17 papers
ClashBench: Conflicts Leading Agents to Seize and Harm
Yuejin Xie, Yu Li, Dadi Guo +6
As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing resources with limited capacit…
SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
Qinghua Mao, Wanying Qu, Dadi Guo +8
The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to safety risks in both harmfu…
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Wanying Qu, Qinghua Mao, Yu Li +12
The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime contro…
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
Zhida He, Xia Hu, Baichen Le +20
Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the…
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
Jingwei Sun, Jianing Zhu, Yuanyi Li +3
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-w…
What Do EEG Foundation Models Capture from Human Brain Signals?
Ling Tang, Qian Chen, Jilin Mei +6
Clinical electroencephalogram (EEG) analysis rests on a hand-crafted feature catalog refined over decades, \emph{e.g.,} band power, connectivity, complexity, and more. Modern EEG f…
Understanding Generalization through Decision Pattern Shift
Huiqi Deng, Yibo Li, Quanshi Zhang +3
Understanding why deep neural networks (DNNs) fail to generalize to unseen samples remains a long-standing challenge. Existing studies mainly examine changes in externally observab…
Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking
Zhida He, Xiaoyu Wen, Han Qi +7
Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns. Recent training-based multi-turn jailbreak method…
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
Kaiwen Luo, Zhenhong Zhou, Leyan Wang +32
Advances in Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs). Among these, Large Audio Language Models (LALMs) are essential for realizi…
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
Chang Jin, An Wang, Zeming Wei +7
Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environm…
Attributing Emergence in Million-Agent Systems
Ling Tang, Jilin Mei, Qian Chen +6
Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents. LLM-powered multi-agent systems (MAS) combine such agents to simulate popul…
Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex
Zhonghao Yang, Yu Li, Yanxu Zhu +6
As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse…
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
Xiangyang Zhu, Yuan Tian, Qi Jia +14
The success of large language models (LLMs) in scientific domains has heightened safety concerns, prompting numerous benchmarks to evaluate their scientific safety. Existing benchm…
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Qihan Ren, Peng Wang, Ruikun Cai +8
A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT…
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
Yu Li, Haoyu Luo, Yuejin Xie +10
Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or…
A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
Tianyu Chen, Dongrui Liu, Xia Hu +2
Clawdbot is a self-hosted, tool-using personal AI agent with a broad action space spanning local execution and web-mediated workflows, which raises heightened safety and security c…
LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
Tianyu Chen, Chujia Hu, Ge Gao +3
Computer-use agents (CUAs) execute multi-stage tasks through tools, where an early unsafe decision can propagate to consequential actions. Evaluating only final outcomes can miss s…