Expert Systems最新文献

{"title":"Data Quality Assessment Based on Single-Valued Neutrosophic Credibility Numbers: A Multi-Attribute Group Decision-Making Approach Integrating Cumulative Prospect Theory and Bidirectional Projection Measure","authors":"Pingqing Liu,&nbsp;Junxin Shen,&nbsp;Baoquan Ning","doi":"10.1111/exsy.70336","DOIUrl":"https://doi.org/10.1111/exsy.70336","url":null,"abstract":"<div>\u0000 \u0000 <p>Data quality assessment is a critical process for enabling efficient data utilisation and supporting scientifically sound decision-making. It not only provides a reliable foundation for data analysis, machine learning, and intelligent decision-making but also serves as a core enabler for the market-based allocation of data resources and the practical realisation of data value. However, existing assessment frameworks often fail to comprehensively capture the fuzziness, uncertainty, and credibility inherent in real-world information. To address these challenges, this study develops a novel multi-attribute group decision-making (MAGDM) framework based on single-valued neutrosophic credibility numbers (SvNCNs). First, a new scoring function is proposed to overcome the mathematical limitations of existing SvNCN models. This function systematically integrates true, false, and indeterminate fuzzy information along with their associated credibility, effectively reducing distortions caused by uncertainty and enhancing the interpretability and robustness of the results. Second, a weighting method combining SvNCN-PIvot Pairwise RElative Criteria Importance Assessment (PIPRECIA) and Grey Relational Analysis (GRA)-Criteria Importance through Intercriteria Correlation (CRITIC) is employed to achieve an organic integration of subjective and objective weights, ensuring the scientific rigour of the weight determination process. Third, a bidirectional projection measure is introduced in the SvNCN environment to comprehensively evaluate the relationship between alternatives and the positive and negative ideal solutions, thereby improving ranking accuracy; meanwhile, cumulative prospect theory (CPT) is incorporated to capture decision-makers' psychological preferences and behavioural characteristics under uncertainty, enhancing the framework's practical applicability and decision rationality. Case validation based on data quality assessment demonstrates that the proposed framework outperforms existing approaches in terms of ranking accuracy, robustness, and decision rationality.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating Large Language Models as Post Hoc Explainability Interfaces for Credit Risk Models","authors":"Wenxi Geng,&nbsp;Dingyuan Liu,&nbsp;Liya Li,&nbsp;Yiqing Wang","doi":"10.1111/exsy.70351","DOIUrl":"https://doi.org/10.1111/exsy.70351","url":null,"abstract":"<div>\u0000 \u0000 <p>Large language models (LLMs) are increasingly considered as potential interfaces for communicating model-based explanations in credit risk decision-support settings. This study evaluates whether LLMs can serve as post hoc explainability tool for credit risk models, focusing on their ability to preserve supplied feature-importance rankings and autonomously generate feature-importance rankings. Using a LendingClub dataset, we compare LLM outputs with SHAP and coefficient-based attributions. Results indicate that LLMs reliably reproduce reference rankings under controlled prompts but show limited alignment when generating explanations autonomously. These findings suggest that LLMs are best deployed as narrative interfaces rather than substitutes for formal attribution methods in credit risk governance. The paper is organized as follows. Section 1 introduces the research problem. Section 2 reviews the related literature on explainable AI and the use of LLMs in financial applications. Section 3 describes the experimental design, including data processing, baseline model training, prompt engineering strategies and evaluation metrics. Section 4 presents the empirical results for both research questions. Section 5 concludes with a discussion of implications and directions for future research.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hi-RAG: A Hierarchical Retrieval-Augmented Generation Framework for Scalable and Generalisable Tool Selection in Large Language Model Agents","authors":"Wei Tian,&nbsp;Yuhao Zhou","doi":"10.1111/exsy.70341","DOIUrl":"https://doi.org/10.1111/exsy.70341","url":null,"abstract":"<div>\u0000 \u0000 <p>As tool repositories for Large Language Model (LLM) agents grow from dozens to hundreds of endpoints, flat retrieval paradigms that treat the repository as an unstructured list suffer from context overload, cross-domain semantic collision and degraded selection accuracy. We propose Hi-RAG, a Hierarchical Retrieval-Augmented Generation framework that exploits the Type <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>→</mo>\u0000 </mrow>\u0000 <annotation>$$ to $$</annotation>\u0000 </semantics></math> Service <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>→</mo>\u0000 </mrow>\u0000 <annotation>$$ to $$</annotation>\u0000 </semantics></math> Tool structure of the Model Context Protocol (MCP) via a principled coarse-to-fine pipeline. Stage 1 applies a <i>Tool-as-Proxy</i> hybrid retrieval strategy (BM25 sparse retrieval combined with dense bi-encoder search, fused via Weighted Reciprocal Rank Fusion) to identify candidate services efficiently. Stage 2 performs type-aware re-ranking over a local heterogeneous graph, integrating a domain-level gating mechanism with contextualised tool attention for precise service scoring. We further introduce <i>MCPBench</i>, the first benchmark for hierarchical tool selection, comprising 201 tools across 40 real-enterprise services—23% of queries require multi-service reasoning. Experiments across five LLMs show Hi-RAG improves Top-1 accuracy by up to 7.5% (single-service) and 10.0% (multi-service) over Flat-RAG, while reducing token consumption by up to 89% against full-context injection. Comparisons with a strong late-interaction baseline (ColBERT-RAG) further confirm the superiority of Hi-RAG. Zero-shot evaluation on ToolLLM (16,464 tools) confirms scalability, and formal analyses establish <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>O</mi>\u0000 <mfenced>\u0000 <mn>1</mn>\u0000 </mfenced>\u0000 </mrow>\u0000 <annotation>$$ O(1) $$</annotation>\u0000 </semantics></math> context growth with respect to repository size.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148387019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DMV-CLIP: Disentangled Multimodal Visual Adaptation for Text-Driven Face Editing","authors":"Minghao Li,&nbsp;Fan Zhang,&nbsp;Xin Wei,&nbsp;Huan Wan,&nbsp;Haoruo Zhang,&nbsp;Xuhui Huang","doi":"10.1111/exsy.70345","DOIUrl":"https://doi.org/10.1111/exsy.70345","url":null,"abstract":"<div>\u0000 \u0000 <p>Text-driven face editing has attracted widespread interest due to its intuitive control and user-friendly interaction. However, current state-of-the-art (SOTA) methods face two main challenges: (1) they utilize unfinetuned general image-text encoders for modality fusion, making it difficult to comprehend domain-specific knowledge in facial attribute editing (dozens of fine-grained facial attributes such as moustache and lipsticks); (2) they roughly optimize all attributes simultaneously using a cross-entropy loss, leading to severe mutual interference among attributes. To this end, we propose Disentangled Multimodal Visual Adaptation for CLIP (DMV-CLIP). First, DMV-CLIP incorporates learnable context tokens to inject facial domain knowledge into the CLIP model via multimodal prompt learning (MPL). Second, it employs directional contrastive learning (DCL) to disentangle facial attributes and enable precise editing. Finally, DMV-CLIP utilizes a vision-language consistency model (VLCM) to maintain identity consistency while ensuring that the generated images strictly adhere to the semantic instructions.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Level Feature Fusion and Interaction for Cross-Modal Fashion Retrieval","authors":"Runbing Wu,&nbsp;Jia Ren,&nbsp;Zijian Hu,&nbsp;Yani Cui,&nbsp;Bo Li,&nbsp;Guanglong Huang","doi":"10.1111/exsy.70342","DOIUrl":"https://doi.org/10.1111/exsy.70342","url":null,"abstract":"<div>\u0000 \u0000 <p>Cross-modal retrieval is a fundamental task in the fashion domain, where the key challenge lies in effectively aligning semantic information and learning discriminative modality representations. However, this task remains highly challenging due to the semantic gap, insufficient utilization of fine-grained features, and limitations of training strategies. To address these issues, this paper proposes a Multi-Level Feature Fusion Interaction Network (MLFFI-Net). The framework leverages a pyramid architecture for multi-scale feature modelling and incorporates a Multi-modal Transformer encoder block (MTEB) to achieve collaborative alignment of global and local semantics. A Dynamic Gated Fusion Mechanism (DGFM) is introduced to aggregate hidden states across Transformer layers, thereby generating richer text representations. In addition, an Alternating Progressive Training Strategy (APTS) is designed to fully exploit different input data streams during joint training, effectively coordinating multiple learning tasks and enhancing overall performance. Experimental results on the FashionGen dataset demonstrate that MLFFI-Net significantly outperforms existing approaches in cross-modal retrieval for the fashion domain, validating the effectiveness of the proposed method in semantic alignment and feature representation.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GT-LLM: Graph Topology-Enhanced LLM for Temporal Knowledge Graph Reasoning","authors":"Jinglu Chen,&nbsp;Wenhao Zhang,&nbsp;Mengpan Chen,&nbsp;Liangliang Zhang,&nbsp;Daniel Dajun Zeng","doi":"10.1111/exsy.70338","DOIUrl":"https://doi.org/10.1111/exsy.70338","url":null,"abstract":"<div>\u0000 \u0000 <p>Temporal knowledge graph reasoning (TKGR) aims to predict future facts based on events that have occurred up to the current timestamp in a temporal knowledge graph (TKG). Traditional learning-based methods focus on structural information but overlook semantics inherent in TKGs, while rule-based methods struggle to generate sufficient high-quality temporal logical rules. Recently, large language models (LLMs) have been introduced into the TKGR task, typically leveraging retrieved relevant historical events and LLMs' semantic understanding and reasoning abilities to infer missing information in the query. Existing LLM-based methods encompass both fine-tuning and non-fine-tuning variants. The former demands high computational cost and exhibits limited transferability, whereas the latter suffers from performance constraints stemming from the absence of specialised adaptation training. In this paper, we introduce GT-LLM, a novel non-fine-tuning TKGR framework that enhances performance by improving history retrieval quality while avoiding costly task-specific LLM fine-tuning and preserving flexible adaptability to different or dynamically updated TKGs. The key to our method is that it transforms a series of TKG subgraphs into a single, unified topological graph, where entities, relations, and timestamps are explicitly modelled as nodes and connected through topological edges to expose richer associations for history retrieval. Based on this unified representation, we design a general TKGR pipeline that performs history retrieval based on topological association strength and temporal relevance, followed by LLM reasoning under vocabulary-level constraints. Furthermore, we integrate the predictions from the LLM with those from a graph-based model to harness their complementary strengths. Extensive experimental results on standard TKGR benchmarks demonstrate that our method significantly improves history retrieval quality and achieves promising overall performance.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging High-Impact User Interactions for Social User Opinion Prediction: An Approach via Block-Wise Matrix Factorisation and Attention Mechanism","authors":"Hua Ma,&nbsp;Jun He,&nbsp;Yutian Liu,&nbsp;Bowen Zheng,&nbsp;Hongyu Zhang","doi":"10.1111/exsy.70339","DOIUrl":"https://doi.org/10.1111/exsy.70339","url":null,"abstract":"<div>\u0000 \u0000 <p>Rapidly growing social media has become a key platform in recent years for influencing public sentiment and shaping hot public opinion. Against this backdrop, accurately predicting social users' opinions holds significant importance for public opinion analysis and guidance. Existing research generally focuses on the macro level of hot events. However, it fails to fully exploit the interaction data between high-impact users and ordinary users. Moreover, such studies often neglect individual user characteristics and behavioural differences, which limits their capability in accurately forecasting user opinion trends. This paper proposes a novel approach to predict social users' opinions by leveraging high-impact users' interaction data. The approach utilises the posts and interactive comments of high-impact users to construct multiple user–post opinion matrices and employs block-wise matrix factorisation to extract the latent embeddings of users and posts. Building upon this, the historical comment–post pairs are encoded using BERT, and a bidirectional cross-attention mechanism is applied to model the semantic correlations between comments and posts, yielding cross-attentional pair representations. To integrate these representations, a dynamic attention mechanism is used to weight and aggregate historical behaviours, generating an attention-weighted semantic representation that is highly relevant to the current task. Finally, the multi-source features of users and posts are fused through a transformer architecture and fed into a multi-layer perceptron for opinion prediction. Experiments on a real-world dataset demonstrate that the proposed approach achieves superior performance in user opinion prediction, showing promising potential for practical applications.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Topic Evolution Analysis for Social Robots Based on Latent Dirichlet Allocation","authors":"Jia-Cheng Shen,&nbsp;Wei-Feng Tung","doi":"10.1111/exsy.70272","DOIUrl":"https://doi.org/10.1111/exsy.70272","url":null,"abstract":"<div>\u0000 \u0000 <p>With the rapid growth of the robotics market, social robots have garnered increasing global attention. Investigating service innovation within the domain of social robots enables a better understanding of the field's developmental trajectory and emerging trends. Such insights can support enterprises and researchers in the development of innovative technologies and related applications. This study collected a total of 1406 abstracts related to social robots published over the past 15 years from the Web of Science journal database, which served as the primary research corpus. The thematic evolution of social robots was analysed from two perspectives: the evolution of thematic intensity and the evolution of thematic content. The findings are as follows: (1) In the early stages, research was predominantly focused on system technologies. As these technologies matured, they facilitated the diversification of research topics, leading to a relative decline in system technology research and a corresponding rise in studies from other domains. (2) The development of social robots has primarily followed three main trajectories: system technologies, research concerning children and research concerning the elderly. Subtopics such as healthcare, companionship, education, interaction and innovative applications in commercial services have evolved independently while also aligning with these major trajectories, resulting in a diversified research landscape.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148274753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Emotion AI on the Edge: A TinyML-Driven Framework for Speech Emotion Recognition in Social Environments","authors":"Md. Sakib Bin Alam,&nbsp;Aiman Lameesa,&nbsp;Barsha Roy,&nbsp;Shams Forruque Ahmed,&nbsp;Amir H. Gandomi","doi":"10.1111/exsy.70322","DOIUrl":"https://doi.org/10.1111/exsy.70322","url":null,"abstract":"<div>\u0000 \u0000 <p>The rise of Emotion AI is transforming how human emotions are detected, interpreted and responded to in real-time social systems. Speech emotion recognition (SER) enables machines to understand human emotions from voice, fostering more empathetic and context-aware interactions. However, the currently deployed SER systems are frequently based on highly resource-consuming large models, which are unsuitable for real-time deployment on edge devices with limited memory and processing power. Most previous studies have focused on single-language or single accent datasets, which results in ineffective extrapolation to various speakers, accents and the real world. This study introduces a scalable and lightweight SER system designed for the TinyML environment and suitable for deployment on resource-constrained systems, including social networks using IoT technologies, assistive technologies and embedded mental health devices. Combining RAVDESS, TESS and SAVEE increases dataset diversity. Their effectiveness in capturing both spectral and temporal emotion cues is tested across six hybrid frameworks of deep learning, such as CNN + BiLSTM and CNN + BiGRU with multi-head attention. The best model achieved 74.15% accuracy, with a macro F1-score of 0.73, a weighted F1-score of 0.74, and a highest class-level F1-score of 0.82, supporting low-latency emotion recognition for affect-aware edge applications. The quantization through TensorFlow Lite further reduces the model size by up to 94.5% and achieves inference latency as low as 3.4 ms, making it suitable for deployment on microcontrollers. This study contributes to Emotion AI as it allows detecting emotions on edge devices to facilitate affect-aware customer service, support mental health, improve education and more broadly, computational social systems.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148274756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Thinking Is Not Enough: The B* Expansion Technique for Enhancing Autonomous LLM Agents","authors":"Sebastián Andrés Mayorquín Posadas,&nbsp;Julio Vega","doi":"10.1111/exsy.70333","DOIUrl":"https://doi.org/10.1111/exsy.70333","url":null,"abstract":"&lt;p&gt;Most autonomous agents built on large language models (LLMs) focus on improving internal reasoning while assuming a fixed and complete set of primitive actions. In this work, we challenge this assumption and introduce the &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;B&lt;/mi&gt;\u0000 &lt;mo&gt;*&lt;/mo&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {B}^{ast } $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; expansion technique, an action-centric method that enables agents to iteratively construct new actions beyond an initial basis &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;B&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ B $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;, forming an expanded action space &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;B&lt;/mi&gt;\u0000 &lt;mo&gt;*&lt;/mo&gt;\u0000 &lt;/msup&gt;\u0000 &lt;mo&gt;=&lt;/mo&gt;\u0000 &lt;mi&gt;B&lt;/mi&gt;\u0000 &lt;mo&gt;∪&lt;/mo&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;A&lt;/mi&gt;\u0000 &lt;mo&gt;*&lt;/mo&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {B}^{ast }=Bcup {A}^{ast } $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;. To formalize this paradigm, we present a unified framework for act-centric autonomy that explicitly models action space evolution, distinguishing our approach from prior frameworks such as ReAct, which operate over fixed action sets. Within this framework, &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;B&lt;/mi&gt;\u0000 &lt;mo&gt;*&lt;/mo&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {B}^{ast } $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; serves as a concrete instantiation that operationalizes dynamic action generation. We evaluate &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;B&lt;/mi&gt;\u0000 &lt;mo&gt;*&lt;/mo&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {B}^{ast } $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; in a non-trivial, fully observable environment—Conway's Game of Life on a &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mn&gt;200&lt;/mn&gt;\u0000 &lt;mo&gt;×&lt;/mo&gt;\u0000 &lt;mn&gt;200&lt;/mn&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ 200times 200 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; grid—where the objective is to maximize the number of live cells after 300 generations. Our results show that expanding the action space leads to improved ex","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70333","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148274755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}