SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.02519 · 2023

Creative Agents: Empowering Agents with Imagination for Creative Tasks

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 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/2312.02519.json · badge: /api/ran/2312.02519.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
pku-rl/creative-agents canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
block2num Ran
ran, honoured the contract we drafted
pku-rl/creative-agents/block2num.py
pointer only (licence: NONE) · get_code("b1c2838ce19a2767")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-rl/creative-agents 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 Ran
ran, violated the contract we drafted
pku-rl/creative-agents/cot_gpt4.py
pointer only (licence: NONE) · get_code("d3928f6429ce22ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-rl/creative-agents 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.

conv1x1x1 Ran
ran; our contract draft was wrong, not the code
pku-rl/creative-agents/BC_Controller/vox2seq/model.py
pointer only (licence: NONE) · get_code("213ccc8fb87ee8d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-rl/creative-agents 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.

conv3x3x3 Ran
ran; our contract draft was wrong, not the code
pku-rl/creative-agents/BC_Controller/vox2seq/model.py
pointer only (licence: NONE) · get_code("c3b215555357b9d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-rl/creative-agents 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.

round1 Not yet run
unverified (harvested, no recorded run)
pku-rl/creative-agents/cot_gpt4.py
pointer only (licence: NONE) · get_code("53d35ee23e46b1d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-rl/creative-agents 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.

round1 Not yet run
unverified (harvested, no recorded run)
pku-rl/creative-agents/diffusion_gpt4v.py
pointer only (licence: NONE) · get_code("635257e85629c12b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-rl/creative-agents 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.

round2 Not yet run
unverified (harvested, no recorded run)
pku-rl/creative-agents/cot_gpt4.py
pointer only (licence: NONE) · get_code("39fc09fc88a4749f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-rl/creative-agents 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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
conv3x3x3 19 other papers
19 dated earlier
1711.08580 (2017-11)
3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes
1711.09577 (2017-11)
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
1908.01373 (2019-08)
Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network
and 16 more not named here
conv1x1x1 6 other papers
6 dated earlier · 1 only as an assembly brick
1711.09577 (2017-11)
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
2003.10432 (2020-03)
Atlas: End-to-End 3D Scene Reconstruction from Posed Images
2004.04968 (2020-04)
Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
and 3 more not named here

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 study building embodied agents for open-ended creative tasks. While existing methods build instruction-following agents that can perform diverse open-ended tasks, none of them demonstrates creativity -- the ability to give novel and diverse solutions implicit in the language instructions. This limitation comes from their inability to convert abstract language instructions into concrete goals and perform long-horizon planning for such complicated goals. Given the observation that humans perform creative tasks with imagination, we propose a class of solutions, where the controller is enhanced with an imaginator generating detailed imaginations of task outcomes conditioned on language instructions. We introduce several approaches to implementing the components of creative agents. We implement the imaginator with either a large language model for textual imagination or a diffusion model for visual imagination. The controller can either be a behavior-cloning policy or a pre-trained foundation model generating executable codes in the environment. We benchmark creative tasks with the challenging open-world game Minecraft, where the agents create diverse buildings given free-form language instructions. We propose novel evaluation metrics for open-ended creative tasks utilizing GPT-4V, which holds many advantages over existing metrics. We perform a detailed experimental analysis of creative agents, showing that creative agents are the first AI agents accomplishing diverse building creation in the survival mode of Minecraft. Our benchmark and models are open-source for future research on creative agents (https://github.com/PKU-RL/Creative-Agents).

For agents

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

get_harvested_code_for_paper("2312.02519")
get_code_for_paper("2312.02519")
have("2312.02519")

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

curl https://syntology.ai/api/ran/2312.02519.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.02519.svg)](https://syntology.ai/paper/2312.02519)

Connect an agent — have() is free.