跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.23219 · v1

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

LLM智能体还需要被告知如何自我改进吗?

首次提交 2026-11-18 02:57
版本更新 2026-11-18 02:57
雷达观测 2026-11-18 12:34
arXiv ↗PDF ↗

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 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.

作者备注:Project page: https://ssundaram21.github.io/self-org/

AI 论文解读

基于摘要 · 非全文审阅

作者让冻结的LLM智能体在仅给定基本原语、资源和总体目标的情况下自行设计基于上下文的自我学习算法,发现能力足够强的模型能够自我改进,且学到的文本产物可迁移到外部基准。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 02:57 · 最新观测版本

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.

查看此版本解读 →查看此版本原文 ↗