This work presents CoworkEnv, a capability-guided framework for synthesizing executable training environments for AI coworkers, and compares RL training dynamics across configurations that vary reward processing and credit assignment.
Abstract
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.
Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires maintaining consistency among task objectives, executable resources, user behavior, and success criteria. We introduce Cowork-Gym, a framework that s...
An-Ni Zou, Cheng Chen, Jia-Ji Deng et al.· 1 citation
Navalia is introduced, a framework for Cowork Agents that combines verifiable task synthesis with long-horizon post-training post-training capabilities and generalizes to broader Cowork settings, including general office tasks.
WorkRover is introduced, a framework for training long-horizon cowork agents through recursive environment evolution that enables construction agents to jointly build and validate semantically aligned work contexts, executable tasks, and evidence-grounded verifiers, adapting their actions to workspace state and executi...
Hang He, Lin-Ting Wang, Guan-Ming Liu et al.· 1 citation
This work introduces Compositional Environment Scaling (\textbf{CompoWorld}), which expands the task space by composing a finite library of reusable services, and guides reinforcement learning toward full task completion by emphasizing criteria with lower pass rates within each rollout group.
Xiao-Wen Yang, Wei-Yi Xu, Wen Da et al.· arXiv.org· 1 citation
Scaling supervised fine-tuning for working agents requires not only broad coverage of professional tasks, but also expert demonstrations that faithfully carry out professional workflows to completion. However, missing or inconsistent task information can disrupt expert demonstrations, weakening the resulting supervisio...
Ziyang Zeng, Ting-Yang Chen, Jia Deng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.