skill-retrieval

Tag

Cards List
#skill-retrieval

@dair_ai: Good measurement work on whether retrieved agent skills actually help. They report that agent skills that lift your agg…

X AI KOLs Timeline · 2026-09-03 Cached

The paper introduces Retrieval-Invoked Actual-Use Effect (RAE) to evaluate whether retrieved skills actually help LLM agents, showing that aggregate metrics can mislead by hiding negative effects on specific tasks.

0 favorites 0 likes
#skill-retrieval

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

arXiv cs.CL · 2026-08-07 Cached

This paper introduces SkillZip, a contract-preserving graph compression framework that compresses agent skill libraries at the section level, improving retrieval and compression efficiency while preserving procedural contracts and dependency closures.

0 favorites 0 likes
#skill-retrieval

SkillSight: Seeing Through Shared Descriptions for Accurate Skill Retrieval

arXiv cs.AI · 2026-07-22 Cached

SkillSight is a training-free retrieval framework that calibrates shared background in skill descriptions to improve skill retrieval accuracy for LLM agents, achieving up to 20.21 percentage point improvement in Recall@10 over dense retrievers.

0 favorites 0 likes
#skill-retrieval

Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval

arXiv cs.AI · 2026-07-08 Cached

Proposes SkillReranker, an inference-time reranking framework that decomposes tasks and skills to build a directed acyclic execution graph and uses a cross-encoder for scoring, improving task performance and efficiency in agent skill selection.

0 favorites 0 likes
#skill-retrieval

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries

arXiv cs.CL · 2026-05-11 Cached

This paper introduces Group of Skills (GoSkills), a retrieval method that organizes atomic skills into role-labeled execution contexts to improve agent performance within limited context budgets.

0 favorites 0 likes
#skill-retrieval

SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents

arXiv cs.AI · 2026-05-08 Cached

This paper introduces SkillRet, a large-scale benchmark for evaluating skill retrieval in LLM agents, addressing the challenge of selecting relevant skills from large libraries. It provides a dataset of over 17,000 skills and demonstrates that task-specific fine-tuning significantly improves retrieval performance.

0 favorites 0 likes
← Back to home

Submit Feedback