# R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory

arXiv: https://arxiv.org/abs/2512.24684 · HTML: https://mlsanity.com/paper/2512.24684/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 16 of its 55 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)
- 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, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning](https://mlsanity.com/paper/2401.01325/) (2024)
- [Make Your LLM Fully Utilize the Context](https://mlsanity.com/paper/2404.16811/) (2024)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [Large Language Models Meet NLP: A Survey](https://mlsanity.com/paper/2405.12819/) (2024)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [Faithful Logical Reasoning via Symbolic Chain-of-Thought](https://mlsanity.com/paper/2405.18357/) (2024)
- [LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering](https://mlsanity.com/paper/2410.18050/) (2024)
- [Argument Generation with Retrieval, Planning, and Realization](https://mlsanity.com/paper/1906.03717/) (2019)
- [Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances](https://mlsanity.com/paper/2106.02227/) (2021)
- [Neural Argument Generation Augmented with Externally Retrieved Evidence](https://mlsanity.com/paper/1805.10254/) (2018)
- [Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM](https://mlsanity.com/paper/2403.08010/) (2024)
- [Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate](https://mlsanity.com/paper/2408.04472/) (2024)
- [ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization](https://mlsanity.com/paper/2410.13667/) (2024)
- [InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debating](https://mlsanity.com/paper/2506.18102/) (2025)

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

- [Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification](https://mlsanity.com/paper/2603.28488/) (2026)
- [Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2605.15343/) (2026)
- [PolyDebate: A Game-Orchestrated Multimodal System for Debate Skills Practice and Evaluation](https://mlsanity.com/paper/2608.16276/) (2026)
- [ARGUS: Theory-of-Mind Guided Argument Generation with Strategy-Aware Planning and Knowledge Grounding](https://mlsanity.com/paper/2608.20405/) (2026)

## Abstract (arXiv)

We present R-Debater, an agentic framework for generating multi-turn debates built on argumentative memory. Grounded in rhetoric and memory studies, the system views debate as a process of recalling and adapting prior arguments to maintain stance consistency, respond to opponents, and support claims with evidence. Specifically, R-Debater integrates a debate knowledge base for retrieving case-like evidence and prior debate moves with a role-based agent that composes coherent utterances across turns. We evaluate on standardized ORCHID debates, constructing a 1,000-item retrieval corpus and a held-out set of 32 debates across seven domains. Two tasks are evaluated: next-utterance generation, assessed by InspireScore (subjective, logical, and factual), and adversarial multi-turn simulations, judged by Debatrix (argument, source, language, and overall). Compared with strong LLM baselines, R-Debater achieves higher single-turn and multi-turn scores. Human evaluation with 20 experienced debaters further confirms its consistency and evidence use, showing that combining retrieval grounding with structured planning yields more faithful, stance-aligned, and coherent debates across turns.