CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
CoworkEnv 透過工作流程引導任務建構及程式化驗證,合成可執行的 AI 協作訓練環境,供 PocketWorker 模型進行監督式微調與強化學習。以 Qwen3-VL-8B-Instruct 為例,微調後在 Claw-Eval 的平均分數由 46.6 升至 64.1,多輪任務提升 31.9 分。研究亦比較不同獎勵處理及信用分配設定下的強化學習訓練動態。
Published on Oct 18
Authors:
,
,
,
,
,
,
,
,
,
,
,
Abstract
CoworkEnv synthesizes executable training environments for AI coworkers using workflow-guided task construction and programmatic validation, enabling supervised fine-tuning and reinforcement learning of compact PocketWorker models that improve multi-turn coordination and tool use.
AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints. Constructing training experience for these capabilities requires coherent requests, service records, tool interfaces, and grading checks. We present CoworkEnv, a capability-guided framework for synthesizing executable training environments for AI coworkers. Workflow requirements guide task construction, and programmatic validation with feedback repair checks generated specifications and grading behavior. Teacher executions yield curated demonstrations for supervised fine-tuning (SFT), while student interactions provide rollouts and rewards for reinforcement learning (RL). Using these resources, we train compact PocketWorker models. For Qwen3-VL-8B-Instruct, SFT raises the mean score from 46.6 to 64.1 on Claw-Eval, including a 31.9-point gain on Multi-turn tasks. An SFT-only extension to ClawMark demonstrates applicability across coworker benchmarks. We further compare RL training dynamics across configurations that vary reward processing and credit assignment. Improving training rewards provide preliminary evidence that the constructed environments support policy optimization.
View arXiv page View PDF GitHub 3 Add to collection
Get this paper in your agent:
hf papers read 2610.24960
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.24960 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.24960 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.24960 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co