Understanding the Effects of Multi-Agent Deliberation for Human-AI Decision-Making
cs.HC, cs.AI
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Training Language Models to Win Debates with Self-Play Improves Judge Accuracy
- Measuring Progress on Scalable Oversight for Large Language Models
- AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs
- Can Domain Experts Rely on AI Appropriately? A Case Study on AI-Assisted Prostate Cancer MRI Diagnosis
- Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks
- "It makes you think": Provocations Help Restore Critical Thinking to AI-Assisted Knowledge Work
- Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
- Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
- Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents
- AI safety via debate
- Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate
- Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation
- Beyond Recommender: An Exploratory Study of the Effects of Different AI Roles in AI-Assisted Decision Making
- Debate Helps Supervise Unreliable Experts
- ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions
- Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions
- Towards AI as Colleagues: Multi-Agent System Improves Structured Ideation Processes
- AI Debate Aids Assessment of Controversial Claims
- Should I Follow AI-based Advice? Measuring Appropriate Reliance in Human-AI Decision-Making
- Towards Understanding Sycophancy in Language Models
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems