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

Research output: Working paperPreprintResearch


  • Fulltext

    Final published version, 423 KB, PDF document

  • Chengkun Cai
  • Xu Zhao
  • Yucheng Du
  • Haoliang Liu
  • Li, Lei
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 ($T^2$) prompting via Particle Swarm Optimization, termed as $T^2$ of Thoughts ($T^2oT$). 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 $T^2oT$ 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 $T^2oT$, 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.
Original languageUndefined/Unknown
Number of pages16
Publication statusPublished - 23 May 2024

Bibliographical note

10 pages, 5 figures


ID: 395084579