paper-with-me

홈 › Papers

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS

2026-05-25 · Bingyu Yan, Xiaoming Zhang, Jinyu Hou, Chaozhuo Li, Ziyi Zhou, Yiming Hei, Litian Zhang arxiv

While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating specialized agents and external tools, the implicit trust in tool outputs creates a critical attack surface. Existing tool attacks are limited by domain specificity or fixed and static templates. To address these challenges, we propose Evo-Attacker, which formulates the tool attack as a self-evolving, memory-augmented reinforcement learning process. Evo-Attacker constructs a dynamic attack memory and employs deliberative reasoning to retrieve adversarial patterns and strategize modifying interventions at critical moments. Furthermore, we introduce Attack-Flow GRPO to optimize intermediate reasoning steps via terminal outcomes, addressing the long-horizon credit assignment challenge. Comprehensive experiments demonstrate that Evo-Attacker consistently outperforms baselines, highlighting its generalization and evolutionary capabilities and the urgent need for defensive tool safeguards.

📄 PDF Abstract BibTeX arXiv:2605.25389

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents

2026-05-20 · Sikuan Yan, Ahmed Bahloul, Ercong Nie, Susanna Schwarzmann 외 arxiv

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-…

Reinforcement Learning

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections

2026-02-17 · Xianglin Yang, Yufei He, Shuo Ji, Bryan Hooi 외 arxiv

Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external …

Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

2026-05-28 · Ziyan Liu, Zhezheng Hao, Yeqiu Chen, Hong Wang 외 arxiv

Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing approaches typically train these memory policies using outcome-base…

Reinforcement Learning

Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning

2024-10-14 · Hung Le, Kien Do, Dung Nguyen, Sunil Gupta 외

Effective decision-making in partially observable environments demands robust memory management. Despite their success in supervised learning, current deep-learning memory models struggle in reinforcement learning enviro…

Decision MakingManagementMeta Reinforcement Learningreinforcement-learning+1

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

2026-01-05 · Yi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan 외 arxiv

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM…

Reinforcement Learning