GeoSR: Cognitive-Agentic Framework for Probing Geospatial Knowledge Boundaries via Iterative Self-Refinement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911093824159744 |
|---|---|
| author | Tang, Jinfan Wu, Kunming Gongxie, Ruifeng He, Yuya Wu, Yuankai |
| author_facet | Tang, Jinfan Wu, Kunming Gongxie, Ruifeng He, Yuya Wu, Yuankai |
| contents | Recent studies have extended the application of large language models (LLMs) to geographic problems, revealing surprising geospatial competence even without explicit spatial supervision. However, LLMs still face challenges in spatial consistency, multi-hop reasoning, and geographic bias. To address these issues, we propose GeoSR, a self-refining agentic reasoning framework that embeds core geographic principles -- most notably Tobler's First Law of Geography -- into an iterative prediction loop. In GeoSR, the reasoning process is decomposed into three collaborating agents: (1) a variable-selection agent that selects relevant covariates from the same location; (2) a point-selection agent that chooses reference predictions at nearby locations generated by the LLM in previous rounds; and (3) a refine agent that coordinates the iterative refinement process by evaluating prediction quality and triggering further rounds when necessary. This agentic loop progressively improves prediction quality by leveraging both spatial dependencies and inter-variable relationships. We validate GeoSR on tasks ranging from physical-world property estimation to socioeconomic prediction. Experimental results show consistent improvements over standard prompting strategies, demonstrating that incorporating geostatistical priors and spatially structured reasoning into LLMs leads to more accurate and equitable geospatial predictions. The code of GeoSR is available at https://github.com/JinfanTang/GeoSR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04080 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeoSR: Cognitive-Agentic Framework for Probing Geospatial Knowledge Boundaries via Iterative Self-Refinement Tang, Jinfan Wu, Kunming Gongxie, Ruifeng He, Yuya Wu, Yuankai Artificial Intelligence Other Statistics Recent studies have extended the application of large language models (LLMs) to geographic problems, revealing surprising geospatial competence even without explicit spatial supervision. However, LLMs still face challenges in spatial consistency, multi-hop reasoning, and geographic bias. To address these issues, we propose GeoSR, a self-refining agentic reasoning framework that embeds core geographic principles -- most notably Tobler's First Law of Geography -- into an iterative prediction loop. In GeoSR, the reasoning process is decomposed into three collaborating agents: (1) a variable-selection agent that selects relevant covariates from the same location; (2) a point-selection agent that chooses reference predictions at nearby locations generated by the LLM in previous rounds; and (3) a refine agent that coordinates the iterative refinement process by evaluating prediction quality and triggering further rounds when necessary. This agentic loop progressively improves prediction quality by leveraging both spatial dependencies and inter-variable relationships. We validate GeoSR on tasks ranging from physical-world property estimation to socioeconomic prediction. Experimental results show consistent improvements over standard prompting strategies, demonstrating that incorporating geostatistical priors and spatially structured reasoning into LLMs leads to more accurate and equitable geospatial predictions. The code of GeoSR is available at https://github.com/JinfanTang/GeoSR. |
| title | GeoSR: Cognitive-Agentic Framework for Probing Geospatial Knowledge Boundaries via Iterative Self-Refinement |
| topic | Artificial Intelligence Other Statistics |
| url | https://arxiv.org/abs/2508.04080 |