DHGRPO: Domain-Induced, Hierarchical Group Relative Policy Optimization Article Swipe

PDF

DeepSeek-AI , Daya Guo , Dejian Yang , Haowei Zhang , Junxiao Song , Ruoyu Zhang , Runxin Xu , Qihao Zhu , Shirong Ma , Peiyi Wang , Xiao Bi , Xiaokang Zhang , Xingkai Yu , Yu Wu , Zhenhua Wu , Zhibin Gou , Zhihong Shao , Zhuoshu Li , Ziyi Gao , Aixin Liu , Bing Xue , Bingxuan Wang , Bowen Wu , Bei Feng , Chengda Lu , Chenggang Zhao , Chengqi Deng , Chenyu Zhang , Chong Ruan , Damai Dai , Deli Chen , Dongjie Ji , Erhang Li , Fangyun Lin , Fengze Dai , Fuli Luo , Guangbo Hao , Guan-Ting Chen , Guowei Li , Hongjun Zhang , Han Bao , Hanwei Xu , Haocheng Wang , Honghui Ding , Huajian Xin , Huazuo Gao , Hui Qu , Hui Li , Jianzhong Guo , Jiashi Li , Jiawei Wang , Jingchang Chen , Jingyang Yuan , Junjie Qiu , Junlong Li , Jiali Cai , Jiaqi Ni , Jian Liang , Jing Chen , Kai Dong , Kai Hu , Kaige Gao , Kang Guan , Kexin Huang , Kuai Yu , Lean Wang , Lecong Zhang , Liang Zhao , Litong Wang , Liyue Zhang , Lei Xu , L. Xia , Mingchuan Zhang , Minghua Zhang , Minghui Tang , Meng Li , Miaojun Wang , Mingming Li , Ning Tian , Panpan Huang , Peng Zhang , Qiancheng Wang , Qinyu Chen , Qiushi Du , Ruiqi Ge , Ruisong Zhang , Rui‐Le Pan , Runji Wang , R. J. Chen , Rong Jin , Ruyi Chen , Shanghao Lu , Shangyan Zhou , Shanhuang Chen , Shengfeng Ye , Shiyu Wang , Shuiping Yu , Shunfeng Zhou , Shuting Pan , Sansan Li ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.5281/zenodo.16786367

DHGRPO (Domain-Induced Hierarchical Group Relative Policy Optimization) is a mathematically grounded extension of Group Relative Policy Optimization (GRPO) that mitigates group-level failure modes in preference-based fine-tuning of large language models. The method integrates: (i) robust per-prompt normalization via median and median absolute deviation (MAD) to suppress outlier influence, (ii) a Domain-Induced Factor (DIF) for trust gating based on long-term reward stability, (iii) a Domain-Optimism Parameter (DOP) for recency-weighted learning emphasis, and (iv) a bounded reward amplifier with optional magnitude matching to preserve update scale. We present a stepwise derivation from the exact policy gradient to the GRPO surrogate and its DHGRPO refinement, a controlled simulation framework with hyperparameter sweeps demonstrating consistent proxy improvements, and actionable implementation recommendations for real-world deployment in large-scale preference optimization.

Related Topics

Reinforcement Learning

Computer Science

Artificial Intelligence

Social Psychology

Concepts

Reinforcement learning Reinforcement Computer science Cognitive science Artificial intelligence Psychology Social psychology

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2501.12948
PDF: https://arxiv.org/pdf/2501.12948
OA Status: green
Cited By: 411
Related Works: 10
OpenAlex ID: https://openalex.org/W4406779522

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4406779522

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.5281/zenodo.16786367

Digital Object Identifier
Title: DHGRPO: Domain-Induced, Hierarchical Group Relative Policy Optimization

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-08-09

Full publication date if available
Authors: DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Zhenhua Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bowen Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fengze Dai, Fuli Luo, Guangbo Hao, Guan-Ting Chen, Guowei Li, Hongjun Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Qu, Hui Li, Jianzhong Guo, Jiashi Li, Jiawei Wang, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, Jiali Cai, Jiaqi Ni, Jian Liang, Jing Chen, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Liang Zhao, Litong Wang, Liyue Zhang, Lei Xu, L. Xia, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Meng Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Rui‐Le Pan, Runji Wang, R. J. Chen, Rong Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shengfeng Ye, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, Sansan Li

List of authors in order
Landing page: https://arxiv.org/abs/2501.12948

Publisher landing page
PDF URL: https://arxiv.org/pdf/2501.12948

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2501.12948

Direct OA link when available
Concepts: Reinforcement learning, Reinforcement, Computer science, Cognitive science, Artificial intelligence, Psychology, Social psychology

Top concepts (fields/topics) attached by OpenAlex
Cited by: 411

Total citation count in OpenAlex
Citations by year (recent): 2025: 408, 2024: 3

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4406779522
doi	https://doi.org/10.5281/zenodo.16786367
ids.doi	https://doi.org/10.5281/zenodo.16786367
ids.openalex	https://openalex.org/W4406779522
fwci
type	preprint
title	DHGRPO: Domain-Induced, Hierarchical Group Relative Policy Optimization
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10260
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.8632000088691711
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1710
topics[0].subfield.display_name	Information Systems
topics[0].display_name	Software Engineering Research
topics[1].id	https://openalex.org/T11652
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.8411999940872192
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Imbalanced Data Classification Techniques
topics[2].id	https://openalex.org/T14351
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.8392999768257141
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1702
topics[2].subfield.display_name	Artificial Intelligence
topics[2].display_name	Statistical and Computational Modeling
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C97541855
concepts[0].level	2
concepts[0].score	0.6568659543991089
concepts[0].wikidata	https://www.wikidata.org/wiki/Q830687
concepts[0].display_name	Reinforcement learning
concepts[1].id	https://openalex.org/C67203356
concepts[1].level	2
concepts[1].score	0.5590121746063232
concepts[1].wikidata	https://www.wikidata.org/wiki/Q1321905
concepts[1].display_name	Reinforcement
concepts[2].id	https://openalex.org/C41008148
concepts[2].level	0
concepts[2].score	0.37950843572616577
concepts[2].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[2].display_name	Computer science
concepts[3].id	https://openalex.org/C188147891
concepts[3].level	1
concepts[3].score	0.3306683301925659
concepts[3].wikidata	https://www.wikidata.org/wiki/Q147638
concepts[3].display_name	Cognitive science
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.3106316924095154
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C15744967
concepts[5].level	0
concepts[5].score	0.2911536693572998
concepts[5].wikidata	https://www.wikidata.org/wiki/Q9418
concepts[5].display_name	Psychology
concepts[6].id	https://openalex.org/C77805123
concepts[6].level	1
concepts[6].score	0.199873685836792
concepts[6].wikidata	https://www.wikidata.org/wiki/Q161272
concepts[6].display_name	Social psychology
keywords[0].id	https://openalex.org/keywords/reinforcement-learning
keywords[0].score	0.6568659543991089
keywords[0].display_name	Reinforcement learning
keywords[1].id	https://openalex.org/keywords/reinforcement
keywords[1].score	0.5590121746063232
keywords[1].display_name	Reinforcement
keywords[2].id	https://openalex.org/keywords/computer-science
keywords[2].score	0.37950843572616577
keywords[2].display_name	Computer science
keywords[3].id	https://openalex.org/keywords/cognitive-science
keywords[3].score	0.3306683301925659
keywords[3].display_name	Cognitive science
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.3106316924095154
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/psychology
keywords[5].score	0.2911536693572998
keywords[5].display_name	Psychology
keywords[6].id	https://openalex.org/keywords/social-psychology
keywords[6].score	0.199873685836792
keywords[6].display_name	Social psychology
language	en
locations[0].id	pmh:oai:arXiv.org:2501.12948
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2501.12948
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2501.12948
locations[1].id	doi:10.48550/arxiv.2501.12948
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2501.12948
locations[2].id	doi:10.4230/oasics.icpec.2025.4
locations[2].is_oa	True
locations[2].source.id	https://openalex.org/S7407052059
locations[2].source.type	repository
locations[2].source.is_oa	False
locations[2].source.issn_l
locations[2].source.is_core	False
locations[2].source.is_in_doaj	False
locations[2].source.display_name	Dagstuhl Research Online Publication Server
locations[2].source.host_organization
locations[2].source.host_organization_name
locations[2].license	cc-by
locations[2].pdf_url
locations[2].version
locations[2].raw_type
locations[2].license_id	https://openalex.org/licenses/cc-by
locations[2].is_accepted	False
locations[2].is_published
locations[2].raw_source_name
locations[2].landing_page_url	https://doi.org/10.4230/oasics.icpec.2025.4
locations[3].id	doi:10.5281/zenodo.16786367
locations[3].is_oa	True
locations[3].source.id	https://openalex.org/S4306400562
locations[3].source.issn
locations[3].source.type	repository
locations[3].source.is_oa	True
locations[3].source.issn_l
locations[3].source.is_core	False
locations[3].source.is_in_doaj	False
locations[3].source.display_name	Zenodo (CERN European Organization for Nuclear Research)
locations[3].source.host_organization	https://openalex.org/I67311998
locations[3].source.host_organization_name	European Organization for Nuclear Research
locations[3].source.host_organization_lineage	https://openalex.org/I67311998
locations[3].license	cc-by
locations[3].pdf_url
locations[3].version
locations[3].raw_type	article
locations[3].license_id	https://openalex.org/licenses/cc-by
locations[3].is_accepted	False
locations[3].is_published
locations[3].raw_source_name
locations[3].landing_page_url	https://doi.org/10.5281/zenodo.16786367
locations[4].id	doi:10.5281/zenodo.16786368
locations[4].is_oa	True
locations[4].source.id	https://openalex.org/S4306400562
locations[4].source.issn
locations[4].source.type	repository
locations[4].source.is_oa	True
locations[4].source.issn_l
locations[4].source.is_core	False
locations[4].source.is_in_doaj	False
locations[4].source.display_name	Zenodo (CERN European Organization for Nuclear Research)
locations[4].source.host_organization	https://openalex.org/I67311998
locations[4].source.host_organization_name	European Organization for Nuclear Research
locations[4].source.host_organization_lineage	https://openalex.org/I67311998
locations[4].license	cc-by
locations[4].pdf_url
locations[4].version
locations[4].raw_type	article
locations[4].license_id	https://openalex.org/licenses/cc-by
locations[4].is_accepted	False
locations[4].is_published
locations[4].raw_source_name
locations[4].landing_page_url	https://doi.org/10.5281/zenodo.16786368
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5093670579
authorships[0].author.orcid
authorships[0].author.display_name	DeepSeek-AI
authorships[0].author_position	first
authorships[0].raw_author_name	DeepSeek-AI
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5060364305
authorships[1].author.orcid
authorships[1].author.display_name	Daya Guo
authorships[1].author_position	middle
authorships[1].raw_author_name	Guo, Daya
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5110130182
authorships[2].author.orcid
authorships[2].author.display_name	Dejian Yang
authorships[2].author_position	middle
authorships[2].raw_author_name	Yang, Dejian
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100615599
authorships[3].author.orcid	https://orcid.org/0000-0002-1985-1126
authorships[3].author.display_name	Haowei Zhang
authorships[3].author_position	middle
authorships[3].raw_author_name	Zhang, Haowei
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5063711526
authorships[4].author.orcid
authorships[4].author.display_name	Junxiao Song
authorships[4].author_position	middle
authorships[4].raw_author_name	Song, Junxiao
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5115605110
authorships[5].author.orcid	https://orcid.org/0009-0003-0410-2194
authorships[5].author.display_name	Ruoyu Zhang
authorships[5].author_position	middle
authorships[5].raw_author_name	Zhang, Ruoyu
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5023594937
authorships[6].author.orcid	https://orcid.org/0000-0002-3876-2284
authorships[6].author.display_name	Runxin Xu
authorships[6].author_position	middle
authorships[6].raw_author_name	Xu, Runxin
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5018225836
authorships[7].author.orcid	https://orcid.org/0000-0002-5566-4491
authorships[7].author.display_name	Qihao Zhu
authorships[7].author_position	middle
authorships[7].raw_author_name	Zhu, Qihao
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5057030499
authorships[8].author.orcid	https://orcid.org/0000-0002-0035-9078
authorships[8].author.display_name	Shirong Ma
authorships[8].author_position	middle
authorships[8].raw_author_name	Ma, Shirong
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5101800668
authorships[9].author.orcid	https://orcid.org/0000-0001-9121-4327
authorships[9].author.display_name	Peiyi Wang
authorships[9].author_position	middle
authorships[9].raw_author_name	Wang, Peiyi
authorships[9].is_corresponding	False
authorships[10].author.id	https://openalex.org/A5068799172
authorships[10].author.orcid	https://orcid.org/0000-0002-2733-0451
authorships[10].author.display_name	Xiao Bi
authorships[10].author_position	middle
authorships[10].raw_author_name	Bi, Xiao
authorships[10].is_corresponding	False
authorships[11].author.id	https://openalex.org/A5048566877
authorships[11].author.orcid	https://orcid.org/0009-0005-4550-6261
authorships[11].author.display_name	Xiaokang Zhang
authorships[11].author_position	middle
authorships[11].raw_author_name	Zhang, Xiaokang
authorships[11].is_corresponding	False
authorships[12].author.id	https://openalex.org/A5100608388
authorships[12].author.orcid	https://orcid.org/0000-0002-7422-7406
authorships[12].author.display_name	Xingkai Yu
authorships[12].author_position	middle
authorships[12].raw_author_name	Yu, Xingkai
authorships[12].is_corresponding	False
authorships[13].author.id	https://openalex.org/A5100861568
authorships[13].author.orcid	https://orcid.org/0009-0002-4233-6461
authorships[13].author.display_name	Yu Wu
authorships[13].author_position	middle
authorships[13].raw_author_name	Wu, Yu
authorships[13].is_corresponding	False
authorships[14].author.id	https://openalex.org/A5011674202
authorships[14].author.orcid	https://orcid.org/0000-0002-5527-0310
authorships[14].author.display_name	Zhenhua Wu
authorships[14].author_position	middle
authorships[14].raw_author_name	Wu, Z. F.
authorships[14].is_corresponding	False
authorships[15].author.id	https://openalex.org/A5094077400
authorships[15].author.orcid
authorships[15].author.display_name	Zhibin Gou
authorships[15].author_position	middle
authorships[15].raw_author_name	Gou, Zhibin
authorships[15].is_corresponding	False
authorships[16].author.id	https://openalex.org/A5103100933
authorships[16].author.orcid	https://orcid.org/0000-0001-7290-5958
authorships[16].author.display_name	Zhihong Shao
authorships[16].author_position	middle
authorships[16].raw_author_name	Shao, Zhihong
authorships[16].is_corresponding	False
authorships[17].author.id	https://openalex.org/A5082206666
authorships[17].author.orcid	https://orcid.org/0000-0002-2168-7986
authorships[17].author.display_name	Zhuoshu Li
authorships[17].author_position	middle
authorships[17].raw_author_name	Li, Zhuoshu
authorships[17].is_corresponding	False
authorships[18].author.id	https://openalex.org/A5006532556
authorships[18].author.orcid	https://orcid.org/0000-0003-2868-8663
authorships[18].author.display_name	Ziyi Gao
authorships[18].author_position	middle
authorships[18].raw_author_name	Gao, Ziyi
authorships[18].is_corresponding	False
authorships[19].author.id	https://openalex.org/A5015078816
authorships[19].author.orcid	https://orcid.org/0000-0001-7152-511X
authorships[19].author.display_name	Aixin Liu
authorships[19].author_position	middle
authorships[19].raw_author_name	Liu, Aixin
authorships[19].is_corresponding	False
authorships[20].author.id	https://openalex.org/A5077569089
authorships[20].author.orcid	https://orcid.org/0000-0002-4865-8026
authorships[20].author.display_name	Bing Xue
authorships[20].author_position	middle
authorships[20].raw_author_name	Xue, Bing
authorships[20].is_corresponding	False
authorships[21].author.id	https://openalex.org/A5008187090
authorships[21].author.orcid
authorships[21].author.display_name	Bingxuan Wang
authorships[21].author_position	middle
authorships[21].raw_author_name	Wang, Bingxuan
authorships[21].is_corresponding	False
authorships[22].author.id	https://openalex.org/A5103178710
authorships[22].author.orcid	https://orcid.org/0009-0005-8791-9689
authorships[22].author.display_name	Bowen Wu
authorships[22].author_position	middle
authorships[22].raw_author_name	Wu, Bochao
authorships[22].is_corresponding	False
authorships[23].author.id	https://openalex.org/A5016665033
authorships[23].author.orcid
authorships[23].author.display_name	Bei Feng
authorships[23].author_position	middle
authorships[23].raw_author_name	Feng, Bei
authorships[23].is_corresponding	False
authorships[24].author.id	https://openalex.org/A5090328003
authorships[24].author.orcid	https://orcid.org/0000-0002-9452-4053
authorships[24].author.display_name	Chengda Lu
authorships[24].author_position	middle
authorships[24].raw_author_name	Lu, Chengda
authorships[24].is_corresponding	False
authorships[25].author.id	https://openalex.org/A5079470006
authorships[25].author.orcid
authorships[25].author.display_name	Chenggang Zhao
authorships[25].author_position	middle
authorships[25].raw_author_name	Zhao, Chenggang
authorships[25].is_corresponding	False
authorships[26].author.id	https://openalex.org/A5084839131
authorships[26].author.orcid
authorships[26].author.display_name	Chengqi Deng
authorships[26].author_position	middle
authorships[26].raw_author_name	Deng, Chengqi
authorships[26].is_corresponding	False
authorships[27].author.id	https://openalex.org/A5100377485
authorships[27].author.orcid	https://orcid.org/0000-0002-7137-8954
authorships[27].author.display_name	Chenyu Zhang
authorships[27].author_position	middle
authorships[27].raw_author_name	Zhang, Chenyu
authorships[27].is_corresponding	False
authorships[28].author.id	https://openalex.org/A5016017027
authorships[28].author.orcid
authorships[28].author.display_name	Chong Ruan
authorships[28].author_position	middle
authorships[28].raw_author_name	Ruan, Chong
authorships[28].is_corresponding	False
authorships[29].author.id	https://openalex.org/A5020456783
authorships[29].author.orcid
authorships[29].author.display_name	Damai Dai
authorships[29].author_position	middle
authorships[29].raw_author_name	Dai, Damai
authorships[29].is_corresponding	False
authorships[30].author.id	https://openalex.org/A5085346370
authorships[30].author.orcid	https://orcid.org/0000-0003-3631-6253
authorships[30].author.display_name	Deli Chen
authorships[30].author_position	middle
authorships[30].raw_author_name	Chen, Deli
authorships[30].is_corresponding	False
authorships[31].author.id	https://openalex.org/A5043755032
authorships[31].author.orcid
authorships[31].author.display_name	Dongjie Ji
authorships[31].author_position	middle
authorships[31].raw_author_name	Ji, Dongjie
authorships[31].is_corresponding	False
authorships[32].author.id	https://openalex.org/A5113091614
authorships[32].author.orcid
authorships[32].author.display_name	Erhang Li
authorships[32].author_position	middle
authorships[32].raw_author_name	Li, Erhang
authorships[32].is_corresponding	False
authorships[33].author.id	https://openalex.org/A5109672590
authorships[33].author.orcid
authorships[33].author.display_name	Fangyun Lin
authorships[33].author_position	middle
authorships[33].raw_author_name	Lin, Fangyun
authorships[33].is_corresponding	False
authorships[34].author.id	https://openalex.org/A5029983760
authorships[34].author.orcid	https://orcid.org/0000-0002-8539-0356
authorships[34].author.display_name	Fengze Dai
authorships[34].author_position	middle
authorships[34].raw_author_name	Dai, Fucong
authorships[34].is_corresponding	False
authorships[35].author.id	https://openalex.org/A5000793347
authorships[35].author.orcid	https://orcid.org/0000-0001-5372-4772
authorships[35].author.display_name	Fuli Luo
authorships[35].author_position	middle
authorships[35].raw_author_name	Luo, Fuli
authorships[35].is_corresponding	False
authorships[36].author.id	https://openalex.org/A5064813063
authorships[36].author.orcid	https://orcid.org/0000-0002-5930-5453
authorships[36].author.display_name	Guangbo Hao
authorships[36].author_position	middle
authorships[36].raw_author_name	Hao, Guangbo
authorships[36].is_corresponding	False
authorships[37].author.id	https://openalex.org/A5085396184
authorships[37].author.orcid	https://orcid.org/0000-0002-0414-1412
authorships[37].author.display_name	Guan-Ting Chen
authorships[37].author_position	middle
authorships[37].raw_author_name	Chen, Guanting
authorships[37].is_corresponding	False
authorships[38].author.id	https://openalex.org/A5100773163
authorships[38].author.orcid	https://orcid.org/0000-0002-2286-3056
authorships[38].author.display_name	Guowei Li
authorships[38].author_position	middle
authorships[38].raw_author_name	Li, Guowei
authorships[38].is_corresponding	False
authorships[39].author.id	https://openalex.org/A5100330900
authorships[39].author.orcid	https://orcid.org/0000-0002-4714-8809
authorships[39].author.display_name	Hongjun Zhang
authorships[39].author_position	middle
authorships[39].raw_author_name	Zhang, H.
authorships[39].is_corresponding	False
authorships[40].author.id	https://openalex.org/A5113417549
authorships[40].author.orcid
authorships[40].author.display_name	Han Bao
authorships[40].author_position	middle
authorships[40].raw_author_name	Bao, Han
authorships[40].is_corresponding	False
authorships[41].author.id	https://openalex.org/A5016073978
authorships[41].author.orcid	https://orcid.org/0009-0001-6301-6339
authorships[41].author.display_name	Hanwei Xu
authorships[41].author_position	middle
authorships[41].raw_author_name	Xu, Hanwei
authorships[41].is_corresponding	False
authorships[42].author.id	https://openalex.org/A5034335736
authorships[42].author.orcid	https://orcid.org/0000-0002-5033-0230
authorships[42].author.display_name	Haocheng Wang
authorships[42].author_position	middle
authorships[42].raw_author_name	Wang, Haocheng
authorships[42].is_corresponding	False
authorships[43].author.id	https://openalex.org/A5066575939
authorships[43].author.orcid
authorships[43].author.display_name	Honghui Ding
authorships[43].author_position	middle
authorships[43].raw_author_name	Ding, Honghui
authorships[43].is_corresponding	False
authorships[44].author.id	https://openalex.org/A5111038333
authorships[44].author.orcid
authorships[44].author.display_name	Huajian Xin
authorships[44].author_position	middle
authorships[44].raw_author_name	Xin, Huajian
authorships[44].is_corresponding	False
authorships[45].author.id	https://openalex.org/A5102602497
authorships[45].author.orcid
authorships[45].author.display_name	Huazuo Gao
authorships[45].author_position	middle
authorships[45].raw_author_name	Gao, Huazuo
authorships[45].is_corresponding	False
authorships[46].author.id	https://openalex.org/A5075888304
authorships[46].author.orcid	https://orcid.org/0000-0002-7610-6413
authorships[46].author.display_name	Hui Qu
authorships[46].author_position	middle
authorships[46].raw_author_name	Qu, Hui
authorships[46].is_corresponding	False
authorships[47].author.id	https://openalex.org/A5117779795
authorships[47].author.orcid	https://orcid.org/0000-0002-7031-8562
authorships[47].author.display_name	Hui Li
authorships[47].author_position	middle
authorships[47].raw_author_name	Li, Hui
authorships[47].is_corresponding	False
authorships[48].author.id	https://openalex.org/A5082534819
authorships[48].author.orcid	https://orcid.org/0000-0003-2144-1764
authorships[48].author.display_name	Jianzhong Guo
authorships[48].author_position	middle
authorships[48].raw_author_name	Guo, Jianzhong
authorships[48].is_corresponding	False
authorships[49].author.id	https://openalex.org/A5104127081
authorships[49].author.orcid
authorships[49].author.display_name	Jiashi Li
authorships[49].author_position	middle
authorships[49].raw_author_name	Li, Jiashi
authorships[49].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2501.12948
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-01-24T00:00:00
display_name	DHGRPO: Domain-Induced, Hierarchical Group Relative Policy Optimization
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10260
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.8632000088691711
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1710
primary_topic.subfield.display_name	Information Systems
primary_topic.display_name	Software Engineering Research
related_works	https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W4310083477, https://openalex.org/W2328553770, https://openalex.org/W2920061524, https://openalex.org/W1977959518, https://openalex.org/W2038908348, https://openalex.org/W2107890255, https://openalex.org/W2106552856
cited_by_count	411
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	408
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	3
locations_count	5
best_oa_location.id	pmh:oai:arXiv.org:2501.12948
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2501.12948
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2501.12948
primary_location.id	pmh:oai:arXiv.org:2501.12948
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2501.12948
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2501.12948
publication_date	2025-08-09
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	8, 49, 62, 72, 86, 102
abstract_inverted_index.We	84
abstract_inverted_index.in	23, 120
abstract_inverted_index.is	7
abstract_inverted_index.of	12, 26
abstract_inverted_index.on	57
abstract_inverted_index.to	44, 80, 94
abstract_inverted_index.(i)	33
abstract_inverted_index.The	30
abstract_inverted_index.and	39, 70, 98, 113
abstract_inverted_index.for	53, 66, 117
abstract_inverted_index.its	99
abstract_inverted_index.the	90, 95
abstract_inverted_index.via	37
abstract_inverted_index.(ii)	48
abstract_inverted_index.(iv)	71
abstract_inverted_index.GRPO	96
abstract_inverted_index.from	89
abstract_inverted_index.that	18
abstract_inverted_index.with	76, 106
abstract_inverted_index.(DIF)	52
abstract_inverted_index.(DOP)	65
abstract_inverted_index.(MAD)	43
abstract_inverted_index.(iii)	61
abstract_inverted_index.Group	3, 13
abstract_inverted_index.based	56
abstract_inverted_index.exact	91
abstract_inverted_index.large	27
abstract_inverted_index.modes	22
abstract_inverted_index.proxy	111
abstract_inverted_index.trust	54
abstract_inverted_index.(GRPO)	17
abstract_inverted_index.DHGRPO	0, 100
abstract_inverted_index.Factor	51
abstract_inverted_index.Policy	5, 15
abstract_inverted_index.gating	55
abstract_inverted_index.median	38, 40
abstract_inverted_index.method	31
abstract_inverted_index.policy	92
abstract_inverted_index.reward	59, 74
abstract_inverted_index.robust	34
abstract_inverted_index.scale.	83
abstract_inverted_index.sweeps	108
abstract_inverted_index.update	82
abstract_inverted_index.bounded	73
abstract_inverted_index.failure	21
abstract_inverted_index.models.	29
abstract_inverted_index.outlier	46
abstract_inverted_index.present	85
abstract_inverted_index.Relative	4, 14
abstract_inverted_index.absolute	41
abstract_inverted_index.gradient	93
abstract_inverted_index.grounded	10
abstract_inverted_index.language	28
abstract_inverted_index.learning	68
abstract_inverted_index.matching	79
abstract_inverted_index.optional	77
abstract_inverted_index.preserve	81
abstract_inverted_index.stepwise	87
abstract_inverted_index.suppress	45
abstract_inverted_index.Parameter	64
abstract_inverted_index.amplifier	75
abstract_inverted_index.deviation	42
abstract_inverted_index.emphasis,	69
abstract_inverted_index.extension	11
abstract_inverted_index.framework	105
abstract_inverted_index.long-term	58
abstract_inverted_index.magnitude	78
abstract_inverted_index.mitigates	19
abstract_inverted_index.surrogate	97
abstract_inverted_index.actionable	114
abstract_inverted_index.consistent	110
abstract_inverted_index.controlled	103
abstract_inverted_index.deployment	119
abstract_inverted_index.derivation	88
abstract_inverted_index.influence,	47
abstract_inverted_index.per-prompt	35
abstract_inverted_index.preference	122
abstract_inverted_index.real-world	118
abstract_inverted_index.simulation	104
abstract_inverted_index.stability,	60
abstract_inverted_index.fine-tuning	25
abstract_inverted_index.group-level	20
abstract_inverted_index.integrates:	32
abstract_inverted_index.large-scale	121
abstract_inverted_index.refinement,	101
abstract_inverted_index.Hierarchical	2
abstract_inverted_index.Optimization	16
abstract_inverted_index.Optimization)	6
abstract_inverted_index.demonstrating	109
abstract_inverted_index.improvements,	112
abstract_inverted_index.normalization	36
abstract_inverted_index.optimization.	123
abstract_inverted_index.Domain-Induced	50
abstract_inverted_index.hyperparameter	107
abstract_inverted_index.implementation	115
abstract_inverted_index.mathematically	9
abstract_inverted_index.(Domain-Induced	1
abstract_inverted_index.Domain-Optimism	63
abstract_inverted_index.recommendations	116
abstract_inverted_index.preference-based	24
abstract_inverted_index.recency-weighted	67
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	200
citation_normalized_percentile