組合環境訓練提升通用智能體

Computer Science > Artificial Intelligence arXiv:2609.

33665 (cs) [Submitted on 27 Sep 2026] Title:CompoWorld: Compositional Environment Scaling for General Agents Authors:Xiao-Wen Yang, Weiyi Xu, Wen Da, Hang Xu, Canwei Li, Hong-Jie You, Pusen Dong, Yucheng Zeng, Zhaokai Luo, Yu-Feng Li, Yao Hu, Mu Chuan View a PDF of the paper titled CompoWorld: Compositional Environment Scaling for General Agents, by Xiao-Wen Yang and 11 other authors View PDF HTML (experimental) Abstract:Automatically generated environments provide a scalable source of interaction data for training general agents.

However, existing approaches mainly generate tasks within a single environment, while real-world workflows require agents to connect information and actions across multiple services.

We introduce Compositional Environment Scaling (\textbf{CompoWorld}), which expands the task space by composing a finite library of reusable services.

Coding agents turn tool specifications into verified services with typed states and shared interfaces, while a world model handles tools that cannot be reliably implemented.

A random-walk procedure connects services through dependency graphs, enabling the generation and verification of tasks that require information to flow across services.

Verified trajectories support supervised fine-tuning (SFT), while our Completion-Focused Rubric Reward guides reinforcement learning (RL) toward full task completion by emphasizing criteria with lower pass rates within each rollout group.

We construct 448 services exposing 10,130 tools and use 3K SFT trajectories and 1K RL tasks to train Qwen3.6-35B-A3B.Experimental results show that CompoWorld improves on its backbone by 9.17 points on average across eight benchmarks.

On AutomationBench, it surpasses frontier models such as Claude Opus 4.6 and leads all compared agent-specialized 35B-A3B models.Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2609.33665 [cs.AI] (or arXiv:2609.33665v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2609.

33665 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Xiao-Wen Yang [view email] [v1] Sun, 27 Sep 2026 15:25:01 UTC (835 KB) Full-text links: Access Paper: View a PDF of the paper titled CompoWorld: Compositional Environment Scaling for General Agents, by Xiao-Wen Yang and 11 other authorsView PDFHTML (experimental)TeX Source view license Current browse context: cs.

AI < prev | next > new | recent | 2026-09 Change to browse by: cs References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading...BibTeX formatted citation × loading...

Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.

ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?

) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.

AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?

) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.Which authors of this paper are endorsers?| Disable MathJax (What is MathJax?)