5 papers
MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents
Yiwen Ma, Songjun Tu, Qichao Zhang +3
Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evidence paradigm assumes retri…
UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
Songjun Tu, Chengdong Xu, Qichao Zhang +6
Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while mi…
Metaphor-based Jailbreak Attacks on Text-to-Image Models
Chenyu Zhang, Lanjun Wang, Yiwen Ma +3
Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversaria…
PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review
Songjun Tu, Yiwen Ma, Jiahao Lin +6
Large language models can generate fluent peer reviews, yet their assessments often lack sufficient critical rigor when substantive issues are subtle and distributed across a paper…
Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning
Chenyu Zhang, Lanjun Wang, Yiwen Ma +2
Text-to-Image(T2I) models typically deploy safety filters to prevent the generation of sensitive images. Unfortunately, recent jailbreaking attack methods manually design instructi…