5 papers
PATH-Bench: Path-Dependent Evaluation of Lifelong Agents
Xidong Yang, Xingyi Zhang, Wenhao Li +7
Lifelong LLM agents increasingly adapt through external learning states that store past interactions as retrievable memories or reusable skills, yet existing benchmarks rarely acco…
Agentic Episodic Control
Xidong Yang, Wenhao Li, Junjie Sheng +4
Reinforcement learning (RL) remains fundamentally limited by poor data efficiency and weak generalization. Prior episodic RL methods attempt to alleviate this via external memory m…
LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas
Yun Hua, Shang Gao, Wenhao Li +5
In multi-agent reinforcement learning, each agent acts to maximize its individual accumulated rewards. Nevertheless, individual accumulated rewards could not fully reflect how othe…
TextAtari: 100K Frames Game Playing with Language Agents
Wenhao Li, Wenwu Li, Chuyun Shen +8
We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representa…
Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents
Yun Hua, Haosheng Chen, Shiqin Wang +3
Large Language Models (LLMs) show strong collaborative performance in multi-agent systems with predefined roles and workflows. However, in open-ended environments lacking coordinat…