Impressive paper showing how much the harness changes a coding agent's results.
This is a AI post classified by Jev as AI coding agents (research), kept by the AI Radar because it carries real work, not commentary.
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 the models. GPT-5.5 was run inside both Claude Code and Codex on the same 1,000 tasks. With a specialized PowerPoint workflow, it improved inside one harness and got worse inside the other. The harness also changed scores when the prompt was identical. ReFigBench asks coding agents to rebuild real arXiv overview figures as editable PowerPoint slides that keep the text, layout and connections. It covers ten configurations across the GPT, Claude, MiMo
Posted by elvis (320.8k followers) 1 h ago · 41 likes · 2.8k views · view the original post on X. Kept by the AI Radar as AI coding agents. Tools mentioned: academy.dair.ai.
More AI work like this
- Getting old personal laptop ready to take with me to Dallas for work trip along with my… — @MichaelGannotti
- Grok Build just beat Claude Code in a cross-project memory test. — @cb_doge
- Omarchy is really good to test such useful things on Agents.👇 — @BkashJosi
- Production is the worst place to find out if your code reviewer is good enough — @Macroscope
- 🏃🏽♂️Agent Merge: Keep Your PR Moving in VS Code — @code
- Also coming to Delta this week... — @zeddotdev
- >releases new benchmark — @synthwavedd
- DigitalOcean launched Managed Agents on its platform, supporting agent harnesses… — @testingcatalog
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 43.1k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 20:50 UTC. Full method.