App. Res. of Comp. Accepted Paper
Vol. 44, 2027 No. 1

Question generation via multi-agent synergy and automatic reward learning

Li Yana,b
Huang Lana,b
Lyu Yanana,b
Wang Xinyuea,b
a. School of Computer Science, b. Artificial Intelligence Research Platform, Yangtze University, Jingzhou Hubei 434023, China
DOI: 10.19734/j.issn.1001-3695.2026.06.0145

Abstract

This paper proposed AgenticGQG to address limited cognitive logic, frequent factual hallucinations, and poor cross-domain generalization of lightweight large language models under edge computing constraints. The architecture integrated multi-agent synergy, group relative policy optimization (GRPO) , and automatic reward learning (AutoRL) . It designed a four-agent collaborative framework to reduce hallucinations, and embedded a value-network-free GRPO with a four-dimensional orthogonal reward for efficient policy alignment. Furthermore, AutoRL implemented dynamic constraint relaxation to enhance cross-domain adaptability. Experiments evaluated a 0.5B model on multi-domain datasets. AgenticGQG effectively overcomes the traditional supervised fine-tuning (SFT) overfitting in cross-domain texts. In the NewsQA domain, it improves ROUGE-1 and ROUGE-L by 46.7% and 42.6% over the SFT model, respectively. These results confirm the architecture expands cognitive depth, suppresses cross-domain hallucinations, and provides a new paradigm for high-quality alignment under low computing power.

Foundation Support

湖北本科高校省级教学改革研究项目(2024276)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.06.0145
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 1

Publish History

[2026-08-28] Accepted Paper

Cite This Article

李焱, 黄岚, 吕亚男, 等. 基于多智能体协同与自动奖励学习的问题生成方法 [J]. 计算机应用研究, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.06.0145. (Li Yan, Huang Lan, Lyu Yanan, et al. Question generation via multi-agent synergy and automatic reward learning [J]. Application Research of Computers, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.06.0145. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)