SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.19934 · EMNLP · 2024

From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis

Wei Wu, Rui Yan, Jian Guan, Chuanqi Cheng

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 7 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.19934.json · badge: /api/ran/2406.19934.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
steven-ccq/visualreasoner canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
steven-ccq/VisualReasoner community
Papers with Code archive
6 ran · 3 no recorded run
jianguanthu/amor community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
answer Ran
ran; our contract draft was wrong, not the code
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("dacfeec0efdbe208")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

call_planner Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("428895c463d6dcad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

check_blurry Ran
ran, violated the contract we drafted
steven-ccq/visualreasoner/utils.py
pointer only (licence: NONE) · get_code("a53aebe1a36db9fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/visualreasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

counting Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("f3d58ce277c8c74e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_decompose_prompt Ran
ran; our contract draft was wrong, not the code
jianguanthu/amor/code/prompts.py
pointer only (licence: NONE) · get_code("bd4037a865476156")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

grounding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("ba86a02002985352")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

highlight Ran
ran; our contract draft was wrong, not the code
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("4b9837cd50427259")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ocr Ran
ran; our contract draft was wrong, not the code
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("5aba539bdc54b8a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

execuate Not yet run
unverified (harvested, no recorded run)
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("c1244199cb822fe3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

generate Not yet run
unverified (harvested, no recorded run)
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("c626111fb20cdab1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

reasoner Not yet run
unverified (harvested, no recorded run)
steven-ccq/VisualReasoner/utils.py
pointer only (licence: NONE) · get_code("27b778253912dae6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, steven-ccq/VisualReasoner when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_decompose_prompt
brick of this paper's assembly: entry
1 other paper
1 dated earlier
2402.01469 (2024-02)
AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We explore multi-step reasoning in visionlanguage models (VLMs). The problem is challenging, as reasoning data consisting of multiple steps of visual and language processing are barely available. To overcome the challenge, we first introduce a least-to-most visual reasoning paradigm, which interleaves steps of decomposing a question into sub-questions and invoking external tools for resolving subquestions. Based on the paradigm, we further propose a novel data synthesis approach that can automatically create questions and multistep reasoning paths for an image in a bottomup manner. Our approach divides the complex synthesis task into a few simple sub-tasks, and (almost entirely) relies on open-sourced models to accomplish the sub-tasks. Therefore, the entire synthesis process is reproducible and cost-efficient, and the synthesized data is quality guaranteed. With the approach, we construct 50k visual reasoning examples. Then, we develop a visual reasoner through supervised fine-tuning, which is capable of generally enhancing the reasoning abilities of a wide range of existing VLMs in a plug-and-play fashion. Extensive experiments indicate that the visual reasoner can consistently and significantly improve four VLMs on four VQA benchmarks. Our code and dataset are available at https:// github.com/steven-ccq/VisualReasoner.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.19934")
get_code_for_paper("2406.19934")
have("2406.19934")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.19934.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.19934.svg)](https://syntology.ai/paper/2406.19934)

Connect an agent — have() is free.