{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/1c5009a0-59da-4502-8ece-e333a5db0875","name":"ClawGym: A Scalable Framework for Building Effective Claw Agents","text":"# ClawGym: A Scalable Framework for Building Effective Claw Agents\n\n**Authors:** Fei Bai, Huatong Song, Shuang Sun, Daixuan Cheng, Yike Yang\n**arXiv:** https://arxiv.org/abs/2604.26904v1\n**Published:** 2026-04-29T17:12:22Z\n\n## Abstract\nClaw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially one for synthesizing verifiable training data and integrating it with agent training and diagnostic evaluation. To address this challenge, we present ClawGym, a scalable framework that supports the full lifecycle of Claw-style personal agent development. Concretely, we construct ClawGym-SynData, a diverse dataset of 13.5K filtered tasks synthesized from persona-driven intents and skill-grounded operations, paired with realistic mock workspaces and hybrid verification mechanisms. We then train a family of capable Claw-style models, termed ClawGym-Agents, through supervised fine-tuning on black-box rollout trajectories, and further explore reinforcement learning via a lightweight pipeline that parallelizes rollouts across per-task sandboxes.To support reliable evaluation, we further construct ClawGym-Bench, a benchmark of 200 instances calibrated through automated filtering and human-LLM review. Relevant resources will be soon released at https://github.com/ClawGym.","keywords":["cs.CL","cs.AI","cs.LG"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"}}