Model Releases
Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.…
Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro
Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro V2 with the same model. The authors report that the gain comes from the harness. The model-agnostic harness name is LongHarness, built for corpora of 100M tokens and more. Why it works: Standard agent harnesses keep evidence and conclusions mixed into one growing chat history. Retrieval keeps expanding without closing the actual gap, and corrections stop reaching the answer. LongHarness stores both as explicit state. Open conclusions decide what to retrieve next, and each new piece of evidence confirms or revises the conclusions that asked for it. On the same benchmark, it beats Claude Code by 12.1 points on V1 and Codex by 18.9 points on V2. https://arxiv.org/abs/2610.13075 Chat with Paper: https://academy.dair.ai/papers/longharness-advancing-agentic-reasoning-over-100m-token-corpora-via-stateful-evi-2610.13075
Related
- Learn to build a custom harness, folks. Mods in Claude Code, DeepSeek Harness, and now Pi Durable. What do these all have in common? Increas…
- Impressive paper showing how much the harness changes a coding agent's results. Harnesses do play a huge role in what you are getting out of…
- Banger paper from Google on agent harnesses for long-horizon tasks. (bookmark it) Google Research built a many-agent harness for long mathem…
- Learn to optimize your own harness, folks. You can squeeze much more performance and value from a harness. This work claims that a self-modi…
Source: DAIR.AI (X) | 2026-10-13