Newest papers

ExpEvolve: Structuring and Reusing Experience for Open-Ended Discovery

Yongqiang Chen, Chenxi Liu, Deyu Zou, Zhenhao Chen, Tongliang Liu, Bo Han, Kun Zhang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29303 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

AlphaEvolve のような進化コードエージェントは、AI 科学者を構築するために Large Language Models (LLMs) を使用して顕著な成功の一つです。これらのエージェントは、プログラムをイテラルに改善し、進化させ、事前の知識と論理能力を活用することによって、オープンエンドの科学的な問題に取り組んでいます。 LLM の成功にもかかわらず、プログラム上の変異は、表面ヘウリスティクスでほとんどが低レベルで、持続的な制御ユニットなしです。対照的に、科学はアイデアを通じて化合物を構築します。この仕事では、私たちは ExpEvolve を提案し、アイデアレベルの抽出とコントロールを進化に注入します:それは、プログラム

Machine translation (Meta M2M100); the English original follows.

Abstract

Evolutionary coding agents such as AlphaEvolve are one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scientific problems by iteratively improving and evolving programs, leveraging the prior knowledge and reasoning capabilities of LLMs. Despite their success, mutations over programs are mostly low-level upon surface heuristics, without a persistent unit of control. In contrast, science compounds through ideas. In this work, we propose ExpEvolve, which injects idea-level extraction and control into evolution: it discovers and leverages the high-level factors from programs that explain scoring differences among different programs. We characterize theoretical conditions on when discovery with idea factors improves sample efficiency. We also build a practical framework to show that the extracted high-level idea factors are helpful for guiding exploitation from experience and exploration when discovery comes to a plateau. Across 11 open-ended mathematical tasks, ExpEvolve significantly improves the final performance and sample efficiency up to 5.0x. The improvements also transfer to 4 other LLMs and to 6 machine learning tasks from MLS-Bench. Analysis shows that ExpEvolve can discover idea-level factors to provide better exploration and exploitation for evolutionary discovery.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Reuse, Structuring, Artificial intelligence, Coding (social sciences), Machine learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange