# T2 of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models

arXiv: https://arxiv.org/abs/2405.14075 · HTML: https://mlsanity.com/paper/2405.14075/

## Key facts

- Cited by 1 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 12 of its 32 references that are in the map.
- First posted on arXiv 23 May 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, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023)
- [LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization](https://mlsanity.com/paper/2306.01102/) (2023)
- [EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling](https://mlsanity.com/paper/2403.14541/) (2024)
- [Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals](https://mlsanity.com/paper/2308.06207/) (2023)
- [CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs](https://mlsanity.com/paper/2404.01343/) (2024)
- [KL-Divergence Guided Temperature Sampling](https://mlsanity.com/paper/2306.01286/) (2023)

## Built on by (most cited first, 1 of 1)

- [The Role of Deductive and Inductive Reasoning in Large Language Models](https://mlsanity.com/paper/2410.02892/) (2024)

## Abstract (arXiv)

Large Language Models (LLMs) have emerged as powerful tools in artificial intelligence, especially in complex decision-making scenarios, but their static problem-solving strategies often limit their adaptability to dynamic environments. We explore the enhancement of reasoning capabilities in LLMs through Temperature Tree (T2) prompting via a heuristic algorithm, termed as T2 of Thoughts (T2oT). The primary focus is on enhancing decision-making processes by dynamically adjusting search parameters, especially temperature, to improve accuracy without increasing computational demands. We empirically validate that our hybrid T2oT approach yields enhancements in, single-solution accuracy, multi-solution generation and text generation quality. Our findings suggest that while dynamic search depth adjustments based on temperature can yield mixed results, a fixed search depth, when coupled with adaptive capabilities of T2oT, provides a more reliable and versatile problem-solving strategy. This work highlights the potential for future explorations in optimizing algorithmic interactions with foundational language models, particularly illustrated by our development for the Game of 24 and Creative Writing tasks.