OpenForgeRL: Train Harness-native Agents in Any Environment
Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While powerful, these complex harnesses also make agents hard to train end-to-end with open infrastructure, whose SFT/RL stacks cannot natively express stateful, multi-process harness inference. To address this, we present OpenForgeRL, an open-source framework for training harness-based agents end-to-end in diverse environments.
Record details
Published: 23 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Agents & autonomy · Environment
Retrieved: 25 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
arXiv · 23 July 2026
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
arXiv · 23 July 2026
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
arXiv · 23 July 2026
From Grasping to Speaking: Generative AI-Based Environment-Grounded VR Communication Training for Autistic Individuals
arXiv cs.HC · 23 July 2026
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
HuggingFace Daily Papers · 23 July 2026
SceneActBench: Can Agents Act on the 3D Scenes They See?
HuggingFace Daily Papers · 23 July 2026
How to cite this record
ethics.ai (23 July 2026), “OpenForgeRL: Train Harness-native Agents in Any Environment,” evidence record 13464, https://ethics.ai/record/13464 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.