# EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

arXiv: https://arxiv.org/abs/2603.08127 · HTML: https://mlsanity.com/paper/2603.08127/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 70 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 27 of 27)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution](https://mlsanity.com/paper/2505.20286/) (2025)
- [Look at the First Sentence: Position Bias in Question Answering](https://mlsanity.com/paper/2004.14602/) (2020)
- [Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2503.08979/) (2025)
- [AgentRxiv: Towards Collaborative Autonomous Research](https://mlsanity.com/paper/2503.18102/) (2025)
- [Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.09403/) (2024)
- [ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition](https://mlsanity.com/paper/2503.21248/) (2025)
- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [AI4Research: A Survey of Artificial Intelligence for Scientific Research](https://mlsanity.com/paper/2507.01903/) (2025)
- [DeepShop: A Benchmark for Deep Research Shopping Agents](https://mlsanity.com/paper/2506.02839/) (2025)
- [Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges](https://mlsanity.com/paper/2412.11427/) (2024)
- [Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation](https://mlsanity.com/paper/2407.08940/) (2024)
- [ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry](https://mlsanity.com/paper/2507.16280/) (2025)
- [Sparks of Science: Hypothesis Generation Using Structured Paper Data](https://mlsanity.com/paper/2504.12976/) (2025)
- [MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization](https://mlsanity.com/paper/2410.07672/) (2024)
- [Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning](https://mlsanity.com/paper/2312.05762/) (2023)
- [Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models](https://mlsanity.com/paper/2509.24365/) (2025)
- [OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists](https://mlsanity.com/paper/2511.16931/) (2025)
- [One Size doesn't Fit All: A Personalized Conversational Tutoring Agent for Mathematics Instruction](https://mlsanity.com/paper/2502.12633/) (2025)
- [A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone](https://mlsanity.com/paper/2505.12781/) (2025)
- [Cognitive Biases in Large Language Models for News Recommendation](https://mlsanity.com/paper/2410.02897/) (2024)

## Built on by (most cited first, 30 of 51)

- [Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops](https://mlsanity.com/paper/2607.07663/) (2026)
- [ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence](https://mlsanity.com/paper/2605.26340/) (2026)
- [ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research](https://mlsanity.com/paper/2606.07591/) (2026)
- [ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration](https://mlsanity.com/paper/2605.03042/) (2026)
- [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery](https://mlsanity.com/paper/2605.23204/) (2026)
- [NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?](https://mlsanity.com/paper/2606.24530/) (2026)
- [Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction](https://mlsanity.com/paper/2607.12835/) (2026)
- [AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle](https://mlsanity.com/paper/2605.31468/) (2026)
- [NeuroClaw Technical Report](https://mlsanity.com/paper/2604.24696/) (2026)
- [NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation](https://mlsanity.com/paper/2605.10813/) (2026)
- [GEAR: Genetic AutoResearch for Agentic Code Evolution](https://mlsanity.com/paper/2605.13874/) (2026)
- [An Empirical Study of Multi-Agent Collaboration for Automated Research](https://mlsanity.com/paper/2603.29632/) (2026)
- [Symbolic-Vector Attention Fusion for Collective Intelligence](https://mlsanity.com/paper/2604.03955/) (2026)
- [Federation over Text: Insight Sharing for Multi-Agent Reasoning](https://mlsanity.com/paper/2604.16778/) (2026)
- [Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks](https://mlsanity.com/paper/2605.21825/) (2026)
- [TianJi:An autonomous AI meteorologist for discovering physical mechanisms in atmospheric science](https://mlsanity.com/paper/2603.27738/) (2026)
- [Socratic agents for autonomous scientific discovery in high-dimensional physical systems](https://mlsanity.com/paper/2606.26722/) (2026)
- [X-Alpha: An AI Quant Researcher with Memory-Driven Self-Evolution](https://mlsanity.com/paper/2607.08332/) (2026)
- [Overview of the NLPCC 2026 Shared Task 11: Agent-Based Experiment Reproduction from Scientific Papers](https://mlsanity.com/paper/2609.11117/) (2026)
- [Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science](https://mlsanity.com/paper/2603.28361/) (2026)
- [SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research](https://mlsanity.com/paper/2605.22878/) (2026)
- [Making AI Scientists Auditable from Evidence to Claim](https://mlsanity.com/paper/2606.18874/) (2026)
- [One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution](https://mlsanity.com/paper/2606.31478/) (2026)
- [Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design](https://mlsanity.com/paper/2608.10299/) (2026)
- [ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs](https://mlsanity.com/paper/2608.12788/) (2026)
- [Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery](https://mlsanity.com/paper/2608.19047/) (2026)
- [Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks](https://mlsanity.com/paper/2608.30047/) (2026)

## Abstract (arXiv)

The increasing adoption of Large Language Models (LLMs) has enabled AI scientists to perform complex end-to-end scientific discovery tasks requiring coordination of specialized roles, including idea generation and experimental execution. However, most state-of-the-art AI scientist systems rely on static, hand-designed pipelines and fail to adapt based on accumulated interaction histories. As a result, these systems overlook promising research directions, repeat failed experiments, and pursue infeasible ideas. To address this, we introduce EvoScientist, an evolving multi-agent AI scientist framework that continuously improves research strategies through persistent memory and self-evolution. EvoScientist comprises three specialized agents: a Researcher Agent (RA) for scientific idea generation, an Engineer Agent (EA) for experiment implementation and execution, and an Evolution Manager Agent (EMA) that distills insights from prior interactions into reusable knowledge. EvoScientist contains two persistent memory modules: (i) an ideation memory, which summarizes feasible research directions from top-ranked ideas while recording previously unsuccessful directions; and (ii) an experimentation memory, which captures effective data processing and model training strategies derived from code search trajectories and best-performing implementations. These modules enable the RA and EA to retrieve relevant prior strategies, improving idea quality and code execution success rates over time. Experiments show that EvoScientist outperforms 7 open-source and commercial state-of-the-art systems in scientific idea generation, achieving higher novelty, feasibility, relevance, and clarity via automatic and human evaluation. EvoScientist also substantially improves code execution success rates through multi-agent evolution, demonstrating persistent memory's effectiveness for end-to-end scientific discovery.