EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery Paper • 2609.40340 • Published 5 days ago • 104
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts Paper • 2606.02404 • Published Jun 1 • 58
ReviewScore: Misinformed Peer Review Detection with Large Language Models Paper • 2509.21679 • Published Sep 25, 2025 • 64
The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think Paper • 2505.10185 • Published May 15, 2025 • 26