6 accepted papers
LLM agents have achieved strong performance in tool-augmented reasoning, but most remain largely stateless: after each episode, the agent discards interaction traces and does not accumulate reusable strategies. Prior work either stores raw trajectories for case-based reuse or relies on external teac…
Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations, including the risk of test data contamination from textbook…
The webpage-to-code task requires models to understand visual representations of webpages and generate corresponding code. However, existing benchmarks primarily focus on static screenshot-to-code tasks, thereby overlooking the dynamic interactions fundamental to real-world web applications. To addr…
This paper introduces DriveArena, the first high-fidelity closed-loop simulation system designed for driving agents navigating real-world scenarios. DriveArena comprises two core components: Traffic Manager, a traffic simulator capable of generating realistic traffic flow on any global street map, a…
Autonomous driving has advanced significantly due to sensors, machine learning, and artificial intelligence improvements. However, prevailing methods struggle with intricate scenarios and causal relationships, hindering adaptability and interpretability in varied environments. To address the above p…
Recent advancements in autonomous driving have relied on data-driven approaches, which are widely adopted but face challenges including dataset bias, overfitting, and uninterpretability. Drawing inspiration from the knowledge-driven nature of human driving, we explore the question of how to instill…