Bilateral Spatial Reasoning about Street Networks: Graph-based RAG with Qualitative Spatial Representations
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
This paper deals with improving the capabilities of Large Language Models (LLM) to provide route instructions for pedestrian wayfinders by means of qualitative spatial relations.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 1 of its 6 references that are in the map. First posted on arXiv 17 Dec 2025.
Builds on
1 of 6 references.
References · 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026A Qualitative Model for Reasoning about Path and Supportcited by 0
- 2026A Qualitative Model for Reasoning about Path and Support17 Sep 2026
Similar, not cited
Close in wording, no citation either way
- 2026Graph-Enhanced Large Language Models for Spatial Search
- 2026DM-KG: A Novel Method for Boosting Spatial Cognition of Vision-Language Models in Street View Imagery
- 2023An Evaluation of ChatGPT-4's Qualitative Spatial Reasoning Capabilities in RCC-8
- 2025RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
- 2025DistRAG: Towards Distance-Based Spatial Reasoning in LLMs
- 2024Can Large Language Models Reason about the Region Connection Calculus?
- 2025Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses
- 2026Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing