AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
AgentOdyssey evaluates test-time continual learning agents through procedurally generated text games, measuring learning, memory, exploration, and planning capabilities in continuo…
Hugging Face · Daily Papers
·Zheyuan Zhang, Zehao Wen
·
·▲ 5 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Zheyuan Zhang, Zehao Wen, Alvin Zhang, Andrew Wang, Jianwen Xie, Daniel Khashabi
- 5 upvotes da comunidade
- Temas: test-time continual learning, procedural generation, text games, world knowledge acquisition, episodic memory, action diversity
Resumo
Resumo original (em inglês), extraído do paper:
AgentOdyssey evaluates test-time continual learning agents through procedurally generated text games, measuring learning, memory, exploration, and planning capabilities in continuous, long-horizon settings.
