arXiv cs.CL· Ivan Moloshnikov, Dmitry Kunitsyn, Alexander Sboev, Maksim Skorokhodov, Roman Rybka, Yuanchao Liu·· 6 天前AI 评分30
多智能体 LLM 系统实现专用神经网络模型自动调优
A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models
AI 导读
一个由分析师、编码员和记录员三种角色组成的多智能体 LLM 框架，可在不改动整体网络结构的前提下，仅针对指定组件生成代码，实现跨模型自动调优。在 MNIST 和 Digits 脉冲分类任务上，准确率分别提升 13 和 6 个百分点；在 GNLSE 任务中相对解析单孤子解的误差降低约 2491 倍，KS 问题质量漂移下降 14 倍。
正文 · 原文
Abstract:Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usually manual. This paper addresses the automatic tuning of these components and proposes a framework transferable across models of different nature. The multi-agent large language model (LLM) framework has three roles---analyst, coder, and recorder~---with an experiment log and a sandboxed execution environment. Unlike systems that optimize the entire ML script or search architectures in a discrete space, the framework operates over an open but semantically narrow space: the agent generates code only for the specified components, leaving the overall network structure unchanged. The approach is validated in two directions: tuning a classification spiking neural network with correlation learning, and solving high-order differential equations with Physics-Informed Neural Networks (PINN). Across five tasks---spiking classification on MNIST and Digits, and boundary-value problems for the generalized nonlinear Schrödinger equation (GNLSE) and Kuramoto--Sivashinsky (KS) equations---the agent outperforms the baselines: classification accuracy is 13 percentage points (MNIST) and 6 percentage points (Digits) higher; the error against the analytical single-soliton solution is reduced approximately 2491-fold; the invariant-preservation error drops approximately 325-fold in the selected GNLSE run with a Gaussian perturbation and by more than 100-fold on average over repeated initializations; and the mass drift drops 14-fold for the KS problem with a Gaussian perturbation. The framework thus tunes key components on tasks of different nature without changing its internal structure.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Neural and Evolutionary Computing (cs.NE) |
| Cite as: | arXiv:2610.13663 [cs.AI] |
| (or arXiv:2610.13663v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13663 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Alexandr Sboev [view email]
[v1]
Fri, 9 Oct 2026 14:34:22 UTC (5,219 KB)
来源：arXiv cs.CL · arxiv.org