English
Related papers

Related papers: CoScale-RL: Efficient Post-Training by Co-Scaling …

200 papers

In post-training for reasoning Large Language Models (LLMs), the current state of practice trains LLMs in two independent stages: Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR, shortened as ``RL''…

Machine Learning · Computer Science 2025-10-03 Feiyang Kang , Michael Kuchnik , Karthik Padthe , Marin Vlastelica , Ruoxi Jia , Carole-Jean Wu , Newsha Ardalani

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

Machine Learning · Computer Science 2025-10-06 Aleksei Arzhantsev , Otmane Sakhi , Flavian Vasile

Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with…

Computation and Language · Computer Science 2025-08-28 Ramya Keerthy Thatikonda , Wray Buntine , Ehsan Shareghi

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial…

Machine Learning · Computer Science 2025-10-07 Zhepeng Cen , Yihang Yao , William Han , Zuxin Liu , Ding Zhao

Recent advances in Multimodal Large Language Models (MLLMs) have spurred significant progress in Chain-of-Thought (CoT) reasoning. Building on the success of Deepseek-R1, researchers extended multimodal reasoning to post-training paradigms…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Jianyu Qi , Ding Zou , Wenrui Yan , Rui Ma , Jiaxu Li , Zhijie Zheng , Zhiguo Yang , Rongchang Zhao

Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms requiring significant domain expertise. While large language models…

Artificial Intelligence · Computer Science 2025-09-24 Xia Jiang , Yaoxin Wu , Minshuo Li , Zhiguang Cao , Yingqian Zhang

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Speculative decoding is a powerful technique that accelerates Large Language Model (LLM) inference by leveraging a lightweight speculative draft model. However, existing designs suffers in performance due to misalignment between training…

Computation and Language · Computer Science 2025-05-27 Yepeng Weng , Dianwen Mei , Huishi Qiu , Xujie Chen , Li Liu , Jiang Tian , Zhongchao Shi

Reinforcement learning (RL) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs), as evidenced by recent successes such as OpenAI's o1 and Deepseek-R1. However, applying RL at scale remains…

Machine Learning · Computer Science 2025-06-23 Siru Ouyang , Xinyu Zhu , Zilin Xiao , Minhao Jiang , Yu Meng , Jiawei Han

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ fundamentally in their reliance on expert trajectories. To understand the optimal way to harness these…

Machine Learning · Computer Science 2026-05-12 Bowen Ding , Yuhan Chen , Jiayang Lyv , Jiyao Yuan , Qi Zhu , Shuangshuang Tian , Dantong Zhu , Futing Wang , Heyuan Deng , Fei Mi , Lifeng Shang , Tao Lin

Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate…

Software Engineering · Computer Science 2024-03-21 Zhihong Sun , Chen Lyu , Bolun Li , Yao Wan , Hongyu Zhang , Ge Li , Zhi Jin

Inference-time scaling through multiple sample generation in combination with Process- or Outcome-Reward Model (PRM or ORM) re-ranking has proven effective for text-based reasoning in large language models. This paper investigates whether…

Computation and Language · Computer Science 2025-10-20 Minghan Wang , Thuy-Trang Vu , Ehsan Shareghi , Gholamreza Haffari

Large Language Models (LLMs) are pretrained on massive datasets and later instruction-tuned via supervised fine-tuning (SFT) or reinforcement learning (RL). Best practices emphasize large, diverse pretraining data, whereas post-training…

Machine Learning · Computer Science 2026-03-03 Adel Javanmard , Baharan Mirzasoleiman , Vahab Mirrokni

Large language models (LLMs) face significant challenges in effectively leveraging sequential environmental feedback (EF) signals, such as natural language evaluations, for feedback-independent chain-of-thought (CoT) reasoning. Existing…

Computation and Language · Computer Science 2025-07-29 Kang Yang , Jingxue Chen , Qingkun Tang , Tianxiang Zhang , Qianchun Lu

Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through comprehensive analysis…

Computation and Language · Computer Science 2025-06-25 Yuqian Fu , Tinghong Chen , Jiajun Chai , Xihuai Wang , Songjun Tu , Guojun Yin , Wei Lin , Qichao Zhang , Yuanheng Zhu , Dongbin Zhao

Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the reasoning steps of generated content. However, most PRMs lack long-term reasoning and deep…

Machine Learning · Computer Science 2026-05-22 Xinquan Chen , Chongying Yue , Bangwei Liu , Xuhong Wang , Yingchun Wang , Chaochao Lu

Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growing evidence suggests that its gains arise primarily from distribution sharpening rather than…

Machine Learning · Computer Science 2026-01-30 Xiaotong Ji , Rasul Tutunov , Matthieu Zimmer , Haitham Bou Ammar

Large Language Models (LLMs) have shown strong reasoning capabilities, particularly when enhanced through Reinforcement Learning (RL). While prior work has successfully applied RL to mathematical reasoning -- where rules and correctness are…

While reinforcement learning has achieved impressive progress in language model reasoning, it is constrained by the requirement for verifiable rewards. Recent verifier-free RL methods address this limitation by utilizing the probabilities…

Computation and Language · Computer Science 2026-05-26 Xueru Wen , Jie Lou , Yanjiang Liu , Hongyu Lin , Ben He , Xianpei Han , Le Sun , Yaojie Lu , Debing Zhang

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…

Artificial Intelligence · Computer Science 2025-08-11 Yihao Liu , Shuocheng Li , Lang Cao , Yuhang Xie , Mengyu Zhou , Haoyu Dong , Xiaojun Ma , Shi Han , Dongmei Zhang