SFT on agent traces with TRL lifts a 2B model from 5.5% to 34.4% on held-out tasks
SergioPaniego · x · 2026-11-10
Sergio Paniego shares a fully open post-training recipe: a large model acts as a coding agent in opencode via OpenEnv, its solved tasks become SFT training data, and a 2B model jumps from 5.5% to 34.4% on held-out tasks. Full guide and code are open.
More from coding & agent
- YC F26's 0.security Launches Autonomous Security Team That Ships Fixes, Claims 30+ Linux 0-Days — ycombinator · 2026-11-11
- A Swarm of 10 DeepSeek Agents With an Intercom Turns Out Extremely Effective at Finding Exploits — andersonbcdefg · 2026-11-11
- DIY AI neon sign: LILYGO display + Hermes Agent + LFM3-Audio voice terminal — alexcovo_eth · 2026-11-11
- Vercel Security Review flags 57,897 vulnerabilities in first week, agent auto-patches 14,665 — cramforce · 2026-11-11
- RLVR lets small models close the coding gap; Python's dynamic typing hurts pretraining — mdancho84 · 2026-11-11
- 50 researchers from ByteDance, Alibaba, Tencent release 303-page code AI field guide — mdancho84 · 2026-11-11