Jiaye Lin
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
SelSkill introduces a dual-granularity preference learning framework that treats skill use as a 'skill-or-skip' decision, significantly improving agent performance and execution precision in complex agentic tasks.
SelSkill introduces a dual-granularity preference learning framework that treats skill use as a 'skill-or-skip' decision, significantly improving agent performance and execution precision in complex agentic tasks.
This paper introduces SafeFlow, a defense framework for multi-agent systems that addresses the safety blind spot caused by task decomposition and role specialization by formalizing malicious cross-agent propagation as a semantic information-flow problem.
Papers
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
Haowen Dai, Zonghao Ying, Wenfeng Li, Xiangfan Wu +9 more
This paper introduces SafeFlow, a defense framework for multi-agent systems that addresses the safety blind spot caused by task decomposition and role specialization by formalizing malicious cross-age…