English
Related papers

Related papers: When To Solve, When To Verify: Compute-Optimal Pro…

200 papers

With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time scaling methods, we place special emphasis on how…

Computation and Language · Computer Science 2025-11-20 Zhuoyi Yang , Xu Guo , Tong Zhang , Huijuan Xu , Boyang Li

To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods…

Computation and Language · Computer Science 2024-10-29 Yukun Huang , Yixin Liu , Raghuveer Thirukovalluru , Arman Cohan , Bhuwan Dhingra

Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts toward Generative Reward Models (GenRMs) that generate…

Formal verification via interactive theorem proving is increasingly used to ensure the correctness of critical systems, yet constructing large proof scripts remains highly manual and limits scalability. Advances in large language models…

Artificial Intelligence · Computer Science 2026-05-08 Baoding He , Zenan Li , Wei Sun , Yuan Yao , Taolue Chen , Xiaoxing Ma , Zhendong Su

Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term…

Machine Learning · Computer Science 2026-04-28 Kefan Song , Amir Moeini , Peng Wang , Lei Gong , Rohan Chandra , Shangtong Zhang , Yanjun Qi

We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback. This integrated…

Artificial Intelligence · Computer Science 2025-02-28 Wei Xiong , Hanning Zhang , Chenlu Ye , Lichang Chen , Nan Jiang , Tong Zhang

Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard paradigm for reasoning in Large Language Models. However, optimizing solely for final-answer correctness often drives models into aimless, verbose exploration,…

Computation and Language · Computer Science 2026-01-14 Jiangshan Duo , Hanyu Li , Hailin Zhang , Yudong Wang , Sujian Li , Liang Zhao

Generative models typically sample outputs independently, and recent inference-time guidance and scaling algorithms focus on improving the quality of individual samples. However, in real-world applications, users are often presented with a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Gaurav Parmar , Or Patashnik , Daniil Ostashev , Kuan-Chieh Wang , Kfir Aberman , Srinivasa Narasimhan , Jun-Yan Zhu

Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost. We introduce sleep-time compute, which allows models to "think"…

Artificial Intelligence · Computer Science 2025-04-18 Kevin Lin , Charlie Snell , Yu Wang , Charles Packer , Sarah Wooders , Ion Stoica , Joseph E. Gonzalez

Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur…

Computation and Language · Computer Science 2026-03-24 Jiayun Wu , Peixu Hou , Shan Qu , Peng Zhang , Ning Gu , Tun Lu

Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectories may still rely on incomplete derivations, weak evidence, or statements that…

Computation and Language · Computer Science 2026-04-22 Mengzhao Jia , Zhihan Zhang , Meng Jiang

Test-time compute (TTC) has become an increasingly prominent paradigm for enhancing large language models (LLMs). Despite the empirical success of methods such as best-of-$n$ (BoN) sampling and sequential revision, their fundamental limits…

Machine Learning · Computer Science 2025-12-05 Yue Yu , Qiwei Di , Quanquan Gu , Dongruo Zhou

Test-time scaling seeks to improve the reasoning performance of large language models (LLMs) by adding computational resources. A prevalent approach within the field is sampling-based test-time scaling methods, which enhance reasoning by…

Machine Learning · Computer Science 2025-10-20 Zhi Zhou , Yuhao Tan , Zenan Li , Yuan Yao , Lan-Zhe Guo , Yu-Feng Li , Xiaoxing Ma

Recent advances in large language models (LLMs) have enabled near-human performance on software coding benchmarks, but their effectiveness in RTL code generation remains limited due to the scarcity of high-quality training data. While prior…

Hardware Architecture · Computer Science 2025-07-17 Chenhui Deng , Yun-Da Tsai , Guan-Ting Liu , Zhongzhi Yu , Haoxing Ren

Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation,…

Computation and Language · Computer Science 2025-03-20 David Wan , Justin Chih-Yao Chen , Elias Stengel-Eskin , Mohit Bansal

Test-time scaling evaluates reasoning LLMs by sampling multiple outputs per prompt, but ranking models in this regime remains underexplored. We formalize dense benchmark ranking under test-time scaling and introduce Scorio, a library that…

Machine Learning · Computer Science 2026-05-12 Mohsen Hariri , Michael Hinczewski , Jing Ma , Vipin Chaudhary

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward…

State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and…

Computation and Language · Computer Science 2024-10-03 Xingxuan Li , Weiwen Xu , Ruochen Zhao , Fangkai Jiao , Shafiq Joty , Lidong Bing

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. While reinforcement…

Machine Learning · Computer Science 2025-06-16 Zhenyu Hou , Xin Lv , Rui Lu , Jiajie Zhang , Yujiang Li , Zijun Yao , Juanzi Li , Jie Tang , Yuxiao Dong
‹ Prev 1 8 9 10 Next ›