Metraipolis › archive › dc_ce2b3fdeca84
CompoWorld: Compositional Environment Scaling for General Agents — arXiv:2609.33665
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33665
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:57:00.406Z
- SHA-256 of the archived text
a64e24ca54b67045f59c1d325c2c8aff50a34cb5c97d0af73c89ce356d95c3f2- Stable URL of this page
https://metraipolis.com/documento/dc_ce2b3fdeca84
How to cite
CompoWorld: Compositional Environment Scaling for General Agents — arXiv:2609.33665 — arXiv (en), https://arxiv.org/abs/2609.33665 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce2b3fdeca84 (Metraipolis archive dc_ce2b3fdeca84, sha256 a64e24ca54b67045f59c1d325c2c8aff50a34cb5c97d0af73c89ce356d95c3f2)
BibTeX
@misc{dcce2b3fdeca84,
title = {CompoWorld: Compositional Environment Scaling for General Agents — arXiv:2609.33665},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33665},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce2b3fdeca84; sha256 a64e24ca54b67045f59c1d325c2c8aff50a34cb5c97d0af73c89ce356d95c3f2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33665. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.33665 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:01.330Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).