HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs Paper • 2605.28398 • Published 4 days ago • 12
Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition Paper • 2510.15280 • Published Oct 17, 2025 • 16 • 4
Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition Paper • 2510.15280 • Published Oct 17, 2025 • 16
Language Models Can Learn from Verbal Feedback Without Scalar Rewards Paper • 2509.22638 • Published Sep 26, 2025 • 70
MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem Paper • 2505.14148 • Published May 20, 2025 • 1
Atom of Thoughts for Markov LLM Test-Time Scaling Paper • 2502.12018 • Published Feb 17, 2025 • 17 • 4
Bag of Tricks for Inference-time Computation of LLM Reasoning Paper • 2502.07191 • Published Feb 11, 2025 • 1