# DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively

arXiv: https://arxiv.org/abs/2509.26603 · HTML: https://mlsanity.com/paper/2509.26603/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 55 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 30 of 42)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [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)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [RADAR: Robust AI-Text Detection via Adversarial Learning](https://mlsanity.com/paper/2307.03838/) (2023)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [AgentRxiv: Towards Collaborative Autonomous Research](https://mlsanity.com/paper/2503.18102/) (2025)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [Personality Alignment of Large Language Models](https://mlsanity.com/paper/2408.11779/) (2024)
- [Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents](https://mlsanity.com/paper/2509.06917/) (2025)
- [AI Scientists Fail Without Strong Implementation Capability](https://mlsanity.com/paper/2506.01372/) (2025)

## Built on by (most cited first, 30 of 63)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery](https://mlsanity.com/paper/2603.08127/) (2026)
- [MARS: Modular Agent with Reflective Search for Automated AI Research](https://mlsanity.com/paper/2602.02660/) (2026)
- [AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations](https://mlsanity.com/paper/2602.03828/) (2026)
- [AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery](https://mlsanity.com/paper/2604.05550/) (2026)
- [ResearchGym: Evaluating Language Model Agents on Real-World AI Research](https://mlsanity.com/paper/2602.15112/) (2026)
- [ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence](https://mlsanity.com/paper/2605.26340/) (2026)
- [OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists](https://mlsanity.com/paper/2511.16931/) (2025)
- [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026)
- [Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper](https://mlsanity.com/paper/2511.04583/) (2025)
- [A Survey of AI Scientists](https://mlsanity.com/paper/2510.23045/) (2025)
- [AI Can Learn Scientific Taste](https://mlsanity.com/paper/2603.14473/) (2026)
- [AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery](https://mlsanity.com/paper/2604.25256/) (2026)
- [SciCoQA: Quality Assurance for Scientific Paper--Code Alignment](https://mlsanity.com/paper/2601.12910/) (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)
- [InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem](https://mlsanity.com/paper/2602.14367/) (2026)
- [TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration](https://mlsanity.com/paper/2604.14116/) (2026)
- [Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network](https://mlsanity.com/paper/2511.02238/) (2025)
- [Towards a Medical AI Scientist](https://mlsanity.com/paper/2603.28589/) (2026)
- [DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review](https://mlsanity.com/paper/2604.09590/) (2026)
- [FARS: A Fully Automated Research System Deployed at Scale](https://mlsanity.com/paper/2606.31651/) (2026)
- [Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs](https://mlsanity.com/paper/2605.02735/) (2026)
- [DeepInnovator: Triggering the Innovative Capabilities of LLMs](https://mlsanity.com/paper/2602.18920/) (2026)
- [AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle](https://mlsanity.com/paper/2605.31468/) (2026)
- [NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation](https://mlsanity.com/paper/2605.10813/) (2026)
- [Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery](https://mlsanity.com/paper/2603.29045/) (2026)
- [Federation over Text: Insight Sharing for Multi-Agent Reasoning](https://mlsanity.com/paper/2604.16778/) (2026)
- [AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents](https://mlsanity.com/paper/2605.06607/) (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)

## Abstract (arXiv)

While previous AI Scientist systems can generate novel findings, they often lack the focus to produce scientifically valuable contributions that address pressing human-defined challenges. We introduce DeepScientist, a system designed to overcome this by conducting goal-oriented, fully autonomous scientific discovery over month-long timelines. It formalizes discovery as a Bayesian Optimization problem, operationalized through a hierarchical evaluation process consisting of "hypothesize, verify, and analyze". Leveraging a cumulative Findings Memory, this loop intelligently balances the exploration of novel hypotheses with exploitation, selectively promoting the most promising findings to higher-fidelity levels of validation. Consuming over 20,000 GPU hours, the system generated about 5,000 unique scientific ideas and experimentally validated approximately 1100 of them, ultimately surpassing human-designed state-of-the-art (SOTA) methods on three frontier AI tasks by 183.7%, 1.9%, and 7.9%. This work provides the first large-scale evidence of an AI achieving discoveries that progressively surpass human SOTA on scientific tasks, producing valuable findings that genuinely push the frontier of scientific discovery. To facilitate further research into this process, we will open-source all experimental logs and system code at https://github.com/ResearAI/DeepScientist/.