4 papers · 1 filter
Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents
Bingyu Yan, Xiaoming Zhang, Chaozhuo Li +3
Self-evolving large language model agents improve their capabilities by distilling interaction trajectories into persistent experiences. Yet this mechanism introduces a new safety…
Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS
Bingyu Yan, Xiaoming Zhang, Jinyu Hou +4
While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating specialized agents and external tools,…
Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
Xiaozhe Zhang, Chaozhuo Li, Hui Liu +4
Large language models remain vulnerable to adversarial prompts that elicit harmful outputs. Existing safety paradigms typically couple red-teaming and post-training in a closed, po…
Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
Bingyu Yan, Ziyi Zhou, Xiaoming Zhang +5
Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantia…