# AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing

arXiv: https://arxiv.org/abs/2510.19661 · HTML: https://mlsanity.com/paper/2510.19661/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 61 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review](https://mlsanity.com/paper/2504.19678/) (2025)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation](https://mlsanity.com/paper/2402.14744/) (2024)
- [UrbanGPT: Spatio-Temporal Large Language Models](https://mlsanity.com/paper/2403.00813/) (2024)
- [Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions](https://mlsanity.com/paper/2312.02913/) (2023)
- [Large Language Model for Participatory Urban Planning](https://mlsanity.com/paper/2402.17161/) (2024)
- [OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents](https://mlsanity.com/paper/2410.21286/) (2024)
- [Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook](https://mlsanity.com/paper/2402.19348/) (2024)
- [LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarios](https://mlsanity.com/paper/2505.11247/) (2025)
- [Automating Traffic Model Enhancement with AI Research Agent](https://mlsanity.com/paper/2409.16876/) (2024)
- [Urban Sensing based on Mobile Phone Data: Approaches, Applications and Challenges](https://mlsanity.com/paper/2008.12992/) (2020)
- [A survey of urban drive-by sensing: An optimization perspective](https://mlsanity.com/paper/2302.00622/) (2023)
- [Modulo: Drive-by Sensing at City-scale on the Cheap](https://mlsanity.com/paper/1910.09155/) (2019)
- [UrbanMind: Urban Dynamics Prediction with Multifaceted Spatial-Temporal Large Language Models](https://mlsanity.com/paper/2505.11654/) (2025)

## Built on by (most cited first, 5 of 5)

- [Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems](https://mlsanity.com/paper/2601.01891/) (2026)
- [EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management](https://mlsanity.com/paper/2606.15532/) (2026)
- [Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling](https://mlsanity.com/paper/2607.13558/) (2026)
- [Language-Grounded Multi-Agent Planning for Personalized and Fair Participatory Urban Sensing](https://mlsanity.com/paper/2603.24014/) (2026)
- [Reinforcement Learning for Delivery Drone-Based Participatory Sensing in Dynamic Environments](https://mlsanity.com/paper/2607.18874/) (2026)

## Abstract (arXiv)

Web-based participatory urban sensing has emerged as a vital approach for modern urban management by leveraging mobile individuals as distributed sensors. However, existing urban sensing systems struggle with limited generalization across diverse urban scenarios and poor interpretability in decision-making. In this work, we introduce AgentSense, a hybrid, training-free framework that integrates large language models (LLMs) into participatory urban sensing through a multi-agent evolution system. AgentSense initially employs classical planner to generate baseline solutions and then iteratively refines them to adapt sensing task assignments to dynamic urban conditions and heterogeneous worker preferences, while producing natural language explanations that enhance transparency and trust. Extensive experiments across two large-scale mobility datasets and seven types of dynamic disturbances demonstrate that AgentSense offers distinct advantages in adaptivity and explainability over traditional methods. Furthermore, compared to single-agent LLM baselines, our approach outperforms in both performance and robustness, while delivering more reasonable and transparent explanations. These results position AgentSense as a significant advancement towards deploying adaptive and explainable urban sensing systems on the web.