CompoWorld is a framework for training generalist software agents by generating tasks that require actions across multiple services, such as email, calendars, and databases. It creates a library of 448 typed services with 10,130 tools, then composes them into workflows via dependency graphs. A random-walk procedure selects services and edges; an agentic system instantiates goals and verifies solvability. Verified successful trajectories are used for supervised fine-tuning (SFT), while a Completion-Focused Rubric Reward guides reinforcement learning (RL) to focus on unmet subgoals. Training Qwen3.6-35B-A3B with 3K SFT trajectories and 1K RL tasks yielded a 9.17 point average improvement over its backbone across eight benchmarks. On AutomationBench, it surpassed Claude Opus 4.6 and led all compared agent-specialized 35B-A3B models.
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
In one line
CompoWorld generates cross-service tasks from reusable services to train agents that outperform frontier models.
Before you read this
Two ideas this paper builds onworld model for agentsA predictive environment model that agents use to simulate outcomes, enabling planning, reasoning, and long-horizon task execution.115 papers →reinforcement learning with verifiable rewardsReinforcement learning that uses rewards from objectively checkable signals like correct answers or verification feedback.163 papers →
Read it as
The authors built 448 executable services with 10,130 tools and composed them into tasks where information and actions must flow between applications.
CompoWorld represents each service with typed state, shared interfaces and explicit transition logic.
How it works
stage by stageThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.