Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation

arXiv:2609.03619 · cs.CL, cs.AI · Submitted 2026-09-03 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-03

Updated: 2026-09-03

Code: https://github.com/KylJin/R2-MAD

Terminology

• Benchmark — 33× in this paper · explained in 2 episodes
• Multi-Agent Debate — 27× in this paper
• Consistency — 25× in this paper · explained in 3 episodes
• Self-consistency — 25× in this paper · explained in 2 episodes
• Accuracy — 17× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Failure Modes — 4× in this paper · explained in 3 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Chain of Thought — 3× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Free-MAD: Consensus-Free Multi-Agent Debate
• The Llama 3 Herd of Models
• GPT-4o System Card
• SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• Enhancing Multi-Agent Debate System Performance via Confidence Expression
• GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• MemGPT: Towards LLMs as Operating Systems
• MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
• Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
• An Explanation of In-context Learning as Implicit Bayesian Inference
• Gemma 3 Technical Report
• Multi-Agent Debate with Memory Masking
• Qwen3 Technical Report
• Qwen2.5 Technical Report
• From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
• Demystifying Multi-Agent Debate: The Role of Confidence and Diversity

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering