ClawGym: A Scalable Framework for Building Effective Claw Agents

TL;DR

ClawGym introduces a comprehensive, scalable framework for developing, training, and evaluating Claw-style personal agents using synthesized datasets, hybrid verification, and benchmark resources.

Contribution

It provides a systematic platform for synthesizing training data, training models, and benchmarking Claw agents, addressing scalability and verifiability challenges.

Findings

Constructed a dataset of 13.5K tasks from persona-driven intents.

Trained ClawGym-Agents via supervised fine-tuning and reinforcement learning.

Developed ClawGym-Bench with 200 benchmark instances for evaluation.

Abstract

Claw-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 have been released at https://github.com/ClawGym.