# Constraint-Aware Route Recommendation from Natural Language via Hierarchical LLM Agents

arXiv: https://arxiv.org/abs/2510.06078 · HTML: https://mlsanity.com/paper/2510.06078/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Reasoning Implicit Sentiment with Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.11255/) (2023)
- [Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case](https://mlsanity.com/paper/1910.07421/) (2019)
- [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)
- [LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?](https://mlsanity.com/paper/2310.17110/) (2023)
- [LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics](https://mlsanity.com/paper/2312.01797/) (2023)
- [Planning with Multi-Constraints via Collaborative Language Agents](https://mlsanity.com/paper/2405.16510/) (2024)
- [Modeling and Analyzing Urban Networks and Amenities with OSMnx](https://mlsanity.com/paper/2505.00736/) (2025)
- [DeepSTCL: A Deep Spatio-temporal ConvLSTM for Travel Demand Prediction](https://mlsanity.com/paper/2009.00096/) (2020)
- [Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streams](https://mlsanity.com/paper/2201.10983/) (2022)
- [Can LLMs plan paths in the real world?](https://mlsanity.com/paper/2411.17912/) (2024)
- [A Training Data Recipe to Accelerate A* Search with Language Models](https://mlsanity.com/paper/2407.09985/) (2024)

## Built on by (most cited first, 3 of 3)

- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem](https://mlsanity.com/paper/2603.08938/) (2026)
- [LifePlanner: Evaluating LLM Agents for Geo-spatial Planning with Social Media Data](https://mlsanity.com/paper/2608.25039/) (2026)

## Abstract (arXiv)

Route recommendation aims to provide users with optimal travel plans that satisfy diverse and complex requirements. Classical routing algorithms (e.g., shortest-path and constraint-aware search) are efficient but assume structured inputs and fixed objectives, limiting adaptability to natural-language queries. Recent LLM-based approaches enhance flexibility but struggle with spatial reasoning and the joint modeling of route-level and POI-level preferences. To address these limitations, we propose RouteLLM, a hierarchical multi-agent framework that grounds natural-language intents into constraint-aware routes. It first parses user queries into structured intents including POIs, paths, and constraints. A manager agent then coordinates specialized sub-agents: a constraint agent that resolves and formally check constraints, a POI agent that retrieves and ranks candidate POIs, and a path refinement agent that refines routes via a routing engine with preference-conditioned costs. A final verifier agent ensures constraint satisfaction and produces the final route with an interpretable rationale. This design bridges linguistic flexibility and spatial structure, enabling reasoning over route feasibility and user preferences. Experiments show that our method reliably grounds textual preferences into constraint-aware routes, improving route quality and preference satisfaction over classical methods.