# CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query

arXiv: https://arxiv.org/abs/2510.07516 · HTML: https://mlsanity.com/paper/2510.07516/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 60 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 24 of 24)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024)
- [GraphLLM: Boosting Graph Reasoning Ability of Large Language Model](https://mlsanity.com/paper/2310.05845/) (2023)
- [Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models](https://mlsanity.com/paper/2408.02442/) (2024)
- [A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations](https://mlsanity.com/paper/2407.04069/) (2024)
- [GPT4GEO: How a Language Model Sees the World's Geography](https://mlsanity.com/paper/2306.00020/) (2023)
- [LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning](https://mlsanity.com/paper/2401.00125/) (2023)
- [Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning](https://mlsanity.com/paper/2310.03249/) (2023)
- [LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning](https://mlsanity.com/paper/2407.02511/) (2024)
- [Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning](https://mlsanity.com/paper/2405.20625/) (2024)
- [LAMP: A Language Model on the Map](https://mlsanity.com/paper/2403.09059/) (2024)
- [3P-LLM: Probabilistic Path Planning using Large Language Model for Autonomous Robot Navigation](https://mlsanity.com/paper/2403.18778/) (2024)
- [LLM-Enhanced Path Planning: Safe and Efficient Autonomous Navigation with Instructional Inputs](https://mlsanity.com/paper/2412.02655/) (2024)
- [LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences](https://mlsanity.com/paper/2509.12273/) (2025)
- [MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration](https://mlsanity.com/paper/2509.05933/) (2025)
- [LLM-Advisor: An LLM Advisor for Cost-efficient Path Planning across Multiple Terrains](https://mlsanity.com/paper/2503.01236/) (2025)
- [PathGPT: Reframing Path Recommendation as a Natural Language Generation Task with Retrieval-Augmented Language Models](https://mlsanity.com/paper/2504.05846/) (2025)

## Abstract (arXiv)

The popular path query - identifying the most frequented routes between locations from historical trajectory data - has important applications in urban planning, navigation optimization, and travel recommendations. While traditional algorithms and machine learning approaches have achieved success in this domain, they typically require model training, parameter tuning, and retraining when accommodating data updates. As Large Language Models (LLMs) demonstrate increasing capabilities in spatial and graph-based reasoning, there is growing interest in exploring how these models can be applied to geo-spatial problems. We introduce CompassLLM, a novel multi-agent framework that intelligently leverages the reasoning capabilities of LLMs into the geo-spatial domain to solve the popular path query. CompassLLM employs its agents in a two-stage pipeline: the SEARCH stage that identifies popular paths, and a GENERATE stage that synthesizes novel paths in the absence of an existing one in the historical trajectory data. Experiments on real and synthetic datasets show that CompassLLM demonstrates superior accuracy in SEARCH and competitive performance in GENERATE while being cost-effective.