Comparative Approaches to Agent Retrieval over Large Skill Libraries
Agents backed by large skill libraries must decide which skills to load and in what order. Loading the entire library into context is expensive and provides no structure for autonomous sequencing. We study two systems for this problem over a corpus of 690 skills: a hybrid ranker combining lexical and dense-embedding retrieval for sparse, on-demand loading, and a typed knowledge graph encoding…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
