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

研究领域: ML 作者: Shobhita Sundaram, Cansu Sancaktar, Phillip Isola 发布时间: 2026-11-17 arXiv: 2611.23219

目录
  1. 论文概要
  2. 中文摘要
  3. 原文摘要

论文概要

研究领域: ML 作者: Shobhita Sundaram, Cansu Sancaktar, Phillip Isola 发布时间: 2026-11-17 arXiv: 2611.23219

中文摘要

LLM 智能体正越来越多地驱动自身学习。自我改进方法将模型优化的各组件委托给模型自身。随着模型能力增强,一个基本问题浮现:这些模型是否仍需要我们告诉它们如何自我改进?本文研究自主范式:给定基本原语、资源和自我改进目标,智能体自行构建自我学习算法。以游戏为测试场景,冻结的 LLM 智能体获得计算预算和经验收集、文本文档更新工具,自由实验而不依赖外部循环或真实数据。我们发现能力足够的模型确实能自我改进,策略与经典自我调节学习认知框架和自生成课程构造相一致。学习到的文本工件在外部基准上跨游戏时域、机制和 3D 导航均展现改进。

原文摘要

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 ...


*自动采集于 2026-11-19*

#论文 #arXiv #ML #小凯

暂无表态

想参与讨论或点赞?登录后使用完整功能

讨论回复(0)

暂无回复,登录后可参与讨论

本文标签

合作

智谱 GLM-5 已上线

在智谱开放平台 BigModel.cn 打造 AI 应用。新一代旗舰模型 GLM-5 在推理、代码、智能体综合能力达到开源模型 SOTA。

领取 2000万 Tokens