# The FM Agent

arXiv: https://arxiv.org/abs/2510.26144 · HTML: https://mlsanity.com/paper/2510.26144/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 51 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

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

- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (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)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving](https://mlsanity.com/paper/2507.23726/) (2025)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement](https://mlsanity.com/paper/2411.00622/) (2024)
- [ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning](https://mlsanity.com/paper/2506.16499/) (2025)
- [CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning](https://mlsanity.com/paper/2507.14111/) (2025)
- [MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement](https://mlsanity.com/paper/2506.15692/) (2025)
- [InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification](https://mlsanity.com/paper/2505.16938/) (2025)
- [GameGPT: Multi-agent Collaborative Framework for Game Development](https://mlsanity.com/paper/2310.08067/) (2023)
- [Mirage: A Multi-Level Superoptimizer for Tensor Programs](https://mlsanity.com/paper/2405.05751/) (2024)
- [ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering](https://mlsanity.com/paper/2506.09050/) (2025)
- [CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation](https://mlsanity.com/paper/2501.07811/) (2025)
- [CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards](https://mlsanity.com/paper/2510.08529/) (2025)
- [LLM-Vectorizer: LLM-based Verified Loop Vectorizer](https://mlsanity.com/paper/2406.04693/) (2024)
- [CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology](https://mlsanity.com/paper/2402.01411/) (2024)
- [CleanAgent: Automating Data Standardization with LLM-based Agents](https://mlsanity.com/paper/2403.08291/) (2024)
- [Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming](https://mlsanity.com/paper/2504.21304/) (2025)
- [(X)-evolve: Solution space evolution powered by large language models](https://mlsanity.com/paper/2508.07932/) (2025)
- [C-Evolve: Consensus-based Evolution for Prompt Groups](https://mlsanity.com/paper/2509.23331/) (2025)
- [Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2510.16511/) (2025)
- [CuAsmRL: Optimizing GPU SASS Schedules via Deep Reinforcement Learning](https://mlsanity.com/paper/2501.08071/) (2025)
- [Automating Energy-Efficient GPU Kernel Generation: A Fast Search-Based Compilation Approach](https://mlsanity.com/paper/2411.18873/) (2024)

## Built on by (most cited first, 21 of 21)

- [MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery](https://mlsanity.com/paper/2606.06473/) (2026)
- [MARS: Modular Agent with Reflective Search for Automated AI Research](https://mlsanity.com/paper/2602.02660/) (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)
- [Towards Automated Kernel Generation in the Era of LLMs](https://mlsanity.com/paper/2601.15727/) (2026)
- [Synthetic Sandbox for Training Machine Learning Engineering Agents](https://mlsanity.com/paper/2604.04872/) (2026)
- [TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration](https://mlsanity.com/paper/2604.14116/) (2026)
- [Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering](https://mlsanity.com/paper/2607.28568/) (2026)
- [AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering](https://mlsanity.com/paper/2602.07906/) (2026)
- [Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search](https://mlsanity.com/paper/2603.01692/) (2026)
- [ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond](https://mlsanity.com/paper/2608.14354/) (2026)
- [What Do Evolutionary Coding Agents Evolve?](https://mlsanity.com/paper/2605.20086/) (2026)
- [AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models](https://mlsanity.com/paper/2605.27873/) (2026)
- [Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games](https://mlsanity.com/paper/2606.10389/) (2026)
- [DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery](https://mlsanity.com/paper/2605.15461/) (2026)
- [A Blueprint for Self-Evolving Coding Agents in Vehicle Aerodynamic Drag Prediction](https://mlsanity.com/paper/2603.21698/) (2026)
- [EvoMem: Memory-Augmented Evolution for Code Optimization](https://mlsanity.com/paper/2608.10795/) (2026)
- [Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning](https://mlsanity.com/paper/2609.22257/) (2026)
- [AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search](https://mlsanity.com/paper/2609.25047/) (2026)
- [Assembling Insights for Agentic Machine Learning Engineering Systems](https://mlsanity.com/paper/2610.04927/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purpose multi-agent framework that leverages a synergistic combination of LLM-based reasoning and large-scale evolutionary search to address complex real-world challenges. The core of FM Agent integrates several key innovations: 1) a cold-start initialization phase incorporating expert guidance, 2) a novel evolutionary sampling strategy for iterative optimization, 3) domain-specific evaluators that combine correctness, effectiveness, and LLM-supervised feedback, and 4) a distributed, asynchronous execution infrastructure built on Ray. Demonstrating broad applicability, our system has been evaluated across diverse domains, including operations research, machine learning, GPU kernel optimization, and classical mathematical problems. FM Agent reaches state-of-the-art results autonomously, without human interpretation or tuning -- 1976.3 on ALE-Bench (+5.2%), 43.56% on MLE-Bench (+4.0pp), up to 20x speedups on KernelBench, and establishes new state-of-the-art(SOTA) results on several classical mathematical problems. Beyond academic benchmarks, FM Agent shows considerable promise for both large-scale enterprise R&D workflows and fundamental scientific research, where it can accelerate innovation, automate complex discovery processes, and deliver substantial engineering and scientific advances with broader societal impact.