Guided Reasoning: A Non-Technical Introduction

Gregor Betz
8/29/2024
cs.AIcs.HC

Official code: logikon-ai/logikon (47 stars, AGPL-3.0, last commit 2024-09-01).

Abstract

We introduce the concept and a default implementation of Guided Reasoning. A multi-agent system is a Guided Reasoning system iff one agent (the guide) primarily interacts with other agents in order to improve reasoning quality. We describe Logikon's default implementation of Guided Reasoning in non-technical terms. This is a living document we'll gradually enrich with more detailed information and examples. Code: https://github.com/logikon-ai/logikon

View on arXivView PDF

Code Implementations(1)

logikon-ai/logikonOfficial100%
AGPL-3.0

Analyzing and scoring reasoning traces of LLMs

470Shell, PythonSep 10, 20232 years agoAGPL-3.0
aiargument-mappingargument-miningargumentationcritical-thinking+9 more

Similar Papers

Toolsuite for Implementing Multiagent Systems Based on Communication Protocols

83% match2025

The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoption

82% match2026

Agentic Systems: A Guide to Transforming Industries with Vertical AI Agents

82% match2025

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

82% match1 repo6512024

AutoGenesisAgent: Self-Generating Multi-Agent Systems for Complex Tasks

81% match2024

LLM Multi-Agent Systems: Challenges and Open Problems

81% match2024

Cite this paper

@article{betz2024guided,
  title  = {Guided Reasoning: A Non-Technical Introduction},
  author = {Gregor Betz},
  year   = {2024},
  eprint = {2408.16331},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.16331v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.16331.svg)](https://codeofpaper.com/paper/2408.16331)

Discussion