GPT-in-the-Loop: Supporting Adaptation in Multiagent Systems
Bibliographic record
Abstract
This paper introduces the ‘GPT-in-the-loop’ approach, which seeks to investigate the reasoning capabilities of Large Language Models (LLMs) like Generative Pre-trained Transformers (GPT) within multiagent systems (MAS). Moving beyond traditional adaptive approaches that generally require long training processes, our framework employs GPT-4 to enhance problem-solving and explanation skills. To explore this approach, we apply it to a smart streetlight application in the Internet of Things (IoT) context, wherein each streetlight is controlled by an autonomous agent equipped with sensors and actuators, tasked with creating an energy-efficient lighting system. With the integration of GPT-4, these agents have shown enhanced decision-making and adaptability, without necessitating prolonged training. We compare this approach with both conventional neuroevolutionary methods and manually crafted solutions by software engineers, underscoring the potential of GPT-driven behavior in multiagent systems. It is important to note that these comparisons are preliminary, and further, more extensive testing is critical to determine the approach’s applicability across a wider range of MAS scenarios. Structurally, the paper delineates the incorporation of GPT into the agent-driven Framework for the Internet of Things (FIoT), details our proposed GPT-in-the-loop approach, presents comparative results within the IoT setting, and concludes with insights and prospective future directions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".