MACO: Multifaceted Research Acronym

Updated 12 July 2026

MACO is a multifaceted acronym representing distinct concepts such as modified ant colony optimization, multi-agent coordination, and magnitude constrained optimization across various fields.
Its applications span swarm-intelligence for routing, cooperative learning benchmarks with significant communication savings, and efficient hardware architectures with notable performance gains.
The term’s disambiguation is critical because papers citing MACO address diverse technical constructs, necessitating clear context based on domain-specific usage.

Searching arXiv for papers using the term “MACO” across research domains. MACO is a recurrent acronym in contemporary research rather than a single standardized concept. In the arXiv literature, it denotes several distinct algorithms, benchmarks, and systems, including swarm-intelligence methods for routing and community detection, a cooperative multi-agent benchmark, a Fourier-domain feature-visualization method, multimodal and medical-learning frameworks, a loosely-coupled GEMM processor architecture, a distributed online-learning algorithm for LLM response selection, and a multi-agent LLM framework for CGRA hardware/software co-design (Jindal et al., 2020, Jin et al., 2013, Wang et al., 2021, Fel et al., 2023, Zhang et al., 2023, Sui et al., 2024, Dai et al., 3 Jan 2025, Jiang et al., 16 Sep 2025).

1. Scope and nomenclature

The term MACO appears in multiple, unrelated technical lineages. Some uses are all-uppercase acronym expansions, such as MAgnitude Constrained Optimization and Modality Adversarial and COntrastive; others function primarily as project names or benchmark names, such as the Multi-Agent COordination benchmark. Capitalization also varies, with MaCo used in several medical-imaging papers (Fel et al., 2023, Huang et al., 2023, Wang et al., 2024).

Domain	Meaning or usage	Representative paper
Network routing	Modified Ant Colony Optimization	(Jindal et al., 2020)
Community detection	Ant colony optimization with a new random walk model	(Jin et al., 2013)
Cooperative MARL	Multi-Agent COordination benchmark	(Wang et al., 2021)
Feature visualization	MAgnitude Constrained Optimization	(Fel et al., 2023)
MMKGC	Modality Adversarial and Contrastive framework	(Zhang et al., 2023)
GEMM architecture	Loosely-coupled multi-core processor for GEMM	(Sui et al., 2024)
Online LLM response identification	Multi-Agent Conversational Online Learning	(Dai et al., 3 Jan 2025)
CGRA co-design	Multi-agent LLM-based HW/SW co-design framework	(Jiang et al., 16 Sep 2025)

This multiplicity is technically important because papers that cite “MACO” often refer to entirely different object classes: an optimization heuristic, a benchmark, a systems architecture, or a learning framework. This suggests that “MACO” operates as an acronymic namespace rather than a unified research program.

2. Swarm-intelligence and networking lineages

One early usage in networking appears in load balancing for packet-switched networks. The paper “Multiple ant-bee colony optimization for load balancing in packet-switched networks” describes a new approach for finding different routes using swarm intelligence techniques and multi colony algorithms, with different colonies of ants and bees appointed as intelligent agents to monitor the network and update routing information; it characterizes the method as an improved version of MACO and reports a tangible improvement in simulation (Kashefikia et al., 2011).

In vehicular networking, MACO is explicitly defined as Modified Ant Colony Optimization for congestion-aware routing in VANETs. The road network is modeled as $G(N,E)$ , routing is biased toward a non-congested path with minimum pheromone value, the selected road is updated with Ph[road]++, and non-selected roads are updated with Ph[Nroad]--. The same line of work introduces MACO-P, which adds preemptive traffic signal control, and GMACO-P, a CUDA implementation that parallelizes route selection and signal handling. On a real map of North-West Delhi with 52 nodes and 128 roads, GMACO-P reduces overall travel time at 4500 vehicles by 74.53% versus Dijkstra, 76.18% versus ACO, 78.00% versus MACO, and 52.12% versus MACO-P (Jindal et al., 2020).

A separate swarm-based usage is the community-detection algorithm in “Ant Colony Optimization with a New Random Walk Model for Community Detection in Complex Networks” (Jin et al., 2013). Here the input network is $N=(V,E)$ , the pheromone-weighted adjacency is $M=(a_{ij}b_{ij})$ , and the random-walk transition rule is

$p_{ij}=\frac{m_{ij}}{\sum_r m_{ir}}.$

Each ant constructs a local solution through a Markov random walk heuristic, the ant solutions are aggregated through a clustering-ensemble idea, and the pheromone matrix is updated by

$B \leftarrow p \cdot B + solution.$

The method progressively strengthens within-community links and weakens between-community links. With the suggested settings $T=20$ , $S=100$ , $p=0.6$ , and $l \approx 20$ , the paper states a practical complexity of $O(n^2)$ and reports strong performance on Newman and Lancichinetti benchmarks as well as several real-world networks (Jin et al., 2013).

Networking also contains a related but distinct shorthand, MAC-centered cooperation, for a cross-layer design combining network coding, multi-packet reception, and an improved fairness policy in wireless networks. That work reports super-additive gains of up to 6.3 times that of routing with the standard IEEE 802.11 MAC (Cloud et al., 2011). It is not the same MACO as the ant-colony papers, but it illustrates the same acronym collision within network research.

3. Coordination, MARL, and online decision-making

In cooperative reinforcement learning, MACO refers to the Multi-Agent COordination benchmark introduced with CASEC, a method for learning context-aware sparse coordination graphs (Wang et al., 2021). The benchmark collects classic coordination problems, increases their difficulty, and classifies them into different types. Its six representative tasks are Aloha, Pursuit, Hallway, Sensor, Gather, and Disperse. The benchmark was designed to stress-test context-dependent interaction structure, and the paper reports typical communication savings of 80% on Aloha, 70% on Pursuit, 50% on Hallway, 90% on Sensor, 30% on Gather, and 60% on Disperse (Wang et al., 2021).

The benchmark was subsequently used by “Non-Linear Coordination Graphs,” which characterizes MACO as covering classic coordination tasks while increasing their complexity, and as having a high demand on the sophistication of agent coordination (Kang et al., 2022). That paper argues that conventional coordination graphs are limited by linear decomposition and introduces a non-linear mixing network with LeakyReLU structure. On MACO, it reports that NL-CG outperforms conventional CGs significantly, and that the iterative optimization method reduces runtime by about 50% to 65% compared with exhaustive enumeration while maintaining very similar $N=(V,E)$ 0-values (Kang et al., 2022).

A different multi-agent usage appears in online LLM response identification. There, MACO expands to Multi-Agent Conversational Online Learning for Adaptive LLM Response Identification and addresses the problem of selecting the best response from a finite response pool while adapting to user preferences (Dai et al., 3 Jan 2025). The reward model is linear,

$N=(V,E)$ 1

and the main theoretical guarantee states

$N=(V,E)$ 2

with a lower bound of $N=(V,E)$ 3. The paper also gives a communication cost of $N=(V,E)$ 4, emphasizes that the conversational mechanism eliminates the traditional computing-intensive “G-optimal design,” and reports lower cumulative regret and faster execution than competing baselines in experiments using Llama-3-8B-Instruct together with Google and OpenAI embedding models (Dai et al., 3 Jan 2025).

4. Feature visualization, explainability, and medical imaging

In interpretability research, MACO is MAgnitude Constrained Optimization, a Fourier-domain feature-visualization method designed to scale to modern deep vision models (Fel et al., 2023). The central construction decomposes the spectrum into magnitude and phase, fixes the magnitude to an average natural-image spectrum,

$N=(V,E)$ 5

and optimizes only the phase,

$N=(V,E)$ 6

The method uses only random crop / resize and additive uniform noise as augmentations, provides a transparency or spatial-importance mask by accumulating $N=(V,E)$ 7, and is evaluated on FlexiViT, ViT, and ResNetV2 with Plausibility score, FID, and Transferability score. Reported results include, for FlexiViT, a plausibility score of 1473 versus 1815 for Fourier and 1866 for CBR, and an FID of 230.68 versus 250.25 and 247.12 respectively (Fel et al., 2023). A later thesis situates MACO alongside CRAFT for concept visualization and reports a psychophysics study with 174 Prolific participants (Fel, 3 Feb 2025).

Medical imaging contains two further, unrelated MaCo formulations. In chest radiography, MaCo is a Masked Contrastive chest X-ray foundation model that combines masked image reconstruction with image-report contrastive learning and a correlation weighting mechanism (Huang et al., 2023). It is pretrained on MIMIC-CXR v2 with 377,110 chest X-rays and 227,827 reports, and its reported downstream results include 91.2 / 92.2 / 93.3 AUC on RSNA at 1% / 10% / 100% labels, 58.8 / 70.7 / 89.6 Dice on SIIM pneumothorax segmentation, and 0.267 mIoU with 1.176 CNR on zero-shot phrase grounding (Huang et al., 2023).

In scribble-supervised segmentation, MaCo stands for Masked context modeling and Continuous pseudo labels (Wang et al., 2024). The method uses an attention-based masking strategy with best settings $N=(V,E)$ 8, masking ratio $N=(V,E)$ 9, and patch size $M=(a_{ij}b_{ij})$ 0, together with continuous pseudo labels defined through an exponential distance decay. Its reported average Dice scores are 90.4 on ACDC, 88.5 on MSCMRseg, and 80.5 on NCI-ISBI, and the paper states that even after reducing scribble pixels by 50%, the model retains about 96.7% of its performance relative to full scribbles (Wang et al., 2024).

5. Hardware architectures and LLM-driven co-design

In computer architecture, MACO denotes a loosely-coupled multi-core processor optimized for GEMM-related applications (Sui et al., 2024). The architecture contains up to 16 homogeneous compute nodes connected by a cache-coherent 2D mesh NoC; each node couples a 64-bit out-of-order, four-issue CPU core with its own matrix multiplication acceleration engine (MMAE). Each MMAE uses a 4×4 two-dimensional systolic array with 192KB of on-chip buffers and supports 2-way FP32 and 4-way FP16 parallel computation. The paper introduces the Matrix Processing Assist Instruction Set (MPAIS), with categories for data migration, GEMM computation, and task management, including instructions such as MA_CFG, MA_MOVE, MA_INIT, MA_STASH, MA_READ, MA_STATE, and MA_CLEAR (Sui et al., 2024).

That processor paper defines peak performance as $M=(a_{ij}b_{ij})$ 1 and reports CPU peak performance of 35.2 GFLOPS (FP64) / 71 GFLOPS (FP32) and MMAE peak performance of 80 GFLOPS (FP64) / 160 GFLOPS (FP32) / 320 GFLOPS (FP16) (Sui et al., 2024). It further states that the MMAE area is only 25% of the CPU core area while delivering more than 2× peak GFLOPS and 25% lower power, with approximately 9× better area efficiency and 2× better theoretical computation efficiency. In scalability experiments, MACO incurs about a 10% average performance loss as the node count increases but still maintains approximately 90% computational efficiency. In deep-learning benchmarks it achieves average performance gains of 1.35× over RASA and 1.30× over Gemmini, reaching up to 1.1 TFLOPS with 88% computational efficiency (Sui et al., 2024).

A later hardware usage is “MACO: A Multi-Agent LLM-Based Hardware/Software Co-Design Framework for CGRAs” (Jiang et al., 16 Sep 2025). This framework decomposes CGRA design into four stages: HW/SW co-design, Design error correction, Best design selection, and Evaluation & Feedback. It uses OpenCGRA and the MapFixer flow for validation, keeps both hardware parameters and compilation parameters in the search space, and introduces an adaptive self-learning mechanism with confidence update

$M=(a_{ij}b_{ij})$ 2

The paper evaluates the method on 8 representative kernels across embedded, machine learning, and high-performance computing, namely fir, fft, latnrm, spmv, conv, relu, mvt, and gemm, using OpenCGRA for RTL generation and Synopsys Design Compiler under the ASAP 7 nm technology library (Jiang et al., 16 Sep 2025).

The reported headline results are average power reductions of 59.4% versus Qwen few-shot, 48.9% versus Qwen domain-augmented, and 27.1% versus manual design, together with an average power-efficiency improvement of 36.8% compared with approaches that do not perform HW/SW co-design (Jiang et al., 16 Sep 2025). For the spmv kernel, MACO selects a 3×3 tile size, 8 FU types, 10 config memory entries, a KingMesh topology, unrolling factor 3, and vectorization factor 2. The physical implementation case study reports a complete GDSII for a 4×4 CGRA with area 2.99 mm² and post-layout average power 30.49 mW at 0.7 V and 435 MHz (Jiang et al., 16 Sep 2025).

6. Multimodal knowledge graphs and persistent ambiguity

In knowledge-graph completion, MACO expands to Modality Adversarial and Contrastive and addresses missing modalities in MMKGC (Zhang et al., 2023). The framework uses an L-layer R-GCN structural encoder, a Vision Transformer (ViT) visual encoder, a conditional generator

$M=(a_{ij}b_{ij})$ 3

a discriminator over structural-visual pairs, and a cross-modal contrastive loss

$M=(a_{ij}b_{ij})$ 4

Experiments are conducted on FB15K-237 with missing-modality rates of 20%, 40%, 60%, and 80%, and the method is tested as a plug-in enhancement for IKRL, TBKGC, and RSME (Zhang et al., 2023).

A recurring misconception is to treat all papers named MACO or MaCo as members of one method family. The corpus shows the opposite. MACA is a different framework, “Multi-Agent Coordination Adaptation via Structure-Guided Orchestration” (Li et al., 25 May 2026); MAKO is a 350 micron pathfinder instrument for submillimeter imaging arrays (Swenson et al., 2012); and MaCo-GAN is a manifold-contrastive GAN framework for single-image super-resolution (Han et al., 3 Jun 2026). Even when neighboring papers share multi-agent, contrastive, or hardware language, their technical objects, assumptions, and evaluation protocols are unrelated.

The most defensible encyclopedic interpretation is therefore lexical rather than doctrinal. MACO names a set of domain-specific constructs whose only commonality is acronym reuse. A plausible implication is that any citation, implementation, or benchmark discussion involving MACO requires immediate disambiguation by field, expansion, and arXiv identifier.