跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-13AI 評分44

WorkRover:透過遞迴式環境演化擴展長時程協作智能體訓練

WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

AI 導讀

WorkRover 框架透過遞迴式環境演化訓練長時程協作智能體,並用於後訓練 Qwen3.5-35B-A3B,得到 WorkRover-35B-A3B。WorkRover-35B-A3B 在 JobBench、OfficeQA Pro 及 GDPval v2 的評分,較 Qwen3.5-35B-A3B 分別高 26.27 個百分點、29.32 個百分點及 413.25 Elo 分。

正文

Published on Oct 13

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require further testing and refinement after initial generation, and correcting defects in a task may also require updating its work context and verifier. However, existing construction pipelines offer limited support for such iterative refinement while keeping these components aligned. We introduce WorkRover, a framework for training long-horizon cowork agents through recursive environment evolution. Its harness-driven synthesis 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 execution feedback rather than following a fixed construction workflow. To support environment evolution, we introduce Factorial Compatibility Replay (FCR), which uses rollout feedback to evaluate combinations of component revisions through dependency-closed replay and selects the smallest validated repair among tested candidates while preserving task requirements and evaluation constraints. To provide finer-grained training signals, we propose Verifier-to-Turn Credit Assignment (VTCA), which augments trajectory-level GRPO advantages with signals from deterministic workspace-progress checks and assigns a bounded share of positive-progress credit to prerequisite turns using recorded tool-output and artifact dependencies. Using WorkRover, we post-train Qwen3.5-35B-A3B to obtain WorkRover-35B-A3B and evaluate it on several cowork-agent benchmarks. Its reported scores exceed those of Qwen3.5-35B-A3B by 26.27 percentage points on JobBench, 29.32 percentage points on OfficeQA Pro, and 413.25 Elo points on GDPval v2. These results suggest that WorkRover offers a promising foundation for scalable training of long-horizon cowork agents.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.18067

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/2610.18067 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/2610.18067 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/2610.18067 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