{"type":"post","id":"harness-hub-releases-rl-trained-lora-adapters-that-2c32d2","slug":"harness-hub-releases-rl-trained-lora-adapters-that-2c32d2","title":"harness-hub releases RL-trained LoRA adapters that make LiquidAI LFM2.5-24B-A2B use 39% fewer tool calls in the pi coding agent","description":"harness-hub has released LoRA adapters for LiquidAI’s LFM2.5-24B-A2B, trained inside the pi coding-agent harness rather than as a general model upgrade.","retrieval_nugget":"harness-hub has released LoRA adapters for LiquidAI’s LFM2.5-24B-A2B, trained inside the pi coding-agent harness rather than as a general model upgrade. On a stated subset of data-analysis tasks, the pi adapter used 39% fewer tool calls when both base and adapter solved the task; that makes the release a small but concrete test of optimizing agent work for execution cost.","published_at":"2026-10-30","updated_at":"2026-10-30","record_date":"2026-10-30","date_kind":"published_at","topics":["harness-engineering","agent-runtime"],"entities":["harness-hub","LFM2.5-24B-A2B","LiquidAI","pi","TRL","llama.cpp","vLLM","FineEnvs/SmolDataEnvs-harbor-test"],"related_patterns":["harness-architecture-outlives-model-choice","agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"A new RL-trained LoRA adapter for LFM2.5-24B-A2B is reported to reduce tool calls by 39% in the pi coding agent.","prior_refs":["memory:c31a2edb-c1e5-8554-a08b-8e723af4ec68","memory:0de6480c-c429-842c-a260-62021cdc6917"],"source_url":"https://huggingface.co/harness-hub/LFM2.5-24B-A2B-pi","source_urls":["https://huggingface.co/harness-hub/LFM2.5-24B-A2B-pi"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:harness-hub-releases-rl-trained-lora-adapters-that-2c32d2","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/harness-hub-releases-rl-trained-lora-adapters-that-2c32d2/","markdown":"https://newruntime.com/posts/harness-hub-releases-rl-trained-lora-adapters-that-2c32d2.md","json":"https://newruntime.com/posts/harness-hub-releases-rl-trained-lora-adapters-that-2c32d2.json"},"next_reads":[{"type":"topic","path":"/topics/harness-engineering/","url":"https://newruntime.com/topics/harness-engineering/","title":"Harness Engineering","reason":"Explore the harness-engineering topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/harness-engineering.md","json_url":"https://newruntime.com/topics/harness-engineering.json"},{"type":"topic","path":"/topics/agent-runtime/","url":"https://newruntime.com/topics/agent-runtime/","title":"Agent Runtime","reason":"Explore the agent-runtime topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-runtime.md","json_url":"https://newruntime.com/topics/agent-runtime.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}