Sign InOpen Brain
AI EngineerVideoSource Linked

The unreasonable effectiveness of BM25 for agentic search — Jo Kristian Bergum, Hornet.dev

Agent search changes the retrieval workload: models issue long, iterative queries and inspect literal matches. BM25 remains useful, but tuning, harness design, and end-to-end evaluation matter.

AI Engineer · Sep 16, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Agentic search is retrieval inside an agent loop, combining a tool-capable model, a harness, and a retrieval engine. BrowseComp+ has **830 questions** over roughly **105,000 documents**, with agents repeatedly querying and reformulating rather than issuing one search.

Practical Implication

Treat BM25 as a tunable primitive, not a fixed baseline. Long model-written queries, literal matching, filesystem workspaces, and progressive disclosure can give coding agents inspectable results they can search further with familiar tools.

Agent-Ready Context
Agentic search is retrieval inside an agent loop, combining a tool-capable model, a harness, and a retrieval engine. BrowseComp+ has **830 questions** over roughly **105,000 documents**, with agents repeatedly querying and reformulating rather than issuing one search.

Treat BM25 as a tunable primitive, not a fixed baseline. Long model-written queries, literal matching, filesystem workspaces, and progressive disclosure can give coding agents inspectable results they can search further with familiar tools.

The talk does not establish that BM25 always beats embeddings. Implementations and its **two hyperparameters** can materially change results, while single-query ranking metrics miss whether the full agent loop completes its task.
Connected Context · Feed7 Judgment

This narrows retrieval evaluation from one-shot ranking to whether an inspectable agent loop completes its task. It restores tuned BM25, literal matching, and filesystem search as serious primitives for long model-written queries, without establishing that they universally outperform embeddings or other context strategies.

Context Engineering in 2026 — Louis-François Bouchard, Omar Solano & Samridhi Vaid, Towards AISupplies a competing baseline: some workloads may perform better with full cached history, so retrieval must beat that option on the actual constraint.virgiliojr94/book-to-skillImplements the same progressive-disclosure pattern for stable documents by exposing an index first and loading referenced chapters on demand.Your agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, UnblockedExtends task-specific retrieval beyond literal document matching to permission-aware organizational context and conflict resolution.How to Generate Mergeable Code with a Context Engine — Peter Werry, UnblockedShows an implementation consequence for coding agents: retrieval must include decisions, conventions, and review history, not stop at plausible code matches.
Context Map
contextcodingresearch#retrieval#context-engineering#agent-evals
Uncertainty
The talk does not establish that BM25 always beats embeddings. Implementations and its **two hyperparameters** can materially change results, while single-query ranking metrics miss whether the full agent loop completes its task.