ClawGym: A Scalable Framework for Building Effective Claw Agents
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916017480925184 |
|---|---|
| author | Bai, Fei Song, Huatong Sun, Shuang Cheng, Daixuan Yang, Yike Hao, Chuan Li, Renyuan Chang, Feng Wei, Yuan Tao, Ran Dai, Bryan Yang, Jian Zhao, Wayne Xin Wen, Ji-Rong |
| author_facet | Bai, Fei Song, Huatong Sun, Shuang Cheng, Daixuan Yang, Yike Hao, Chuan Li, Renyuan Chang, Feng Wei, Yuan Tao, Ran Dai, Bryan Yang, Jian Zhao, Wayne Xin Wen, Ji-Rong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26904 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ClawGym: A Scalable Framework for Building Effective Claw Agents Bai, Fei Song, Huatong Sun, Shuang Cheng, Daixuan Yang, Yike Hao, Chuan Li, Renyuan Chang, Feng Wei, Yuan Tao, Ran Dai, Bryan Yang, Jian Zhao, Wayne Xin Wen, Ji-Rong Computation and Language Artificial Intelligence Machine Learning 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. |
| title | ClawGym: A Scalable Framework for Building Effective Claw Agents |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.26904 |