arXiv cs.CL· Roberto I. Ono Filho·· 13 小时前AI 评分31
办公规模验证搜索中的算子包、提议器强度与构造族平台期
Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search
AI 导读
一项 FunSearch 风格验证搜索研究在笔记本上用 30B 本地模型、每次运行 120-600 个验证样本，测试三种算子包对提议器侧的影响。完整 2^3 因子实验显示组合算子缩小了种子到记录差距的 +0.196（名义合并 p=0.023），排斥算子使 9 个问题中 8 个的构造哈希多样性提升（单侧 p=0.0039）。
正文 · 原文
Abstract:Verified search, in which a language model proposes programs, a hard evaluator scores them, and selection keeps the best, has recently moved mathematical records; controlled ablations of the proposer-side components remain rare. We instrument a minimal FunSearch-style loop at office scale (a 30B local model on a laptop, 120-600 verified samples per run) with three operator packages: a schematic notebook the model writes and carries instead of verbatim elites, a named obstacle, and behavioural repulsion from constructions already found. On nine construction problems from a public repository, the complete 2^3 factorial with two replicates favours the primary contrast in a nominal two-stage analysis: the composition closes more of the seed-to-record gap (+0.196; nominal pooled p=0.023, stage-combination p~0.08; median per-problem effect +0.045). Repulsion raises construction-hash diversity in eight of nine problems (one-sided p=0.0039; partly a manipulation check). The factorial finds no positive memory-by-repulsion interaction (bounded to about +/-0.04); the gain decomposes additively, and memory+repulsion is the only arm that never collapses (0 of 18 runs), within 0.025 of the full composition. A frontier proposer under the identical loop reaches in tens of samples what the local model does not in hundreds; in single scoping runs its gains arrive without the operators. The searches stall after closing 85-92% of the gap on the flagship problem, and a later analysis reads that plateau as a resolution limit: the reference value is a continuum limit and the unaided long-run finals already carry its family's structure. In the registered family-hint test the family named in words is adopted and loses; handed as code, it is optimized, but our best finite-grid encoding stays below the plateau reached unaided. We release the harness, every candidate, and the dated pre-registrations.
| Comments: | Version 4 of the paper (arXiv v2): adds the note on the wall (Zenodo v3) and corrections after an audit against the records (listed in the paper). 14 pages. Code: this https URL. Data: Zenodo https://doi.org/10.5281/zenodo.22714138, https://doi.org/10.5281/zenodo.22713807 and https://doi.org/10.5281/zenodo.23163299%3B this version also at https://doi.org/10.5281/zenodo.23163677 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE) |
| Cite as: | arXiv:2609.29636 [cs.CL] |
| (or arXiv:2609.29636v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.29636 arXiv-issued DOI via DataCite |
Submission history
From: Roberto I Ono Filho [view email]
[v1]
Fri, 28 Aug 2026 21:48:30 UTC (179 KB)
[v2]
Thu, 22 Oct 2026 10:43:35 UTC (183 KB)
来源：arXiv cs.CL · arxiv.org