English
Related papers

Related papers: Cast a Wider Net: Coordinated Pass@K Policy Optimi…

200 papers

We propose a new perspective on policy optimization: rather than reweighting all samples by their importance ratios, an optimizer should select which samples are trustworthy enough to drive a policy update. Building on this view, we…

Machine Learning · Computer Science 2026-04-17 Ziwu Sun , Zhen Gao , Jiyong Zhang , Jiaheng Li

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)…

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

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Jing Wang , Jiajun Liang , Jie Liu , Henglin Liu , Gongye Liu , Jun Zheng , Wanyuan Pang , Ao Ma , Zhenyu Xie , Xintao Wang , Meng Wang , Pengfei Wan , Xiaodan Liang

Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems. However, this…

Computation and Language · Computer Science 2024-10-18 Zhenyu Wu , Qingkai Zeng , Zhihan Zhang , Zhaoxuan Tan , Chao Shen , Meng Jiang

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

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to…

Machine Learning · Computer Science 2026-02-24 Yuchen Zhu , Wei Guo , Jaemoo Choi , Petr Molodyk , Bo Yuan , Molei Tao , Yongxin Chen

Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent…

Computation and Language · Computer Science 2026-01-27 Wengao Ye , Yan Liang , Lianlei Shan

Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow matching for image generation. To advance this direction, we…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Jie Liu , Zilyu Ye , Linxiao Yuan , Shenhan Zhu , Yu Gao , Jie Wu , Kunchang Li , Xionghui Wang , Xiaonan Nie , Weilin Huang , Wanli Ouyang

Many reinforcement learning algorithms can be seen as versions of approximate policy iteration (API). While standard API often performs poorly, it has been shown that learning can be stabilized by regularizing each policy update by the…

Machine Learning · Computer Science 2021-02-15 Nevena Lazić , Botao Hao , Yasin Abbasi-Yadkori , Dale Schuurmans , Csaba Szepesvári

We propose the Constraint-Generation Policy Optimization (CGPO) framework to optimize policy parameters within compact and interpretable policy classes for mixed discrete-continuous Markov Decision Processes (DC-MDP). CGPO can not only…

Optimization and Control · Mathematics 2025-03-18 Michael Gimelfarb , Ayal Taitler , Scott Sanner

Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands…

Machine Learning · Computer Science 2025-08-08 Ziyin Gu , Jingyao Wang , Ran Zuo , Chuxiong Sun , Zeen Song , Changwen Zheng , Wenwen Qiang

Group Relative Policy Optimization (GRPO) has emerged as an effective method for training reasoning models. While it computes advantages based on group mean, GRPO treats each output as an independent sample during the optimization and…

Artificial Intelligence · Computer Science 2026-03-16 Yu Li , Tian Lan , Zhengling Qi

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated…

Machine Learning · Computer Science 2026-05-21 Shengfan Cao , Francesco Borrelli , Eunhyek Joa

Reinforcement learning (RL) for LLM post-training faces a fundamental design choice: whether to use a learned critic as a baseline for policy optimization. Classical theory favors critic-based methods such as PPO for variance reduction, yet…

The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…

Artificial Intelligence · Computer Science 2024-12-25 Jiacai Liu , Chaojie Wang , Chris Yuhao Liu , Liang Zeng , Rui Yan , Yiwen Sun , Yang Liu , Yahui Zhou

Decentralized multi-agent path finding (MAPF) routes a team of agents on a shared grid, each acting from its own local view. The standard solution trains one shared neural policy with Proximal Policy Optimization (PPO), a popular on-policy…

Machine Learning · Computer Science 2026-05-13 Riad Ahmed

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

Reinforcement Learning (RL) algorithms have shown tremendous success in simulation environments, but their application to real-world problems faces significant challenges, with safety being a major concern. In particular, enforcing…

Machine Learning · Computer Science 2024-06-19 Weiye Zhao , Rui Chen , Yifan Sun , Tianhao Wei , Changliu Liu

Large reasoning models (LRMs) exhibit diverse high-level reasoning patterns (e.g., direct solution, reflection-and-verification, and exploring multiple solutions), yet prevailing training recipes implicitly bias models toward a limited set…

Artificial Intelligence · Computer Science 2026-01-13 Hanbin Wang , Jingwei Song , Jinpeng Li , Fei Mi , Lifeng Shang
‹ Prev 1 8 9 10 Next ›