mlsanityData to 14 Oct 2026

Towards Efficient and Evidence-grounded Mobility Prediction with LLM-Driven Agent

arXiv 2606.05130 ↗First posted 3 Jun 2026cs.LG cs.AIcited by 1

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Individual-level mobility prediction is central to urban simulation, transportation planning, and policy analysis. Supervised sequence models achieve strong accuracy but require task-specific training and offer limited decision-level transparency. Recent LLM-based methods improve interpretability, yet mostly rely on static prompts and single-pass inference, limiting their ability to seek additional evidence when mobility signals are weak or conflicting. We propose method, a training-free LLM-driven agent framework that formulates next-location prediction as adaptive evidence-controlled decision making. method resolves routine cases through a fast path based on historical regularity, while ambiguous cases trigger iterative tool use over recent trajectories, historical behavior, stay-move likelihood, and geographical evidence. Across three mobility datasets, AgentMob achieves the strongest overall performance among training-free LLM-based methods, with GPT-5.4 reaching 71.42% Acc@1 on BW, 33.14% on YJMob100K, and 33.50% on Shanghai ISP. On BW non-fast-path cases, the LLM controller improves Acc@1 from 30.65% to 48.62% over a same-tool statistical baseline, showing that its main benefit lies in resolving ambiguous predictions through adaptive evidence gathering. Our code is available at https://github.com/Unknown-zoo/AgentMob.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 50 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

21 of 50 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026ARMove: Learning to Predict Human Mobility through Agentic Reasoning19 Apr
  2. 2025From Narrative to Action: A Hierarchical LLM-Agent Framework for Human Mobility Generation28 Oct
  3. 2025GATSim: Urban Mobility Simulation with Generative Agents29 Jun
  4. 2025CoMaPOI: A Collaborative Multi-Agent Framework for Next POI Prediction Bridging the Gap Between Trajectory and Language28 May
  5. 2025TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation26 Feb
  6. 2024AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction26 Aug
  7. 2024Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation22 Feb

Other references · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  6. 2024TinyLlama: An Open-Source Small Language Modelcited by 618
  7. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 131
  8. 2021STAN: Spatio-Temporal Attention Network for Next Location Recommendationcited by 102
  9. 2023Where Would I Go Next? Large Language Models as Human Mobility Predictorscited by 93
  10. 2020A Survey on Deep Learning for Human Mobilitycited by 88
  11. 2023Exploring Large Language Models for Human Mobility Prediction under Public Eventscited by 34
  12. 2023Spatiotemporal-Augmented Graph Neural Networks for Human Mobility Simulationcited by 15
2 more
  1. 2025ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agentscited by 15
  2. 2024LIMP: Large Language Model Enhanced Intent-aware Mobility Predictioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understandingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems
  2. 2026TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation
  3. 2025SeMob: Semantic Synthesis for Dynamic Urban Mobility Prediction
  4. 2026Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment
  5. 2026When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulation
  6. 2026Mobility Anomaly Generation using LLM-Driven Behavior with Kinematic Constraints
  7. 2026MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
  8. 2026Evaluating Large Language Models for Decision-Making in Agent-Based Urban Mobility Simulations