跳到正文
arXiv cs.AI· Hui Shao, Tao Wang, Xiaotian Liu, Yijie Peng·· 4 小时前AI 评分47

用大语言模型智能体构建搜索流水线改进 Thomson 问题已知最优构型

Certified Improvements to Best-Known Thomson-Problem Configurations with a Search Pipeline Built with Large Language Model Agents

AI 导读

研究者用大语言模型智能体(Claude,通过聊天界面和 Claude Code)构建并运行搜索流水线,为 Thomson 问题(球面上 N 个单位电荷的最小 Coulomb 能量排布)找到 N = 912、1382 和 2502 的构型。

正文 · 原文

View PDF HTML (experimental)

Abstract:The Thomson problem asks for N unit charges on a sphere with minimum Coulomb energy; for large N the best configurations known are curated in the Cambridge Cluster Database, whose largest-N entries were set in October 2026. We report configurations for N = 912, 1382 and 2502 with energies 0.0036186, 0.0109730 and 0.0614033 below the database values, certified by exact integer arithmetic. All three are numerically strict local minima modulo rotations and keep the defect inventory and scar compositions of the database configurations; the database value for N = 912 had been reached by two different methods. Our search runs unconstrained replica-exchange basin hopping from the database configurations, with a shared pool of minima, recombination of improved regions after relabelling by geometry, and gradient-only polishing; replica-exchange basin hopping alone found the N = 912 and 1382 configurations, the former in one of five runs. We built and ran it with large language model agents (Claude, through a chat interface and the Claude Code agent), and we report every search, including those that failed. Two findings matter for others who search the database. Polishing alone lowers two entries by more than the threshold at which our pipeline reports a candidate, which produced two spurious records until candidates were compared with the polished database energies (the polished baseline). A local-relaxation speed-up passed its exactness test yet found nothing in a controlled comparison in which every arm with full relaxation went below the database value within 15 minutes. We distil three practices for computational discovery with large language model agents: calibrate the search code and verify candidates with code separate from the search, compare candidates with the polished baseline, and test design changes in controlled comparisons with pass criteria fixed in advance.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.17776 [cs.AI]
  (or arXiv:2611.17776v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.17776

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yijie Peng [view email]
[v1] Fri, 13 Nov 2026 05:38:15 UTC (250 KB)

来源:arXiv cs.AI · arxiv.org