New research with Microsoft's and colleagues on training agents inside the harnesses they actually run in. (bookmark it) Why it matters: Age…

New research with Microsoft's and colleagues on training agents inside the harnesses they actually run in. (bookmark it) Why it matters: Agents today live inside elaborate harnesses like Claude Code, Codex, and OpenClaw. Those harnesses are hard to train end to end because open RL stacks cannot express stateful, multi-process harness inference. Most training happens in stripped-down environments that look nothing like deployment. OpenForgeRL closes that gap. A lightweight proxy serves the harness model calls while recording them as training data for a standard RL codebase, and a Kubernetes orchestrator runs each rollout in its own container. You train directly in the real harness, at scale. Using only hundreds to a few thousand tasks, OpenForgeGUI reaches 72.3 on WebVoyager, 63.0 on Online-Mind2Web, and 37.7 on OSWorld-Verified, beating open baselines of similar size and matching models several times larger. Harness choice turns out to be a training variable. Some harnesses are much harder to learn than others, and RL improves self-verification and multi-step completion while error recovery stays weak. That is a useful map for anyone doing agentic RL. Paper: https://arxiv.org/abs/2607.21557 Learn to build effective AI agents in our academy: https://academy.dair.ai/

Source: DAIR.AI (X) | 2026-07-24