论文

arXiv 论文:LLM 智能体无需人工指定即可自主构建自我改进算法

Do LLM Agents Still Need to Be Told How to Self-Improve?

精选理由

斯坦福系研究团队把训练循环的设计权交给了模型本身,冻结的 LLM 只靠改文本就变强了,还能迁移到 3D 导航。做 Agent 开发和强化学习的人应该看看,它可能预示下一阶段 post-training 的写法。

arXiv 论文 2611.23219 研究了一个自主自我改进范式:给定基础工具、计算预算和通用目标后,一个冻结的 LLM 智能体能否自行设计自我学习算法。实验以游戏为测试环境,智能体只能收集经验并更新文本文档,没有外部强加的训练循环,也无法访问真实世界数据。

正文

结果显示,能力足够的模型确实在这种条件下实现自我改进,其采用的策略与经典自我调节学习认知框架以及自生成课程(self-generated curricula)相关研究一致。论文还考察了学习到的文本产物能否迁移:在更长游戏时间线、不同游戏机制以及 3D 导航的外部基准上均观察到提升。

这项工作回应了一个核心问题:随着模型能力增强,人类是否还需要为它们指定自我改进的方式。论文给出的答案是基本机制可以交给模型自己,人类只需提供原语、资源和目标。

原文 · arXiv cs.AI

Do LLM Agents Still Need to Be Told How to Self-Improve?

LLM agents increasingly drive their own learning. Self-improvement methods delegate various components of model optimization to the models themselves. As models become more capable, this motivates a basic question: do these increasingly capable models still need us to specify how they should self-improve? In this paper we study an autonomous paradigm in which, given basic primitives, resources, and a general goal for self-improvement, agents construct their own self-learning algorithm for context-based optimization. Using the setting of gameplay as a testbed, a frozen LLM agent is given a compute budget and tools for collecting experience and updating text documents, and allowed to freely experiment without an externally imposed loop or access to real-world data. We find that sufficiently capable models do self-improve under these conditions, demonstrating strategies that align with classic cognitive frameworks for self-regulated learning and constructs from machine learning literature on self-generated curricula. Furthermore, we study the extent to which the learned text artifacts transfer to external benchmarks, observing improvement across different game horizons, mechanics, and 3D navigation.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:LLM Agent、自我改进、自生成课程、arXiv,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Shobhita Sundaram, Cansu Sancaktar, Phillip Isola),经 AITOP 多维评分管线结构化提炼。