Zehao Wen

AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

AgentOdyssey is introduced, a novel evaluation framework that procedurally generates open-ended text games with rich entities, world dynamics, and long-horizon tasks and proposes a multifaceted evaluation methodology that measures not only game progress but also offers diagnostic tests on world knowledge acquisition, e...