CaP-X open-sources agentic robotics toolkit, benchmark, and RL setup

Jim Fan announced the open-source release of CaP-X, an agentic robotics framework in which LLM-driven agents control robot arms and humanoids through perception and actuation APIs.

The release includes CaP-Gym with 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR, and CaP-Bench, which evaluates 12 frontier LLMs and VLMs across 8 tiers.

The post also reports that a 7B open-source model rose from 20% to 72% success after 50 RL training iterations, with synthesized programs transferring to real robots.