mlsanityData to 7 Oct 2026

AlphaEvolve: A coding agent for scientific and algorithmic discovery

arXiv 2506.13131 ↗First posted 16 Jun 2025cs.AI cs.LG cs.NEcited by 763

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tackling open scientific problems or optimizing critical pieces of computational infrastructure. AlphaEvolve orchestrates an autonomous pipeline of LLMs, whose task is to improve an algorithm by making direct changes to the code. Using an evolutionary approach, continuously receiving feedback from one or more evaluators, AlphaEvolve iteratively improves the algorithm, potentially leading to new scientific and practical discoveries. We demonstrate the broad applicability of this approach by applying it to a number of important computational problems. When applied to optimizing critical components of large-scale computational stacks at Google, AlphaEvolve developed a more efficient scheduling algorithm for data centers, found a functionally equivalent simplification in the circuit design of hardware accelerators, and accelerated the training of the LLM underpinning AlphaEvolve itself. Furthermore, AlphaEvolve discovered novel, provably correct algorithms that surpass state-of-the-art solutions on a spectrum of problems in mathematics and computer science, significantly expanding the scope of prior automated discovery methods (Romera-Paredes et al., 2023). Notably, AlphaEvolve developed a search algorithm that found a procedure to multiply two 4 × 4 complex-valued matrices using 48 scalar multiplications; offering the first improvement, after 56 years, over Strassen's algorithm in this setting. We believe AlphaEvolve and coding agents like it can have a significant impact in improving solutions of problems across many areas of science and computation.

Key facts. Cited by 763 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 53 of its 115 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

53 of 115 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug

Other references · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  6. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  7. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  8. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  9. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  10. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  11. 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Modelscited by 414
  12. 2015Illuminating search spaces by mapping elitescited by 406
38 more
  1. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 348
  2. 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 266
  3. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 258
  4. 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 174
  5. 2022Evolution through Large Modelscited by 131
  6. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  7. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  8. 2023Large Language Models for Automated Open-domain Scientific Hypotheses Discoverycited by 100
  9. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  10. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 96
  11. 2025LLM4SR: A Survey on Large Language Models for Scientific Researchcited by 81
  12. 2024Formal Mathematical Reasoning: A New Frontier in AIcited by 80
  13. 2023An In-Context Learning Agent for Formal Theorem-Provingcited by 78
  14. 2024Symbolic Regression with a Learned Concept Librarycited by 76
  15. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directionscited by 74
  16. 2023Evaluating Language Models for Mathematics through Interactionscited by 69
  17. 2024Hypothesis Generation with Large Language Modelscited by 68
  18. 2024MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypothesescited by 68
  19. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 59
  20. 2023DrugAssist: A Large Language Model for Molecule Optimizationcited by 57
  21. 2024Large Language Models As Evolution Strategiescited by 57
  22. 2024HoneyComb: A Flexible LLM-Based Agent System for Materials Sciencecited by 56
  23. 2024Multi-objective Evolution of Heuristic Using Large Language Modelcited by 52
  24. 2024Evolving Code with A Large Language Modelcited by 42
  25. 2024LLMatDesign: Autonomous Materials Discovery with Large Language Modelscited by 41
  26. 2023Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Networkcited by 40
  27. 2024Are LLMs Ready for Real-World Materials Discovery?cited by 40
  28. 2025Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learningcited by 39
  29. 2024Quantum Circuit Optimization with AlphaTensorcited by 36
  30. 2025Nature Language Model: Deciphering the Language of Nature for Scientific Discoverycited by 35
  31. 2024FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearchcited by 22
  32. 2024Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaderscited by 21
  33. 2024Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysiscited by 20
  34. 2024LLM Guided Evolution -- The Automation of Models Advancing Modelscited by 20
  35. 2022Evolving symbolic density functionalscited by 19
  36. 2024Quantum Many-Body Physics Calculations with Large Language Modelscited by 17
  37. 2025Accelerating Earth Science Discovery via Multi-Agent LLM Systemscited by 13
  38. 2024Amplifying human performance in combinatorial competitive programmingcited by 10

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 147; 2026: 616.

763 papers.

Sort:

By area:

  1. 2026Reinforcement Learning via Self-Distillationcited by 285
  2. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 248
  3. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  4. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  5. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
  6. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  7. 2026Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnessescited by 119
  8. 2025The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injectionscited by 108
  9. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  10. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
  11. 2026AutoHarness: improving LLM agents by automatically synthesizing a code harnesscited by 63
  12. 2025CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learningcited by 59
38 more
  1. 2025From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflowscited by 57
  2. 2025DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressivelycited by 56
  3. 2025Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agentscited by 52
  4. 2025ThetaEvolve: Test-time Learning on Open Problemscited by 52
  5. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  6. 2025Astra: A Multi-Agent System for GPU Kernel Performance Optimizationcited by 46
  7. 2026AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimizationcited by 46
  8. 2026EvoX: Meta-Evolution for Automated Discoverycited by 45
  9. 2026PostTrainBench: Can LLM Agents Automate LLM Post-Training?cited by 45
  10. 2026Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injectionscited by 44
  11. 2026ASPIRE: Agentic /Skills Discovery for Roboticscited by 44
  12. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 42
  13. 2026Code as Agent Harnesscited by 40
  14. 2026Rethinking the Evaluation of Harness Evolution for Agentscited by 39
  15. 2026Building Production-Ready Probes For Geminicited by 38
  16. 2026CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discoverycited by 38
  17. 2025CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimizationcited by 37
  18. 2025Measuring Agents in Productioncited by 35
  19. 2025EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systemscited by 34
  20. 2026Dive into Claude Code: The Design Space of Today's and Future AI Agent Systemscited by 33
  21. 2025EoH-S: Evolution of Heuristic Set using LLMs for Automated Heuristic Designcited by 32
  22. 2026Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharingcited by 32
  23. 2025Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Modelscited by 30
  24. 2025SR-Scientist: Scientific Equation Discovery With Agentic AIcited by 30
  25. 2025KL-Regularized Reinforcement Learning is Designed to Mode Collapsecited by 29
  26. 2025Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learningcited by 28
  27. 2025Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystemcited by 28
  28. 2025AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunitiescited by 26
  29. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 25
  30. 2026SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agentscited by 25
  31. 2025AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?cited by 24
  32. 2026InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discoverycited by 24
  33. 2026DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolutioncited by 23
  34. 2026AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaborationcited by 23
  35. 2025GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimizationcited by 22
  36. 2025IterResearch: Rethinking Long-Horizon Agents with Interaction Scalingcited by 22
  37. 2026Recursive Harness Self-Improvementcited by 22
  38. 2025AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimizationcited by 21

50 most cited of 763 All 763 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Mathematical exploration and discovery at scale
  2. 2025ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
  3. 2025ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms
  4. 2025Evolution without an Oracle: Driving Effective Evolution with LLM Judges
  5. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
  6. 2026Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits
  7. 2026Is manual software optimization a thing of the past?
  8. 2026AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding