English
Related papers

Related papers: HiPO: Hybrid Policy Optimization for Dynamic Reaso…

200 papers

Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited. To address this, we propose a novel framework HDFlow…

Computation and Language · Computer Science 2024-09-27 Wenlin Yao , Haitao Mi , Dong Yu

Large Language Models (LLMs) are increasingly embedded in enterprise workflows, yet their performance remains highly sensitive to prompt design. Automatic Prompt Optimization (APO) seeks to mitigate this instability, but existing approaches…

Artificial Intelligence · Computer Science 2026-02-03 Wei Chen , Yanbin Fang , Shuran Fu , Fasheng Xu , Xuan Wei

Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…

Machine Learning · Computer Science 2025-02-20 Wang Yang , Hongye Jin , Jingfeng Yang , Vipin Chaudhary , Xiaotian Han

In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain…

Computation and Language · Computer Science 2025-10-27 Weibin Liao , Xu Chu , Yasha Wang

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

Machine Learning · Computer Science 2025-08-07 Jinghang Han , Jiawei Chen , Hang Shao , Hao Ma , Mingcheng Li , Xintian Shen , Lihao Zheng , Wei Chen , Tao Wei , Lihua Zhang

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches.…

Machine Learning · Computer Science 2026-04-21 Yifeng Ding , Hung Le , Songyang Han , Kangrui Ruan , Zhenghui Jin , Varun Kumar , Zijian Wang , Anoop Deoras

While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential of reasoning rewards based on chain-of-thought quality for…

Computation and Language · Computer Science 2026-01-16 Zihan Lin , Xiaohan Wang , Hexiong Yang , Jiajun Chai , Jie Cao , Guojun Yin , Wei Lin , Ran He

Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccurate reasoning.…

Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…

Machine Learning · Computer Science 2026-04-13 Taojie Zhu , Dongyang Xu , Ding Zou , Sen Zhao , Qiaobo Hao , Zhiguo Yang , Yonghong He

When applying reinforcement learning--typically through GRPO--to large vision-language model reasoning struggles to effectively scale reasoning length or generates verbose outputs across all tasks with only marginal gains in accuracy. To…

Computation and Language · Computer Science 2025-10-24 Wenyi Xiao , Leilei Gan

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…

Computation and Language · Computer Science 2026-01-07 Nathanaël Carraz Rakotonirina , Ren Pang , Neha Anna John , Michael Bohlke-Schneider , Momchil Hardalov

Recent advances in Large Reasoning Models (LRMs) have demonstrated strong performance on complex tasks through long Chain-of-Thought (CoT) reasoning. However, their lengthy outputs increase computational costs and may lead to overthinking,…

Artificial Intelligence · Computer Science 2026-04-16 Bin Hong , Jiayu Liu , Kai Zhang , Jianwen Sun , Mengdi Zhang , Zhenya Huang

Reinforcement learning has become a central paradigm for improving LLM reasoning. However, existing methods use a single policy to produce both inference responses and training optimization trajectories. The objective conflict between…

Machine Learning · Computer Science 2026-01-26 Jingchu Wang , Bingbing Xu , Yige Yuan , Bin Xie , Xiaoqian Sun , Huawei Shen

The VAPO framework has demonstrated significant empirical success in enhancing the efficiency and reliability of reinforcement learning for long chain-of-thought (CoT) reasoning tasks with large language models (LLMs). By systematically…

Machine Learning · Computer Science 2025-05-28 Jintian Shao , Yiming Cheng , Hongyi Huang , Beiwen Zhang , Zhiyu Wu , You Shan , Mingkai Zheng

Recently, latent reasoning has been introduced into large language models (LLMs) to leverage rich information within a continuous space. However, without stochastic sampling, these methods inevitably collapse to deterministic inference,…

Machine Learning · Computer Science 2026-05-12 Yuyan Zhou , Jiarui Yu , Hande Dong , Zhezheng Hao , Hong Wang , Jianqing Zhang , Qiang Lin

Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Yunheng Li , Hangyi Kuang , Hengrui Zhang , Jiangxia Cao , Zhaojie Liu , Qibin Hou , Ming-Ming Cheng

Large Language Models (LLMs) often generate unnecessarily verbose Chain-of-Thought (CoT) reasoning that increases computational costs and latency without proportional performance gains. In this paper, we propose Fine-grained Group policy…

Machine Learning · Computer Science 2026-03-12 Xinchen Han , Hossam Afifi , Michel Marot , Xilu Wang , Lu Yin

Policy optimization (PO) algorithms are used to refine Large Language Models for complex, multi-step reasoning. Current state-of-the-art pipelines enforce a strict think-then-answer format to elicit chain-of-thought (CoT); however, the…

Computation and Language · Computer Science 2025-10-28 Debdeep Sanyal , Aakash Sen Sharma , Dhruv Kumar , Saurabh Deshpande , Murari Mandal

Recent work on enhancing the reasoning abilities of large language models (LLMs) has introduced explicit length control as a means of constraining computational cost while preserving accuracy. However, existing approaches rely on…

Computation and Language · Computer Science 2025-08-13 Hasan Abed Al Kader Hammoud , Kumail Alhamoud , Abed Hammoud , Elie Bou-Zeid , Marzyeh Ghassemi , Bernard Ghanem

Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model…

Sound · Computer Science 2026-02-17 Cong Wang , Changfeng Gao , Yang Xiang , Zhihao Du , Keyu An , Han Zhao , Qian Chen , Xiangang Li , Yingming Gao , Ya Li