AgentOdyssey：用於測試時持續學習智能體的開放式長程文字遊戲生成

摘要

為了讓代理（agent）在測試階段能從與世界的持續互動中學習，它們必須具備有效探索、獲取新世界知識與技能、保留相關情節經驗，以及在長時域中規劃的能力。為評估這些測試時持續學習代理的關鍵能力，我們提出AgentOdyssey——一個新穎的評估框架，能程序化生成包含豐富實體、世界動態與長時域任務的開放式文字遊戲。關鍵的是，AgentOdyssey突破了傳統機器學習中「學習不在測試時發生」的假設，將代理置於持續、長時域的設定中，讓學習與推理在整個部署過程中交織進行。我們進一步提出多面向的評估方法，不僅衡量遊戲進展，還提供關於世界知識獲取、情節記憶、物體與行動探索、行動多樣性及模型成本的診斷測試。我們在生成的遊戲中評估了多種代理範式。實驗結果揭示了代理在關鍵能力上的極限，以及影響其有意義時域長度的因素。雖然性能隨著基礎模型增強而提升，但即使是最強的代理仍遠低於人類表現，留下充足的改進空間。在代理機制中，我們發現短期記憶對多種代理範式有益，是代理測試時訓練的重要組成部分。

English

For agents to learn continuously from interaction with the world at test time, they must be able to explore effectively, acquire new world knowledge and skills, retain relevant episodic experiences, and plan over long horizons. To evaluate these key abilities of test-time continual learning agents, we introduce AgentOdyssey, a novel evaluation framework that procedurally generates open-ended text games with rich entities, world dynamics, and long-horizon tasks. Critically, AgentOdyssey goes beyond the conventional machine learning assumption that learning does not occur at test time by placing agents in a continuous, long-horizon setting that interleaves learning and inference throughout deployment. We further propose a multifaceted evaluation methodology that measures not only game progress but also offers diagnostic tests on world knowledge acquisition, episodic memory, object and action exploration, action diversity, and model cost. We evaluate diverse agent paradigms in the generated games. Our experimental results reveal critical limits in agents' key abilities, as well as factors that influence their meaningful horizon. Although performance scales with stronger base models, even the top agent remains far below human performance, leaving substantial headroom for improvement. Among agent mechanisms, we find that short-term memory benefits multiple agent paradigms and is an important component of agent test-time training.