Self-Adaptive Large Language Model (LLM)-Based Multiagent Systems
Bibliographic record
Abstract
The complexity of managing multiagent systems (MASs) in autonomic computing can be mitigated using a self-adaptation approach, where systems are equipped to monitor and adjust themselves based on specific concerns. Communication in these systems is key given that in scenarios involving agent interaction, it enhances cooperation and reduces coordination challenges by enabling direct, clear information exchange. However, the tasks of boosting communication expressiveness within MASs and logically processing a multitude of variables in dynamic environments are still challenging. This paper presents a novel strategy: integrating large language models (LLMs) like GPT-based technologies into MASs to boost communication and agent autonomy. Our proposal encompasses the development of a novel LLM/GPT-based agent architecture, focusing not only on advanced conversation features but also on the reasoning and decision-making capacities of these models. This is grounded in the MAPE-K model, known for supporting system adaptability in dynamic environments. We illustrate our approach through a marketplace scenario. This work represents a paradigm shift in MAS self-adaptation, utilizing LLMs' capabilities and indicating further research opportunities to assess LLMs' applicability in more complex MAS scenarios. This could pave the way for more potent problem-solving capabilities and refined communication within MASs.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".