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

​NICE Talk NO.175 invites the Guanlin Dong to share a new paradigm for general-purpose agent training: environment-agent co-evolution.

​Speaker: Guanlin Dong, PhD student, Renmin University of China Host: Boyang Xue, PhD student The Chinese University of Hong Kong

​TIME:
Beijing: May 26, 20:00–21:00
Eastern USA: May 26, 08:00–09:00
Pacific Time: May 26, 05:00–06:00

​💡 Most current agent training approaches treat environments as static benchmarks. Agent-World explores a different direction: agents and environments evolving together.

​The framework tightly couples:
• Autonomous environment exploration from the real world
• Continuous self-evolution training through multi-environment RL
• Automatic diagnosis of capability weaknesses
• Targeted expansion of environments and tasks

​🚀 Key results:
• 1,978 interactive environments
• 19,822 executable tools
• Long-horizon tasks with 15+ interaction turns on average
• Strong performance across 23 challenging benchmarks, including τ²-Bench, BFCL V4, MCP-Mark, ClawEval, and SkillsBench

​arXiv： https://arxiv.org/pdf/2604.18292
GitHub：https://agent-tars-world.github.io

​#AI #LLM #Agents #AgenticAI #ReinforcementLearning #OpenSource #AGI