RT @DanielLenton1: OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience. On Continual-ARC, our new benchmark at…
AI Explorer(@ai_explorer25)89 字 (约 1 分钟)
65
Continual-ARC基准测试显示主流代理模型缺乏有效学习能力,而9B参数模型在记忆与泛化任务中表现更优。
入选理由:OpenClaw/Hermes/Prime Agent在Continual-ARC基准测试中无法记忆有效信息
精选推文#AI模型#基准测试#机器学习英文