# MARS: Modular Agent with Reflective Search for Automated AI Research

arXiv: https://arxiv.org/abs/2602.02660 · HTML: https://mlsanity.com/paper/2602.02660/

## Key facts

- Cited by 25 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 14 of its 36 references that are in the map.
- First posted on arXiv 2 Feb 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, 14 of 14)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning](https://mlsanity.com/paper/2506.16499/) (2025)
- [InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification](https://mlsanity.com/paper/2505.16938/) (2025)
- [Budget-Aware Tool Use Enables Effective Agent Scaling](https://mlsanity.com/paper/2511.17006/) (2025)
- [R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science](https://mlsanity.com/paper/2505.14738/) (2025)
- [PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration](https://mlsanity.com/paper/2505.15047/) (2025)
- [Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering](https://mlsanity.com/paper/2601.10402/) (2026)
- [The FM Agent](https://mlsanity.com/paper/2510.26144/) (2025)
- [Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement](https://mlsanity.com/paper/2512.18950/) (2025)

## Built on by (most cited first, 25 of 25)

- [MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery](https://mlsanity.com/paper/2606.06473/) (2026)
- [Toward Generalist Autonomous Research via Hypothesis-Tree Refinement](https://mlsanity.com/paper/2606.11926/) (2026)
- [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026)
- [AIBuildAI: An AI Agent for Automatically Building AI Models](https://mlsanity.com/paper/2604.14455/) (2026)
- [AIRA_2: Overcoming Bottlenecks in AI Research Agents](https://mlsanity.com/paper/2603.26499/) (2026)
- [AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement](https://mlsanity.com/paper/2608.20318/) (2026)
- [AI Research Preference Models](https://mlsanity.com/paper/2608.13940/) (2026)
- [FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics](https://mlsanity.com/paper/2605.17373/) (2026)
- [Revisiting DAgger in the Era of LLM-Agents](https://mlsanity.com/paper/2605.12913/) (2026)
- [EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery](https://mlsanity.com/paper/2606.13662/) (2026)
- [ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond](https://mlsanity.com/paper/2608.14354/) (2026)
- [Towards Autonomous and Auditable Medical Imaging Model Development](https://mlsanity.com/paper/2607.10522/) (2026)
- [Figures as Programs: Recursive Generation of Editable Scientific Figures](https://mlsanity.com/paper/2609.01006/) (2026)
- [Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills](https://mlsanity.com/paper/2609.02749/) (2026)
- [Agentic Discovery with Active Hypothesis Exploration for Visual Recognition](https://mlsanity.com/paper/2604.12999/) (2026)
- [DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery](https://mlsanity.com/paper/2605.15461/) (2026)
- [Learning the ARTS of Search for Automated Discovery](https://mlsanity.com/paper/2606.21891/) (2026)
- [Towards Persistent Case-Based Memory for Autonomous Data Science: A CBR-Augmented R&D-Agent with a Locally Deployable Small Language Model](https://mlsanity.com/paper/2606.05250/) (2026)
- [Evolutionary Ensemble Search: Council-Guided Program Evolution with Persistent Memory](https://mlsanity.com/paper/2609.17590/) (2026)
- [PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research](https://mlsanity.com/paper/2609.17846/) (2026)
- [AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search](https://mlsanity.com/paper/2609.25047/) (2026)
- [How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?](https://mlsanity.com/paper/2609.40303/) (2026)
- [Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents](https://mlsanity.com/paper/2610.02525/) (2026)
- [Assembling Insights for Agentic Machine Learning Engineering Systems](https://mlsanity.com/paper/2610.04927/) (2026)
- [JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models](https://mlsanity.com/paper/2610.13194/) (2026)

## Abstract (arXiv)

A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and opaque performance attribution. Current LLM-based agents struggle here, often generating monolithic scripts that ignore execution costs and causal factors. We introduce MARS (Modular Agent with Reflective Search), a framework optimized for autonomous AI research. MARS relies on three pillars: (1) Budget-Aware Planning via cost-constrained Monte Carlo Tree Search (MCTS) to explicitly balance performance with execution expense; (2) Modular Construction, employing a "Design-Decompose-Implement" pipeline to manage complex research repositories; and (3) Comparative Reflective Memory, which addresses credit assignment by analyzing solution differences to distill high-signal insights. MARS achieves state-of-the-art performance among open-source frameworks on MLE-Bench under comparable settings, maintaining competitiveness with the global leaderboard's top methods. Furthermore, the system exhibits qualitative "Aha!" moments, where 63% of all utilized lessons originate from cross-branch transfer, demonstrating that the agent effectively generalizes insights across search paths.