English
Related papers

Related papers: Matching Accuracy, Different Geometry: Evolution S…

200 papers

Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all tokens within the same…

Computation and Language · Computer Science 2026-02-06 Hongze Tan , Zihan Wang , Jianfei Pan , Jinghao Lin , Hao Wang , Yifan Wu , Tao Chen , Zhihang Zheng , Zhihao Tang , Haihua Yang

Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business…

Computation and Language · Computer Science 2025-05-29 Xiaoqian Liu , Ke Wang , Yongbin Li , Yuchuan Wu , Wentao Ma , Aobo Kong , Fei Huang , Jianbin Jiao , Junge Zhang

Reinforcement learning (RL) plays a central role in large language model (LLM) post-training. Among existing approaches, Group Relative Policy Optimization (GRPO) is widely used, especially for RL with verifiable rewards (RLVR) fine-tuning.…

Group Relative Policy Optimization (GRPO) has shown promise in aligning image and video generative models with human preferences. However, applying it to modern flow matching models is challenging because of its deterministic sampling…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Dailan He , Guanlin Feng , Xingtong Ge , Yazhe Niu , Yi Zhang , Bingqi Ma , Guanglu Song , Yu Liu , Hongsheng Li

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

Computation and Language · Computer Science 2026-05-19 Zhichao Wang , Kiran Ramnath , Bin Bi , Shiva Kumar Pentyala , Sougata Chaudhuri , Shubham Mehrotra , Zixu , Zhu , Xiang-Bo Mao , Sitaram Asur , Na , Cheng

Combinatorial optimization problems are notoriously challenging due to their discrete structure and exponentially large solution space. Recent advances in deep reinforcement learning (DRL) have enabled the learning heuristics directly from…

Machine Learning · Computer Science 2025-06-12 Shengda Gu , Kai Li , Junliang Xing , Yifan Zhang , Jian Cheng

Reinforcement Learning (RL) robot controllers usually aggregate many task objectives into one scalar reward. While large-scale proximal policy optimisation (PPO) has enabled impressive results such as robust robot locomotion in the real…

Robotics · Computer Science 2025-09-19 Humphrey Munn , Brendan Tidd , Peter Böhm , Marcus Gallagher , David Howard

Because stochastic gradient descent (SGD) has shown promise optimizing neural networks with millions of parameters and few if any alternatives are known to exist, it has moved to the heart of leading approaches to reinforcement learning…

Neural and Evolutionary Computing · Computer Science 2017-12-19 Xingwen Zhang , Jeff Clune , Kenneth O. Stanley

Process reward models (PRMs) allow for fine-grained credit assignment in reinforcement learning (RL), and seemingly contrast with outcome reward models (ORMs), which assign a single reward to an entire trajectory. However, we provide…

Machine Learning · Computer Science 2026-05-29 Michael Sullivan , Alexander Koller

Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first demonstrated by Betley et al. (2025). We conduct the most comprehensive EM study to date,…

Machine Learning · Computer Science 2026-05-13 Joel Schreiber , Ariel Goldstein

Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines training stability. Using pathwise policy gradients, i.e.…

Asynchronous reinforcement learning has become increasingly central to scaling LLM post-training, delivering major throughput gains by decoupling rollout generation from policy updates. However, widely used policy-gradient objectives such…

Machine Learning · Computer Science 2026-03-03 Luke J. Huang , Zhuoyang Zhang , Qinghao Hu , Shang Yang , Song Han

We present a simple, sample-efficient algorithm for introducing large but directed learning steps in reinforcement learning (RL), through the use of evolutionary operators. The methodology uses a population of RL agents training with a…

Neural and Evolutionary Computing · Computer Science 2023-05-15 Harshad Khadilkar

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

In user-agent interaction scenarios such as recommendation, brainstorming, and code suggestion, Large Language Models (LLMs) often generate sets of candidate recommendations where the objective is to maximize the collective utility of the…

Artificial Intelligence · Computer Science 2026-04-01 Rui Ai , Yu Pan , David Simchi-Levi , Chonghuan Wang

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

We introduce Entropy-Guided Sequence Weighting (EGSW), a novel approach that enhances the exploration-exploitation tradeoff by dynamically assigning weights to generated outputs based on their advantage and entropy for Reinforcement…

Machine Learning · Computer Science 2025-04-01 Abdullah Vanlioglu

Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse.…

Machine Learning · Computer Science 2026-05-20 Khiem Le , Phuc Nguyen , Youssef Mroueh , Chi-Heng Lin , Shangqian Gao , Ting Hua , Nitesh V. Chawla

Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…

Machine Learning · Computer Science 2025-10-22 Youssef Mroueh

This study presents a systematic comparison of three Reinforcement Learning (RL) algorithms (PPO, GRPO, and DAPO) for improving complex reasoning in large language models (LLMs). Our main contribution is a controlled transfer-learning…

Artificial Intelligence · Computer Science 2025-12-09 Yongsheng Lian