Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

摘要

Recent advances in large language model (LLM) have empowered autonomous agents to perform complex tasks that require multi-turn interactions with external tools and environments. However, scaling such agent training is limited by the lack of diverse and reliable environments. In this paper, we propose Agent World Model (AWM), a fully synthetic environments generation pipeline. Using this pipeline, we scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets (35 tools per environment on average) and obtain high-quality observations. Notably, these environments are code-driven and backed by databases, providing more reliable and consistent state transitions compared to environments simulated by LLMs. Moreover, they enable more efficient agent interaction compared to collecting trajectories from realistic environments. To demonstrate the effectiveness of this resource, we perform large-scale reinforcement learning for multi-turn tool-use agents. Thanks to the fully executable environments and accessible database states, we can also design reliable reward functions. Experiments on three benchmarks validate that training exclusively in synthetic environments, rather than benchmark-specific ones, yields strong out-of-distribution generalization.