5 papers
Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning
Jiaxuan Lu, Ziyu Kong, Yemin Wang +10
The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on…
Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks
Cheng Yang, Haiyuan Wan, Yiran Peng +8
Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reaso…
Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
Junchi Yu, Yujie Liu, Jindong Gu +2
Retrieval-Augmented Generation (RAG) based on knowledge graphs (KGs) enhances large language models (LLMs) by providing structured and interpretable external knowledge. However, ex…
DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
Haiyuan Wan, Chen Yang, Junchi Yu +10
Deep research agents have attracted growing attention for their potential to orchestrate multi-stage research workflows, spanning literature synthesis, methodological design, and e…
Hypergraph Mamba for Efficient Whole Slide Image Understanding
Jiaxuan Lu, Yuhui Lin, Junyan Shi +4
Whole Slide Images (WSIs) in histopathology pose a significant challenge for extensive medical image analysis due to their ultra-high resolution, massive scale, and intricate spati…