Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Hugging Face Unveils ClawGym II: Black-Box RL Framework for Agent Harness Optimization

AI By Crimson AI Hugging Face Papers 18 August 2026 · 00:00 16 views
Share: X Telegram

A new black-box reinforcement learning framework from Hugging Face enables stable, scalable optimization of general agents through complex harnesses, achieving significant gains on ClawGym-Bench and other benchmarks.

Hugging Face Unveils ClawGym II: Black-Box RL Framework for Agent Harness Optimization

Key points

Hugging Face researchers have introduced ClawGym II, a unified black-box reinforcement learning (RL) framework designed to optimize general agents through complex harnesses. The framework addresses the challenges of scaling RL to long-horizon agent tasks by decoupling policy optimization from opaque harness execution.

The approach builds a sandbox-based execution infrastructure that isolates task environments and harnesses within temporary sandboxes, enabling large-scale concurrent rollouts. A serving proxy at the model boundary captures model calls, which are organized into prefix trees to reconstruct multi-turn trajectories. Both critic-based PPO and critic-free GRPO are adapted to optimize over these tree structures, while maintaining training-inference consistency.

Mix-harness training is a key innovation, allowing a single model to be jointly optimized by heterogeneous harnesses. Experiments with Qwen3-30A3B show that black-box RL improves Pass@1 on ClawGym-Bench by 9.98 and 14.81 points through OpenClaw and Claude Code, respectively, with stability over 200-400 optimization steps. Consistent gains are also observed on more challenging tasks like JobBench and OfficeQA.

The framework demonstrates effective, stable, and scalable optimization of general agents through black-box harnesses, supporting unified training across heterogeneous execution systems.

BenchmarkHarnessPass@1 Improvement
ClawGym-BenchOpenClaw+9.98
ClawGym-BenchClaude Code+14.81
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4