Human-Drone Swarm Collaboration Using LLMs: Case Study on DRL-Based Anti-jamming
Bibliographic record
Abstract
Abstract As autonomous systems such as drone swarms become increasingly crucial in complex missions, it is essential to ensure effective human oversight and explainable human-machine collaboration. We propose to integrate large language models (LLMs) as an interface with artificial intelligence (AI) agents to enhance explainability and incorporate human-in-the-loop control. We discuss how LLMs can bridge the gap between the technical complexities of AI-based autonomous systems and post-hoc interpretation techniques. LLM as an interface can enhance human-machine collaboration and control and increase trust and safety. Moreover, it has the potential to provide emergent capabilities and enhanced meta-learning. In our preliminary work, we integrate LLMs with deep reinforcement learning (DRL) to enhance anti-jamming capabilities of autonomous systems. Through a detailed case study, we demonstrate how this approach not only mitigates jamming threats but also facilitates human-in-the-loop control, enabling dynamic adjustments to mission parameters. Additionally, the natural language interface provided by LLMs enhances communication efficiency between human operators and drone swarms, ensuring seamless collaboration and improved operational resilience.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".