16 papers
ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents
Kai Wang, Zeming Wei, BiaoJie Zeng +7
As large language model (LLM) agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent hijacked by a malicious third-p…
JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills
Xiaoyu Wen, Jiajia Li, Zhida He +11
Automated red-teaming has produced a growing collection of attack strategies, yet they typically remain scattered across prompts and workflows, making them difficult to systematica…
Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations
Xuan Liu, Hefeng Zhou, Sicheng Chen +6
When distributed agents exchange text across organizational boundaries, privacy leakage arises not only from explicit identifiers but also from distributional signatures such as fo…
AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
Yulei Ye, Wenhao Li, Zhong Wen +23
Despite the rapid deployment of LLMs into classrooms, validating educational AI remains uniquely intractable: interventions act on developing learners whose cognitive and social tr…
PhyGround: Benchmarking Physical Reasoning in Generative World Models
Juyi Lin, Arash Akbari, Yumei He +13
Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, ev…
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…
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…
TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
Kai Wang, Biaojie Zeng, Zeming Wei +7
With the rapid development of LLM-based multi-agent systems (MAS), their significant safety and security concerns have emerged, which introduce novel risks going beyond single agen…
MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
Xiaoyu Wen, Zhida He, Han Qi +7
Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on s…
RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
Zeming Wei, Qiaosheng Zhang, Xia Hu +1
Large Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT) reasoning, yet also face safety issues similar to those of basic language models. I…
CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
Zhao Tong, Chunlin Gong, Yiping Zhang +5
From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response s…
KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning
Qitan Lv, Tianyu Liu, Qiaosheng Zhang +2
Despite the impressive performance of large language models (LLMs) pretrained on vast knowledge corpora, advancing their knowledge manipulation-the ability to effectively recall, r…
The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs
Zibo Zhao, Yuanting Zha, Haipeng Zhang +1
Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT counterparts. Yet the mechanism of how…
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
Shanghai AI Lab, :, Yicheng Bao +115
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…
The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models
Xingcheng Xu
Reinforcement learning (RL) plays a crucial role in shaping the behavior of large language and reasoning models (LLMs/LRMs). However, it often produces brittle and unstable policie…
A Global Dataset Mapping the AI Innovation from Academic Research to Industrial Patents
Haixing Gong, Hui Zou, Xingzhou Liang +4
In the rapidly evolving field of artificial intelligence (AI), mapping innovation patterns and understanding effective technology transfer from research to applications are essenti…