SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.10933 · 2026

CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control

Alexander Denker, Riccardo Barbano, Francisco Vargas, Željko Kereta, Runchang Li

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 6 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2602.10933.json · badge: /api/ran/2602.10933.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
rb876/multiagent-diffusion-soc community
Papers with Code archive
7 ran · 1 no recorded run
FunctionStatusWhere it lives
SDE Ran
ran on a synthesized input · constructed an object; no result was computed
rb876/multiagent-diffusion-soc/src/trainer/soc_am_ft.py
pointer only (licence: NONE) · get_code("5666b720ec085d22")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rb876/multiagent-diffusion-soc 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.

_to_tensor Ran
ran; our contract draft was wrong, not the code
rb876/multiagent-diffusion-soc/src/trainer/soc_am_ft.py
pointer only (licence: NONE) · get_code("a3cf841e8a0e6469")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rb876/multiagent-diffusion-soc 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.

compute_grad_norms Ran
ran; our contract draft was wrong, not the code
rb876/multiagent-diffusion-soc/src/trainer/soc_am_ft.py
pointer only (licence: NONE) · get_code("0b1f63567c93cd99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rb876/multiagent-diffusion-soc 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.

compute_vectorized_guidance_grads Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rb876/multiagent-diffusion-soc/src/trainer/soc_am_ft.py
pointer only (licence: NONE) · get_code("68c92df9b8342eb9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rb876/multiagent-diffusion-soc 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_tweedy_estimate Ran
ran; our contract draft was wrong, not the code
rb876/multiagent-diffusion-soc/src/trainer/soc_am_ft.py
pointer only (licence: NONE) · get_code("d8a20d8fd32164c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rb876/multiagent-diffusion-soc 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.

make_ve_sde Ran
ran; our contract draft was wrong, not the code
rb876/multiagent-diffusion-soc/src/trainer/soc_am_ft.py
pointer only (licence: NONE) · get_code("eed8619580bb3289")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rb876/multiagent-diffusion-soc 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.

make_vp_sde Ran
ran; our contract draft was wrong, not the code
rb876/multiagent-diffusion-soc/src/trainer/soc_am_ft.py
pointer only (licence: NONE) · get_code("63dd43b77c1c2d36")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rb876/multiagent-diffusion-soc 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.

control_wise_adjoint_matching Not yet run
unverified (harvested, no recorded run)
rb876/multiagent-diffusion-soc/src/trainer/soc_am_ft.py
pointer only (licence: NONE) · get_code("585607aea6153a71")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rb876/multiagent-diffusion-soc 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

Continuous-time generative models have achieved remarkable success in image restoration and synthesis. However, controlling the composition of multiple pretrained models remains an open challenge. Current approaches largely treat composition as an algebraic composition of probability densities, such as via products or mixtures of experts. This perspective assumes the target distribution is known explicitly, which is almost never the case. In this work, we propose a different paradigm that formulates compositional generation as a cooperative Stochastic Optimal Control problem. Rather than combining probability densities, we treat pre-trained diffusion models as interacting agents whose diffusion trajectories are jointly steered, via optimal control, toward a shared objective defined on their aggregated output. We validate our framework on conditional MNIST generation and compare it against a naïve inference-time DPS-style baseline replacing learned cooperative control with per-step gradient guidance. https://github.com/rb876/multiagent-diffusion-soc/

For agents

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

get_harvested_code_for_paper("2602.10933")
get_code_for_paper("2602.10933")
have("2602.10933")

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

curl https://syntology.ai/api/ran/2602.10933.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.10933.svg)](https://syntology.ai/paper/2602.10933)

Connect an agent — have() is free.