相关论文: Ranking Reasoning LLMs under Test-Time Scaling

We construct evaluation tasks where extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance, exhibiting an inverse scaling relationship between test-time compute and accuracy. Our evaluation tasks span four…

In recent months, substantial progress has been made in complex reasoning of Large Language Models, particularly through the application of test-time scaling. Notable examples include o1/o3/o4 series and DeepSeek-R1. When responding to a…

Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly…

The current focus of AI research is shifting from emphasizing model training towards enhancing evaluation quality, a transition that is crucial for driving further advancements in AI systems. Traditional evaluation methods typically rely on…

Large Language Models (LLMs) are demonstrating rapid improvements on complex reasoning benchmarks, particularly when allowed to utilize intermediate reasoning steps before converging on a final solution. However, current literature often…

Spatiotemporal reasoning plays a key role in Cyber-Physical Systems (CPS). Despite advances in Large Language Models (LLMs) and Large Reasoning Models (LRMs), their capacity to reason about complex spatiotemporal signals remains…

We present AMO-Bench, an Advanced Mathematical reasoning benchmark with Olympiad level or even higher difficulty, comprising 50 human-crafted problems. Existing benchmarks have widely leveraged high school math competitions for evaluating…

We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in parallel, or to run fewer chains that iteratively refine through…

As evaluation designs of large language models may shape our trajectory toward artificial general intelligence, comprehensive and forward-looking assessment is essential. Existing benchmarks primarily assess static knowledge, while…

Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning ability of Large Language Models (LLMs) by allocating additional computation at inference, yet its application to multimodal systems such as…

In this paper, we ask: what truly determines the effectiveness of RL training data for enhancing language models' reasoning capabilities? While recent advances like o1, Deepseek R1, and Kimi1.5 demonstrate RL's potential, the lack of…

The rise of Large Language Models (LLMs) has driven progress in reasoning tasks -- from program synthesis to scientific hypothesis generation -- yet their ability to handle ranked preferences and structured algorithms in combinatorial…

Recent advances in test-time scaling of large language models (LLMs), exemplified by DeepSeek-R1 and OpenAI's o1, show that extending the chain of thought during inference can significantly improve general reasoning performance. However,…

Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvements in CoT capabilities often come with redundant reasoning…

Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource-intensive models introduces significant deployment…

Large language models (LLMs) have showcased remarkable reasoning capabilities, yet they remain susceptible to errors, particularly in temporal reasoning tasks involving complex temporal logic. Existing research has explored LLM performance…

Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…

The rapid proliferation of benchmarks for evaluating large language models (LLMs) has created an urgent need for systematic methods to assess benchmark quality itself. We propose Benchmark^2, a comprehensive framework comprising three…

Large language models (LLMs) have demonstrated remarkable capabilities in problem-solving. However, their proficiency in solving mathematical problems remains inadequate. We propose MathScale, a simple and scalable method to create…

Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: generating multiple candidate responses and selecting the best…