Tag
This paper formalizes and empirically measures whether semantic retrieval via Language Server Protocol saves tokens for coding agents, finding that benefits are conditional and often negative, suggesting an adaptive tool-routing approach.
A controlled scaling study of retrieval-augmented generation paradigms finds that BM25 lexical retrieval outperforms agentic and graph-based retrieval at scale, while agentic search only leads on small corpora.
This paper introduces Pi-Serini, a BM25-based agentic search system that demonstrates lexical retrieval can suffice for deep search when agents refine queries, achieving high accuracy and reducing costs compared to default settings.