AutoHelix: Budgeted Iteration Lets Agents Escape Plateaus, GSM8K Jumps from 72%
elmanmansimov · x · 2026-07-31
The author shares insights from AutoHelix, an open-source harness for iterative optimization. By external verification and budgeted iterations, coding agents continuously improve metrics. On GSM8K, the agent autonomously chose SFT, rejection sampling, GRPO, etc., plateaued at 72% for two iterations, then GRPO unlocked further gains.
More from coding & agent
- Connected steps are not a workflow: nobody designs the handoff — usehive · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Running PolyStrata + Cline coding agent on a $0-fancy laptop at ~90 tok/s — rpwoerk · 2026-10-16
- How do you attribute agent gains: model training or infrastructure? — jrxna · 2026-10-16
- Feed Claude your books, blogs and top engineers' code for claude.md — 'it now writes better code than me' — blaizedsouza · 2026-10-16
- Open-source /label plugin auto-names and colors Claude Code sessions in one step — hermanschutte · 2026-10-16