address this gap, we introduce SocialMaze, a new benchmark specifically designed to evaluate social reasoning. SocialMaze systematically incorporates three core challenges: deep reasoning, dynamic interaction, and information uncertainty. It provides six diverse tasks across three key settings: social reasoning games, daily-life interactions, and digital community platforms. Both automated and human validation are used to ensure data quality. Our evaluation reveals several key insights: models vary substantially in their ability to handle dynamic interactions and integrate temporally evolving information; models with strong chain-of-thought reasoning perform better on tasks requiring deeper inference beyond surface-level cues; and model reasoning degrades significantly under uncertainty. Furthermore, we show that targeted fine-tuning on curated reasoning examples can greatly improve model performance in complex social scenarios. The dataset is publicly available at: https://huggingface.co/datasets/MBZUAI/SocialMaze

Haomin Zhuang, Yujun Zhou, Taicheng Guo et al.

Reinforcement Learning has demonstrated substantial improvements in the reasoning abilities of Large Language Models (LLMs), exhibiting significant applicability across various domains. Recent research has identified that tokens within LLMs play distinct roles during reasoning tasks, categorizing them into high-entropy reasoning tokens and low-entropy knowledge tokens. Prior approaches have typically focused on restricting updates to indirectly encourage exploration, yet they do not explicitly facilitate exploratory behavior during the token generation stage itself. In this work, we introduce a complementary approach that explicitly promotes exploration during sampling by applying distinct temperature settings for different token types. Specifically, our method employs higher temperatures for reasoning tokens to actively encourage exploration, while retaining lower temperatures for knowledge tokens to maintain factual correctness. Furthermore, we systematically investigate various multi-temperature scheduling strategies and their impacts within reinforcement learning contexts. Empirical evaluations on several reasoning benchmarks demonstrate that our approach significantly enhances the reasoning performance of LLMs. The code is available at https://github.com/zhmzm/Multi_Temperature_Verl.git.

Sihan Niu, Yifan Zhou, Zhikai Li et al.

This paper presents a unique solution to challenges in medical image processing by incorporating an adaptive curve grey wolf optimization (ACGWO) algorithm into neural network backpropagation. Neural networks show potential in medical data but suffer from issues like overfitting and lack of interpretability due to imbalanced and scarce data. Traditional Gray Wolf Optimization (GWO) also has its drawbacks, such as a lack of population diversity and premature convergence. This paper addresses these problems by introducing an adaptive algorithm, enhancing the standard GWO with a sigmoid function. This algorithm was extensively compared to four leading algorithms using six well-known test functions, outperforming them effectively. Moreover, by utilizing the ACGWO, we increase the robustness and generalization of the neural network, resulting in more interpretable predictions. Applied to the publicly accessible Cleveland Heart Disease dataset, our technique surpasses ten other methods, achieving 86.8% accuracy, indicating its potential for efficient heart disease prediction in the clinical setting.

Zhenwen Liang, Ruosen Li, Yujun Zhou et al.

Assessing the quality of Large Language Model (LLM) outputs presents a critical challenge. Previous methods either rely on text-level information (e.g., reward models, majority voting), which can overfit to superficial cues, or on calibrated confidence from token probabilities, which would fail on less-calibrated models. Yet both of these signals are, in fact, partial projections of a richer source of information: the model's internal hidden states. Early layers, closer to token embeddings, preserve semantic and lexical features that underpin text-based judgments, while later layers increasingly align with output logits, embedding confidence-related information. This paper explores hidden states directly as a unified foundation for verification. We show that the correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations. To validate this, we present Clue (Clustering and Experience-based Verification), a deliberately minimalist, non-parametric verifier. With no trainable parameters, CLUE only summarizes each reasoning trace by an hidden state delta and classifies correctness via nearest-centroid distance to ``success'' and ``failure'' clusters formed from past experience. The simplicity of this method highlights the strength of the underlying signal. Empirically, CLUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates, improving both top-1 and majority-vote accuracy across AIME 24/25 and GPQA. As a highlight, on AIME 24 with a 1.5B model, CLUE boosts accuracy from 56.7% (majority@64) to 70.0% (top-maj@16).