Showing cs.IRShow all
3 papers · 1 filter
cs.IR2026
Skills Know Their Neighbors: Cluster-Contrastive Capability Pages for Skill Retrieval
Zifei Wang, Wei Wen, Qiang Ji +1
As skill libraries grow, large language model agents must retrieve reusable skills from candidates that often share the same topic and vocabulary but implement different capabiliti…
cs.IR2026
Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints
Juntao Wu, Wei Wen, Xianting Huang +4
Evaluating the exhaustive search capabilities of large language models (LLMs) is plagued by a fundamental paradox: verifying completeness requires complete ground truth, yet high-e…
cs.IR2026
Skill Is Not Document: Query-Conditioned Compatibility for LLM Agent Skill Routing
Zifei Wang, Wei Wen, Qiang Ji +3
Large language model agents increasingly rely on reusable skills, making skill retrieval a critical front-end component of agent systems. Skill retrieval, however, is not ordinary…