paper-with-me

홈 › Papers

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction

2026-04-19 · Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang, Sibo wang, Linglin Liao arxiv

This paper investigates the length problem in sequence-level relative reinforcement learning. We observe that, although existing methods partially alleviate length-related phenomena, a more fundamental issue remains insufficiently characterized: the comparison units used during training lack inherent comparability. Building on this observation, we propose a new perspective: the length problem should not be viewed merely as a loss-scaling or normalization bias, but rather as a \emph{comparison unit construction} problem. We further establish a sample-construction-based training framework that, instead of applying post-hoc corrections to unequal-length responses, proactively constructs equal-length, alignable, and comparable training segments during generation. Within this framework, we propose EqLen, a concrete method applicable to group-relative comparison algorithms such as GRPO, GSPO, and RLOO. Through dual-track synchronous generation, prefix inheritance, and segment masking, EqLen efficiently collects effective equal-length training segments and enables stable

📄 PDF Abstract BibTeX arXiv:2604.17328

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

A Compare-Aggregate Model for Matching Text Sequences

2016-11-06 · Shuohang Wang, Jing Jiang

Many NLP tasks including machine comprehension, answer selection and text entailment require the comparison between sequences. Matching the important units between sequences is a key to solve these problems. In this pape…

Answer SelectionmodelReading Comprehension

Rethinking Decision Transformer via Hierarchical Reinforcement Learning

2023-11-01 · Yi Ma, Chenjun Xiao, Hebin Liang, Jianye Hao

Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT is its reliance on recalling trajectorie…

Decision MakingHierarchical Reinforcement LearningOffline RLreinforcement-learning+3

Rethinking Reinforcement Learning based Logic Synthesis

2022-05-16 · Chao Wang, Chen Chen, Dong Li, Bin Wang

Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process. However, through extensive experiments, we find out that t…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Rethinking Transformers in Solving POMDPs

2024-05-27 · Chenhao Lu, Ruizhe Shi, Yuyao Liu, Kaizhe Hu 외

Sequential decision-making algorithms such as reinforcement learning (RL) in real-world scenarios inevitably face environments with partial observability. This paper scrutinizes the effectiveness of a popular architectur…

Decision MakingReinforcement Learning (RL)Sequential Decision Making

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective

2026-05-08 · Yuheng Zhang, Chenlu Ye, Shuowei Jin, Changlong Yu 외 arxiv

Reinforcement learning, including reinforcement learning with verifiable rewards (RLVR), has emerged as a powerful approach for LLM post-training. Central to these approaches is the design of the importance sampling (IS)…

Reinforcement LearningMathematical Reasoning