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

• URL: http://arxiv.org/abs/2311.08803v3
• Date: Fri, 24 May 2024 13:55:23 GMT
• Title: StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
• Authors: Chang Gao, Haiyun Jiang, Deng Cai, Shuming Shi, Wai Lam,
• Abstract summary: StrategyLLM allows 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. 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
• Score: 76.5322280307861
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming [13.246017517159043]
  Large language models (LLMs) have recently demonstrated strong potential in solving planning problems. We propose LLpreview, a framework that leverages LLMs to capture key information from planning problems and formally formulate and solve them as optimization problems from scratch. We apply LLpreview to 9 planning problems, ranging from multi-constraint decision making to multi-step planning problems, and demonstrate that LLpreview achieves on average 83.7% and 86.8% optimal rate across 9 tasks for GPTo and Claude 3.5 Sonnet.
  arXiv  Detail & Related papers  (2024-10-15T23:20:54Z)
• Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation [16.350747493026432]
  The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs) We propose the textbfStrategic Chain-of-Thought (SCoT) to refine LLM performance by integrating strategic knowledge prior to generating intermediate reasoning steps. SCoT employs a two-stage approach within a single prompt: first eliciting an effective problem-solving strategy, which is then used to guide the generation of high-quality CoT paths and final answers.
  arXiv  Detail & Related papers  (2024-09-05T06:28:05Z)
• GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning [2.9312156642007294]
  Spatial reasoning is one of the core commonsense skills that is not purely language-based and requires some minimum degree of planning. Existing benchmarks of Commonsense Spatial Reasoning (CSR) tend to evaluate how Large Language Models (LLMs) interpret text-based spatial descriptions. We construct a large-scale benchmark called $textbfGRASP$, which consists of 16,000 grid-based environments where the agent is tasked with an energy collection problem.
  arXiv  Detail & Related papers  (2024-07-02T02:27:46Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• Meta Reasoning for Large Language Models [58.87183757029041]
  We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs) MRP guides LLMs to dynamically select and apply different reasoning methods based on the specific requirements of each task. We evaluate the effectiveness of MRP through comprehensive benchmarks.
  arXiv  Detail & Related papers  (2024-06-17T16:14:11Z)
• Self-Guiding Exploration for Combinatorial Problems [2.636330943305939]
  Self-Guiding Exploration (SGE) is designed to enhance the performance of solving Combinatorial Problems. SGE operates autonomously, generating multiple thought trajectories for each CP task. It then breaks these trajectories down into actionable subtasks, executes them sequentially, and refines the results to ensure optimal outcomes.
  arXiv  Detail & Related papers  (2024-05-28T08:26:54Z)
• Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection [80.63946798650653]
  Decision centers on whether to use a large LLM with better performance or a smaller one with reduced costs. We propose a simpler solution; we use only the uncertainty of the generations of the small LLM as the decision criterion. Our experiments reveal this simple solution optimally balances cost and performance, outperforming existing methods on 25 out of 27 experimental setups.
  arXiv  Detail & Related papers  (2024-05-03T14:38:59Z)
• Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning [56.82041895921434]
  Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities. When used as agents for dealing with complex problems in the real world, their performance is far inferior to large commercial models such as ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2024-03-29T03:48:12Z)
• DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation [53.62727171363384]
  We introduce a novel reasoning principle: Dynamic Reflection with Divergent Thinking. Our methodology is dynamic reflection, a process that emulates human learning through probing, critiquing, and reflecting. We evaluate our approach on three datasets using six pre-trained LLMs.
  arXiv  Detail & Related papers  (2023-12-18T16:41:22Z)
• Which is better? Exploring Prompting Strategy For LLM-based Metrics [6.681126871165601]
  This paper describes the DSBA submissions to the Prompting Large Language Models as Explainable Metrics shared task. Traditional similarity-based metrics such as BLEU and ROUGE have shown to misalign with human evaluation and are ill-suited for open-ended generation tasks.
  arXiv  Detail & Related papers  (2023-11-07T06:36:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.