Hugging Face and Liquid AI's LFM2.5 Jumps 12 Points Across Four Agent Harnesses
Hugging Face released an open framework that trains small models with reinforcement learning inside real coding agents like Claude Code and Codex, with no modifications to the harness.
Source
Hugging Face
Published
Author
AlphaSignal Newsroom
Read
1 min read
Hugging Face released an open framework that trains small models with reinforcement learning inside real coding agents like Claude Code and Codex, with no modifications to the harness.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
