LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios

TL;DR

This survey reviews various agentic reasoning frameworks based on large language models, classifying them systematically and analyzing their applications across multiple scientific and social domains.

Contribution

It introduces a unified formal language to classify agentic reasoning systems and provides a comprehensive comparison of their frameworks and application scenarios.

Findings

Classifies agentic reasoning frameworks into single-agent, tool-based, and multi-agent methods.

Analyzes applications in scientific discovery, healthcare, and social simulation.

Summarizes evaluation strategies for different frameworks.

Abstract

Recent advances in the intrinsic reasoning capabilities of large language models (LLMs) have given rise to LLM-based agent systems that exhibit near-human performance on a variety of automated tasks. However, although these systems share similarities in terms of their use of LLMs, different reasoning frameworks of the agent system steer and organize the reasoning process in different ways. In this survey, we propose a systematic taxonomy that decomposes agentic reasoning frameworks and analyze how these frameworks dominate framework-level reasoning by comparing their applications across different scenarios. Specifically, we propose an unified formal language to further classify agentic reasoning systems into single-agent methods, tool-based methods, and multi-agent methods. After that, we provide a comprehensive review of their key application scenarios in scientific discovery, healthcare, software engineering, social simulation, and economics. We also analyze the characteristic features of each framework and summarize different evaluation strategies. Our survey aims to provide the research community with a panoramic view to facilitate understanding of the strengths, suitable scenarios, and evaluation practices of different agentic reasoning frameworks.