Assessment and evaluation have long been critical challenges in artificial intelligence (AI)
and natural language processing (NLP). However, traditional methods, whether matching …

Language has long been conceived as an essential tool for human reasoning. The
breakthrough of Large Language Models (LLMs) has sparked significant research interest in …

OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-
level performances on many challanging tasks that require strong reasoning ability. OpenAI …

Dense process rewards have proven a more effective alternative to the sparse outcome-
level rewards in the inference-time scaling of large language models (LLMs), particularly in …

In this paper, we introduce AceMath, a suite of frontier math models that excel in solving
complex math problems, along with highly effective reward models capable of evaluating …

Training large language models (LLMs) to spend more time thinking and reflection before
responding is crucial for effectively solving complex reasoning tasks in fields such as …

We propose a novel framework, Meta Chain-of-Thought (Meta-CoT), which extends
traditional Chain-of-Thought (CoT) by explicitly modeling the underlying reasoning required …

Existing large language models (LLMs) show exceptional problem-solving capabilities but
might struggle with complex reasoning tasks. Despite the successes of chain-of-thought and …

Multi-step multimodal reasoning tasks pose significant challenges for multimodal large
language models (MLLMs), and finding effective ways to enhance their performance in such …

Recent studies have demonstrated the effectiveness of LLM test-time scaling. However,
existing approaches to incentivize LLMs' deep thinking abilities generally require large …