10 papers
Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers
Pengyu Dai, Weihao Xuan, Junjue Wang +4
Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-int…
The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents
Weihao Xuan, Qingcheng Zeng, Heli Qi +3
Autonomous agents based on large language models (LLMs) are rapidly evolving to handle multi-turn tasks, but ensuring their trustworthiness remains a critical challenge. A fundamen…
Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery
Mai Tsujimoto, Junjue Wang, Weihao Xuan +1
Three-dimensional geospatial analysis is critical for applications in urban planning, climate adaptation, and environmental assessment. However, current methodologies depend on cos…
The Invisible Leash: Why RLVR May or May Not Escape Its Origin
Fang Wu, Weihao Xuan, Ximing Lu +4
Recent advances highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising method for enhancing LLMs' capabilities. However, it remains unclear whether the curr…
Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models
Weihao Xuan, Qingcheng Zeng, Heli Qi +2
Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models expr…
DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
Junjue Wang, Weihao Xuan, Heli Qi +8
Large vision-language models (VLMs) have made great achievements in Earth vision. However, complex disaster scenes with diverse disaster types, geographic regions, and satellite se…