Multi-harness RL guide: LFM2.5 jumps 42% to 54% with 31% fewer tool calls
SergioPaniego · x · 2026-10-01
Adithya S K released an open guide to multi-harness RL, built on the observation that the same model behaves differently across agent harnesses. The method trains any model with RL on any task set inside real-world harnesses like Claude Code, Codex, and OpenCode, without changing harness or training code. Trained across four harnesses, LFM2.5-2.6B improved from 42% to 54% while making 31% fewer tool calls.
Related event: Hugging Face Open-Sources Ultimate Guide to Multi-Harness RL(6 posts)→
More from coding & agent
- New TLAPS-Bench blog: formally proving correctness of real-world system specs with TLA+ — tianyin_xu · 2026-11-19
- Pierre releases Words, a streaming Markdown parser 2x faster than md4x and 20x faster than Streamdown — andersonbcdefg · 2026-11-19
- Ex-Claude superfan: getting the best from Astra/Sol requires relearning how you prompt — mariofilhoml · 2026-11-19
- Rivet's lesson: JEV doesn't reason—split severity classification into tiny yes/no prompts — yawnxyz · 2026-11-19
- 16x Microsoft MVP demos a native PowerShell agent built on Microsoft's Intelligent Terminal — dfinke · 2026-11-19
- Musk: Treat Grok Bot like a really smart employee, says most users underuse it — elonmusk · 2026-11-19