论文概要
研究领域: ML 作者: Ren Zhenzhuo 发布时间: 2026-09-03 arXiv: 2509.00009
中文摘要
数学社区使用不同的对象、不变量和工具，因此跨社区转移问题成本高昂且经常被跳过。我们提出了EULER，一个多智能体系统，将这种转移——一座桥梁——作为其搜索单元。围绕一个固定的猜想，EULER运行直接、相邻域和远域路径的竞争；一座桥梁只有在提供源表示无法执行的操作且其目标侧证据沿经过检查的蕴含返回原始陈述时才保留其预算。在昂贵的搜索开始之前，六个有序的压力测试拒绝无效的桥梁。我们在120个近期猜想上评估EULER。这些猜想在搜索前被冻结并筛选污染，来自最近在《组合理论杂志，A辑》（组合学领域领先期刊）上发表论文的作者。EULER产生了10个证明和3个反驳，以及45个范围化的部分结果。两个机制在消融实验中站得住脚：桥梁特定的压力测试将错误结论从9个减少到3个，桥梁材料与目标原生操作的结合产生了+4.2个已解决任务的正向交互，这是两个因素单独都无法实现的。域距离不能可靠预测成功；可执行操作增益和有效返回才能。
原文摘要
Mathematical communities work with different objects, invariants, and tools, so transferring a problem across them is expensive and often skipped. We present EULER, a multi-agent system that takes such a transfer–a bridge–as its unit of search. Around a fixed conjecture, EULER runs direct, adjacent-domain, and distant-domain routes in competition; a bridge keeps its budget only if it supplies an operation the source representation cannot execute and its target-side evidence returns to the original statement along a checked implication. Six ordered stress tests reject invalid bridges before expensive search begins. We evaluate EULER on 120 recent conjectures. The conjectures were frozen before search and screened for contamination, and are drawn from public papers by authors who had recen…
— 自动采集于 2026-09-03
#论文 #arXiv #ML #小凯