12 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…
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Hefeng Zhou, Jinxuan Zhang, Jiong Lou +4
The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step tasks. However, when errors o…
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…
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…
Optimizing Soft Prompt Tuning via Structural Evolution
Zhenzhen Huang, Chaoning Zhang, Haoyu Bian +8
Soft prompt tuning leverages continuous embeddings to capture task-specific information in large pre-trained language models (LLMs), achieving competitive performance in few-shot s…
Epistemic Traps: Rational Misalignment Driven by Model Misspecification
Xingcheng Xu, Jingjing Qu, Qiaosheng Zhang +4
The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, ha…
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…
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report
Shanghai AI Lab, :, Xiaoyang Chen +35
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier…
Epitome: Pioneering an Experimental Platform for AI-Social Science Integration
Jingjing Qu, Kejia Hu, Jun Zhu +9
Large Language Models (LLMs) enable unprecedented social science experimentation by creating controlled hybrid human-AI environments. We introduce Epitome (www.epitome-ai.com), an…
Data Quality Control in Federated Instruction-tuning of Large Language Models
Yaxin Du, Rui Ye, Fengting Yuchi +4
Federated Learning (FL) enables privacy-preserving collaborative instruction tuning of large language models (LLMs) by leveraging massively distributed data. However, the decentral…