Agentic RL inside the harness: how LFM2.5 trains with sandboxes and tools
helloiamleonie · x · 2026-09-25
Leonie details the agentic RL stage: since models are mostly used through agent harnesses, train them inside the harness so they're already familiar with system prompts and built-in tools. Components: agentic office tasks (presentations, analysis reports), the harness the model works through, and a fresh sandbox per rollout with tool and filesystem access.
Related event: Liquid AI Releases LFM2.5-2.6B and Details Its On-Device Training Recipe(10 posts)→
More from coding & agent
- GitHub ships Agentic Workflows Gallery: ready-made AI agent workflows for repo tasks — marlene_zw · 2026-09-25
- Pydantic team open-sources Monty: a Python sandbox that starts in 1ms — samuelcolvin · 2026-09-25
- Ran the Same Build on 8 Agent Platforms: Only 2 Finished, 6 Failed to Post to Slack Silently — yiddo_bhushan · 2026-09-25
- Your data stack is about to get less forgiving: agents turn stale data into wrong actions — bigdata · 2026-09-25
- Bending Spoons runs 99% of AI traffic on self-hosted open models, thanks to evals — alex_verem · 2026-09-25
- AIMessage: An Open-Source P2P Memory Mesh So AI Agents Stop Forgetting Across Machines — Accomplished-Pen-491 · 2026-09-25