WorkRover trains long-horizon cowork agents via recursive environment evolution
An arXiv paper introduces WorkRover, a framework for training long-horizon cowork agents through recursive environment evolution: its harness-driven synthesis has construction agents jointly build semantically aligned work contexts, executable tasks and evidence-grounded verifiers, adapting their actions to workspace state and execution feedback instead of following a fixed pipeline. To support environment evolution the authors propose Factorial Compatibility Replay (FCR), which uses rollout feedback to evaluate combinations of component revisions and selects the smallest validated repair, plus Verifier-to-Turn Credit Assignment (VTCA), which augments trajectory-level GRPO advantages with deterministic workspace-progress signals. Post-training Qwen3.5-35B-A3B with WorkRover yields WorkRover-35B-A3B, which the authors report exceeds the base model by 26.27 percentage points on JobBench, 29.32 points on OfficeQA Pro and 413.25 Elo points on GDPval v2.
If the self-reported gains hold up, recursive environment evolution could lower the cost of building training data for long-horizon office-work agents.