# Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis

arXiv: https://arxiv.org/abs/2502.14767 · HTML: https://mlsanity.com/paper/2502.14767/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 10 of its 35 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 10 of 10)

- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes](https://mlsanity.com/paper/2310.10648/) (2023)
- [Active Learning for Convolutional Neural Networks: A Core-Set Approach](https://mlsanity.com/paper/1708.00489/) (2017)
- [Explaining Relationships Between Scientific Documents](https://mlsanity.com/paper/2002.00317/) (2020)
- [Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging](https://mlsanity.com/paper/2406.11709/) (2024)
- [Bursting Scientific Filter Bubbles: Boosting Innovation via Novel Author Discovery](https://mlsanity.com/paper/2108.05669/) (2021)
- [STRUM-LLM: Attributed and Structured Contrastive Summarization](https://mlsanity.com/paper/2403.19710/) (2024)

## Built on by (most cited first, 6 of 6)

- [Idea2Plan: Exploring AI-Powered Research Planning](https://mlsanity.com/paper/2510.24891/) (2025)
- [Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy](https://mlsanity.com/paper/2606.24177/) (2026)
- [Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges](https://mlsanity.com/paper/2607.26212/) (2026)
- [The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems](https://mlsanity.com/paper/2509.26126/) (2025)
- [Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique](https://mlsanity.com/paper/2608.20777/) (2026)
- [Reinforcing Agentic Creativity in Scientific Ideation with Night Science](https://mlsanity.com/paper/2609.35706/) (2026)

## Abstract (arXiv)

With the exponential growth of research facilitated by modern technology and improved accessibility, scientific discoveries have become increasingly fragmented within and across fields. This makes it challenging to assess the significance, novelty, incremental findings, and equivalent ideas between related works, particularly those from different research communities. Large language models (LLMs) have recently demonstrated strong quantitative and qualitative reasoning abilities, and multi-agent LLM debates have shown promise in handling complex reasoning tasks by exploring diverse perspectives and reasoning paths. Inspired by this, we introduce Tree-of-Debate (ToD), a framework which converts scientific papers into LLM personas that debate their respective novelties. To emphasize structured, critical reasoning rather than focusing solely on outcomes, ToD dynamically constructs a debate tree, enabling fine-grained analysis of independent novelty arguments within scholarly articles. Through experiments on scientific literature across various domains, evaluated by expert researchers, we demonstrate that ToD generates informative arguments, effectively contrasts papers, and supports researchers in their literature review.