StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving

TL;DR

StrategyLLM introduces a multi-agent framework enabling large language models to generate, evaluate, and optimize problem-solving strategies, significantly improving performance and consistency across diverse reasoning tasks without human input.

Contribution

This work presents a novel multi-agent approach with strategy generation, evaluation, and optimization modules, enhancing generalizability and consistency in few-shot prompting for LLMs.

Findings

Outperforms baseline CoT-SC on 13 datasets across 4 tasks.

Achieves notable accuracy improvements in math, reasoning, and symbolic tasks.

Demonstrates applicability to various LLMs and scenarios.

Abstract

Most existing prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other instances and lack task-level consistency across the selected few-shot examples. To address these limitations, we propose a comprehensive framework, StrategyLLM, allowing LLMs to perform inductive reasoning, deriving general strategies from specific task instances, and deductive reasoning, applying these general strategies to particular task examples, for constructing generalizable and consistent few-shot prompts. It employs four LLM-based agents: strategy generator, executor, optimizer, and evaluator, working together to generate, evaluate, and select promising strategies for a given task. Experimental results demonstrate that StrategyLLM outperforms the competitive baseline CoT-SC that requires human-annotated solutions on 13 datasets across 4 challenging tasks without human involvement, including math reasoning (34.2\% $\rightarrow$ 38.8\%), commonsense reasoning (70.3\% $\rightarrow$ 72.5\%), algorithmic reasoning (73.7\% $\rightarrow$ 85.0\%), and symbolic reasoning (30.0\% $\rightarrow$ 79.2\%). Further analysis reveals that StrategyLLM is applicable to various LLMs and demonstrates advantages across numerous scenarios.