5 papers
BRA-Audit: Budgeted Runtime Auditing for LLM Multi-Agent Systems via Cumulative-Exposure Audit-Point Placement
Kaixiang Wang, Yidan Lin, Jiong Lou +1
LLM-based multi-agent systems (LLM-MAS) solve complex tasks through specialized collaboration, but inter-agent dependencies can propagate hallucinated or malicious outputs into sys…
Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents
Yidan Lin, Kaixiang Wang, Jiong Lou +1
The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse information across interacti…
E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory
Kaixiang Wang, Yidan Lin, Jiong Lou +3
The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical…
OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
Kaixiang Wang, Jiong Lou, Zhaojiacheng Zhou +1
Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agent…
MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS
Kaixiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov +2
Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the network. Existing defenses face a fu…