# Exploring Learners' Expectations and Engagement When Collaborating with Constructively Controversial Peer Agents

arXiv: https://arxiv.org/abs/2601.13479 · HTML: https://mlsanity.com/paper/2601.13479/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 154 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Placed in

- 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, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making](https://mlsanity.com/paper/2102.09692/) (2021)
- [The Metacognitive Demands and Opportunities of Generative AI](https://mlsanity.com/paper/2312.10893/) (2023)
- [Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models](https://mlsanity.com/paper/2402.11723/) (2024)
- [Improving Human-AI Collaboration With Descriptions of AI Behavior](https://mlsanity.com/paper/2301.06937/) (2023)
- [Proactive Conversational Agents with Inner Thoughts](https://mlsanity.com/paper/2501.00383/) (2024)
- [Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks](https://mlsanity.com/paper/2310.19740/) (2023)
- [Are Large Language Models Reliable Argument Quality Annotators?](https://mlsanity.com/paper/2404.09696/) (2024)
- [ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions](https://mlsanity.com/paper/2310.01331/) (2023)
- [Understanding Nonlinear Collaboration between Human and AI Agents: A Co-design Framework for Creative Design](https://mlsanity.com/paper/2401.07312/) (2024)
- [GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency](https://mlsanity.com/paper/2402.08855/) (2024)
- [PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning](https://mlsanity.com/paper/2403.14227/) (2024)
- [Argumentative Experience: Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates](https://mlsanity.com/paper/2412.04629/) (2024)
- [User Characteristics in Explainable AI: The Rabbit Hole of Personalization?](https://mlsanity.com/paper/2403.00137/) (2024)
- [THOUGHTSCULPT: Reasoning with Intermediate Revision and Search](https://mlsanity.com/paper/2404.05966/) (2024)
- [What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices](https://mlsanity.com/paper/2504.03803/) (2025)
- [From Paper to Card: Transforming Design Implications with Generative AI](https://mlsanity.com/paper/2403.08137/) (2024)
- [SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning](https://mlsanity.com/paper/2408.13891/) (2024)
- [Algorithms for the Greater Good! On Mental Modeling and Acceptable Symbiosis in Human-AI Collaboration](https://mlsanity.com/paper/1801.09854/) (2018)
- [Imitating Mistakes in a Learning Companion AI Agent for Online Peer Learning](https://mlsanity.com/paper/2507.12801/) (2025)
- [Influence of agent's self-disclosure on human empathy](https://mlsanity.com/paper/2106.09906/) (2021)

## Abstract (arXiv)

Peer agents can supplement real-time collaborative learning in asynchronous online courses. Constructive Controversy (CC) theory suggests that humans deepen their understanding of a topic by confronting and resolving controversies. This study explores whether CC's benefits apply to LLM-based peer agents, focusing on the impact of agents' disputatious behaviors and disclosure of agents' behavior designs on the learning process. In our mixed-method study (n=144), we compare LLMs that follow detailed CC guidelines (regulated) to those guided by broader goals (unregulated) and examine the effects of disclosing the agents' design to users (transparent vs. opaque). Findings show that learners' values influence their agent interaction: those valuing control appreciate unregulated agents' willingness to cease push-back upon request, while those valuing intellectual challenges favor regulated agents for stimulating creativity. Additionally, design transparency lowers learners' perception of agents' abilities. Our findings lay the foundation for designing effective collaborative peer agents in isolated educational settings.