{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:14:26Z","timestamp":1783703666901,"version":"3.55.0"},"reference-count":48,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>This paper investigates whether structured collaboration between multiple large language models (LLMs), each assigned a distinct cognitive role grounded in psychological theory, produces benefits beyond simple answer aggregation. We propose the Parallel Synthesis architecture, in which three cognitively specialized roles Analyzer (hierarchical decomposition), Creative (divergent thinking), and Critic (critical evaluation) process each task independently and in parallel, and a Synthesizer integrates their outputs into a final response. To evaluate collaborative reasoning, we introduce the Emergent Reasoning Score (ERS), a composite metric that separates perspective integration (Synthesis Effectiveness) from novel concept generation (Emergent Value). Experiments on the AI2 Reasoning Challenge (ARC-Challenge) (1172 questions) and and the Massive Multitask Language Understanding benchmark (MMLU) (1531 questions) show two consistent findings. First, the architecture achieves high Synthesis Effectiveness (SE=0.711\u20130.744), indicating reliable integration of all three cognitive perspectives. Second, Emergent Value remains low (EV=0.096\u20130.112), indicating that synthesis primarily recombines existing concepts rather than generating substantial novel content. A Majority Voting baseline achieves comparable or slightly higher answer accuracy than the Synthesizer on both benchmarks, showing that the architecture\u2019s main contribution lies not in answer selection but in producing integrated reasoning traces that draw on multiple perspectives. These findings suggest that the practical value of cognitively grounded multi-agent architectures lies in reliable perspective integration, while ERS provides a reusable framework for distinguishing integration from genuinely novel reasoning in multi-agent LLM systems. The empirical results reported here constitute a pilot validation of the proposed framework on closed-form benchmarks, intended to establish a proof of concept and motivate larger-scale evaluation.<\/jats:p>","DOI":"10.3390\/computers15050277","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T08:12:31Z","timestamp":1777363951000},"page":"277","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cognitive Grounding for Perspective Integration in Multi-LLM Systems"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4389-1353","authenticated-orcid":false,"given":"Lev","family":"Sukherman","sequence":"first","affiliation":[{"name":"Computer Science Department, Worcester Polytechnic Institute, Worcester, MA 01609, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3122-0570","authenticated-orcid":false,"given":"Yetunde","family":"Longe-Folajimi","sequence":"additional","affiliation":[{"name":"School of Computing and Data Science, Wentworth Institute of Technology, Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1664-4153","authenticated-orcid":false,"given":"Marina","family":"Konkol","sequence":"additional","affiliation":[{"name":"Department of English Language No. 3, Moscow State Institute of International Relations (MGIMO University), Moscow 119454, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"key":"ref_1","unstructured":"Zhao, W.X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., and Dong, Z. (2023). A Survey of Large Language Models. arXiv."},{"key":"ref_2","unstructured":"Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M.A., Socher, R., Amatriain, X., and Gao, J. (2024). Large Language Models: A Survey. arXiv."},{"key":"ref_3","unstructured":"Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W.T., and Rockt\u00e4schel, T. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Proceedings of the Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Curran Associates."},{"key":"ref_4","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2022, January 25\u201329). LoRA: Low-Rank Adaptation of Large Language Models. Proceedings of the Tenth International Conference on Learning Representations (ICLR 2022), Online."},{"key":"ref_5","unstructured":"Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., and Schulhoff, S. (2024). The Prompt Report: A Systematic Survey of Prompting Techniques. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q.V., and Zhou, D. (2022). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Proceedings of the Advances in Neural Information Processing Systems 35 (NeurIPS 2022), Curran Associates.","DOI":"10.52202\/068431-1800"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/EMR.2010.5559142","article-title":"The Collective Intelligence Genome","volume":"38","author":"Malone","year":"2010","journal-title":"IEEE Eng. Manag. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hutchins, E. (1995). Cognition in the Wild, MIT Press.","DOI":"10.7551\/mitpress\/1881.001.0001"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1126\/science.1193147","article-title":"Evidence for a Collective Intelligence Factor in the Performance of Human Groups","volume":"330","author":"Woolley","year":"2010","journal-title":"Science"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101074","DOI":"10.1016\/j.patter.2024.101074","article-title":"AI-enhanced Collective Intelligence","volume":"5","author":"Cui","year":"2024","journal-title":"Patterns"},{"key":"ref_11","unstructured":"Malone, T.W., and Bernstein, M.S. (2022). Handbook of Collective Intelligence, The MIT Press."},{"key":"ref_12","unstructured":"Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N.V., Wiest, O., and Zhang, X. (2024). Large Language Model based Multi-Agents: A Survey of Progress and Challenges. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI 2024), Jeju Island, Republic of Korea, 3\u20139 August 2024, IJCAI Organization."},{"key":"ref_13","unstructured":"Du, Y., Li, S., Torralba, A., Tenenbaum, J.B., and Mordatch, I. (2024). Improving Factuality and Reasoning in Language Models through Multiagent Debate. Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 21\u201327 July 2024, PMLR."},{"key":"ref_14","unstructured":"Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., and Liu, J. (2024, January 7\u20139). AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. Proceedings of the 1st Conference on Language Modeling (COLM 2024), Philadelphia, PA, USA."},{"key":"ref_15","unstructured":"Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S.K.S., and Lin, Z. (2024, January 7\u201311). MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, G., Hammoud, H.A.A.K., Itani, H., Khizbullin, D., and Ghanem, B. (2023). CAMEL: Communicative Agents for \u201cMind\u201d Exploration of Large Language Model Society. Proceedings of the Advances in Neural Information Processing Systems 36 (NeurIPS 2023), New Orleans, LA, USA, 10\u201316 December 2023, Curran Associates.","DOI":"10.52202\/075280-2264"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Chen, J., Saha, S., and Bansal, M. (2024). ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand, 11\u201316 August 2024, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.acl-long.381"},{"key":"ref_18","unstructured":"Chen, J., Wang, X., Xu, R., Yuan, S., Zhang, Y., Shi, W., Xie, J., Li, S., Yang, R., and Zhu, T. (2024). From Persona to Personalization: A Survey on Role-Playing Language Agents. arXiv."},{"key":"ref_19","unstructured":"Clark, P., Cowhey, I., Etzioni, O., Khot, T., Sabharwal, A., Schoenick, C., and Tafjord, O. (2018). Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge. arXiv."},{"key":"ref_20","unstructured":"Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., and Steinhardt, J. (2021, January 3\u20137). Measuring Massive Multitask Language Understanding. Proceedings of the International Conference on Learning Representations (ICLR 2021), Virtual Event."},{"key":"ref_21","unstructured":"Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences, Lawrence Erlbaum Associates. [2nd ed.]."},{"key":"ref_22","unstructured":"Simon, H.A. (1979). Models of Thought, Yale University Press."},{"key":"ref_23","unstructured":"Torrance, E.P. (1974). The Torrance Tests of Creative Thinking: Norms-Technical Manual, Personnel Press."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1449","DOI":"10.1257\/000282803322655392","article-title":"Maps of Bounded Rationality: Psychology for Behavioral Economics","volume":"93","author":"Kahneman","year":"2003","journal-title":"Am. Econ. Rev."},{"key":"ref_25","unstructured":"Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., and Metzler, D. (2022). Emergent Abilities of Large Language Models. arXiv."},{"key":"ref_26","unstructured":"Kaplan, J., McCandlish, S., Henighan, T., Brown, T.B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. (2020). Scaling Laws for Neural Language Models. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Schaeffer, R., Miranda, B., and Koyejo, S. (2023). Are Emergent Abilities of Large Language Models a Mirage?. Proceedings of the Advances in Neural Information Processing Systems 36 (NeurIPS 2023), New Orleans, LA, USA, 10\u201316 December 2023, Curran Associates.","DOI":"10.52202\/075280-2425"},{"key":"ref_28","unstructured":"Srivastava, A., Rastogi, A., Rao, A., Shoeb, M.A., Abid, A., Fisch, A., Brown, A.R., Santoro, A., Gupta, A., and Garriga-Alonso, A. (2023). Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models. arXiv."},{"key":"ref_29","unstructured":"Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y.T., Li, Y., and Lundberg, S. (2023). Sparks of Artificial General Intelligence: Early experiments with GPT-4. arXiv."},{"key":"ref_30","unstructured":"Tian, L., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., and Tu, Z. (2024). Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, FL, USA, 12\u201316 November 2024, Association for Computational Linguistics."},{"key":"ref_31","unstructured":"Li, J., Zhang, Q., Yu, Y., Fu, Q., and Ye, D. (2024). More Agents Is All You Need. arXiv."},{"key":"ref_32","unstructured":"Wang, J., Wang, J., Athiwaratkun, B., Zhang, C., and Zou, J. (2025, January 24\u201328). Mixture-of-Agents Enhances Large Language Model Capabilities. Proceedings of the The Thirteenth International Conference on Learning Representations (ICLR 2025), Singapore."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tang, X., Zou, A., Zhang, Z., Li, Z., Zhao, Y., Zhang, X., Cohan, A., and Gerstein, M. (2024). MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand, 11\u201316 August 2024, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.findings-acl.33"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Kim, Y.H., Park, C., Jeong, H., Chan, Y.S., Xu, X., McDuff, D., Breazeal, C., and Park, H.W. (2024). MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making. Proceedings of the Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Vancouver, BC, Canada, 10\u201315 December 2024, Curran Associates.","DOI":"10.52202\/079017-2522"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s44336-024-00009-2","article-title":"A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges","volume":"1","author":"Li","year":"2024","journal-title":"Vicinagearth"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1613\/jair.1.18675","article-title":"Agentic Large Language Models, a Survey","volume":"84","author":"Plaat","year":"2025","journal-title":"J. Artif. Intell. Res."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhu, K., Du, H., Hong, Z., Yang, X., Guo, S., Wang, Z., Wang, Z., Qian, C., Tang, X., and Ji, H. (2025). MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents. arXiv.","DOI":"10.18653\/v1\/2025.acl-long.421"},{"key":"ref_38","unstructured":"Riedl, C. (2025). Emergent Coordination in Multi-Agent Language Models. arXiv."},{"key":"ref_39","first-page":"149","article-title":"LLM-Based Multi-agent Systems: Frameworks, Evaluation, Open Challenges, and Research Frontiers","volume":"Volume 2827","author":"Shaikh","year":"2026","journal-title":"Communications in Computer and Information Science, Proceedings of the Computational Intelligence (IJCCI 2025), Marbella, Spain, 22\u201324 October 2025"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., and Bernstein, M.S. (2023). Generative Agents: Interactive Simulacra of Human Behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST 2023), San Francisco, CA, USA, 29 October\u20131 November 2023, ACM.","DOI":"10.1145\/3586183.3606763"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"29","DOI":"10.26599\/CVM.2025.9450460","article-title":"Mindstorms in Natural Language-Based Societies of Mind","volume":"11","author":"Zhuge","year":"2025","journal-title":"Comput. Vis. Media"},{"key":"ref_42","unstructured":"Guilford, J.P. (1967). The Nature of Human Intelligence, McGraw-Hill Book Company."},{"key":"ref_43","first-page":"84","article-title":"Design Thinking","volume":"86","author":"Brown","year":"2008","journal-title":"Harv. Bus. Rev."},{"key":"ref_44","unstructured":"Surowiecki, J. (2005). The Wisdom of Crowds: Why the Many Are Smarter Than the Few and How Collective Wisdom Shapes Business, Economies, Societies, and Nations, Anchor Books."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"9020","DOI":"10.1073\/pnas.1008636108","article-title":"How social influence can undermine the wisdom of crowd effect","volume":"108","author":"Lorenz","year":"2011","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_46","unstructured":"DeepSeek-AI (2024). DeepSeek-V3 Technical Report. arXiv."},{"key":"ref_47","unstructured":"Llama Team (2024). The Llama 3 Herd of Models. arXiv."},{"key":"ref_48","unstructured":"Qwen Team (2024). Qwen2.5 Technical Report. arXiv."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/5\/277\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:31:34Z","timestamp":1783701094000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/5\/277"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["computers15050277"],"URL":"https:\/\/doi.org\/10.3390\/computers15050277","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,27]]}}}