The unreasonable effectiveness of BM25 for agentic search
SessionEngineering trackconfirmed
The unreasonable effectiveness of BM25 for agentic search
- Day
- Day 2 — Session Day 1
- Time
- 11:10am-11:30am
- Room
- Track 3
- Track
- Search & Retrieval
Accessible with the Engineering pass and above.
About this session
GPT-5 is shockingly good at search, and that changes the "BM25 as a baseline" story. Using GPT-5 search trajectories from BrowseComp-Plus, I'll show how default BM25 parameters and evaluation harnesses can make lexical retrieval look weak, while real agent queries often play directly to BM25's strengths. Much like grep became a core retrieval primitive for coding agents, BM25 is re-emerging as a powerful primitive for agentic search.
Topics
Search & Retrieval (RAG, Deep Research, Web search)
