{"id":"agentbench-evaluating-llms-as-agents","name":"AgentBench: Evaluating LLMs as Agents","desc":"多维度评估LLM作为智能体能力的基准测试","url":"https://huggingface.co/papers/2308.03688","category":"对话助手","tags":["LLM","agent"],"rating":0,"users":null,"updated":"2026-04-08T00:00:00.000Z","source":"filipecalegario/awesome-generative-ai","addedAt":"2026-04-08T00:00:00.000Z","hot":false,"isNew":false}