Cumulative Reasoning with Large Language Models

• URL: http://arxiv.org/abs/2308.04371v8
• Date: Sun, 20 Jul 2025 09:11:20 GMT
• Title: Cumulative Reasoning with Large Language Models
• Authors: Yifan Zhang, Jingqin Yang, Yang Yuan, Andrew Chi-Chih Yao,
• Abstract summary: Cumulative Reasoning (CR) is a structured framework that enhances large language models (LLMs) problem-solving.<n>CR orchestrates LLMs in three distinct roles--Proposer, Verifier(s), and Reporter--to systematically decompose tasks, generate and validate intermediate reasoning steps, and compose them into a solution.
• Score: 12.267474250936123
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in large language models (LLMs) have shown remarkable progress, yet their ability to solve complex problems remains limited. In this work, we introduce Cumulative Reasoning (CR), a structured framework that enhances LLM problem-solving by emulating human-like iterative and cumulative thought processes. CR orchestrates LLMs in three distinct roles--Proposer, Verifier(s), and Reporter--to systematically decompose tasks, generate and validate intermediate reasoning steps, and compose them into a solution by building a dynamic Directed Acyclic Graph (DAG) of verified propositions. This approach substantially enhances problem-solving capabilities. We demonstrate CR's advantage through several complex reasoning tasks: it outperforms existing methods in logical inference tasks with up to a 9.3% improvement, achieving 98.04% accuracy on the curated FOLIO wiki dataset. In the Game of 24, it achieves 98% accuracy, marking a 24% improvement over previous methods. In solving MATH problems, CR achieves a 4.2% increase from previous methods and a 43% relative improvement in the most challenging level 5 problems. When incorporating a code environment with CR, we further harness LLMs' reasoning capabilities and outperform the Program of Thought (PoT) method by 38.8%. The code is available at https://github.com/iiis-ai/cumulative-reasoning.

Related papers

• Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code [76.80306464249217]
  We propose TeaR, which aims at teaching LLMs to reason better.<n>TeaR leverages careful data curation and reinforcement learning to guide models in discovering optimal reasoning paths through code-related tasks.<n>We conduct extensive experiments using two base models and three long-CoT distillation models, with model sizes ranging from 1.5 billion to 32 billion parameters, and across 17 benchmarks spanning Math, Knowledge, Code, and Logical Reasoning.
  arXiv  Detail & Related papers  (2025-07-10T07:34:05Z)
• Benchmarking Large Language Models for Calculus Problem-Solving: A Comparative Analysis [0.0]
  Five leading large language models (LLMs) were evaluated on their performance in solving calculus differentiation problems. Chat GPT 4o achieved the highest success rate (94.71%), followed by Claude Pro (85.74%), Gemini Advanced (84.42%), Copilot Pro (76.30%), and Meta AI (56.75%)
  arXiv  Detail & Related papers  (2025-03-31T00:39:40Z)
• Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning [55.6623318085391]
  Recent large language model (LLM) reasoning suffers from limited domain knowledge, susceptibility to hallucinations, and constrained reasoning depth.<n>This paper presents the first investigation into integrating step-wise knowledge graph retrieval with step-wise reasoning.<n>We propose KG-RAR, a framework centered on process-oriented knowledge graph construction, a hierarchical retrieval strategy, and a universal post-retrieval processing and reward model.
  arXiv  Detail & Related papers  (2025-03-03T15:20:41Z)
• Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models [1.4956870931936515]
  We introduce RDoLT, a novel framework that significantly boosts Large Language Models reasoning performance. RDoLT is built on three key innovations: (1) breaking down complex reasoning tasks into sub-tasks of progressive complexity; (2) employing an advanced selection and scoring mechanism to identify the most promising reasoning thoughts; and (3) integrating a knowledge propagation module that mimics human learning. Our approach was evaluated across multiple benchmarks, including GSM8K, SVAMP, MultiArithm, LastLetterConcatenation, and Gaokao2023 Math.
  arXiv  Detail & Related papers  (2025-01-03T02:55:44Z)
• Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving [0.0]
  Recent advances in large language models (LLMs) have predominantly focused on maximizing accuracy and reasoning capabilities. This paper investigates the potential synergy between reasoning enhancement and computational efficiency by analyzing the integration of two contrasting approaches.
  arXiv  Detail & Related papers  (2024-12-20T08:42:45Z)
• Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs [29.735465300269993]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often struggle with spatial reasoning.<n>This paper presents a novel neural-symbolic framework that enhances LLMs' spatial reasoning abilities through iterative feedback between LLMs and Answer Set Programming (ASP)<n>We evaluate our approach on two benchmark datasets: StepGame and SparQA.
  arXiv  Detail & Related papers  (2024-11-27T18:04:05Z)
• Exploring Performance Contrasts in TableQA: Step-by-Step Reasoning Boosts Bigger Language Models, Limits Smaller Language Models [6.083393426133172]
  This paper proposes a detailed prompting flow, termed Table-Logic, to investigate the performance contrasts between bigger and smaller language models (LMs) By deploying this method, we observe a 7.8% accuracy improvement in bigger LMs like Llama-3-70B compared to the vanilla on HybridQA. Our findings highlight the limitations of the step-by-step reasoning method in small models and provide potential insights for making improvements.
  arXiv  Detail & Related papers  (2024-11-24T22:48:44Z)
• Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning [7.702162381335683]
  Step-by-step Chain-of-Thought (CoT) inference has advanced the mathematical capabilities of large language models (LLMs) We propose a novel method called Step Guidance Reasoning without involving further model fine-tuning. Our method significantly improved the math performance, raising the accuracy on the AMC23 dataset from 30% to 57.5%, a relative improvement of 91.7%, and on the sampled level 5 problem of the MATH dataset, we achieved a relative accuracy improvement of 55.8%, increasing from 43% to 67%.
  arXiv  Detail & Related papers  (2024-10-18T01:38:24Z)
• Enhancing Mathematical Reasoning in LLMs by Stepwise Correction [39.67266805233599]
  Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems. We propose a novel prompting method named Stepwise Correction (StepCo) that helps LLMs identify and revise incorrect steps in their generated reasoning paths. The verify-then-revise process not only improves answer correctness but also reduces token consumption with fewer paths needed to generate.
  arXiv  Detail & Related papers  (2024-10-16T18:18:42Z)
• Instructive Code Retriever: Learn from Large Language Model's Feedback for Code Intelligence Tasks [10.867880635762395]
  We introduce a novel approach named Instructive Code Retriever (ICR) ICR is designed to retrieve examples that enhance model inference across various code intelligence tasks and datasets. We evaluate our model's effectiveness on various tasks, i.e., code summarization, program synthesis, and bug fixing.
  arXiv  Detail & Related papers  (2024-10-15T05:44:00Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search [22.672130194493793]
  Large Language Models (LLMs) have exhibited exceptional performance across a broad range of tasks and domains. They still encounter difficulties in solving mathematical problems due to the rigorous and logical nature of mathematics. We propose a novel approach, BEATS, to enhance mathematical problem-solving abilities.
  arXiv  Detail & Related papers  (2024-09-26T15:47:42Z)
• MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning [60.55556283848063]
  Large Language Models' (LLM) reasoning can be improved using test-time aggregation strategies, i.e., generating multiple samples and voting among generated samples. Refinement offers an alternative by using LLM-generated feedback to improve solution quality. We propose MAgICoRe, which avoids excessive refinement by categorizing problem difficulty as easy or hard.
  arXiv  Detail & Related papers  (2024-09-18T17:12:41Z)
• SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories [55.161075901665946]
  Super aims to capture the realistic challenges faced by researchers working with Machine Learning (ML) and Natural Language Processing (NLP) research repositories. Our benchmark comprises three distinct problem sets: 45 end-to-end problems with annotated expert solutions, 152 sub problems derived from the expert set that focus on specific challenges, and 602 automatically generated problems for larger-scale development. We show that state-of-the-art approaches struggle to solve these problems with the best model (GPT-4o) solving only 16.3% of the end-to-end set, and 46.1% of the scenarios.
  arXiv  Detail & Related papers  (2024-09-11T17:37:48Z)
• Building Math Agents with Multi-Turn Iterative Preference Learning [56.71330214021884]
  This paper studies the complementary direct preference learning approach to further improve model performance. Existing direct preference learning algorithms are originally designed for the single-turn chat task. We introduce a multi-turn direct preference learning framework, tailored for this context.
  arXiv  Detail & Related papers  (2024-09-04T02:41:04Z)
• What's Wrong with Your Code Generated by Large Language Models? An Extensive Study [80.18342600996601]
  Large language models (LLMs) produce code that is shorter yet more complicated as compared to canonical solutions. We develop a taxonomy of bugs for incorrect codes that includes three categories and 12 sub-categories, and analyze the root cause for common bug types. We propose a novel training-free iterative method that introduces self-critique, enabling LLMs to critique and correct their generated code based on bug types and compiler feedback.
  arXiv  Detail & Related papers  (2024-07-08T17:27:17Z)
• Navigating the Labyrinth: Evaluating and Enhancing LLMs' Ability to Reason About Search Problems [59.72548591120689]
  We introduce a new benchmark, SearchBench, containing 11 unique search problem types. We show that even the most advanced LLMs fail to solve these problems end-to-end in text. Instructing LLMs to generate code that solves the problem helps, but only slightly, e.g., GPT4's performance rises to 11.7%.
  arXiv  Detail & Related papers  (2024-06-18T00:44:58Z)
• MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time [51.5039731721706]
  MindStar is a purely inference-based searching method for large language models. It formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths. It significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1.
  arXiv  Detail & Related papers  (2024-05-25T15:07:33Z)
• Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems [50.76385564061713]
  Chain-of-Thought (CoT) prompting has enhanced the performance of Large Language Models (LLMs) across various reasoning tasks. CoT usually suffers from three pitfalls: semantic misunderstanding errors, calculation errors, and step-missing errors. We propose Deeply Understanding the Problems (DUP) to improve the LLMs' math problem-solving ability by addressing semantic misunderstanding errors.
  arXiv  Detail & Related papers  (2024-04-23T12:16:05Z)
• Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models [102.72940700598055]
  In reasoning tasks, even a minor error can cascade into inaccurate results. We develop a method that avoids introducing external resources, relying instead on perturbations to the input. Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks.
  arXiv  Detail & Related papers  (2024-03-04T16:21:54Z)
• Tool-Augmented Reward Modeling [58.381678612409]
  We propose a tool-augmented preference modeling approach, named Themis, to address limitations by empowering RMs with access to external environments. Our study delves into the integration of external tools into RMs, enabling them to interact with diverse external sources. In human evaluations, RLHF trained with Themis attains an average win rate of 32% when compared to baselines.
  arXiv  Detail & Related papers  (2023-10-02T09:47:40Z)
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning [70.65666982566655]
  Permutation flow shop scheduling (PFSS) is widely used in manufacturing systems. We propose to train the model via expert-driven imitation learning, which accelerates convergence more stably and accurately. Our model's network parameters are reduced to only 37% of theirs, and the solution gap of our model towards the expert solutions decreases from 6.8% to 1.3% on average.
  arXiv  Detail & Related papers  (2022-10-31T09:46:26Z)
• Logic-Guided Data Augmentation and Regularization for Consistent Question Answering [55.05667583529711]
  This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions. Our method leverages logical and linguistic knowledge to augment labeled training data and then uses a consistency-based regularizer to train the model.
  arXiv  Detail & Related papers  (2020-04-21T17:03:08Z)

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.