Can I read Pheromone-based Learning of Optimal Reasoning Paths on EtoBox?

Pheromone-based Learning of Optimal Reasoning Paths by Chari, Anirudh; Tiwari, Aditya; Lian, Richard; Reddy, Suraj; Zhou, Brian is a scholarly article available to read on EtoBox.

What is Pheromone-based Learning of Optimal Reasoning Paths about?

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities through chain-of-thought prompting, yet discovering effective reasoning methods for complex problems remains challenging due to the vast space of possible intermediate steps. We introduce Ant Colony Optimization-guided Tree of Thought (ACO-ToT), a novel algorithm that combines ACO with LLMs to discover optimal reasoning paths for complex problems efficiently. Drawing inspiration from Hebbian learning in neurological systems, our method employs a collection of distinctly fine-tuned LLM "ants" to traverse and lay pheromone trails through a centralized tree of thought, with each ant's movement governed by a weighted combination of existing pheromone trails and its own specialized expertise. The algorithm evaluates complete reasoning paths using a mixture-of-experts-based scoring function, with pheromones reinforcing productive reasoning paths across iterations. Experiments on three challenging reasoning tasks (GSM8K, ARC-Challenge, and MATH) demonstrate that ACO-ToT performs significantly better than existing chain-of-thought optimization approaches, suggesting that incorporating biologically inspired col

Author

Chari, Anirudh; Tiwari, Aditya; Lian, Richard; Reddy, Suraj; Zhou, Brian

Published

2025

Language

EN