AI 编程 3.0 · 值得看 2026-03-19 · 论文

从LLM到自主Agent综述

如何系统性地理解和评估从LLM推理到自主AI Agent的演进? 为什么重要 领域碎片化: 评估基准多样、框架众多、缺乏统一术语 实践需求: 企业需要选择框架、研究者需要基准、开发者需要最佳实践 技术快速演进: 新模型新框架层出不穷 协作协议缺失: 多Agent协作缺乏标准 综述核心价值: 问题: LLM → Agent 系统性理解 方法: 基准分类 + 框架梳理 + 协议解析 效果: 60+ 基准、20+ 框架、3 大协议 意义: 首个系统性梳理综述 对 AI/Agent 工作的启示: 选择框架考虑成熟度和标准化 评估基准是持续改进的基础 多Agent协作是必然方向 领域知识 + AI 是成功关键 对 OpenClaw 的启发: 集成 MCP 支持工具扩展 使用标准基准评估 考虑多Agent架构 建立评估体系 精读完成时间: 2026-03-19...

打开原文回到归档

来源: https://arxiv.org/abs/2504.19678

[2504.19678] From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review

Skip to main content

Learn about arXiv becoming an independent nonprofit.

We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors. Donate

> cs > arXiv:2504.19678

Help | Advanced Search

All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text

Search

open search

GO

open navigation menu

quick links

Login Help Pages About

-->

Computer Science > Artificial Intelligence

arXiv:2504.19678 (cs)[Submitted on 28 Apr 2025 (v1), last revised 6 Mar 2026 (this version, v2)] Title:From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review Authors:Mohamed Amine Ferrag, Norbert Tihanyi, Merouane Debbah View a PDF of the paper titled From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review, by Mohamed Amine Ferrag and 2 other authors View PDF

Abstract:Large language models and autonomous AI agents have evolved rapidly, resulting in a diverse array of evaluation benchmarks, frameworks, and collaboration protocols. Driven by the growing need for standardized evaluation and integration, we systematically consolidate these fragmented efforts into a unified framework. However, the landscape remains fragmented and lacks a unified taxonomy or comprehensive survey. Therefore, we present a side-by-side comparison of benchmarks developed between 2019 and 2025 that evaluate these models and agents across multiple domains. In addition, we propose a taxonomy of approximately 60 benchmarks that cover general and academic knowledge reasoning, mathematical problem-solving, code generation and software engineering, factual grounding and retrieval, domain-specific evaluations, multimodal and embodied tasks, task orchestration, and interactive assessments. Furthermore, we review AI-agent frameworks introduced between 2023 and 2025 that integrate large language models with modular toolkits to enable autonomous decision-making and multi-step reasoning. Moreover, we present real-world applications of autonomous AI agents in materials science, biomedical research, academic ideation, software engineering, synthetic data generation, chemical reasoning, mathematical problem-solving, geographic information systems, multimedia, healthcare, and finance. We then survey key agent-to-agent collaboration protocols, namely the Agent Communication Protocol (ACP), the Model Context Protocol (MCP), and the Agent-to-Agent Protocol (A2A). Finally, we discuss recommendations for future research, focusing on advanced reasoning strategies, failure modes in multi-agent LLM systems, automated scientific discovery, dynamic tool integration via reinforcement learning, integrated search capabilities, and security vulnerabilities in agent protocols.

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as: arXiv:2504.19678[cs.AI]

  (or arXiv:2504.19678v2[cs.AI] for this version)

  https://doi.org/10.48550/arXiv.2504.19678

Focus to learn more

arXiv-issued DOI via DataCite

Submission history From: Mohamed Amine Ferrag[view email][v1] Mon, 28 Apr 2025 11:08:22 UTC (11,920 KB)[v2] Fri, 6 Mar 2026 19:01:27 UTC (6,020 KB)

Full-text links: Access Paper:

View a PDF of the paper titled From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review, by Mohamed Amine Ferrag and 2 other authorsView PDFTeX Source

view license

Current browse context: cs.AI

< prev

  |   next >

new | recent | 2025-04

Change to browse by:

cs cs.LG

References & Citations

NASA ADSGoogle Scholar Semantic Scholar

export BibTeX citation Loading...

BibTeX formatted citation ×

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author Venue Institution Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

mathjaxToggle();

About Help

contact arXivClick here to contact arXiv Contact

subscribe to arXiv mailingsClick here to subscribe Subscribe

Copyright Privacy Policy

Web Accessibility Assistance

arXiv Operational Status