JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

CONSTRAINT-AWARE MULTI-AGENT TASK SCHEDULING FOR AI-ENABLED ONE-PERSON COMPANIES IN DIGITAL CONTENT SERVICES

Shanning Fu1, Ya Han2

1 National Research University “Tashkent Institute of Irrigation and Agricultural Mechanization Engineers”

2 Shandong Hongjitang Pharmaceutical Group Co., Ltd.

Zenodo DOI: 10.5281/zenodo.22039236

Keywords

small-scale experiment AI-enabled one-person company multi-agent system constraint-aware scheduling digital content services human evaluation

Abstract

AI-enabled one-person companies use large language models and software agents to organize content planning, generation, review, and delivery with limited human resources. However, additional roles and model calls may raise cost and propagate errors without producing a stable quality gain. This paper presents a constraint-aware multi-agent task-scheduling prototype for digital content services and compares four execution configurations under controlled conditions. Six frozen tasks were processed by G1 one-shot generation, G2 same-role staged generation, G3 a fixed multi-agent workflow, and G4, which combined constraint-aware role selection, deterministic validator feedback, and bounded final-node revision. Each configuration was repeated three times per task, producing 72 formal runs and 406 API calls at a total cost of USD 0.221318. G4 achieved the highest automatic pass rate (72.22%) and validation score (0.9689), but also the highest mean call volume and cost. After Holm correction, the pass-rate difference remained significant only between G3 and G4; G4 validation scores exceeded G2 and G3 but not G1. Two non-author evaluators independently rated all 72 anonymized outputs. Averaged-score reliability was ICC(2,2)=0.7288, while human mean scores did not differ significantly across groups. Automatic validation was not significantly associated with human ratings. Because G4 changed several mechanisms together, the experiment does not identify their independent effects. The findings support a limited improvement in compliance with encoded rules, not a comprehensive human-perceived quality advantage.

Views: 126 Published: 2026-08-21 Pages: 87-99 Volume: 4 Issue: 4

References

  1. Wan P., Gu X. Human–AI collaborative evaluation supported by generative AI: practice models and explanatory cases // Modern Distance Education. 2024. No. 2. P. 33–41. (In Chinese).
  2. Wang P. Compliance dilemmas and adjustment of knowledge production under AIGC publishing // Editorial Friend. 2024. No. 3. P. 14–22. (In Chinese).
  3. Yao S., Zhao J., Yu D., et al. ReAct: Synergizing Reasoning and Acting in Language Models // International Conference on Learning Representations (ICLR). 2023. [Electronic resource]. URL: https://openreview.net/forum?id=WE_vluYUL-X (accessed: 01.08.2026).
  4. Wu Q., Bansal G., Zhang J., et al. AutoGen: Enabling Next-Generation LLM Applications via Multi-Agent Conversation // Proceedings of the First Conference on Language Modeling (COLM). 2024. [Electronic resource]. URL: https://openreview.net/forum?id=BAakY1hNKS (accessed: 01.08.2026).
  5. Feng S., Fu L., Song L. Growth mechanism of digital content entrepreneurship from the perspective of entrepreneurial capability: a longitudinal case study of FD Reading // China Business and Market. 2022. Vol. 36, No. 10. P. 80–91. (In Chinese).
  6. Chen C. Copyrightability of artificial-intelligence-generated content: taking ChatGPT-generated content as an example // Science-Technology & Publication. 2023. No. 8. P. 95–103. (In Chinese).
  7. Choi H.L., Brunet L., How J.P. Consensus-based decentralized auctions for robust task allocation // IEEE Transactions on Robotics. 2009. Vol. 25, No. 4. P. 912–926.
  8. Shenzhen Municipal Bureau of Industry and Information Technology. Action Plan for Building a Leading AI-OPC Entrepreneurship Ecosystem in Shenzhen, 2026-2027. Shen Gong Xin [2026] No. 2. 14 January 2026. (In Chinese). [Electronic resource]. URL: https://gxj.sz.gov.cn/gkmlpt/content/12/12602/post_12602272.html (accessed: 01.08.2026).
  9. People's Government of Yangpu District, Shanghai. Measures for Supporting the Development of an OPC Super-Individual Community. Yang Fu Fa [2026] No. 4. 13 May 2026. (In Chinese). [Electronic resource]. URL: https://www.shanghai.gov.cn/tszczq-cxcyqj8/20260520/4317e33bbb6c4faaae22b59626a9436c.html (accessed: 01.08.2026).
  10. Wooldridge M., Jennings N.R. Intelligent agents: theory and practice // The Knowledge Engineering Review. 1995. Vol. 10, No. 2. P. 115–152.
  11. Yan C., Liu J. Digital entrepreneurship research: conceptual clarification, integrated framework, and future prospects // Journal of North University of China (Social Science Edition). 2024. Vol. 40, No. 2. P. 19–30. (In Chinese).
  12. Gerkey B.P., Mataric M.J. A formal analysis and taxonomy of task allocation in multi-robot systems // The International Journal of Robotics Research. 2004. Vol. 23, No. 9. P. 939–954.
  13. Zhang K., Jiang M. Current status and research trends of digital entrepreneurship at home and abroad: a bibliometric analysis // Journal of Xi’an University of Technology. 2023. Vol. 39, No. 2. P. 227–240. (In Chinese).
  14. Shinn N., Cassano F., Berman E., et al. Reflexion: Language Agents with Verbal Reinforcement Learning // Advances in Neural Information Processing Systems. 2023. Vol. 36. [Electronic resource]. URL: https://papers.nips.cc/paper_files/paper/2023/hash/1b44b878bb782e6954cd888628510e90-Abstract-Conference.html (accessed: 01.08.2026).
  15. Guo X., Zhang M., Ma J. A review of agent construction based on large language models // Communication Technology. 2024. Vol. 57, No. 9. P. 873–879. (In Chinese).
  16. Suzhou Industrial Park Administrative Committee. Measures for Accelerating the Development of a Globally Leading AI-OPC Entrepreneurship Zone. Su Yuan Guan [2025] No. 40. 28 November 2025. (In Chinese). [Electronic resource]. URL: https://www.sipac.gov.cn/kjhxxhj/kjzc/202511/100fff909fb44586882b0a90d04c5f0b.shtml (accessed: 01.08.2026).
  17. Hangzhou Municipal Administration for Market Regulation. Measures Supporting One-Person Company (OPC) Innovation and Entrepreneurship. Hang Shi Jian [2026] No. 43. 15 April 2026. (In Chinese). [Electronic resource]. URL: https://zfgb.hangzhou.gov.cn/upload/default/bigfile/2026/05/13/20260513_4c5a80bed00443268bcc250c13286413.pdf (accessed: 01.08.2026).
  18. Li Y., Xu F., Xie G., et al. Review of the development and applications of multi-agent technology // Computer Engineering and Applications. 2018. Vol. 54, No. 9. P. 13–21. (In Chinese).
  19. Yan J., Li X., Liu B. Multi-agent cooperative task allocation considering temporal constraints // Control and Decision. 2015. Vol. 30, No. 11. P. 1999–2003. (In Chinese).
  20. He L., Li B. A multi-objective cloud workflow scheduling algorithm satisfying Pareto optimality // Computer Applications and Software. 2019. Vol. 36, No. 5. P. 289–297. (In Chinese).
  21. Liu J., Li N., Liang X., et al. Chinese academic question answering and applications based on multi-agent systems // Journal of Kunming University of Science and Technology (Natural Sciences). 2025. Vol. 50, No. 3. P. 58–69. (In Chinese).
  22. Smith R.G. The contract net protocol: high-level communication and control in a distributed problem solver // IEEE Transactions on Computers. 1980. Vol. C-29, No. 12. P. 1104–1113.
  23. Wang Y., Cao Y. Technical logic and system construction of an intelligent book-topic planning system empowered by AIGC // Publishing Research. 2024. No. 2. P. 31–37. (In Chinese).
  24. Hong S., Zhuge M., Chen J., et al. MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework // International Conference on Learning Representations (ICLR). 2024. [Electronic resource]. URL: https://openreview.net/forum?id=VtmBAGCN7o (accessed: 01.08.2026).
  25. Zhang J., Tu Y., Jin X. Digital business model research: review and prospects // Science & Technology Progress and Policy. 2022. Vol. 39, No. 13. P. 151–160. (In Chinese).