// Context as Infrastructure for Agents //
This is a dev post classified by AGK Intelligence as Databases (a free resource), kept by the Dev Radar because it carries real work, not commentary.
// Context as Infrastructure for Agents // The RAGFlow team at InfiniFlow ran a harness with only BM25 and grep on MiniMax M3. It answered 85% of BrowseComp-Plus and 91% of FRAMES with no vector or compiled index. They then tested summary trees, PageIndex-style outlines, wikis, and graphs on top. None improved FRAMES accuracy, and the outline got worse at scale. The structures help with context cost. A navigation tree whose leaves are claim and evidence pairs cut query tokens by 91% when the evidence was enough, and added 1.9% when it was not. That averages to a 38% reduction. The savings
Posted by DAIR.AI (136.6k followers) 1 days ago · 120 likes · 9.2k views · view the original post on X. Kept by the Dev Radar as Databases.
More dev work like this
- Most developers treat database indexes like salt: sprinkle a little on every foreign key… — @iamspiggle
- Bringing Local Analytics to the Quant’s Desktop 🧮 — @duckdb
- Just launched a game on http://pgx.dev 🐘💣 — @alxshp
- HLD Interview Notes: Day 15/30 — @SCR01111
- On Chroma Cloud and looking at Qdrant? Writes stop Nov 22. — @qdrant_engine
- #SQL Commands! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch… — @gp_pulipaka
- Amazon RedShift Cookbook! #BigData #Analytics #DataScience #AI #MachineLearning #IoT… — @gp_pulipaka
- IronBeetle⚡️ Ep 126 — @TigerBeetleDB
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 20:22 UTC. Full method.