Understanding and extracting spatial information from text is vital for a wide range of applications, including geographic information systems (GIS), smart cities, disaster prevention, and logistics planning. This capability empowers decision-makers to gain crucial insights into geographic distributions and trends.However, the inherent complexity of geographic expressions in natural language presents significant hurdles for traditional extraction methods. These challenges stem from variations in place names, vague directional cues, and implicit spatial relationships.To address these challenges, we introduce SpatialWebAgent, an automated agent system that leverages large language models (LLMs). SpatialWebAgent is designed to extract, standardize, and ground spatial information from natural language text directly onto maps. Our system excels at handling the diverse and often ambiguous nature of geographic expressions—from varying place names and vague directions to implicit spatial relationships that demand flexible combinations of localization functions—by tapping into the powerful geospatial reasoning capabilities of LLMs. SpatialWebAgent employs a series of specialized tools to convert this extracted information into precise coordinates, which are then visualized on interactive maps.A demonstration of SpatialWebAgent is available at https://sites.google.com/view/SpatialWebAgent.

Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning—such as solving Olympiad-level physics problems—remains largely unexplored. Inspired by the way students prepare for competitions by reviewing past problems, we investigate the potential of RAG to enhance physics reasoning in foundation models. We introduce PhoPile, a high-quality multimodal dataset specifically designed for Olympiad-level physics, enabling systematic study of retrieval-based reasoning. PhoPile includes diagrams, graphs, and equations, capturing the inherently multimodal nature of physics problem solving. Using PhoPile, we benchmark RAG-augmented foundation models, covering both large language models (LLMs) and large multimodal models (LMMs) with multiple retrievers. Our results demonstrate that integrating retrieval with physics corpora can improve model performance, while also highlighting challenges that motivate further research in retrieval-augmented physics reasoning.

The Spiral of Silence (SoS) theory holds that individuals with minority views often refrain from speaking out for fear of social isolation, enabling majority positions to dominate public discourse. When the “agents” are large language models (LLMs), however, the classical psychological explanation is not directly applicable, since SoS was developed for human societies. This raises a central question: can SoS-like dynamics nevertheless emerge from purely statistical language generation in LLM collectives? We propose an evaluation framework for examining SoS in LLM agents. Specifically, we consider four controlled conditions that systematically vary the availability of “History” and “Persona” signals. Opinion dynamics are assessed using trend tests such as Mann–Kendall and Spearman’s rank, along with concentration measures including kurtosis and interquartile range. Experiments across open-source and closed-source models show that history and persona together produce strong majority dominance and replicate SoS patterns; history signals alone induce strong anchoring; and persona signals alone foster diverse but uncorrelated opinions, indicating that without historical anchoring, SoS dynamics cannot emerge. The work bridges computational sociology and responsible AI design, highlighting the need to monitor and mitigate emergent conformity in LLM-agent systems.