Related papers: GeoSR: Cognitive-Agentic Framework for Probing Geo…

With the widespread adoption of large language models (LLMs) in code generation tasks, geospatial code generation has emerged as a critical frontier in the integration of artificial intelligence and geoscientific analysis. This trend…

Vision-language models (VLMs) have shown a promising ability in image geolocation, but they still lack structured geographic reasoning and the capacity for autonomous self-evolution. Existing methods predominantly rely on implicit…

Although Large Language Models (LLMs) show exceptional fluency, efforts persist to extract stronger reasoning capabilities from them. Drawing on search-based interpretations of LLM computation, this paper advances a systematic framework for…

Spatial reasoning, an important faculty of human cognition with many practical applications, is one of the core commonsense skills that is not purely language-based and, for satisfying (as opposed to optimal) solutions, requires some…

Geospatial reasoning requires solving image-grounded problems over the complex spatial structure of a scene. However, developing this capability is hindered by the cost of annotating a vast and combinatorial question space. We propose GeoX,…

Remote sensing imagery presents vast, inherently unstructured spatial data, necessitating sophisticated reasoning to interpret complex user intents and contextual relationships beyond simple recognition tasks. In this paper, we aim to…

While general-purpose Large Language Models (LLMs) applied to Geology often hallucinate when reasoning about subsurface structures and deep-time evolution, current AI in Earth sciences predominantly targets surface remote sensing and GIS.…

The rise of spatiotemporal data and the need for efficient geospatial modeling have spurred interest in automating these tasks with large language models (LLMs). However, general LLMs often generate errors in geospatial code due to a lack…

Large Vision-Language Models (LVLMs) have demonstrated strong reasoning capabilities in geo-localization, yet they often struggle in real-world scenarios where visual cues are sparse, long-tailed, and highly ambiguous. Previous approaches,…

As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard to disentangle agentic reasoning when evaluated in complex…

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning,…

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

Visual Language Models (VLMs) have increasingly become the main paradigm for understanding indoor scenes, but they still struggle with metric and spatial reasoning. Current approaches rely on end-to-end video understanding or large-scale…

Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting are limited as their performance depends on the quality of candidate responses, making them…

The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static knowledge, factual hallucinations, and the inability to…

The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined…

Recent advances in vision-language models have opened up new possibilities for reasoning-driven image geolocalization. However, existing approaches often rely on synthetic reasoning annotations or external image retrieval, which can limit…

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Despite advancements in Multi-modal Large Language Models (MLLMs) for scene understanding, their performance on complex spatial reasoning tasks requiring mental simulation remains significantly limited. Current methods often rely on passive…

Motivated by the substantial achievements observed in Large Language Models (LLMs) in the field of natural language processing, recent research has commenced investigations into the application of LLMs for complex, long-horizon sequential…