# Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters

arXiv: https://arxiv.org/abs/2505.14886 · HTML: https://mlsanity.com/paper/2505.14886/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 22 of 22)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023)
- [Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation](https://mlsanity.com/paper/2310.01320/) (2023)
- [Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication](https://mlsanity.com/paper/2312.01823/) (2023)
- [Argument Generation with Retrieval, Planning, and Realization](https://mlsanity.com/paper/1906.03717/) (2019)
- [Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate](https://mlsanity.com/paper/2401.16788/) (2024)
- [Exploring the Role of Argument Structure in Online Debate Persuasion](https://mlsanity.com/paper/2010.03538/) (2020)
- [Conversational flow in Oxford-style debates](https://mlsanity.com/paper/1604.03114/) (2016)
- [Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM](https://mlsanity.com/paper/2403.08010/) (2024)
- [Prompt-Based Length Controlled Generation with Multiple Control Types](https://mlsanity.com/paper/2406.10278/) (2024)
- [The Role of Pragmatic and Discourse Context in Determining Argument Impact](https://mlsanity.com/paper/2004.03034/) (2020)
- [Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate](https://mlsanity.com/paper/2408.04472/) (2024)
- [GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates](https://mlsanity.com/paper/2202.08175/) (2022)
- [Precise Length Control in Large Language Models](https://mlsanity.com/paper/2412.11937/) (2024)
- [Exploring Discourse Structures for Argument Impact Classification](https://mlsanity.com/paper/2106.00976/) (2021)
- [Overview of AI-Debater 2023: The Challenges of Argument Generation Tasks](https://mlsanity.com/paper/2407.14829/) (2024)

## Built on by (most cited first, 2 of 2)

- [ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind](https://mlsanity.com/paper/2505.22961/) (2025)
- [DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal](https://mlsanity.com/paper/2601.18081/) (2026)

## Abstract (arXiv)

Winning competitive debates requires sophisticated reasoning and argument skills. There are unique challenges in the competitive debate: (1) The time constraints force debaters to make strategic choices about which points to pursue rather than covering all possible arguments; (2) The persuasiveness of the debate relies on the back-and-forth interaction between arguments, which a single final game status cannot evaluate. To address these challenges, we propose TreeDebater, a novel debate framework that excels in competitive debate. We introduce two tree structures: the Rehearsal Tree and Debate Flow Tree. The Rehearsal Tree anticipates the attack and defenses to evaluate the strength of the claim, while the Debate Flow Tree tracks the debate status to identify the active actions. TreeDebater allocates its time budget among candidate actions and uses the speech time controller and feedback from the simulated audience to revise its statement. The human evaluation on both the stage-level and the debate-level comparison shows that our TreeDebater outperforms the state-of-the-art multi-agent debate system, with a +15.6% improvement in stage-level persuasiveness with DeepSeek and +10% debate-level opinion shift win. Further investigation shows that TreeDebater shows better strategies in limiting time to important debate actions, aligning with the strategies of human debate experts.