2 citations · 2 across the 2 of their papers we have counts for
4 papers
SkillRep: Characterizing and Understanding the Representation Design Space of Agent Skill Retrieval
Tianyi Sun, Pengfei Yao, Yanze Wang +5
Retrieving the right skill from a large library is essential for LLM agents, yet requests and skills are written for different purposes and in different words. Existing retrievers…
Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement
Yanze Wang, Pengfei Yao, Tianyi Sun +5
LLM agents retrieve skills from public hubs that hold up to about 100,000 entries and serve many models. As models improve, a hub must find the skills a given model has internalize…
SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents
Yanze Wang, Pengfei Yao, Tianyi Sun +7
Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them i…
EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer
Xingze Gao, Chuanrui Hu, Hongda Chen +9
Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and ve…