Researchers target RL training for agent harnesses
LEGO-RL and ClawGym II propose sandboxed, proxy-based methods for training long-horizon agents.
Why it matters
The work addresses a practical gap between agent harnesses used at inference time and policy-gradient training systems. Better harness-native RL methods could make long-horizon agent training more stable, observable and closer to real deployment conditions.
The key points
- 1.LEGO-RL targets coding-agent harnesses with proxying and sandbox orchestration.
- 2.ClawGym II frames harness training as black-box RL over captured calls.
- 3.Both papers emphasize training-inference consistency for long-horizon agents.
Two new arXiv papers describe reinforcement learning frameworks for agents that operate through complex harnesses used in long-horizon tasks such as coding. LEGO-RL focuses on coding-agent harnesses, using in-process LLM proxying, sandbox orchestration, validation and monitoring tools to align training with native harness execution. ClawGym II presents a black-box RL framework that isolates rollouts in temporary sandboxes, captures model calls at the serving boundary, reconstructs multi-turn trajectories with prefix trees, and adapts PPO and GRPO for the recovered structure.
⚡ Try this today
Read the papers before designing RL pipelines for coding or long-horizon agents that depend on harness execution.
Sources & original reporting
This brief summarizes and links to reporting from the publishers below.
- arXiv cs.AILEGO-RL: Harness-Native Reinforcement Learning for Coding AgentsAug 19, 12:00 PM↗
- arXiv cs.CLClawGym II: Exploring Black-Box RL on Agent HarnessAug 18, 12:00 PM↗
- arXiv cs.AIClawGym II: Exploring Black-Box RL on Agent HarnessAug 18, 12:00 PM↗
- arXiv cs.LGClawGym II: Exploring Black-Box RL on Agent HarnessAug 18, 12:00 PM↗
- HF Daily PapersClawGym II: Exploring Black-Box RL on Agent HarnessAug 17, 4:00 AM↗
Enjoyed this brief? Get the next one in your inbox.
More in Research
HarnessRisk benchmarks agent harness safety risks
The benchmark tests safety failures across agent harness lifecycle phases and configurations.
Agent Lightning v1.0 targets harnessed agentic RL
The framework connects arbitrary agent harnesses to RL training through an LLM endpoint proxy.
Paper tests cross-model memory transfer for LLMs
Researchers study how frozen learned memory can move between model backbones using a target-side reader.