Multiagent Actor-Critic Generative AI for Query Resolution and Analysis
Open accessAbstract
In this article, we introduce multiagent strategic query resolution and diagnostic tool (MASQRAD), a transformative framework for query resolution based on the actor-critic model, which utilizes multiple generative AI agents. MASQRAD is excellent at translating imprecise or ambiguous user inquiries into precise and actionable requests. This framework generates pertinent visualizations and responses to these focused queries, as well as thorough analyses and insightful interpretations for users. MASQRAD addresses the common shortcomings of existing solutions in domains that demand fast and precise data interpretation, such as their incapacity to successfully apply AI for generating actionable insights and their challenges with the inherent ambiguity of user queries. MASQRAD functions as a sophisticated multiagent system but “masquerades” to users as a single AI entity, which lowers errors and enhances data interaction. This approach makes use of three primary AI agents: Actor Generative AI, Critic Generative AI, and Expert Analysis Generative AI. Each is crucial for creating, enhancing, and evaluating data interactions. The Actor AI generates Python scripts to generate data visualizations from large datasets within operational constraints, and the Critic AI rigorously refines these scripts through multiagent debate. Finally, the Expert Analysis AI contextualizes the outcomes to aid in decision-making. With an accuracy rate of 87% when handling tasks related to natural language visualization, MASQRAD establishes new benchmarks for automated data interpretation and showcases a noteworthy advancement that has the potential to revolutionize AI-driven applications.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Tool-augmented LLM-powered AI Agents have demonstrated potentials across a range of applications.
“Toolaugmented LLM-powered AI Agents have demonstrated potentials across a range of applications.”
From AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025) · cites this paper as [141]
The Actor Agent-Driven Python Script Generation section describes LLM-powered agents generating Python scripts for analysis and visualization, and the Implementation in Domain-Agnostic Setting section reports strong results on benchmark subsets. But that section also says the system's dependence on domain-specific models limits generalization to new domains. The paper therefore demonstrates potential in query resolution and visualization, not across a broad range of applications. (LLM, conf=0.86)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983 · see citing works
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · see citing works
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 1× · see citing works
“The pursuit of more resilient and moral AI systems has led to continuous endeavors to enhance the accountability and transparency of data-driven natural language processing models [21], [22].”
ELIZA—a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1966) · Communications of the ACM · doi:10.1145/365153.365168 · Cited by 4,452 · see citing works
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361 · cited 1× · see citing works
“In order to ensure that the responses from generative language models are accurate and specifically tailored to the operational requirements at various stages of query resolution, prompt engineering is a fundamental technique in our system [40], [41], [42].”
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096 · cited 1× · see citing works
“In order to ensure that the responses from generative language models are accurate and specifically tailored to the operational requirements at various stages of query resolution, prompt engineering is a fundamental technique in our system [40], [41], [42].”
Model Cards for Model Reporting
Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287596 · Cited by 2,681 · cited 1× · see citing works
“The pursuit of more resilient and moral AI systems has led to continuous endeavors to enhance the accountability and transparency of data-driven natural language processing models [21], [22].”
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.295 · Cited by 1,380 · see citing works
Review - Mastering the game of Go with deep neural networks and tree search
Babbar, S. (2017) · Unpublished · doi:10.13140/rg.2.2.18893.74727 · Cited by 929 · see citing works
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., & Kaplan, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.08073 · Cited by 326 · see citing works
Maddigan, P., & Susnjak, T. (2023) · IEEE Access · doi:10.1109/access.2023.3274199 · Cited by 242 · see citing works
Flagged first, then by citations
Research works printed but not linked: 31
- T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., "Language models are few-shot learners," arXiv preprint arXiv:2005.14165, 2020. · arXiv
- A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, "Language models are unsupervised multitask learners," OpenAI Blog, vol. 1, no. 8, p. 9, 2019.
- A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, "Attention is all you need," Advances in neural information processing systems, vol. 30, 2017.
- S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
- Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015.
- T. Karras, S. Laine, and T. Aila, "A style-based generator architecture for generative adversarial networks," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4401-4410.
- I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," in Advances in neural information processing systems, 2014, pp. 2672- 2680.
- T. Winograd, Procedures as a representation for data in a computer program for understanding natural language. MIT Press, 1971.
- D. Ferrucci, E. Brown, J. Chu-Carroll, J. Fan, D. Gondek, A. Kalyanpur, A. Lally, J. W. Murdock, E. Nyberg, J. Prager et al., "Building watson: An overview of the deepqa project," AI Magazine, vol. 31, no. 3, pp. 59-79, 2010.
- W. A. Woods, "Progress in natural language understanding: An applica- tion to lunar geology," Proceedings of the National Academy of Sciences, 1973.
- M. W. U. Rahman, S. Shao, P. Satam, S. Hariri, C. Padilla, Z. Taylor, and C. Nevarez, "A bert-based deep learning approach for reputation analysis in social media," in 2022 IEEE/ACS 19th International Conference on Computer Systems and Applications (AICCSA). IEEE, 2022, pp. 1-8.
- C. Qu, L. Yang, M. Qiu, W. B. Croft, Y. Zhang, and M. Iyyer, "Bert with history answer embedding for conversational question answering," in Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval, 2019, pp. 1133-1136.
- I. Tenney, P. Xia, B. Chen, A. Wang, A. Poliak, R. T. McCoy, N. Kim, B. Van Durme, S. R. Bowman, and D. Das, "What do you learn from context? probing for sentence structure in contextualized word repre- sentations," in International Conference on Learning Representations, 2019.
- Y. Yang, M. Richardson, M. Surdeanu, and E. Riloff, "Jointly learning to extract entities and classify semantic roles," in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 6098-6109.
- J. Konečnỳ, H. B. McMahan, F. X. Yu, P. Richtárik, A. T. Suresh, and D. Bacon, "Federated learning: Strategies for improving communication efficiency," in NIPS Workshop on Private Multi-Party Machine Learning, 2016.
- L. Busoniu, R. Babuska, and B. De Schutter, "A comprehensive survey of multiagent reinforcement learning," IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 38, no. 2, pp. 156-172, 2008.
- J. Kennedy and R. Eberhart, "Particle swarm optimization," in Proceed- ings of ICNN'95-International Conference on Neural Networks, vol. 4. IEEE, 1995, pp. 1942-1948.
- M. Dorigo and T. Stützle, Ant colony optimization: Overview and recent advances. Springer, 2019.
- S. Kraus, "Negotiation and cooperation in multi-agent environments," Artificial intelligence, vol. 94, no. 1-2, pp. 79-98, 1997.
- S. S. Fatima, M. Wooldridge, and N. R. Jennings, "An analysis of feasible solutions for multi-agent negotiation with incomplete informa- tion," in Game Theory and Decision Theory in Agent-Based Systems. Springer, 2002, pp. 99-124.
- V. R. Konda and J. N. Tsitsiklis, "Actor-critic algorithms," SIAM Journal on Control and Optimization, vol. 42, no. 4, pp. 1143-1166, 2000.
- Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, "Roberta: A robustly optimized bert pretraining approach," arXiv preprint arXiv:1907.11692, 2019. · arXiv
- W. Xu, S. Agrawal, E. Briakou, M. J. Martindale, and M. Carpuat, "Understanding and detecting hallucinations in neural machine trans- lation via model introspection," Transactions of the Association for Computational Linguistics, vol. 11, pp. 546-564, 2023.
- A. Smit, P. Duckworth, N. Grinsztajn, K.-a. Tessera, T. D. Barrett, and A. Pretorius, "Are we going mad? benchmarking multi-agent debate between language models for medical q&a," arXiv preprint arXiv:2311.17371, 2023. · arXiv
- Y. Luo, J. Tang, and G. Li, "nvbench: A large-scale synthesized dataset for cross-domain natural language to visualization task," arXiv preprint arXiv:2112.12926, 2021. · arXiv
- A. Narechania, A. Srinivasan, and J. Stasko, "Nl4dv: A toolkit for generating analytic specifications for data visualization from natural language queries," IEEE Transactions on Visualization and Computer Graphics, vol. 27, no. 2, pp. 369-379, 2020.
- L. Podo, M. Ishmal, and M. Angelini, "Vi (e) va llm! a conceptual stack for evaluating and interpreting generative ai-based visualizations," arXiv preprint arXiv:2402.02167, 2024. · arXiv
- Y. Luo, N. Tang, G. Li, C. Chai, W. Li, and X. Qin, "Synthesizing natural language to visualization (nl2vis) benchmarks from nl2sql benchmarks," in Proceedings of the 2021 International Conference on Management of Data, 2021, pp. 1235-1247.
- Y. Luo, N. Tang, G. Li, J. Tang, C. Chai, and X. Qin, "Natural language to visualization by neural machine translation," IEEE Transactions on Visualization and Computer Graphics, vol. 28, no. 1, pp. 217-226, 2021.
- Y. Song, X. Zhao, R. C.-W. Wong, and D. Jiang, "Rgvisnet: A hybrid retrieval-generation neural framework towards automatic data visualiza- tion generation," in Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, pp. 1646-1655.
- G. Li, X. Wang, G. Aodeng, S. Zheng, Y. Zhang, C. Ou, S. Wang, and C. H. Liu, "Visualization generation with large language models: An evaluation," arXiv preprint arXiv:2401.11255, 2024. · arXiv
Cited by
Sorted by citations
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 244 · see citing works
“In a coding context, tools like GPT-Engineer combine LLM-driven design with local code execution environments to iteratively develop software artifacts as output produced during the development process, including source code, .exe files, documentation and configurations [138,139].”
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186 · see citing works
- Authors
- Ur Rahman, M. W., Nevarez, R., Mim, L. T., & Hariri, S.
- Affiliations
- Department of Electrical and Computer Engineering, The University of Arizona, Tucson, AZ, USA
- Trustweb, New York, NY, USA
- Avirtek (United States) (US)
- University of Arizona (US)
- Venue
- IEEE Transactions on Artificial Intelligence
- Published
- 2025-08
- Volume
- 6
- Issue
- 8
- Pages
- 2226-2240
- ISSN
- 2691-4581 (ISSN-L)
- OpenAlex
- W4407826123
- Cited by
- 8
- References
- 14
- Citations by year
- 2026: 4 · 2025: 4
- FWCI
- 2.43
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1624668, 1921485, 2335046)
- Department of Energy, National Nuclear Security Administration (DE-NA0003946)
- AGILITY project (4263090)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Data Visualization and Analytics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- multi-agent systems, actor-critic, generative AI agents, query resolution, automated data interpretation, expert analysis, decision support
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
