9 papers
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…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Shuqi Lu, Chaofan Li, Kun Luo +21
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed i…
Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
Bingyu Yan, Zhibo Zhou, Litian Zhang +6
Large language model-based multi-agent systems have recently gained significant attention due to their potential for complex, collaborative, and intelligent problem-solving capabil…
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,…
OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks
Litian Zhang, Chaozhuo Li, Yuting Zhang +3
LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions through inter-agent communication…
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…