AlphaResearch: Accelerating New Algorithm Discovery with Language Models

• URL: http://arxiv.org/abs/2511.08522v1
• Date: Wed, 12 Nov 2025 02:03:05 GMT
• Title: AlphaResearch: Accelerating New Algorithm Discovery with Language Models
• Authors: Zhaojian Yu, Kaiyue Feng, Yilun Zhao, Shilin He, Xiao-Ping Zhang, Arman Cohan,
• Abstract summary: Large language models have made significant progress in complex but easy-to-verify problems, yet they still struggle with discovering the unknown.<n>We present textbfAlphaResearch, an autonomous research agent designed to discover new algorithms on open-ended problems.
• Score: 60.502137348923156
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models 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. To synergize the feasibility and innovation of the discovery process, we construct a novel dual research environment by combining the execution-based verify and simulated real-world peer review environment. AlphaResearch discovers new algorithm by iteratively running the following steps: (1) propose new ideas (2) verify the ideas in the dual research environment (3) optimize the research proposals for better performance. To promote a transparent evaluation process, we construct \textbf{AlphaResearchComp}, a new evaluation benchmark that includes an eight open-ended algorithmic problems competition, with each problem carefully curated and verified through executable pipelines, objective metrics, and reproducibility checks. AlphaResearch gets a 2/8 win rate in head-to-head comparison with human researchers, demonstrate the possibility of accelerating algorithm discovery with LLMs. 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 remaining challenges of the 6/8 failure cases, providing valuable insights for future research.

Related papers

• Landscape-aware Automated Algorithm Design: An Efficient Framework for Real-world Optimization [32.203665659052845]
  Large Language Models (LLMs) have opened new frontiers in automated algorithm design.<n>LLMs require extensive evaluation of the target problem to guide the search process.<n>This research proposes an innovative and efficient framework that decouples algorithm discovery from high-cost evaluation.
  arXiv  Detail & Related papers  (2026-02-04T13:18:45Z)
• Deep Researcher with Sequential Plan Reflection and Candidates Crossover (Deep Researcher Reflect Evolve) [0.0]
  This paper introduces a novel Deep Researcher architecture designed to generate detailed research reports on complex PhD level topics.<n>Our system utilizes two key innovations: Sequential Research Plan Refinement via Reflection and a Candidates Crossover algorithm.<n>Our architecture achieved an overall score of 46.21, demonstrating superior performance by surpassing leading deep research agents.
  arXiv  Detail & Related papers  (2026-01-28T18:45:39Z)
• InnoGym: Benchmarking the Innovation Potential of AI Agents [74.64144272881414]
  InnoGym is the first benchmark designed to evaluate the innovation potential of AI agents.<n>InnoGym introduces two complementary metrics: performance gain, which measures improvement over the best-known solutions, and novelty, which captures methodological differences from prior approaches.
  arXiv  Detail & Related papers  (2025-12-01T16:03:04Z)
• Barbarians at the Gate: How AI is Upending Systems Research [58.95406995634148]
  We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery.<n>We term this approach as AI-Driven Research for Systems ( ADRS), which iteratively generates, evaluates, and refines solutions.<n>Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.
  arXiv  Detail & Related papers  (2025-10-07T17:49:24Z)
• AlphaEvolve: A coding agent for scientific and algorithmic discovery [63.13852052551106]
  We present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs.<n>AlphaEvolve orchestrates an autonomous pipeline of LLMs, whose task is to improve an algorithm by making direct changes to the code.<n>We demonstrate the broad applicability of this approach by applying it to a number of important computational problems.
  arXiv  Detail & Related papers  (2025-06-16T06:37:18Z)
• Discovering new robust local search algorithms with neuro-evolution [0.9786690381850356]
  This paper explores a novel approach aimed at overcoming existing challenges in the realm of local search algorithms.<n>Our aim is to improve the decision process that takes place within a local search algorithm so as to make the best possible transitions in the neighborhood at each iteration.<n>This approach offers a promising avenue for the emergence of new local search algorithms and the improvement of their problem-solving capabilities for black-box problems.
  arXiv  Detail & Related papers  (2025-01-08T10:31:16Z)
• Resolving the Exploration-Exploitation Dilemma in Evolutionary Algorithms: A Novel Human-Centered Framework [0.0]
  A systematic resolution to the exploration-exploitation dilemma in algorithm design requires an independent yet coordinated control over exploration and exploitation.<n>We propose a Human-Centered Two-Phase Search (HCTPS) framework, in which the actualization of (1) and (2) is enabled through an external variable--the Search Space Control.<n>We prove that the HCTPS strictly surpasses the current approach in terms of search space coverage without disrupting the EAs' inherent convergence mechanisms.
  arXiv  Detail & Related papers  (2025-01-04T01:06:46Z)
• RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation [54.707460684650584]
  Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. Current research addresses this bottleneck by equipping LLMs with external knowledge, a technique known as Retrieval Augmented Generation (RAG) RAGLAB is a modular and research-oriented open-source library that reproduces 6 existing algorithms and provides a comprehensive ecosystem for investigating RAG algorithms.
  arXiv  Detail & Related papers  (2024-08-21T07:20:48Z)
• Empirical Evaluation of Project Scheduling Algorithms for Maximization of the Net Present Value [0.0]
  This paper presents an empirical performance analysis of three project scheduling algorithms. The selected algorithms are: Recursive Search (RS), Steepest Ascent Approach (SAA) and Hybrid Search (HS)
  arXiv  Detail & Related papers  (2022-07-05T03:01:33Z)
• Identifying Co-Adaptation of Algorithmic and Implementational Innovations in Deep Reinforcement Learning: A Taxonomy and Case Study of Inference-based Algorithms [15.338931971492288]
  We focus on a series of inference-based actor-critic algorithms to decouple their algorithmic innovations and implementation decisions. We identify substantial performance drops whenever implementation details are mismatched for algorithmic choices. Results show which implementation details are co-adapted and co-evolved with algorithms.
  arXiv  Detail & Related papers  (2021-03-31T17:55:20Z)
• AutoSpace: Neural Architecture Search with Less Human Interference [84.42680793945007]
  Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. We propose a novel differentiable evolutionary framework named AutoSpace, which evolves the search space to an optimal one. With the learned search space, the performance of recent NAS algorithms can be improved significantly compared with using previously manually designed spaces.
  arXiv  Detail & Related papers  (2021-03-22T13:28:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.