SMaRT: Select, Mix, and ReinvenT -- A Strategy Fusion Framework for LLM-Driven Reasoning and Planning
This addresses the need for more robust and adaptable LLM-driven reasoning systems, though it appears incremental as it builds on existing strategy fusion concepts.
The paper tackles the problem of single-strategy prompting in LLMs for complex tasks by introducing the SMaRT framework, which fuses diverse reasoning strategies to improve performance, and it consistently outperforms state-of-the-art baselines in benchmarks for reasoning, planning, and decision-making.
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.