RL-trained LFM2.5-24B adapter matches accuracy with 20% fewer tool calls
yb2698 · x · 2026-11-02
The harness-hub team finished LoRA training a Hermes agent adapter for LiquidAI's LFM2.5-24B-A2B, reporting no accuracy drop on held-out test tasks while cutting tool calls by 20%. A collection of RL-trained adapters for different agent harnesses (Hermes, Claude Code, pi) is now on Hugging Face, with GGUF versions included.
Related event: Hermes LoRA Adapter Released for LFM2.5-24B, Cutting Tool Calls 20%(2 posts)→
More from coding & agent
- GitHub Actions has a lesser-known ubuntu-slim runner: 1 CPU, 5GB RAM, cheaper CI — DanielLockyer · 2026-11-02
- Before automating a workflow with AI, ask if anyone understands it end to end — djgoel123 · 2026-11-02
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02