Applied Sciences

Research

Jump to: Review

24 pages, 4245 KB

Open AccessArticle

AgentProphet: Source-Aware Multi-Agent Emerging Technology Forecasting for Upstream Decision-Making in AI-Based IoT Systems

by Taorui Chen, Huan Wang and Guo Kai

Appl. Sci. 2026, 16(13), 6787; https://doi.org/10.3390/app16136787 - 6 Jul 2026

Abstract

AI-based internet of things (IoT) systems increasingly require upstream decision-making mechanisms to identify emerging technologies that may shape future sensing–memory–communication–computation capabilities (SMCC). However, early technology signals are often weak, fragmented, and distributed across heterogeneous sources with different reliability levels, making reliable capability planning [...] Read more.

AI-based internet of things (IoT) systems increasingly require upstream decision-making mechanisms to identify emerging technologies that may shape future sensing–memory–communication–computation capabilities (SMCC). However, early technology signals are often weak, fragmented, and distributed across heterogeneous sources with different reliability levels, making reliable capability planning difficult. This paper proposes AgentProphet, a source-aware multi-agent framework for emerging AI technology forecasting in AI-based IoT systems. AgentProphet integrates evidence from papers, patents, policy documents, and reports into a unified concept space, and combines role-specialized agent reasoning, source-aware confidence calibration, and critic-guided refinement to generate target-year technology rankings. In the main balanced weak-signal forecasting task, AgentProphet achieves a Growth-Aware NDCG@10 of

0.410 \pm 0.076

, improving over GRU, DirectLLM, DLinear, and ARIMA by 58.3%, 91.6%, 108.1%, and 314.1%, respectively. It also obtains the highest E-Gain@10 of

0.305 \pm 0.060

, E-MAP@10 of

0.056 \pm 0.008

, and NDCG@10 of

0.474 \pm 0.039

. Cross-task robustness analysis shows that DirectLLM remains competitive, and can be stronger in sparser or more mature signal regimes. A qualitative case study maps the forecasted capability directions to representative SMCC concerns as a data-level interpretation of possible planning implications. These findings suggest that AgentProphet is most suitable for balanced weak-signal settings where early evidence is available but incomplete, rather than serving as a universally superior emerging technology forecaster. Full article

(This article belongs to the Special Issue Advances in Intelligent Decision-Making Systems)

► Show Figures

Figure 1

23 pages, 1100 KB

Open AccessArticle

Pob-CFR: A Population-Based Counterfactual Regret Minimization Approach for Strategy Optimization in Two-Player Zero-Sum Imperfect-Information Games

by Lei Zhang, Dingzhong Cai and Xuan Wang

Appl. Sci. 2026, 16(11), 5711; https://doi.org/10.3390/app16115711 - 5 Jun 2026

Viewed by 254

Abstract

Sequentialdecision-making under imperfect information is naturally modeled as an extensive-form game, where the Nash equilibrium serves as the predominant solution concept for two-player zero-sum settings. Counterfactual regret minimization (CFR) is a widely used framework for this purpose, iteratively reducing regret through regret matching [...] Read more.

Sequentialdecision-making under imperfect information is naturally modeled as an extensive-form game, where the Nash equilibrium serves as the predominant solution concept for two-player zero-sum settings. Counterfactual regret minimization (CFR) is a widely used framework for this purpose, iteratively reducing regret through regret matching so that the average strategy approaches a Nash equilibrium. However, the convergence efficiency of CFR remains a practical challenge. In this work, we refine and reformulate an advantage-based exponential weighting scheme, Exponential CFR (ExpCFR), which accelerates convergence by allocating greater attention to highly profitable actions during the regret-accumulation process. Building on this heuristic, we further introduce Pob-CFR, a framework that integrates population-based evolutionary training with CFR. Pob-CFR maintains a diverse population of heterogeneous CFR variants, periodically evaluating them by exploitability and replacing underperforming individuals with the elite to synchronize strategy exploration. Systematic evaluations across five benchmark games demonstrate that these methods accelerate early-to-mid convergence compared to standard CFR baselines. Furthermore, within the evaluated benchmarks, the relative advantage of the population-based architecture appears more evident in the games with larger strategic complexity. Full article

(This article belongs to the Special Issue Advances in Intelligent Decision-Making Systems)

► Show Figures

Figure 1

16 pages, 7605 KB

Open AccessArticle

Decision of Nonsynchronous Framework: Agents in MARL Have Different Priorities While Making Decisions

by Shanghui Xie, Junyang Zhao, Jiajia Zhang and Lei Wang

Appl. Sci. 2026, 16(11), 5202; https://doi.org/10.3390/app16115202 - 22 May 2026

Viewed by 225

Abstract

Multi-Agent Reinforcement Learning (MARL) faces key challenges in credit assignment and the curse of dimensionality as agent numbers grow. In cooperative settings, uniform treatment of agents often exacerbates these issues. We argue that an agent’s importance depends on its personalized attributes and environment [...] Read more.

Multi-Agent Reinforcement Learning (MARL) faces key challenges in credit assignment and the curse of dimensionality as agent numbers grow. In cooperative settings, uniform treatment of agents often exacerbates these issues. We argue that an agent’s importance depends on its personalized attributes and environment states and propose concentrating computational resources on key agents while others act simply, alleviating dimensionality explosion and improving generalization. We propose the Decision of Nonsynchronous Framework (DNF), which identifies and prioritizes key agents at each time step for optimized decision-making, while assigning predefined or simplified behaviors to the remaining agents based on computational outcomes. To realize this, we introduce a Core Extractor (CE) architecture that categorizes agents into Priorities Key Agents (PKAs) and followers. Although agents are differentiated by priority, we still adhere to the Centralized Training with Decentralized Execution (CTDE) paradigm. This approach reduces the dimensionality of the joint state-action space, mitigates the dimensionality explosion problem in MARL, and fosters improved collaboration among agents. Experimental results demonstrate that DNF achieves a 100% win rate on multiple SMAC maps, including 3m, 2s3z, and 1c3s5z, and achieves 98.9–100% win rates on challenging hard and super-hard scenarios such as 2c_vs_64zg and Corridor, significantly outperforming baseline methods like QMIX and QPLEX in both final performance and training stability, while incurring only a modest increase in computational overhead. In the continuous MPE, DNF matches or exceeds HAPPO in performance and demonstrates substantially higher time efficiency, with both advantages growing more pronounced as the number of agents increases. Full article

(This article belongs to the Special Issue Advances in Intelligent Decision-Making Systems)

► Show Figures

Figure 1

26 pages, 3759 KB

Open AccessArticle

Prediction-Regularized Spatio-Temporal Transformer Framework for Offline Multi-Intersection Traffic Signal Control

by Yueting Deng, Huale Li, Tong Xia, Zhaobin Wang and Ruoming Lei

Appl. Sci. 2026, 16(10), 5156; https://doi.org/10.3390/app16105156 - 21 May 2026

Viewed by 334

Abstract

Multi-intersection traffic signal control must jointly address local coordination and delayed traffic propagation under strongly time-varying conditions. Existing offline sequence-imitation methods mainly recover actions from historical trajectories and make limited use of short-term future traffic evolution in shared-representation learning. To address this issue, [...] Read more.

Multi-intersection traffic signal control must jointly address local coordination and delayed traffic propagation under strongly time-varying conditions. Existing offline sequence-imitation methods mainly recover actions from historical trajectories and make limited use of short-term future traffic evolution in shared-representation learning. To address this issue, we propose PR-STLight, a prediction-regularized spatio-temporal extension of TransformerLight for offline multi-intersection traffic signal control. PR-STLight introduces short-term future inbound-queue evolution as structural supervision for shared representation learning. The model combines neighborhood-constrained spatial self-attention, causal temporal self-attention, and a Topology-Recurrent Queue Predictor (TRQP) to capture topology-aware spatio-temporal dependencies and near-future congestion dynamics. Training adopts a two-stage strategy, namely queue-prediction pretraining followed by joint control-prediction optimization, to improve optimization stability on a fixed offline replay buffer. In experiments on the adopted CityFlow benchmarks, PR-STLight obtains average travel times of 274.39 s on Jinan

3 \times 4

and 288.09 s on Hangzhou

4 \times 4

, corresponding to 1.14% and 2.82% lower travel times than the strongest non-PR baseline, and 21.27% and 22.54% lower travel time than the TransformerLight backbone, respectively. It also achieves the lowest average inbound queue on Hangzhou and remains competitive on Jinan. These results show that PR-STLight provides an effective offline spatio-temporal sequence framework for coordinated multi-intersection signal control. Full article

(This article belongs to the Special Issue Advances in Intelligent Decision-Making Systems)

► Show Figures

Figure 1

27 pages, 15426 KB

Open AccessArticle

Active Distribution Network Voltage Control with a Physics-Informed Spatiotemporal Attention Network

by Tong Xia, Huale Li, Yueting Deng, Zetao Lin and Lei Wang

Appl. Sci. 2026, 16(10), 5109; https://doi.org/10.3390/app16105109 - 20 May 2026

Viewed by 281

Abstract

Active voltage control (AVC) in active distribution networks coordinates the reactive power outputs of distributed inverters to maintain bus voltages within secure limits. Although multi-agent reinforcement learning (MARL) shows promise for AVC, current methods face three main limitations: graph topologies rely on unweighted [...] Read more.

Active voltage control (AVC) in active distribution networks coordinates the reactive power outputs of distributed inverters to maintain bus voltages within secure limits. Although multi-agent reinforcement learning (MARL) shows promise for AVC, current methods face three main limitations: graph topologies rely on unweighted adjacency, ignoring physical parameters like line impedance and electrical distance; centralized critics output a single global Q-value, leading to coarse spatial credit assignment; and temporal critic modules suffer from vanishing gradients and representation drift. To address these issues, we propose physics-informed spatiotemporal multi-agent value learning (PST-MA), a physics-informed spatiotemporal value-learning framework integrating three coupled designs: a physics-informed graph attention mechanism with electrical-distance-aware sparsification; node-conditional value outputs utilizing a replicated-graph diagonal-extraction strategy; and a temporal latent compression module featuring a gated bypass and late action fusion. Experiments on the IEEE 33-bus and 141-bus systems validate the effectiveness of the proposed PST-MA method. Results demonstrate that it consistently achieves a higher controllable ratio than baseline methods for coordinated voltage regulation under uncertainty. Full article

(This article belongs to the Special Issue Advances in Intelligent Decision-Making Systems)

► Show Figures

Figure 1

30 pages, 4413 KB

Open AccessArticle

Dotsformer: Capturing Chain-Loop Structures for Transformer in Dots-and-Boxes

by Ranran Zhang, Changming Xu, Kuo Wu, Mingze Zheng, Xingcan Liu and Junwei Wang

Appl. Sci. 2026, 16(7), 3395; https://doi.org/10.3390/app16073395 - 31 Mar 2026

Viewed by 677

Abstract

In many board games, AlphaZero has demonstrated superhuman abilities. Dots-and-Boxes is a classic board game with simple rules but requiring skills to win. This paper proposes Dotsformer, which extracts chain-loop structures from the game board. These structures connect distant boxes, providing long-range relational [...] Read more.

In many board games, AlphaZero has demonstrated superhuman abilities. Dots-and-Boxes is a classic board game with simple rules but requiring skills to win. This paper proposes Dotsformer, which extracts chain-loop structures from the game board. These structures connect distant boxes, providing long-range relational information as input to the Transformer. We employ multiple convolutional kernels to generate Q, K, and V, and incorporate information about the box structure itself into the attention scores. We also incorporate auxiliary training tasks, including an initiative task and a classification task. These tasks determine whether to retain or relinquish the initiative in the current situation, and classify actions into forbidden, conceding, safe, and scoring moves. They provide additional supervisory signals and accelerate learning. The experimental results show that Dotsformer outperforms AlphaZero in both rollback speed and playing strength: it achieved a winning rate of 87.6% and an ELO rating lead of 340 points against the baseline. Additionally, ablation studies verify the effectiveness of each key module. Full article

(This article belongs to the Special Issue Advances in Intelligent Decision-Making Systems)

► Show Figures

Figure 1

26 pages, 972 KB

Open AccessArticle

Constructing Non-Markovian Decision Process via History Aggregator

by Yongyi Wang, Lingfeng Li and Wenxin Li

Appl. Sci. 2026, 16(2), 955; https://doi.org/10.3390/app16020955 - 16 Jan 2026

Viewed by 497

Abstract

In the domain of algorithmic decision-making, non-Markovian dynamics manifest as a significant impediment, especially for paradigms such as Reinforcement Learning (RL), thereby exerting far-reaching consequences on the advancement and effectiveness of the associated systems. Nevertheless, the existing benchmarks are deficient in comprehensively assessing [...] Read more.

In the domain of algorithmic decision-making, non-Markovian dynamics manifest as a significant impediment, especially for paradigms such as Reinforcement Learning (RL), thereby exerting far-reaching consequences on the advancement and effectiveness of the associated systems. Nevertheless, the existing benchmarks are deficient in comprehensively assessing the capacity of decision algorithms to handle non-Markovian dynamics. To address this deficiency, we have devised a generalized methodology grounded in category theory. Notably, we established the category of Markov Decision Processes (MDP) and the category of non-Markovian Decision Processes (NMDP), and proved the equivalence relationship between them. This theoretical foundation provides a novel perspective for understanding and addressing non-Markovian dynamics. We further introduced non-Markovianity into decision-making problem settings via the History Aggregator for State (HAS). With HAS, we can precisely control the state dependency structure of decision-making problems in the time series. Our analysis demonstrates the effectiveness of our method in representing a broad range of non-Markovian dynamics. This approach facilitates a more rigorous and flexible evaluation of decision algorithms by testing them in problem settings where non-Markovian dynamics are explicitly constructed. Full article

(This article belongs to the Special Issue Advances in Intelligent Decision-Making Systems)

► Show Figures

Figure 1

Review

Jump to: Research

27 pages, 3581 KB

Open AccessReview

Co-Inertia Analysis in Neutrosophic Spaces: An Exploratory Bibliometric Study

by Mayra D’Armas Regnault, Purificación Vicente-Galindo and Purificación Galindo-Villardón

Appl. Sci. 2026, 16(12), 5948; https://doi.org/10.3390/app16125948 - 12 Jun 2026

Viewed by 303

Abstract

This study explores the intersection between co-inertia analysis and neutrosophic spaces through a bibliometric analysis of 259 scientific articles indexed in Scopus (1994–2025). Employing PRISMA methodology and the bibliometrix software (version 5.2.0), the temporal evolution, intellectual structure, and collaboration networks in both fields [...] Read more.

This study explores the intersection between co-inertia analysis and neutrosophic spaces through a bibliometric analysis of 259 scientific articles indexed in Scopus (1994–2025). Employing PRISMA methodology and the bibliometrix software (version 5.2.0), the temporal evolution, intellectual structure, and collaboration networks in both fields are examined. Results reveal sustained growth in scientific production since 2010, primarily concentrated in France (71 articles, 27.4% of the corpus). Stéphane Dray emerges as the most influential author with 7252 citations, while Bioinformatics leads in impact (6863 citations across 6 articles). Keyword analysis positions ‘multivariate analysis’ as the central term, articulating three clusters: ecology, multivariate statistics, and genomics. However, explicit integration between co-inertia analysis and neutrosophic theory remains incipient, located in the emerging topics zone with low centrality and density. The thematic map identifies consolidated applications in ecology (macroinvertebrates, functional traits) and development opportunities in data integration under high uncertainty. This work establishes a conceptual foundation for future research on the coupling of multivariate methods with neutrosophic frameworks in contexts of heterogeneous information and indeterminacy. Full article

(This article belongs to the Special Issue Advances in Intelligent Decision-Making Systems)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Intelligent Decision-Making Systems

Share This Special Issue

Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI