Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

TL;DR

Agent-World introduces a scalable, self-evolving environment platform that autonomously generates tasks and environments to enhance general agent training and capabilities.

Contribution

It presents a novel self-evolving training arena combining environment discovery and continuous reinforcement learning for advancing general agent intelligence.

Findings

Agent-World outperforms proprietary models on 23 benchmarks.

Scaling trends relate to environment diversity and self-evolution rounds.

The platform enables co-evolution of agent policies and environments.

Abstract

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting agents with scalable real-world services, but training robust agents remains limited by the lack of realistic environments and principled mechanisms for life-long learning. In this paper, we present \textbf{Agent-World}, a self-evolving training arena for advancing general agent intelligence through scalable environments. Agent-World has two main components: (1) Agentic Environment-Task Discovery, which autonomously explores topic-aligned databases and executable tool ecosystems from thousands of real-world environment themes and synthesizes verifiable tasks with controllable difficulty; and (2) Continuous Self-Evolving Agent Training, which combines multi-environment reinforcement learning with a self-evolving agent arena that automatically identifies capability gaps through dynamic task synthesis and drives targeted learning, enabling the co-evolution of agent policies and environments. Across 23 challenging agent benchmarks, Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines. Further analyses reveal scaling trends in relation to environment diversity and self-evolution rounds, offering insights for building general agent intelligence.