# Conversational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-making

arXiv: https://arxiv.org/abs/2503.14263 · HTML: https://mlsanity.com/paper/2503.14263/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 15 of its 111 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 15 of 15)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog](https://mlsanity.com/paper/2010.10874/) (2020)
- [Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models](https://mlsanity.com/paper/2304.13835/) (2023)
- [AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation](https://mlsanity.com/paper/2402.14978/) (2024)
- [The Effects of Generative AI on Design Fixation and Divergent Thinking](https://mlsanity.com/paper/2403.11164/) (2024)
- [Proactive Conversational Agents with Inner Thoughts](https://mlsanity.com/paper/2501.00383/) (2024)
- [ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions](https://mlsanity.com/paper/2310.01331/) (2023)
- [How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experiment](https://mlsanity.com/paper/2401.13481/) (2024)
- [AI Should Challenge, Not Obey](https://mlsanity.com/paper/2411.02263/) (2024)
- [Antagonistic AI](https://mlsanity.com/paper/2402.07350/) (2024)
- [Beyond Recommender: An Exploratory Study of the Effects of Different AI Roles in AI-Assisted Decision Making](https://mlsanity.com/paper/2403.01791/) (2024)
- [Learning Multi-Party Turn-Taking Models from Dialogue Logs](https://mlsanity.com/paper/1907.02090/) (2019)
- [Amplifying Minority Voices: AI-Mediated Devil's Advocate System for Inclusive Group Decision-Making](https://mlsanity.com/paper/2502.06251/) (2025)
- [Integrating Flow Theory and Adaptive Robot Roles: A Conceptual Model of Dynamic Robot Role Adaptation for the Enhanced Flow Experience in Long-term Multi-person Human-Robot Interactions](https://mlsanity.com/paper/2401.02833/) (2024)

## Built on by (most cited first, 4 of 4)

- [Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation](https://mlsanity.com/paper/2509.20553/) (2025)
- [Cognitive Agency Surrender: Defending Epistemic Sovereignty via Scaffolded AI Friction](https://mlsanity.com/paper/2603.21735/) (2026)
- [AI Workers, Geopolitics, and Algorithmic Collective Action](https://mlsanity.com/paper/2511.17331/) (2025)
- [Beyond Compliance: How AI Could Help Creative Writers by Refusing Them](https://mlsanity.com/paper/2605.16272/) (2026)

## Abstract (arXiv)

Group decision-making processes frequently suffer when social influence and power dynamics suppress minority viewpoints, leading to compliance and groupthink. Conversational agents can counteract these harmful dynamics by encouraging critical thinking. This study investigates how LLM-powered devil's advocate systems affect psychological safety, opinion expression, and satisfaction in power-imbalanced group dynamics. We conducted an experiment with 48 participants in 12 four-person groups, each containing three high-power (senior) and one low-power (junior) member. Each group completed decision tasks in both baseline and AI intervention conditions. Results show AI counterarguments fostered a more flexible atmosphere and significantly enhanced both process and outcome satisfaction for all participants, with particularly notable improvements for minority members. Cognitive workload increased slightly, though not significantly. This research contributes empirical evidence on how AI systems can effectively navigate power hierarchies to foster more inclusive decision-making environments, highlighting the importance of balancing intervention frequency, maintaining conversational flow, and preserving group cohesion.