R-Debater: Retrieval-Augmented Debate Generation
Published:Dec 31, 2025 07:33
•1 min read
•ArXiv
Analysis
This paper introduces R-Debater, a novel agentic framework for generating multi-turn debates. It's significant because it moves beyond simple LLM-based debate generation by incorporating an 'argumentative memory' and retrieval mechanisms. This allows the system to ground its arguments in evidence and prior debate moves, leading to more coherent, consistent, and evidence-supported debates. The evaluation on standardized debates and comparison with strong LLM baselines, along with human evaluation, further validates the effectiveness of the approach. The focus on stance consistency and evidence use is a key advancement in the field.
Key Takeaways
- •R-Debater is an agentic framework for generating multi-turn debates.
- •It uses an 'argumentative memory' to retrieve evidence and prior debate moves.
- •The system is evaluated on ORCHID debates and compared with LLM baselines.
- •R-Debater achieves higher scores and demonstrates improved consistency and evidence use compared to baselines.
Reference
“R-Debater achieves higher single-turn and multi-turn scores compared with strong LLM baselines, and human evaluation confirms its consistency and evidence use.”