Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning

TL;DR

The paper introduces an Adaptive-Solver framework that dynamically adjusts problem-solving strategies in large language models, reducing computational costs and enhancing accuracy by tailoring approaches based on problem complexity.

Contribution

It presents a novel adaptive framework for LLM reasoning that intelligently switches strategies at test time, unlike traditional fixed-method approaches.

Findings

Reduces API costs by up to 85%.

Achieves up to 4.5% higher accuracy at the same cost.

Effectively adapts to various problem complexities.

Abstract

Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a one-size-fits-all approach. These methods employ consistent models, sample sizes, prompting methods and levels of problem decomposition, regardless of the problem complexity. The inflexibility of these methods can bring unnecessary computational overhead or sub-optimal performance. To address this limitation, we introduce an Adaptive-Solver (AS) framework tha dynamically adapts solving strategies to suit various problems, enabling the flexible allocation of test-time computational resources. The framework functions with two primary modules. The initial evaluation module assesses the reliability of the current solution using answer consistency. If the solution is deemed unreliable, the subsequent adaptation module comes into play. Within this module, various types of adaptation strategies are employed collaboratively. Through such dynamic and multi-faceted adaptations, our framework can help reduce computational consumption and improve performance. Experimental results from complex reasoning benchmarks reveal that our method can significantly reduce API costs (up to 85%) while maintaining original performance. Alternatively, it achieves up to 4.5% higher accuracy compared to the baselines at the same cost. The code and dataset are available at https://github.com/john1226966735/Adaptive-Solver.