Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice

• URL: http://arxiv.org/abs/2603.07339v2
• Date: Sun, 15 Mar 2026 15:18:56 GMT
• Title: Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice
• Abstract summary: Deliberative democratic theory suggests that civic competence is not innate but developed through practice.<n>We present Agora, an early-stage AI-powered platform that uses LLMs to organize authentic human voices on policy issues.
• Score: 12.169152880991819
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deliberative democratic theory suggests that civic competence: the capacity to navigate disagreement, weigh competing values, and arrive at collective decisions is not innate but developed through practice. Yet opportunities to cultivate these skills remain limited, as traditional deliberative processes like citizens' assemblies reach only a small fraction of the population. We present Agora, an early-stage AI-powered platform that uses LLMs to organize authentic human voices on policy issues, helping users build consensus-finding skills by proposing and revising policy recommendations, hearing supporting and opposing perspectives, and receiving feedback on how policy changes affect predicted support. In a preliminary study with 44 university students, participants using the full interface (with access to voice explanations) reported higher levels of problem-solving skills, internal deliberation, and produced higher quality consensus statements compared to a control condition showing only aggregate support distributions. These initial findings point toward a promising direction for scaling civic education.

Related papers

• Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing [66.03354630509942]
  This paper reports on a study where we compare three designs for user-AI interaction in a learning context.<n>Fifty study participants were tasked with learning about nuclear safety protocols.
  arXiv  Detail & Related papers  (2026-09-01T02:24:35Z)
• AI and Collective Decisions: Strengthening Legitimacy and Losers' Consent [13.048352696221741]
  We ask how can AI help ground collective decisions in participants' different experiences and beliefs.<n>We built a system that uses a semi-structured AI interviewer to elicit personal experiences on policy topics.<n> interacting with the visualization increased perceived legitimacy, trust in outcomes, and understanding of others' perspectives.
  arXiv  Detail & Related papers  (2026-04-07T03:10:40Z)
• Beyond Detection: Governing GenAI in Academic Peer Review as a Sociotechnical Challenge [7.402573615005516]
  Generative AI tools are increasingly entering academic peer review, raising questions about fairness, accountability, and the legitimacy of evaluative judgment.<n>This paper presents discourse analysis of 448 social media posts with interviews with 14 area chairs and program chairs from leading AI and HCI conferences.<n>We find broad agreement that GenAI may be acceptable for limited supportive tasks, but that core evaluative judgments, assessing novelty, contribution, and acceptance, should remain human responsibilities.<n>We argue that AI-assisted peer review is best governed not by blanket bans or detection alone, but by explicitly reserving evaluative judgment for humans while instituting enforceable, role-specific controls
  arXiv  Detail & Related papers  (2026-03-02T19:23:04Z)
• Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation [56.84819098277464]
  CoNL is a framework that unifies generation, evaluation, and meta-evaluation through multi-agent self-play.<n>CoNL achieves consistent improvements over self-rewarding baselines while maintaining stable training.
  arXiv  Detail & Related papers  (2026-01-29T09:41:14Z)
• Can AI mediation improve democratic deliberation? [10.125698716274286]
  We ask whether and how artificial intelligence could help navigate the "trilemma" of broad participation, meaningful deliberation, and political equality.<n>We look at a large language model (LLM)-based system designed to help people with diverse viewpoints find common ground.<n>Ultimately, a range of empirical, technical, and theoretical advancements are needed to fully realize the promise of AI-mediated deliberation.
  arXiv  Detail & Related papers  (2026-01-09T16:22:26Z)
• Of the People, By the Algorithm: How AI Transforms Democratic Representation [0.0]
  AI technologies are transforming democratic representation, focusing on citizen participation and algorithmic decision-making.<n>Social media platforms' AI-driven algorithms currently mediate much political discourse.<n>The emergence of Mass Online Deliberation platforms suggests possibilities for scaling up meaningful citizen participation.<n>Algorithmic Decision-Making systems promise more efficient policy implementation but face limitations in handling complex political trade-offs.
  arXiv  Detail & Related papers  (2025-08-26T13:54:17Z)
• The AI Imperative: Scaling High-Quality Peer Review in Machine Learning [49.87236114682497]
  We argue that AI-assisted peer review must become an urgent research and infrastructure priority.<n>We propose specific roles for AI in enhancing factual verification, guiding reviewer performance, assisting authors in quality improvement, and supporting ACs in decision-making.
  arXiv  Detail & Related papers  (2025-06-09T18:37:14Z)
• The Empty Chair: Using LLMs to Raise Missing Perspectives in Policy Deliberations [12.862709275890563]
  We develop and evaluate a tool that transcribes conversations in real-time and simulates input from relevant but absent stakeholders.<n>We deploy this tool in a 19-person student citizens' assembly on campus sustainability.<n>Participants and facilitators found that the tool sparked new discussions and surfaced valuable perspectives they had not previously considered.
  arXiv  Detail & Related papers  (2025-03-18T01:45:08Z)
• Aligning AI with Public Values: Deliberation and Decision-Making for Governing Multimodal LLMs in Political Video Analysis [48.14390493099495]
  How AI models should deal with political topics has been discussed, but it remains challenging and requires better governance.<n>This paper examines the governance of large language models through individual and collective deliberation, focusing on politically sensitive videos.
  arXiv  Detail & Related papers  (2024-09-15T03:17:38Z)
• Consensus-based Participatory Budgeting for Legitimacy: Decision Support via Multi-agent Reinforcement Learning [3.3504365823045044]
  Participatory budgeting is a process where voting outcomes may not always be fair or inclusive. This paper introduces a novel and legitimate consensus-based participatory budgeting process. Voters are assisted to interact with each other to make viable compromises.
  arXiv  Detail & Related papers  (2023-07-24T16:16:23Z)
• Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework [41.04606578479283]
  We introduce a novel initiative advisor-in-the-loop actor-critic framework, termed as Ask-AC. At the heart of Ask-AC are two complementary components, namely action requester and adaptive state selector. Experimental results on both stationary and non-stationary environments demonstrate that the proposed framework significantly improves the learning efficiency of the agent.
  arXiv  Detail & Related papers  (2022-07-05T10:58:11Z)
• PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings [69.87899694963251]
  We propose a novel Peer-Contrastive Learning (PCL) with diverse augmentations. PCL constructs diverse contrastive positives and negatives at the group level for unsupervised sentence embeddings. PCL can perform peer-positive contrast as well as peer-network cooperation, which offers an inherent anti-bias ability.
  arXiv  Detail & Related papers  (2022-01-28T13:02:41Z)
• Characterizing the adversarial vulnerability of speech self-supervised learning [95.03389072594243]
  We make the first attempt to investigate the adversarial vulnerability of such paradigm under the attacks from both zero-knowledge adversaries and limited-knowledge adversaries. The experimental results illustrate that the paradigm proposed by SUPERB is seriously vulnerable to limited-knowledge adversaries.
  arXiv  Detail & Related papers  (2021-11-08T08:44:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.