Peng-Fei He

发表论文 42 篇 · 总被引 1108 次 · h-index 17

代表论文

• Red-Teaming LLM Multi-Agent Systems via Communication Attacks (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 131)
• Memory Injection Attacks on LLM Agents via Query-Only Interaction (2025 · Neural Information Processing Systems · 被引 116)
• Unveiling Privacy Risks in LLM Agent Memory (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 114)
• How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 90)
• Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 46)
• TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use (2025 · arXiv.org · 被引 35)