# Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination

arXiv: https://arxiv.org/abs/2410.17820 · HTML: https://mlsanity.com/paper/2410.17820/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations](https://mlsanity.com/paper/2402.12348/) (2024)
- [Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models](https://mlsanity.com/paper/2308.10379/) (2023)
- [Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation](https://mlsanity.com/paper/2311.04254/) (2023)
- [When is Tree Search Useful for LLM Planning? It Depends on the Discriminator](https://mlsanity.com/paper/2402.10890/) (2024)
- [Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions](https://mlsanity.com/paper/2311.13982/) (2023)
- [Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning](https://mlsanity.com/paper/2409.12618/) (2024)
- [Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models](https://mlsanity.com/paper/2406.12546/) (2024)
- [Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts](https://mlsanity.com/paper/2311.08097/) (2023)
- [AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability](https://mlsanity.com/paper/2402.09404/) (2024)

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

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Multi-LLM Collaborative Search for Complex Problem Solving](https://mlsanity.com/paper/2502.18873/) (2025)

## Abstract (arXiv)

Tree of Thoughts (ToT) is a reasoning strategy for Large Language Models (LLMs) that employs a generator to suggest reasoning steps and a discriminator to decide which steps to implement. ToT demonstrates strong performance on reasoning tasks, often surpassing simple methods such as Input-Output (IO) prompting and Chain-of-Thought (CoT) reasoning. However, ToT does not consistently outperform such simpler methods across all models, leaving large knowledge gaps on the conditions under which ToT is most beneficial. In this paper, we analyze the roles of the generator and discriminator separately to better understand the conditions when ToT is beneficial. We find that the generator plays a more critical role than the discriminator in driving the success of ToT. Scaling the generator leads to notable improvements in ToT performance, even when using a smaller model as the discriminator, whereas scaling the discriminator with a fixed generator yields only marginal gains. Our results show that models across different scales exhibit comparable discrimination capabilities, yet differ significantly in their generative performance for ToT.