online-mind2web-86924349·3 events·first seen Aliases: Online-Mind2Web
OpenForgeRL is an open-source framework that enables end-to-end reinforcement learning training of AI agents operating within real inference harnesses (e.g., Claude Code, Codex, OpenClaw) and diverse environments. It uses a lightweight proxy to record harness model calls as training data for standard RL codebases like veRL, plus a Kubernetes orchestrator for scalable rollouts in isolated containers. Trained agents (OpenForgeClaw and OpenForgeGUI) achieve competitive results on benchmarks including ClawEval, OSWorld-Verified, Online-Mind2Web, and WebVoyager, matching or surpassing models several times larger in GUI tasks. The work also analyzes how harness choice and RL shape agent behavior, finding meaningful variation in learnability across harnesses.
This edition of The Batch covers five significant AI developments: Alibaba's Qwen3.7-Max reasoning model with 1M token context and agentic capabilities ranking fifth on the Artificial Analysis Intelligence Index; an OpenAI reasoning model resolving the 80-year-old Erdős planar unit distance problem; Nvidia's Gated DeltaNet-2 outperforming Mamba-3 and other linear attention architectures; Trump pulling back a proposed AI regulation executive order; and Microsoft Research's Fara1.5 computer-use agent family beating OpenAI Operator and Google Gemini on the Online-Mind2Web benchmark.
Anthropic has released Claude Opus 4.8, a new frontier model in their Claude lineup. The announcement appeared on Anthropic's official news page and generated significant community engagement on Hacker News with over 1,000 points and 800+ comments. Specific capability details and benchmarks are not available from the source snippet alone.