用AI自主发现新算法，解决开放问题并超越人类表现。
AlphaResearch: Accelerating New Algorithm Discovery with Language Models
- 构建双环境机制，结合执行验证与模拟同行评审
- 在8个开放问题中6个表现优于现有系统，圆打包问题达最优已知性能
- 适合对自主科研、算法创新感兴趣的学者与工程师
大型语言模型在复杂但易验证的问题上取得显著进展，但在未知领域的算法发现仍面临挑战。本文提出 extbf{AlphaResearch}，一个自主研究智能体，通过迭代执行：提出新思路、编程验证、优化研究提案三步，在开放性问题中发现新算法。为平衡可行性与创新性，构建新型双环境：基于执行的可验证奖励与模拟真实同行评审的奖励相结合。我们还构建了 extbf{ extit{dataset}}，包含8个开放性算法竞赛题以评估 AlphaResearch。实验表明，在6个开放性问题上，其发现性能超过其他智能体系统。尤其在“packing circles”问题上，所发现算法达到最优已知性能，超越人类研究人员及近期强基线（如 AlphaEvolve）。此外，我们对自主研究智能体的优势与现存挑战进行了全面分析，为未来研究提供重要洞见。
原文摘要 · Abstract (English)
LLMs have made significant progress in complex but easy-to-verify problems, yet they still struggle with discovering the unknown. In this paper, we present \textbf{AlphaResearch}, an autonomous research agent designed to discover new algorithms on open-ended problems by iteratively running the following steps: (1) propose new ideas (2) program to verify (3) optimize the research proposals. To synergize the feasibility and innovation of the discovery process, we construct a novel dual environment by combining the execution-based verifiable reward and reward from simulated real-world peer review environment in AlphaResearch. We construct \textbf{\dataset}, a set of questions that includes an eight open-ended algorithmic problems competition to benchmark AlphaResearch. Experimental results show that AlphaResearch achieves stronger discovery performance than other agentic discovery systems on six open-ended problems. Notably, the algorithm discovered by AlphaResearch on the \emph{``packing circles''} problem achieves the best-of-known performance, surpassing the results of human researchers and strong baselines from recent work (e.g., AlphaEvolve). Additionally, we conduct a comprehensive analysis of the benefits and remaining challenges of autonomous research agent, providing valuable insights for future research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。