Papers › Cumulative Reasoning with Large Language Models

Cumulative Reasoning with Large Language Models

8 Aug 2023arXiv:2308.04371archive 2025-07-28

Yifan Zhang, Jingqin Yang, Yang Yuan, Andrew Chi-Chih Yao

Despite the recent advancements in language models (LMs), their ability to solve complex problems remains limited. This paper introduces Cumulative Reasoning (CR), a novel approach that utilizes LMs cumulatively and iteratively, mirroring human thought processes for problem-solving. CR decomposes tasks into smaller, manageable components and leverages previous propositions for effective composition, significantly enhancing problem-solving capabilities. We demonstrate CR's superiority 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 the prior state-of-the-art. Additionally, CR sets new state-of-the-art on the MATH dataset, achieving a 4.2% increase from previous methods and a 43% relative improvement in the most challenging problems. By extending CR to incorporate a code environment without external aids like retrieval or web browsing, we further harness the computational and logical reasoning capabilities of LMs, achieving a remarkable 72.2% accuracy on the MATH dataset and outperforming the PAL/PoT method by 38.8%. Our work not only sets new state-of-the-art but also paves the way toward more sophisticated AI reasoning methods. The code is available at https://github.com/iiis-ai/cumulative-reasoning.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.04371")

Code

Syntology Ran 5 of 6 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

iiis-ai/cumulative-reasoning officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 5 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
3ran
1unverified

Licence: 6 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from iiis-ai/cumulative-reasoning. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

encode_with_messages_format iiis-ai/cumulative-reasoning/CR-Agent/train/finetune.py official repository ran · our draft was wrong no licence file found · pointer only · bc1a96ec28a11a5f · report
encode_with_prompt_completion_format iiis-ai/cumulative-reasoning/CR-Agent/train/finetune.py official repository ran · our draft was wrong no licence file found · pointer only · 1906977026be9a86 · report
get_time_str iiis-ai/cumulative-reasoning/MATH/math-complex-cot.py official repository ran fingerprinted no licence file found · pointer only · da8f1e8f740ab7e8 · report
is_sure iiis-ai/cumulative-reasoning/Game24/game24-openai.py official repository ran no licence file found · pointer only · 8e901d4768f46792 · report
run iiis-ai/cumulative-reasoning/Game24/game24-openai.py official repository ran no licence file found · pointer only · ae7597e49bb0a65a · report
try_wrapper iiis-ai/cumulative-reasoning/MATH/math-complex-cot.py official repository unverified no licence file found · pointer only · bcfffe8211f7aac9 · report

Tasks

Decision MakingLogical ReasoningMathMath Word Problem Solving

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Math Word Problem Solving MATH CR (GPT-4-turbo model, w/ code) Accuracy 72.2 #14 of 135 Archive leaderboard report
Math Word Problem Solving MATH CR (GPT-4 model, w/o code) Accuracy 58.0 #30 of 135 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

fail

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections