# LLM-Enabled In-Context Learning for Data Collection Scheduling in UAV-assisted Sensor Networks

arXiv: https://arxiv.org/abs/2504.14556 · HTML: https://mlsanity.com/paper/2504.14556/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 20 Apr 2025.

## Builds on (most cited first, 17 of 17)

- [Jailbreak Attacks and Defenses Against Large Language Models: A Survey](https://mlsanity.com/paper/2407.04295/) (2024)
- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities](https://mlsanity.com/paper/2309.16739/) (2023)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [Large Language Models for UAVs: Current State and Pathways to the Future](https://mlsanity.com/paper/2405.01745/) (2024)
- [Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey](https://mlsanity.com/paper/2211.04324/) (2022)
- [Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends](https://mlsanity.com/paper/2409.14457/) (2024)
- [Large Language Model (LLM)-enabled In-context Learning for Wireless Network Optimization: A Case Study of Power Control](https://mlsanity.com/paper/2408.00214/) (2024)
- [Large Language Models in Wireless Application Design: In-Context Learning-enhanced Automatic Network Intrusion Detection](https://mlsanity.com/paper/2405.11002/) (2024)
- [Generative AI for Unmanned Vehicle Swarms: Challenges, Applications and Opportunities](https://mlsanity.com/paper/2402.18062/) (2024)
- [Large Language Models for Wireless Networks: An Overview from the Prompt Engineering Perspective](https://mlsanity.com/paper/2411.04136/) (2024)
- [On-board Deep Q-Network for UAV-assisted Online Power Transfer and Data Collection](https://mlsanity.com/paper/1906.07064/) (2019)
- [Leveraging Large Language Models for Wireless Symbol Detection via In-Context Learning](https://mlsanity.com/paper/2409.00124/) (2024)
- [Deep Reinforcement Learning for Joint Cruise Control and Intelligent Data Acquisition in UAVs-Assisted Sensor Networks](https://mlsanity.com/paper/2312.09953/) (2023)
- [Aero-LLM: A Distributed Framework for Secure UAV Communication and Intelligent Decision-Making](https://mlsanity.com/paper/2502.05220/) (2025)

## Built on by (most cited first, 12 of 12)

- [UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios](https://mlsanity.com/paper/2511.11252/) (2025)
- [From Prompts to Protection: Large Language Model-Enabled In-Context Learning for Smart Public Safety UAV](https://mlsanity.com/paper/2506.02649/) (2025)
- [FRSICL: LLM-Enabled In-Context Learning Flight Resource Allocation for Fresh Data Collection in UAV-Assisted Wildfire Monitoring](https://mlsanity.com/paper/2507.10134/) (2025)
- [Large Language Model-Assisted UAV Operations and Communications: A Multifaceted Survey and Tutorial](https://mlsanity.com/paper/2602.19534/) (2026)
- [AIC-VDS: Attention-Based In-Context Learning for Joint Velocity Control and Data Collection Scheduling in Multi-UAV-Assisted Pipeline Monitoring](https://mlsanity.com/paper/2510.05698/) (2025)
- [Safe and Economical UAV Trajectory Planning in Low-Altitude Airspace: A Hybrid DRL-LLM Approach with Compliance Awareness](https://mlsanity.com/paper/2506.08532/) (2025)
- [Advancing Autonomous Emergency Response Systems: A Generative AI Perspective](https://mlsanity.com/paper/2511.09044/) (2025)
- [Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration](https://mlsanity.com/paper/2604.02659/) (2026)
- [Hierarchical LLM-Driven Control for HAPS-Assisted UAV Networks: Joint Optimization of Flight and Connectivity](https://mlsanity.com/paper/2605.11509/) (2026)
- [LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies, and Open Problems](https://mlsanity.com/paper/2607.09756/) (2026)
- [LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset](https://mlsanity.com/paper/2608.15175/) (2026)
- [Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2609.27847/) (2026)

## Abstract (arXiv)

Unmanned Aerial Vehicles (UAVs) are increasingly being utilized in various private and commercial applications, e.g., traffic control, parcel delivery, and Search and Rescue (SAR) missions. Machine Learning (ML) methods used in UAV-Assisted Sensor Networks (UASNETs) and, especially, in Deep Reinforcement Learning (DRL) face challenges such as complex and lengthy model training, gaps between simulation and reality, and low sampling efficiency, which conflict with the urgency of emergencies, such as SAR missions. In this paper, an In-Context Learning (ICL)-Data Collection Scheduling (ICLDC) system is proposed as an alternative to DRL in emergencies. The UAV collects sensory data and transmits it to a Large Language Model (LLM), which creates a task description in natural language. From this description, the UAV receives a data collection schedule that must be executed. A verifier ensures safe UAV operations by evaluating the schedules generated by the LLM and overriding unsafe schedules based on predefined rules. The system continuously adapts by incorporating feedback into the task descriptions and using this for future decisions. This method is tested against jailbreaking attacks, where the task description is manipulated to undermine network performance, highlighting the vulnerability of LLMs to such attacks. The proposed ICLDC significantly reduces cumulative packet loss compared to both the DQN and Maximum Channel Gain baselines. ICLDC presents a promising direction for intelligent scheduling and control in UASNETs.