arXiv：cs.AI· Yonatan Gideoni, Sebastian Risi, Yarin Gal·· 21 小时前
简单基线在代码演化任务中媲美复杂流水线
Simple Baselines are Competitive with Code Evolution
AI 导读
研究提出两个简单基线，在寻找数学边界、设计智能体脚手架、启发式组合优化算法和机器学习竞赛等任务上与流行代码演化流水线对比，结果基线在所有领域均达到或超越现有方法。
正文
Abstract:Code evolution is a family of techniques that rely on large language models to search through possible computer programs by evolving existing code. While code evolution pipelines have shown impressive performance across domains, many are highly complex and are typically not compared to simpler alternatives. To prevent bad comparisons from stagnating the field, we propose two simple baselines and compare them to popular pipelines across several domains: finding better mathematical bounds, designing agentic scaffolds, developing heuristic combinatorial optimization algorithms, and machine learning competitions. Surprisingly, the baselines match or outperform existing methods across all domains, prompting a closer look at which factors drive performance in different settings. For mathematical bounds, we find that the search space matters far more than the exact search algorithm, with both simple and complex methods performing similarly given the same search space. Thus, expanding the search space is what matters for improving performance, and does so across all pipelines. Moreover, different domain knowledge embedded in prompts can significantly affect the search's efficiency, potentially leading to overestimating a pipeline's sample efficiency. For automated agentic scaffold design, we show that typical high-variance evaluations lead to all automated search methods picking subpar scaffolds relative to a simple majority vote. To mitigate this, we propose improved evaluation procedures that reduce stochasticity while keeping the search economically feasible. Overall, these results indicate that further improving code evolution's performance depends more on the setup surrounding the search pipeline than on the pipeline itself. We hope these insights will enable developing new code evolution methods and help spur meaningful progress in the field.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2602.16805 [cs.AI] |
| (or arXiv:2602.16805v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2602.16805 arXiv-issued DOI via DataCite |
Submission history
From: Yonatan Gideoni [view email]
[v1]
Wed, 18 Feb 2026 19:07:22 UTC (2,596 KB)
[v2]
Mon, 12 Oct 2026 15:28:24 UTC (2,488 KB)
来源：arXiv：cs.AI · arxiv.org