SMaRT: Select, Mix, and ReinvenT -- A Strategy Fusion Framework for LLM-Driven Reasoning and Planning

TL;DR

SMaRT is a novel framework that fuses multiple reasoning strategies in LLMs to enhance task performance, robustness, and adaptability across various benchmarks, surpassing existing single-strategy methods.

Contribution

Introduces SMaRT, a strategy fusion framework that uses LLMs as integrators to combine diverse reasoning approaches, improving over single-strategy prompting methods.

Findings

Outperforms state-of-the-art baselines in multiple benchmarks

Enhances solution quality and constraint adherence

Demonstrates robustness and adaptability across tasks

Abstract

Large Language Models (LLMs) have redefined complex task automation with exceptional generalization capabilities. Despite these advancements, state-of-the-art methods rely on single-strategy prompting, missing the synergy of diverse reasoning approaches. No single strategy excels universally, highlighting the need for frameworks that fuse strategies to maximize performance and ensure robustness. We introduce the Select, Mix, and ReinvenT (SMaRT) framework, an innovative strategy fusion approach designed to overcome this constraint by creating balanced and efficient solutions through the seamless integration of diverse reasoning strategies. Unlike existing methods, which employ LLMs merely as evaluators, SMaRT uses them as intelligent integrators, unlocking the "best of all worlds" across tasks. Extensive empirical evaluations across benchmarks in reasoning, planning, and sequential decision-making highlight the robustness and adaptability of SMaRT. The framework consistently outperforms state-of-the-art baselines in solution quality, constraint adherence, and performance metrics. This work redefines LLM-driven decision-making by pioneering a new paradigm in cross-strategy calibration, unlocking superior outcomes for reasoning systems and advancing the boundaries of self-refining methodologies.