CompoWorld represents each service with typed state, shared interfaces and explicit transition logic.
Composed service environments improve agents across diverse tool-use benchmarks
CompoWorld generates verifiable workflows spanning reusable digital services, then uses them for supervised and reinforcement learning.
Independent
Xiao-Wen Yang · Weiyi Xu · Wen Da · Hang Xu · Canwei Li · Hong-Jie You · +6 more
Research Digest··2 min read
Thread:RL for Tool Agents
The authors built 448 executable services with 10,130 tools and composed them into tasks where information and actions must flow between applications.
Why this paper
Independent · Part of RL for Tool Agents, now 13 papers
In one line
CompoWorld generates cross-service tasks from reusable services to train agents that outperform frontier models.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§