arXiv AI October 19, 2026 By Jihao Huang, Guangjia Chai, Zhirui Chen, Lei Wang, Yao Liu, Liu Qi, Pengjie Ding, Xinyang Liu, Chengxun Jia, Ling Shao, Hongyu Chen, Junchen Wan

MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning

Read the original on arXiv AI →

MGE-PO introduces an entropy-aware credit assignment framework for mathematical reasoning, using a four-quadrant advantage shaping that blends verified correctness with rollout generation entropy. The method assigns larger bonuses to low-entropy successful responses and larger penalties to high-entropy failures, guided by an online entropy-based question curriculum. Experiments on Qwen3-8B-Base and Qwen2.5-7B-Base show significant macro average and pass rate improvements across multiple benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv AI

Oct 1

Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization

The paper introduces Proximal Entropy Policy Optimization (PEPO), a method that assigns token‑level advantages in reinforcement learning for language models based on a local measure of entropy called proximal entropy. Unlike prior approaches that use global token entropy, PEPO evaluates importance relative to neighboring tokens, making it invariant to prompt difficulty and positional effects. Experiments on Qwen3 and Llama‑3.2 models show PEPO outperforms GRPO and other entropy‑based baselines in mathematical reasoning tasks.

By Yun Kim, Nojun Kwak

llms reinforcement-learning

arXiv AI

Jun 4

Rollout-Level Advantage-Prioritized Experience Replay for GRPO

arXiv:2606. 04560v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards with GRPO is a standard approach for post-training reasoning LLMs.

By Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang, Ik-hwan Kim, Sungroh Yoon

llms reinforcement-learning benchmarks

arXiv Machine Learning

Oct 19

Grounded Credit Assignment in Reinforcement Learning for Multi-Turn Search Agents

The paper introduces Grounded Credit Assignment (GCA) for reinforcement learning in multi‑turn search agents. GCA separates credit for evidence retrieval and answer correctness, correcting the bias in GRPO that favors evidence‑retrieving rollouts only proportionally to accuracy gains. Applying GCA to Search‑R1 boosts average EM by 5.7–6.3 points and increases the proportion of evidence‑supported correct answers from 76.9% to 93.4%.

By Qirui Liu, Hao Chen, Yi Wen, Weijie Shi, Yao Zhao, Xianhe Chen, Hao Zhao, Xing Tang, Weihong Luo, Yuyu Luo

agents reinforcement-learning benchmarks

arXiv Machine Learning

Oct 15

Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling

arXiv:2610.20497v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) trains language models from checked task outcomes, but assigning a terminal reward to individual...

By Wei Chen, Yubing Wu, Zhou Xu, Haoyue Zhang, Delu Zeng, Jiahao Wang, Junmei Yang, Pan tiewen, Jingfeng Liu, Zhiheng Zhou, Bo Li, Min Chen

llms reinforcement-learning

arXiv Machine Learning

Sep 10

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

arXiv:2609.06107v1 Announce Type: new Abstract: Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly they are weighted, and which do...

By Hao Liang, Mingrui Chen, Hengyi Feng, Meiyi Qiang, Wentao Zhang

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 16

A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization

arXiv:2606. 16154v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but GRPO-style optimization remains prone to collapse.

By Prasanth YSS, Zhichen Ren, Rasa Hosseinzadeh, Ilan Gofman, Yuqi Chen, Zhaoyan Liu, Guangwei Yu, Jesse C. Cresswell, Satya Krishna Gorti

reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization

Rollout-Level Advantage-Prioritized Experience Replay for GRPO

Grounded Credit Assignment in Reinforcement Learning for Multi-Turn Search Agents

Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization