---
title: "The unreasonable effectiveness of BM25 for agentic search"
category: "talks"
date: "2026-06-29"
time: "11:10am-11:30am"
track: "Search & Retrieval"
room: "Track 3"
speakers: ["Jo Kristian Bergum"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Search & Retrieval"
scheduleRoom: "Track 3"
scheduleLabels: ["Search & Retrieval", "Track 3", "session", "confirmed"]
---
# The unreasonable effectiveness of BM25 for agentic search

## Conference Context
- Date/time: 2026-06-29 · 11:10am-11:30am
- Track/room: Search & Retrieval · Track 3
- Speaker(s): Jo Kristian Bergum
- Session type/status: session · confirmed

- Track: Search & Retrieval
- Room: Track 3
- Session type: session
- Status: confirmed

## Session Description
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.

## Media Evidence
No related AI Engineer channel video found yet.

These are phone-photo slide captures from the Google Photos `AIE Slides` album. They are supporting slide evidence and do not override official schedule fields.
- [[google-photos-aie-slides-9gWZzS1EpXM1C5eK6-bm25-agentic-search-slides]] - Google Photos Slides: The Unreasonable Effectiveness of BM25 for Agentic Search (confidence: high).

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
No linked video, transcript, or slide source has been attached yet.

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

## People
- [[jo-kristian-bergum]]

## Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.

## Synthesis
### Synthesized Breakdown
# The unreasonable effectiveness of BM25 for agentic search ## Conference Context - Date/time: 2026-06-29 · 11:10am-11:30am - Track/room: Search & Retrieval · Track 3 - Speaker(s): Jo Kristian Bergum - Session type/status: session · confirmed - Track: Search & Retrieval - Room: Track 3 - Session type: session - Status: confirmed ## Session Description 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. ## Media Evidence No related AI Engineer channel video found yet.

### Speaker And Company Context
- [[jo-kristian-bergum|Jo Kristian Bergum]] — CEO at [[hornet-dev|Hornet.dev]].

### Topics Covered
- [[agentic-search]]
- [[coding-agents]]

### Derived Links And Source Material

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.