Papers › R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large...

R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models

23 Oct 2024arXiv:2410.17885archive 2025-07-28

Linger Deng, Yuliang Liu, Bohan Li, Dongliang Luo, Liang Wu, Chengquan Zhang, Pengyuan Lyu, Ziyang Zhang, Gang Zhang, Errui Ding, Yingying Zhu, Xiang Bai

Existing Large Multimodal Models (LMMs) struggle with mathematical geometric reasoning due to a lack of high-quality image-text paired data. Current geometric data generation approaches, which apply preset templates to generate geometric data or use Large Language Models (LLMs) to rephrase questions and answers (Q&A), unavoidably limit data accuracy and diversity. To synthesize higher-quality data, we propose a two-stage Reverse Chain-of-Thought (R-CoT) geometry problem generation pipeline. First, we introduce GeoChain to produce high-fidelity geometric images and corresponding descriptions highlighting relations among geometric elements. We then design a Reverse A&Q method that reasons step-by-step based on the descriptions and generates questions in reverse from the reasoning results. Experiments demonstrate that the proposed method brings significant and consistent improvements on multiple LMM baselines, achieving new performance records in the 2B, 7B, and 8B settings. Notably, R-CoT-8B significantly outperforms previous state-of-the-art open-source mathematical models by 16.6% on MathVista and 9.2% on GeoQA, while also surpassing the closed-source model GPT-4o by an average of 13% across both datasets. The code is available at https://github.com/dle666/R-CoT.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 21 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 3 violated, 3 with no contract checked; 14 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 13 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 20 ran (6 with no instrument failure; 14 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 20 samples that ran have no recorded date.

dle666/r-cot officialmentioned in papermentioned on GitHubpytorchSyntology: 21 samples, 20 ran (14 instrument-failed) · 1 unverified report
yuliang-liu/monkey mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models (arXiv:2311.06607; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 3 violated, 3 with no contract checked; 14 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · violated contract
13ran · our draft was wrong
1ran; the contract check could not run
3ran
1unverified

Licence: 21 of the 21 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 dle666/r-cot. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

dle666/r-cot official repository 21 samples, 20 ran (14 instrument-failed) · 1 unverified
build_transform in 170 papers GeoQA_test/model_vqa_rcot2b.py ran · our draft was wrong no licence file found · pointer only · 57e95166ade5f25c · report fixture: signature input_size:int/0/int · returned Compose · level recorded 2026-09-24
conv2text R-CoT7B-main/data_mix.py ran · our draft was wrong no licence file found · pointer only · 8b526bb8355d1e07 · report fixture: signature sources:list/1/dict · returned str · level recorded 2026-09-26
create_one_query in 6 papers MathVista_eval/evaluation/build_query.py ran · our draft was wrong no licence file found · pointer only · ecc1e50a10f04fa0 · report fixture: signature problem:dict/0/?, examples:list/1/dict, shot_num:int/0/int, shot_type:str/0/str, use_caption:bool/0/bool, use_ocr:bool/0/bool · returned str · level recorded 2026-09-22
dynamic_preprocess in 40 papers GeoQA_test/model_vqa_rcot2b.py ran · our draft was wrong no licence file found · pointer only · 93f012e28ba3ca67 · report fixture: signature image:Image/0/?, min_num:int/0/int, max_num:int/0/int, image_size:int/0/int, use_thumbnail:bool/0/bool · returned tuple · level recorded 2026-09-22
evaluate_code in 7 papers MathVista_eval/evaluation/generate_response_geo_qwenvl.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 6a7cafccc873c34d · report fixture: signature code_string:str/0/str · returned tuple · level recorded 2026-09-22
extract_answer in 112 papers MathVista_eval/evaluation/extract_answer.py ran no licence file found · pointer only · c1eaa5bf4d5f383d · report fixture: signature response:str/0/str, problem:dict/0/?, quick_extract:bool/0/bool · returned str · level recorded 2026-09-26
extract_choice in 9 papers GeoQA_test/geo_acc_calculate.py ran fingerprinted no licence file found · pointer only · ababfc3520297c21 · report fixture: signature q:str/0/str, answer:str/0/str, i:int/0/int · returned str · level recorded 2026-09-26
find_closest_aspect_ratio in 45 papers GeoQA_test/model_vqa_rcot2b.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · bd77f5f8067f18e9 · report fixture: signature aspect_ratio:float/0/float, target_ratios:list/1/tuple, width:int/0/int, height:int/0/int, image_size:int/0/int · returned tuple · level recorded 2026-09-22
get_chunk in 197 papers GeoQA_test/model_vqa_rcot7b.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 42a46570620cd9fa · report fixture: signature lst:list/1/int, n:int/0/int, k:int/0/int · returned list · level recorded, date not recorded
get_most_similar in 8 papers MathVista_eval/evaluation/calculate_score.py ran · our draft was wrong no licence file found · pointer only · c28eb86a8d14e4ed · report fixture: signature prediction:str/0/str, choices:list/1/str · returned str · level recorded 2026-09-25
normalize_extracted_answer in 9 papers MathVista_eval/evaluation/calculate_score.py ran no licence file found · pointer only · 0da7b678f70430a0 · report fixture: signature extraction:str/0/str, choices:list/1/str, question_type:str/0/str, answer_type:str/0/str, precision:int/0/int · returned str · level recorded 2026-09-26
read_csv in 60 papers MathVista_eval/utilities.py ran · our draft was wrong no licence file found · pointer only · 1694e6d4f46ff13e · report fixture: signature file:str/0/str · returned list · level recorded 2026-09-25
read_json in 250 papers MathVista_eval/utilities.py ran · our draft was wrong no licence file found · pointer only · 9ffa907555068ff3 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-22
read_pandas_csv MathVista_eval/utilities.py ran · our draft was wrong no licence file found · pointer only · 32ae2fb99638aba7 · report fixture: signature csv_path:str/0/str · returned DataFrame · level recorded 2026-09-25
refine_caption in 5 papers MathVista_eval/evaluation/build_query.py ran · our draft was wrong fingerprinted no licence file found · pointer only · d027e6e473c9fcd4 · report fixture: signature caption:str/0/str · returned str · level recorded 2026-09-22
refine_ocr in 5 papers MathVista_eval/evaluation/build_query.py ran · our draft was wrong fingerprinted no licence file found · pointer only · bfd184123c9012c3 · report fixture: signature ocr:str/0/str · returned str · level recorded 2026-09-22
safe_equal in 9 papers MathVista_eval/evaluation/calculate_score.py ran · violated contract fingerprinted no licence file found · pointer only · e7a23ea3695f6437 · report fixture: signature prediction:int/0/int, answer:int/0/int · returned bool · level recorded 2026-09-25
split_list in 223 papers GeoQA_test/model_vqa_rcot7b.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 076c252c52cbb161 · report fixture: signature lst:list/1/int, n:int/0/int · returned list · level recorded, date not recorded
verify_extraction in 5 papers MathVista_eval/evaluation/extract_answer.py ran · violated contract no licence file found · pointer only · a7852c6582967cfa · report fixture: signature extraction:str/0/str · returned bool · level recorded 2026-09-26
verify_response in 6 papers MathVista_eval/evaluation/generate_response_geo_qwenvl.py ran · violated contract no licence file found · pointer only · d6259b0d9750cac7 · report fixture: signature response:str/0/str · returned bool · level recorded 2026-09-22
calculate_accuracy in 65 papers GeoQA_test/geo_acc_calculate.py unverified no licence file found · pointer only · 6d0fed830d6f1474 · report

Tasks

Diversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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