arXiv · cs.AI · Yimin Tang, Han Zhang, Shao-Hung Chan, Erdem B{\i}y{\i}k, Sven Koenig, Jingkai Chen · 8 小时前模型评分60
Late Autumn：大语言模型（LLM，Large Language Model） 智能体为单个仓库特化通用多机器人规划器
Late Autumn: LLM Agents Specialize a General Multi-Robot Planner for One Warehouse
导读
论文 Late Autumn 研究让 大语言模型（LLM，Large Language Model） 编码智能体自主开展研究，把一个通用多机器人规划器特化到单个仓库场景，以牺牲通用性换取吞吐量。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
应用领域：交通与物流、制造与工业
事件类型：研究发布
证据摘录
- “In this work, which we call Late Autumn, we explore whether LLM coding agents running autonomous research can specialize a general planner for one site, trading generality for throughput, much as post-training adapts a pretrained LLM to one task.”
- “the agents raise throughput by 22--60%, and the gains hold on unseen seeds”
- “each final patch (0.7k--2.4k lines) is a chain of scored commits with a median step of 27 lines, so experts can review it, and review finds problems that the score misses”
- “some patches multiply planner compute by over 100x”
来源：arXiv · cs.AI · arxiv.org