# GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems

arXiv: https://arxiv.org/abs/2308.10435 · HTML: https://mlsanity.com/paper/2308.10435/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [Explainable Goal-Driven Agents and Robots -- A Comprehensive Review](https://mlsanity.com/paper/2004.09705/) (2020)
- [Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability](https://mlsanity.com/paper/2112.09054/) (2021)
- [Towards the Neuroevolution of Low-level Artificial General Intelligence](https://mlsanity.com/paper/2207.13583/) (2022)

## Built on by (most cited first, 9 of 9)

- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [MACRec: a Multi-Agent Collaboration Framework for Recommendation](https://mlsanity.com/paper/2402.15235/) (2024)
- [TransLLaMa: LLM-based Simultaneous Translation System](https://mlsanity.com/paper/2402.04636/) (2024)
- [From Interaction to Impact: Towards Safer AI Agents Through Understanding and Evaluating Mobile UI Operation Impacts](https://mlsanity.com/paper/2410.09006/) (2024)
- [The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs](https://mlsanity.com/paper/2602.11583/) (2026)
- [Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2405.16854/) (2024)
- [360^circREA: Towards A Reusable Experience Accumulation with 360deg Assessment for Multi-Agent System](https://mlsanity.com/paper/2404.05569/) (2024)
- [SafePilot: A Framework for Assuring LLM-enabled Cyber-Physical Systems](https://mlsanity.com/paper/2603.21523/) (2026)
- [Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems](https://mlsanity.com/paper/2609.16599/) (2026)

## Abstract (arXiv)

This paper introduces the "GPT-in-the-loop" approach, a novel method combining the advanced reasoning capabilities of Large Language Models (LLMs) like Generative Pre-trained Transformers (GPT) with multiagent (MAS) systems. Venturing beyond traditional adaptive approaches that generally require long training processes, our framework employs GPT-4 for enhanced problem-solving and explanation skills. Our experimental backdrop is the smart streetlight Internet of Things (IoT) application. Here, agents use sensors, actuators, and neural networks to create an energy-efficient lighting system. By integrating GPT-4, these agents achieve superior decision-making and adaptability without the need for extensive training. We compare this approach with both traditional neuroevolutionary methods and solutions provided by software engineers, underlining the potential of GPT-driven multiagent systems in IoT. Structurally, the paper outlines the incorporation of GPT into the agent-driven Framework for the Internet of Things (FIoT), introduces our proposed GPT-in-the-loop approach, presents comparative results in the IoT context, and concludes with insights and future directions.