Deliberation Within AI: A Reproducible Pipeline for Multi-Agent Deliberation Simulation
Open Access
- 13 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in Digital Government: Research and Practice
Abstract
Recent advances in generative AI have renewed interest in whether large language models can simulate aspects of public deliberation. Current deliberation simulations remain methodologically fragile: fluent conversational outputs are often treated as evidence of deliberative quality despite limited reproducibility, weak safeguards for viewpoint diversity, and limited systematic evaluation. This article argues that AI-deliberation simulations can function as credible analytical instruments only if they incorporate infrastructures for reproducibility, plurality preservation, and deliberative quality assessment. The article develops a stage-structured method for deliberative simulation combining persona validation, plurality auditing, and discourse-quality assessment within a reproducible pipeline. The framework is presented as a methodological proof-of-concept and evaluated through a simulation study on the June 2023 Swiss federal referendum on the Climate and Innovation Act together with a batch replication study comparing direct and structured deliberation architectures. The findings show that, as an integrated theory-driven architecture, the structured pipeline generates more stable deliberative dynamics than unconstrained interaction, including clearer plurality preservation and more coherent opinion updating. At the same time, the simulations remain below human minipublics in terms of contextual grounding and justificatory depth. The article positions AI-deliberation simulations as methodological infrastructures for cumulative and empirically testable research on AI-supported deliberation in digital governance.Keywords
This publication has 38 references indexed in Scilit:
- The simulation of judgment in LLMsProceedings of the National Academy of Sciences, 2025
- Deliberative reason and the effect of minipublic configurationsEuropean Political Science Review, 2025
- ChatGPT is bullshitEthics and Information Technology, 2024
- AI deception: A survey of examples, risks, and potential solutionsPatterns, 2024
- Can Generative AI improve social science?Proceedings of the National Academy of Sciences, 2024
- How Deliberation Happens: Enabling Deliberative ReasonAmerican Political Science Review, 2023
- Out of One, Many: Using Language Models to Simulate Human SamplesPolitical Analysis, 2023
- Evaluating Deliberative Public Events and Projects2012
- When the People Speak2011
- Measuring Political Deliberation: A Discourse Quality IndexComparative European Politics, 2003