# Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research

arXiv: https://arxiv.org/abs/2510.06056 · HTML: https://mlsanity.com/paper/2510.06056/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 18 of 18)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [Graph Rationalization with Environment-based Augmentations](https://mlsanity.com/paper/2206.02886/) (2022)
- [Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning](https://mlsanity.com/paper/2504.17192/) (2025)
- [A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications](https://mlsanity.com/paper/2506.12594/) (2025)
- [CodePDE: An Inference Framework for LLM-driven PDE Solver Generation](https://mlsanity.com/paper/2505.08783/) (2025)
- [EXP-Bench: Can AI Conduct AI Research Experiments?](https://mlsanity.com/paper/2505.24785/) (2025)
- [AI Scientists Fail Without Strong Implementation Capability](https://mlsanity.com/paper/2506.01372/) (2025)
- [AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers](https://mlsanity.com/paper/2504.20115/) (2025)

## Built on by (most cited first, 19 of 19)

- [AI co-mathematician: Accelerating mathematicians with agentic AI](https://mlsanity.com/paper/2605.06651/) (2026)
- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback](https://mlsanity.com/paper/2602.12612/) (2026)
- [NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?](https://mlsanity.com/paper/2606.24530/) (2026)
- [Improving Coherence and Persistence in Agentic AI for System Optimization](https://mlsanity.com/paper/2603.21321/) (2026)
- [Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection](https://mlsanity.com/paper/2602.07892/) (2026)
- [Effective Harness Engineering for Algorithm Discovery with Coding Agents](https://mlsanity.com/paper/2605.15221/) (2026)
- [Automated Discovery Has No Universally Superior Harness](https://mlsanity.com/paper/2607.18235/) (2026)
- [PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks](https://mlsanity.com/paper/2512.03549/) (2025)
- [Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization](https://mlsanity.com/paper/2604.25083/) (2026)
- [Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs](https://mlsanity.com/paper/2605.06123/) (2026)
- [Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment](https://mlsanity.com/paper/2608.23691/) (2026)
- [CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery](https://mlsanity.com/paper/2604.01210/) (2026)
- [Lectures on AI for Mathematics](https://mlsanity.com/paper/2604.11504/) (2026)
- [CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing](https://mlsanity.com/paper/2605.11359/) (2026)
- [Learning to Solve and Optimize by Evolving Code](https://mlsanity.com/paper/2605.31049/) (2026)
- [Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks](https://mlsanity.com/paper/2606.01975/) (2026)
- [Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization](https://mlsanity.com/paper/2609.38757/) (2026)
- [EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery](https://mlsanity.com/paper/2609.40340/) (2026)

## Abstract (arXiv)

Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in AlphaEvolve, depends only on the internal knowledge of LLMs and quickly plateaus in complex domains, while pure deep research proposes ideas without validation, resulting in unrealistic or unimplementable solutions. We present DeepEvolve, an agent that integrates deep research with algorithm evolution, uniting external knowledge retrieval, cross-file code editing, and systematic debugging under a feedback-driven iterative loop. Each iteration not only proposes new hypotheses but also refines, implements, and tests them, avoiding both shallow improvements and unproductive over-refinements. Across nine benchmarks in chemistry, mathematics, biology, materials, and patents, DeepEvolve consistently improves the initial algorithm, producing executable new algorithms with sustained gains. By bridging the gap between unguided evolution and research without grounding, DeepEvolve provides a reliable framework for advancing scientific algorithm discovery. Our code is available at https://github.com/liugangcode/deepevolve.