The unreasonable effectiveness of BM25 for agentic search

Official Schedule Context

Official 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.

Related YouTube Video

No related AI Engineer channel video found yet.

Transcript Status

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

People

Notes