English
Related papers

Related papers: A Practical Two-Stage Recipe for Mathematical LLMs…

200 papers

Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away from the supervised fine-tuning (SFT) paradigm. Many studies…

Large Language Models (LLMs) have achieved remarkable success in natural language processing tasks, with Reinforcement Learning (RL) playing a key role in adapting them to specific applications. In mathematical problem solving, however, the…

Computation and Language · Computer Science 2026-02-02 Rihui Xin , Han Liu , Zecheng Wang , Yupeng Zhang , Dianbo Sui , Xiaolin Hu , Bingning Wang

The effective training of Large Language Models (LLMs) for function calling faces a critical challenge: balancing exploration of complex reasoning paths with stable policy optimization. Standard methods like Supervised Fine-Tuning (SFT)…

Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains…

Computation and Language · Computer Science 2025-09-15 Tong Zheng , Hongming Zhang , Wenhao Yu , Xiaoyang Wang , Runpeng Dai , Rui Liu , Huiwen Bao , Chengsong Huang , Heng Huang , Dong Yu

Generating grounded and trustworthy responses remains a key challenge for large language models (LLMs). While retrieval-augmented generation (RAG) with citation-based grounding holds promise, instruction-tuned models frequently fail even in…

Computation and Language · Computer Science 2025-06-19 Shang Hong Sim , Tej Deep Pala , Vernon Toh , Hai Leong Chieu , Amir Zadeh , Chuan Li , Navonil Majumder , Soujanya Poria

Extending large language models (LLMs) to low-resource languages often incurs an "alignment tax": improvements in the target language come at the cost of catastrophic forgetting in general capabilities. We argue that this trade-off arises…

Computation and Language · Computer Science 2026-05-15 Zeli Su , Ziyin Zhang , Zhou Liu , Xuexian Song , Zhankai Xu , Longfei Zheng , Xiaolu Zhang , Rong Fu , Guixian Xu , Wentao Zhang

Reinforcement learning (RL) has emerged as a promising strategy for improving the reasoning capabilities of language models (LMs) in domains such as mathematics and coding. However, most modern RL algorithms were designed to target robotics…

Artificial Intelligence · Computer Science 2025-05-26 Lianghuan Huang , Shuo Li , Sagnik Anupam , Insup Lee , Osbert Bastani

Recent breakthroughs in large language models (LLMs) have effectively improved their reasoning abilities, particularly on mathematical and logical problems that have verifiable answers, through techniques such as supervised finetuning (SFT)…

Artificial Intelligence · Computer Science 2025-06-02 Hongyi James Cai , Junlin Wang , Xiaoyin Chen , Bhuwan Dhingra

Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and tool utilization. However, the generalization of tool-augmented reinforcement learning (RL) across diverse domains remains a…

Machine Learning · Computer Science 2026-01-08 Zhengyu Chen , Jinluan Yang , Teng Xiao , Ruochen Zhou , Luan Zhang , Xiangyu Xi , Xiaowei Shi , Wei Wang , Jinggang Wang

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Computation and Language · Computer Science 2025-10-22 Rohit Patel

Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio…

Sound · Computer Science 2025-05-15 Gang Li , Jizhong Liu , Heinrich Dinkel , Yadong Niu , Junbo Zhang , Jian Luan

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

Although LLMs have demonstrated improved performance by scaling parallel test-time compute, doing so relies on generating reasoning paths that are both diverse and accurate. For challenging problems, the forking tokens that trigger diverse…

Computation and Language · Computer Science 2026-03-03 Sheng Jia , Xiao Wang , Shiva Prasad Kasiviswanathan

Reinforcement learning is now widely adopted as the final stage of large language model training, especially for reasoning-style tasks such as maths problems. Typically, models attempt each question many times during a single training step…

Machine Learning · Computer Science 2026-05-01 Thomas Foster , Anya Sims , Johannes Forkel , Mattie Fellows , Jakob Foerster

Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). Despite their prevalence, both approaches suffer from…

Machine Learning · Computer Science 2026-04-21 Yuming Yan , Kai Tang , Sihong Chen , Ke Xu , Dan Hu , Qun Yu , Pengfei Hu

We propose reinforcement learning (RL) strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits, with a particular focus on compatibility with LoRA fine-tuning. Building on early policy…

Machine Learning · Computer Science 2025-06-13 Alan Lee , Harry Tong

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Machine Learning · Computer Science 2025-10-21 Mengqi Liao , Xiangyu Xi , Ruinian Chen , Jia Leng , Yangen Hu , Ke Zeng , Shuai Liu , Huaiyu Wan

Mathematical reasoning continues to be a critical challenge in large language model (LLM) development with significant interest. However, most of the cutting-edge progress in mathematical reasoning with LLMs has become \emph{closed-source}…

Computation and Language · Computer Science 2024-10-08 Shubham Toshniwal , Wei Du , Ivan Moshkov , Branislav Kisacanin , Alexan Ayrapetyan , Igor Gitman

Large language models (LLMs) acquire extensive prior knowledge through large-scale pretraining and can be further enhanced via supervised fine-tuning (SFT) or reinforcement learning (RL)-based post-training. A growing body of evidence has…

Machine Learning · Computer Science 2026-01-28 Honglin Zhang , Qianyue Hao , Fengli Xu , Yong Li

This study investigates the effectiveness of reinforcement learning (RL) fine-tuning techniques on a compact language model (Qwen2.5-0.5B Base) for two challenging tasks: instruction following and mathematical reasoning. We compare…

Computation and Language · Computer Science 2025-07-29 Yifu Han , Geo Zhang