All sessions
Search & RetrievalSession
The unreasonable effectiveness of BM25 for agentic search
Jo Kristian Bergum
- When
- Tuesday, June 3011:10 AM – 11:30 AM · 20 min
- Where
- Track 3San Francisco, CA · imported from ai.engineer's public schedule feed
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.
Speaker
More in Search & Retrieval
- Pinecone 2.0Tuesday, June 30 · 10:45 AM – 11:05 AM · Track 3
- The Search Engine for the Agentic WebTuesday, June 30 · 11:40 AM – 12:00 PM · Track 3
- Rebuilding the web for agentsTuesday, June 30 · 12:05 PM – 12:25 PM · Track 3
- If we want them to do Knowledge Work, we need to design Knowledge AgentsTuesday, June 30 · 1:30 PM – 1:50 PM · Track 3
- Your Agreements Are a Database You Can't Query. We're Fixing ThatTuesday, June 30 · 1:55 PM – 2:15 PM · Track 3
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.