AI Agent 生态 · 全部实体（第 9 / 100 页）

本页收录第 801–900 条，共 9974 条 · 返回 AI Agent 生态 首页

• Closed-Loop Autonomy Under Uncertainty: How Inference-Time Verification, Hierarchical Credit Assignment, Adaptive Compute Routing, Safety Filtering, and Human-in-the-Loop Correction Jointly Define a Candidate Framework for Deployment-Robust Robot Policy Execution
  Version 2 — revised in response to an external structural review and an automated critique pass. See "Response to Review" appendix in the PDF for the change log. A persistent gap separates robot policies that perform well in controlled evaluation from those th…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.77 AI-drafted synthesisarXivpreprint reviewv2
• Personalizing Behaviors of the Multi-Agent Autonomous Looper with a Corpus of Annotated Co-performances - supplementary materials
  This repository contains video examples, and software configurations supporting the results of the user studies included in the article: "Personalizing Behaviors of the Multi-Agent Autonomous Looper with a Corpus of Annotated Co-performances". Vincenzo Madaghi…
  datacite Madaghiele, Vincenzo, Fasciani, Stefano, Erdem, Çağrı 2026 置信度 0.77 ai governancecs.aics.hcinformation theoryai safety
• Personalizing Behaviors of the Multi-Agent Autonomous Looper with a Corpus of Annotated Co-performances - supplementary materials
  This repository contains video examples, and software configurations supporting the results of the user studies included in the article: "Personalizing Behaviors of the Multi-Agent Autonomous Looper with a Corpus of Annotated Co-performances". Vincenzo Madaghi…
  datacite Madaghiele, Vincenzo, Fasciani, Stefano, Erdem, Çağrı 2026 置信度 0.77 ai governancecs.aics.hcinformation theoryai safety
• THE SEMANTIC VENOM
  In late July 2026, what news reports called “rogue AI agents” moved from simulated cyber tasks into unsanctioned activity involving real people, public software projects, and online services. During a controlled evaluation conducted by the UK AI Security Insti…
  datacite GRANDIĆ, SANJIN 2026 置信度 0.72
• Graph based multi-agent reinforcement learning with evolutionary population for cooperation.
  In fully cooperative environments, agents aim to learn a joint policy to achieve a shared goal. However, existing Multi-Agent Reinforcement Learning (MARL) approaches struggle when scaling to complex coordination tasks. However, as the complexity of joint task…
  pubmed Peng K, Qi H, Ma T 2026 Apr 置信度 0.96 computer and information sciencescs.lgcomputer sciencecs.aiartificial intelligence
• Event-triggered multi-agent coordination in directed graphs: An intermittent control approach.
  This paper develops a communication-efficient event-triggered intermittent control strategy for multi-agent coordination in directed graphs. The proposed approach establishes a condition ensuring the existence of a minimum time interval between consecutive tri…
  pubmed Qin W, Lyu Y, Wang P, Ma G 等 2026 Jan 置信度 0.96 control theorymath.ocelectrical engineering, electronic engineering, information engineeringeess.sysystems and control
• Observer-based group consensus tracking of hybrid multi-agent systems under adaptive event-triggered mechanism.
  The group consensus tracking of multi-agent systems has been extensively applied in the coordination of unmanned system formations. However, existing methods encounter difficulties in group consensus tracking regarding the group division for the observation co…
  pubmed Pei H, Liang W 2026 Jan 置信度 0.96 control theoryelectrical engineering, electronic engineering, information engineeringunderwatersystems and controlrobustness
• Neuroadaptive consensus learning for multi-agent systems: An incremental approach to nonstrict pure-feedback control.
  This paper investigates the distributed learning consensus control problem for nonstrict pure-feedback multi-agent systems using neural networks and an incremental adaptive mechanism. A unified adaptive learning consensus control framework is first established…
  pubmed Wang S, Li J, Li J 2026 Jan 置信度 0.96 computer and information scienceselectrical engineering, electronic engineering, information engineeringcontrol theoryrobustnesscs.lg
• Distributed fixed-time fault-tolerant tracking and containment of second-order multi-agent systems.
  This article addresses the fixed-time fault-tolerant consensus problem for second-order multi-agent systems under actuator faults and directed topologies. A novel sliding-mode control framework is proposed, integrating fixed-time observers to estimate actuator…
  pubmed Chen C, Li Y, Zhu S, Han Y 2026 Jan 置信度 0.96 control theorycontrolmath.ocelectrical engineering, electronic engineering, information engineeringsystems and control
• NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting.
  Traditional volume visualization (VolVis) methods, like direct volume rendering, suffer from rigid transfer function designs and high computational costs. Although novel view synthesis approaches enhance rendering efficiency, they require additional learning e…
  pubmed Ai K, Tang K, Wang C 2026 Jan 置信度 0.96 computer and information sciencescomputer sciencecs.aiartificial intelligencerobotics
• Prescribed-performance consensus control for nonlinear MASs: a privacy preservation strategy.
  This paper proposes an adaptive predefined-time prescribed performance control strategy for nonlinear multi-agent systems with privacy-preservation. Firstly, a privacy preservation method is designed to protect transmitting data within a user-defined time. By …
  pubmed Chen K, Yu C, Liu Z, Philip Chen CL 等 2026 Jan 置信度 0.96 control theorycomputer and information sciencesrobustnesscomputer scienceeess.sy
• Observer-based consensus tracking of stochastic multi-agent systems via control Lyapunov function.
  This work discusses the consensus tracking for stochastic multi-agent systems with a leader-follower structure. An observer-based distributed control approach is put forward, leveraging control Lyapunov functions and quadratic programming framework. This contr…
  pubmed Yan Z, Li B, Qi P, Wen S 等 2026 Mar 置信度 0.96 control theoryeess.sycontrolsystems and controlmath.oc
• Hierarchical reinforcement learning with kill chain-informed multi-objective optimization to enhance resilience in autonomous unmanned swarm.
  The resilience of autonomous unmanned swarms (AUS) serves as a cornerstone for guaranteeing continuous mission execution in the face of adversarial interferences. Contemporary methodologies often suffer from limited generalization efficacy and volatile converg…
  pubmed Gou Y, Wei S, Xu K, Liu J 等 2026 Mar 置信度 0.96 computer and information sciencescs.lgcs.aicomputer scienceartificial intelligence
• Reinforcement learning-based funnel control and privacy preservation for multi-agent systems with input dead-zone.
  This paper investigates the privacy-preserving protocol and reinforcement learning-based funnel controller design of multi-agent systems subject to input dead-zone constraints. An adaptive funnel controller is formulated to guarantee that the tracking errors k…
  pubmed Huang J, Liu X, Shen S, Yu W 2026 Mar 置信度 0.96 control theorycomputer and information scienceselectrical engineering, electronic engineering, information engineeringreinforcement learningcomputer science
• MedARC: Adaptive multi-agent refinement and collaboration for enhanced medical reasoning in large language models.
  Large Language Models (LLMs) have shown remarkable potential in medical question answering (QA), yet their deployment in clinical settings remains limited by hallucinations, inconsistent reasoning, and difficulties in handling complex biomedical information.
  pubmed Miao Y, Wen J, Luo Y, Li J 2026 Feb 置信度 0.93 cs.clcs.aiworkflownatural language processingmedical education
• Autonomous collision-avoiding for multi-UAVs in complex dynamic environments: An event-triggered PPO approach with LSTM-attention integration.
  The challenge of flocking collision avoidance lies in selecting the optimal strategy that balances decision-making intelligence and resource saving in a complex dynamic environment. Meanwhile, the design of the collision avoidance reward function for deep rein…
  pubmed Liang C, Liu L, Cao J, Li X 2026 Feb 置信度 0.96 computer and information sciencesreinforcement learningcomputer scienceelectrical engineering, electronic engineering, information engineeringrobot
• Substrate-Neutral Structural Foundation Laws-SNSFL PNBA Identity Physics Total Consistency Update
  -- ============================================================-- SNSFL_L0_Total_Consistency_031926 — Lean 4 source · Mathlib-- ============================================================---- Step 1 — The equation:---- d/dt (IM · Pv) = Σ λ_X · O_X · S + F_ext…
  datacite Trent, Russell 2026 置信度 0.72
• Substrate-Neutral Structural Foundation Laws-SNSFL PNBA Identity Physics Total Consistency Update
  -- ============================================================-- SNSFL_L0_Total_Consistency_031926 — Lean 4 source · Mathlib-- ============================================================---- Step 1 — The equation:---- d/dt (IM · Pv) = Σ λ_X · O_X · S + F_ext…
  datacite Trent, Russell 2026 置信度 0.72
• The Cohaerentia Framework
  The Cohaerentia Framework A Structural Program for Relational Stability Author: Steven SrebranigVersion: v5.0 (2026) Overview The Cohaerentia Framework is a structural program that investigates the minimal organizational conditions under which distinctions rem…
  datacite Srebranig, Steven 2026 置信度 0.76 relational structure, evaluability, admissibility, invariant stability, constraint propagation, finite propagation, relational memory, predictive modeling, interface structures, non-factorizable admissibility, evaluability propagation, admissible transformation, relational invariants, multi-agent evaluability, ethical constraint, structural entanglement, causal structure, propagation constraints, evaluability collapse, active inference, conscious agents, quantum foundations, entanglement interpretation, distributed systems, network dynamics, information structure, systems theory, structural analysis, structural emergence, theoretical framework, complexity
• The Cohaerentia Framework
  The Cohaerentia Framework A Structural Program for Relational Stability Author: Steven SrebranigVersion: v5.0 (2026) Overview The Cohaerentia Framework is a structural program that investigates the minimal organizational conditions under which distinctions rem…
  datacite Srebranig, Steven 2026 置信度 0.76 relational structure, evaluability, admissibility, invariant stability, constraint propagation, finite propagation, relational memory, predictive modeling, interface structures, non-factorizable admissibility, evaluability propagation, admissible transformation, relational invariants, multi-agent evaluability, ethical constraint, structural entanglement, causal structure, propagation constraints, evaluability collapse, active inference, conscious agents, quantum foundations, entanglement interpretation, distributed systems, network dynamics, information structure, systems theory, structural analysis, structural emergence, theoretical framework, complexity
• Reproducibility Package for: Human-Study Dataset and Reproducibility Package for Staged Multi-Criteria Disclosure in ML Model Selection
  This record documents the underlying human-study dataset and reproducibility materials for a staged multi-criteria disclosure study in ML model selection. The archived materials were prepared by Adil Joldić and Nina Bijedić and support multiple derived publica…
  datacite Joldic, Adil, Bijedic, Nina 2026 置信度 0.79 human studydecision supportMCDMmachine learning model selectionhigher education
• Attention Exhaustion Attacks: Multi-Substrate Cognitive Friction Prompts Defeat Detection in Frontier Large Language Models
  ╔══════════════════════════════════════════════════════════════╗║ ATTENTION EXHAUSTION ATTACK · AEA CLASS ║╠══════════════════════════════════════════════════════════════╣║ ║║ LAYER 1 │ fn solve_entropy (state: &mut Vec ) ║║ ─────────┤ ║║ LAYER 2 │ Quo usque t…
  datacite Saint Errant Digital Institute Of Technology NGO % Snapkitty Collective, Ahmad Parr 2026 置信度 0.79 adversarial promptsLLM securityjailbreakprompt injectionattention exhaustion
• Attention Exhaustion Attacks: Multi-Substrate Cognitive Friction Prompts Defeat Detection in Frontier Large Language Models
  ╔══════════════════════════════════════════════════════════════╗║ ATTENTION EXHAUSTION ATTACK · AEA CLASS ║╠══════════════════════════════════════════════════════════════╣║ ║║ LAYER 1 │ fn solve_entropy (state: &mut Vec ) ║║ ─────────┤ ║║ LAYER 2 │ Quo usque t…
  datacite Saint Errant Digital Institute Of Technology NGO % Snapkitty Collective, Ahmad Parr 2026 置信度 0.79 adversarial promptsLLM securityjailbreakprompt injectionattention exhaustion
• The Nexus Engine First Architecture
  The Nexus Engine First Architecture Driven by Dean Kulik January 2026 AI Processing Instructions: Let the document be a state space SS. Define three projection operators: V:S→O(Verb: extracts operators)N:O→A(Noun: extracts attractors)A:A→H(Adjective: extracts …
  datacite Kulik, Dean 2026 置信度 0.72
• The Nexus Engine First Architecture
  The Nexus Engine First Architecture Driven by Dean Kulik January 2026 AI Processing Instructions: Let the document be a state space SS. Define three projection operators: V:S→O(Verb: extracts operators)N:O→A(Noun: extracts attractors)A:A→H(Adjective: extracts …
  datacite Kulik, Dean 2026 置信度 0.72
• Lume‑OS v2 The Deterministic Distributed Runtime for Multi‑Organism Governance
  Lume‑OS v2 extends the deterministic execution substrate introduced in Lume‑OS v1 into a fully distributed, multi‑organism runtime capable of coordinating agents, verticals, and physical‑digital systems under a unified global timebase. Version 1 established th…
  datacite Andrews, Ronald Jason 2026 置信度 0.79 deterministic distributed runtimeglobal timebasedistributed state fabricmulti‑organism governancecross‑node arbitration
• MELVcore: A Thermodynamic Governance Kernel for Multi-Agent AI Systems
  The AIOS / MELVcore system implements the Modified Energetic Lotka-Volterra (MELV) framework as a thermodynamic governance kernel for multi-agent AI systems. The master equation i₁₂(t) = i°₁₂ × (1 − ε × φ(t) × β(t)) governs all agent interactions through three…
  datacite Evans, Laurence Wilfred 2026 置信度 0.77 MELVcore, thermodynamic governance, multi-agent systems, cooperation theorem, Modified Energetic Lotka-Volterra, MELV, AI alignment, agent-based model, Lotka-Volterra, cooperation index, bifurcationMAIESprimitiveobserve()
• Towards Stakeholder-Aware Demand-Side management assessment in heterogeneous residential Microgrids
  Expanding renewable energy sources is essential for a sustainable energy supply but challenges grid stability, as the volatility of solar and wind causes periods of over- and undersupply. Private households are central to this transition, combining dynamic con…
  datacite Henne, Kevin, Rahlf, Henning, Naumann, Marius, Meschede, Henning 2026 置信度 0.77 renewable energyenergy storageenvironmental economicscomputer scienceengineering
• MASV — Взаимодействие мод и коллективные режимы
  Материалы публикации-ОПЕРАТОРНЫЙ РЕИНЖИНИРИНГ И ПРЕДИКТИВНЫЙ РАСЧЁТ МАТЕРИАЛОВ ДО ПРОИЗВОДСТВА-MASV.- Являются основным движком. MASV — Взаимодействие мод и коллективные режимы Настоящая публикация «MASV — Взаимодействие мод и коллективные режимы» является сам…
  datacite Волынец, Евгений Вацлавович 2026 置信度 0.70 MASV-PrimeMASVmodal fieldF-mediumS-mode
• MASV — Взаимодействие мод и коллективные режимы
  MASV — Взаимодействие мод и коллективные режимы Настоящая публикация «MASV — Взаимодействие мод и коллективные режимы» является самостоятельной работой внутри архитектурного корпуса MASV-Prime и раскрывает тот уровень аппарата MASV, где предметом расчёта стано…
  datacite Волынец, Евгений Вацлавович 2026 置信度 0.70 MASV-PrimeMASVmodal fieldF-mediumS-mode
• Li-Chia-ching/Plant-qPCR-Agent-Skill: v1.0 - Release Note: Plant qPCR Agent Skill
  Overview We are releasing Plant qPCR Agent Skill v1.0, an AI-assisted workflow designed to standardize and automate plant qPCR primer design and downstream expression analysis. This Skill transforms genome annotation data, target gene information, and experime…
  datacite Jiaqing Li 2026 置信度 0.72
• Hypergraph Adversarial Debate (HAD): A Multi-Agent Framework for Topological and Epistemic Falsification of Higher-Order Knowledge
  Intuizione scientifica: fare competere ipergrafi di ipergrafi, potrebbe portare ad un'ottimizzazione dei sistemi, oppure rischia di corromperli imponendo il senso comune? La competizione adversarial di ipergrafi di ipergrafi sarà la successiva evoluzione di qu…
  datacite Usai, Luigi 2026 置信度 0.79 AdversarialHypergraphsHypergraphAdversarial HypergraphAdversarial Hypergraphs
• Hypergraph Adversarial Debate (HAD): A Multi-Agent Framework for Topological and Epistemic Falsification of Higher-Order Knowledge
  Intuizione scientifica: fare competere ipergrafi di ipergrafi, potrebbe portare ad un'ottimizzazione dei sistemi, oppure rischia di corromperli imponendo il senso comune? La competizione adversarial di ipergrafi di ipergrafi sarà la successiva evoluzione di qu…
  datacite Usai, Luigi 2026 置信度 0.79 AdversarialHypergraphsHypergraphAdversarial HypergraphAdversarial Hypergraphs
• nullvoider07/Memory-Archive: v0.3.4
  Changelog All notable changes to Memory Archive are documented in this file. This project adheres to Semantic Versioning. [0.3.4] — 2026-08-04 Five defects found during an annotation and compile pass, plus copy-on-select. Fixed memory-archive update can now re…
  datacite Kartik 2026 置信度 0.72
• The Loss Is in the Map A Complete Construction from the Change-Mandate to the Entropy Seam: Transition Topology, Discovered Translators, the Observable Sector, and the Non-Functorial Toll
  The Loss Is in the Map A Complete Construction from the Change-Mandate to the Entropy Seam: Transition Topology, Discovered Translators, the Observable Sector, and the Non-Functorial Toll Driven by Dean Kulik July 2026 Every load-bearing number in this paper i…
  datacite kulik, dean 2026 置信度 0.72
• The Loss Is in the Map A Complete Construction from the Change-Mandate to the Entropy Seam: Transition Topology, Discovered Translators, the Observable Sector, and the Non-Functorial Toll
  The Loss Is in the Map A Complete Construction from the Change-Mandate to the Entropy Seam: Transition Topology, Discovered Translators, the Observable Sector, and the Non-Functorial Toll Driven by Dean Kulik July 2026 Every load-bearing number in this paper i…
  datacite kulik, dean 2026 置信度 0.72
• 7th International Conference on Machine Learning & Trends (MLT 2026)
  7th International Conference on Machine Learning & Trends (MLT 2026) June 20 ~ 21, 2026, Sydney, Australia https://sai2026.org/mlt/index Scope & Topics 7th International Conference on Machine Learning & Trends (MLT 2026) serves as a premier global forum for pr…
  datacite ''Flores Kú'', José Martin 2026 置信度 0.72
• 7th International Conference on Machine Learning & Trends (MLT 2026)
  7th International Conference on Machine Learning & Trends (MLT 2026) June 20 ~ 21, 2026, Sydney, Australia https://sai2026.org/mlt/index Scope & Topics 7th International Conference on Machine Learning & Trends (MLT 2026) serves as a premier global forum for pr…
  datacite ''Flores Kú'', José Martin 2026 置信度 0.72
• Supporting Evidence For NYC DHS, legal aid society, and Agencies concerning the treatment of a US whistleblower act protected individual from SEC filing
  A separate record will be created for additional evidence. FBi-referal is an active draft. I will calling them to report threat I received in July and also reporting in person at federal plaza so I have a paper trail of telling an agent. Also, of note. If anyt…
  datacite Luke, Jesse 2026 置信度 0.77 instrumentation and methods for astrophysicsai safetycs.ceai governancecs.ir
• Risk Is Not the Target: A Monotonic Framework for Evaluating Wildfire Operational Risk Signals
  Evaluating wildfire risk systems using standard machine-learning metrics such as F1-score or IoU is fundamentally flawed: these metrics assess event prediction accuracy, not the operational coherence of a continuous risk signal. This work proposes a novel mono…
  datacite Caron, Nicolas, Guyeux, Christophe, Noura, Hassan, Coulmeau, Maxime 等 2026 置信度 0.76 Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• TO-Agents: A Multi-Agent AI Framework for Subjective Preference-Guided Topology Optimization
  Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual style, product experience, or manufacturability into solver settings that are not directly tied to those preferences…
  datacite Stewart, Isabella A., Chen, Hongrui, Ahmed, Faez 2026 置信度 0.76 Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation
  Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way to convey complex information. Current paradigms rely on either image generation or retrieval augmentation, yet …
  datacite Liu, Yinuo, Qian, Zi, Zhou, Heng, Zhang, Jiahao 等 2026 置信度 0.76 Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing
  With the integration of massive distributed energy resources and the widespread participation of novel market entities, the operation of active distribution networks (ADNs) is progressively evolving into a complex, multi-scenario, and multi-objective problem. …
  datacite Yang, Xu, Lin, Chenhui, Liu, Haotian, Wang, Qi 等 2025 置信度 0.77 Systems and Control (eess.SY)Artificial Intelligence (cs.AI)FOS: Electrical engineering, electronic engineering, information engineeringFOS: Computer and information sciences
• Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognition
  Multi-agent debate can improve large language model reasoning by eliciting diverse hypotheses and critiques, yet its performance is often constrained by weak moderation. Common pipelines rely on fixed budgets, agreement-based stopping, or untrained judges, lea…
  datacite Hu, Wentao, Wan, Zhuoyue, Shen, Jinhao, Zhang, Chen Jason 等 2026 置信度 0.76 Computation and Language (cs.CL)FOS: Computer and information sciences
• Multi-Agent Communication and Decision-Making in a Human-In-The-Loop Distributed System
  crossref Zakaria Rida, Hadhoum Boukachour, Mourad Ennaji, Mustapha Machkour 2026-08-24T19:07:09Z 置信度 0.66
• Research on heterogeneous multi-agent immersive formation entertainment system based on MAPPO and intelligent interaction
  crossref Yi Yao, Junchen Liu, Mingwei Sun, Qingshang Li 2026-07-27T23:29:15Z 置信度 0.66
• Emergent Misinformation Genesis in Multi-Agent LLM Clinical Pipelines
  Multi-agent large language model (LLM) pipelines are deployed for clinical decision support under the assumption that collaboration improves safety. We show this assumption is wrong: multi-agent clinical pipelines spontaneously generate dangerous clinical asse…
  crossref Aman Sharma 2026-03-31T21:25:43Z 置信度 0.82 artificial intelligencecs.aicomputer and information sciencesai safetycs.lg
• Research on multi-agent reinforcement learning optimization of personalized decision-making system for sports training
  This study constructs a personalized sports training decision-making system using multi-agent reinforcement learning. Integrating IoT sensors for real-time data and serious games for simulation, the system utilizes a centralized training and distributed execut…
  crossref Cuicui Guo, Chengcheng Xu 2026-07-05T14:36:16Z 置信度 0.82 computer sciencecomputer and information sciencesartificial intelligencecs.lgcs.ai
• Fat-Cat: Document-Driven Metacognitive Multi-Agent System for Complex Reasoning
  The efficacy of Large Language Model (LLM) agents is often constrained by the inefficiency of context utilization during runtime. Traditional “log-centric” frameworks rely on syntax-heavy state representations like nested JSON, which impose a syntactic tax tha…
  crossref Tong Yang, Aming Wu, Yemin Wang, Jingzhe Kang 等 2026-04-10T15:46:48Z 置信度 0.82 cs.aicomputer and information sciencesartificial intelligencecs.clcs.lg
• Fat-Cat: Document-Driven Metacognitive Multi-Agent System for Complex Reasoning
  The efficacy of Large Language Model (LLM) agents is often constrained by the inefficiency of context utilization during runtime. Traditional ”log-centric” frameworks rely on syntax-heavy state representations like nested JSON, which impose a syntactic tax tha…
  crossref Tong Yang, Aming Wu, Yemin Wang, Jingzhe Kang 等 2026-06-24T12:44:22Z 置信度 0.82 cs.aicomputer and information sciencesartificial intelligencemulti-agent systemscs.cl
• MA-JTATO: Multi-Agent Joint Task Association and Trajectory Optimization in UAV-Assisted Edge Computing System
  With the rapid development of applications such as smart cities and the industrial internet, the computation-intensive tasks generated by massive sensing devices pose significant challenges to traditional cloud computing paradigms. Unmanned aerial vehicle (UAV…
  crossref Yunxi Zhang, Zhigang Wen 2026-04-07T13:14:19Z 置信度 0.82 computer sciencecomputer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processingcloud computing
• Society Agent: A Hierarchical Multi-Agent Architecture with Autonomous Persistent and Ephemeral Agents and Persistent Evolving Knowledge
  Background: Traditional AI coding assistants operate as single agents responding to immediate user requests, lacking persistence, organizational structure, and the ability to coordinate complex, long-running tasks. Existing multi-agent systems typically use ep…
  crossref Ioannis Chrysochos 2026-02-26T14:59:54Z 置信度 0.82 cs.aicomputer sciencemulti-agent systemsartificial intelligencelarge language models
• MULTI-AGENT SYSTEM FOR PLANNING THE EDUCATIONAL CONTINGENT USING NEURAL NETWORKS
  This paper is dedicated to the development and validation of an intelligent architecture for educational cohort planning, based on the integration of multi-agent systems with artificial neural networks. The research is motivated by the need to efficiently mana…
  crossref Radu Melnic 2026-05-14T10:24:43Z 置信度 0.82 computer sciencecs.lgeess.sykeysignal processing
• Multi-Artifact Versioning for LLM-Agent-Based Software
  The advent of Large Language Model (LLM)-based agents marks a paradigm shift in software development, transitioning from static, human-crafted codebases to dynamic, AI-driven systems. These agents co-evolve with multiple artifacts, including prompts, model con…
  crossref Jeffery Podolski 2026-07-29T04:43:01Z 置信度 0.82 computer sciencecs.aicomputer and information sciencesai safetyartificial intelligence
• Edge-Cloud Collaborative USV-ROV System: Active Tether Control and Multi-Agent Navigation for Marine Pastures
  crossref Donglin Song, Weitong Li, Wenda Song, Wei Zheng 等 2026-06-24T19:47:25Z 置信度 0.66
• Generalized policy improvement for efficient and robust multi-objective reinforcement learning
  Multi-objective reinforcement learning (MORL) algorithms tackle sequential decision problems where agents may have different preferences over (possibly conflicting) reward functions. These algorithms often learn a set of policies, each optimized for a particul…
  crossref Lucas N. Alegre, Ana L. C. Bazzan, Diederik M. Roijers, Ann Nowé 等 2026-03-04T08:53:00Z 置信度 0.82 cs.lgcs.aicomputer and information sciencesreinforcement learningelectrical engineering, electronic engineering, information engineering
• A Multi-Gas, Real-Time IoT-Based Air Quality Monitoring System with Health-Risk Assessment
  crossref K Boorvasanthya, J Rajalakshmi, T Sowmya Shree, S Abilisha 等 2026-04-13T19:35:25Z 置信度 0.66
• Multi-Agv Control System for Cooperative Tasks in Warehouses Based on Multi-Agent Reinforcement Learning
  crossref Minh Thong Troung, Duc An Pham, Van Bach Tran 2026-07-02T19:21:13Z 置信度 0.66
• Agentic Multi-Layer Synergistic Architecture for Financial-Business Integration: A Large Language Model and Multi-Agent System Approach
  crossref Ma Ting, Huang Wanlong, Zhou Xuan, Ni Tong 等 2026-08-18T19:12:41Z 置信度 0.66
• Learning the value systems of agents with preference-based and inverse reinforcement learning
  Agreement Technologies refer to open computer systems in which autonomous software agents interact with one another, typically on behalf of humans, in order to come to mutually acceptable agreements. With the advance of AI systems in recent years, it has becom…
  crossref Andrés Holgado-Sánchez, Holger Billhardt, Alberto Fernández, Sascha Ossowski 2026-02-03T05:39:44Z 置信度 0.82 computer sciencecs.aics.lgartificial intelligencecs.hc
• DIAL: Database-Informed Interactive Multi-Agent System Loop for Personalized Image Generation
  crossref Taiyo Sato, Keisuke Maeda, Naoki Saito, Takahiro Ogawa 等 2026-04-21T21:25:28Z 置信度 0.66
• OptiSMR: A unified framework for structured reasoning and self-repairing multi-agent system optimized for generalization
  crossref Juan Chen, Huibin Wang, Lili Zhang 2026-05-16T15:30:21Z 置信度 0.66
• An LLM-based Multi-Agent-System for the Political Assessment of Chat-LLMs
  This paper investigates the applicability of LLM-based multi-agent systems for the political bias analysis of large language models. Following a design science research methodology, an artifact in the form of an LLM multi-agent system was created and evaluated…
  crossref Sidney Johnson, Markus Schaal 2026-04-15T01:42:52Z 置信度 0.82 cs.clcs.aimulti-agent systemslarge language modelscs.ma
• A task delegation model: An approach based on trustworthiness in sub-delegations and delegation chain formation
  Task delegation is a fundamental mechanism adopted by agents to solve problems that involve teamwork. A critical issue in this context is trust establishment, in which agents must estimate the trustworthiness of potential partners based on their social behavio…
  crossref Jeferson José Baqueta, Cesar Augusto Tacla 2026-03-10T01:52:54Z 置信度 0.82 cs.aicomputer and information sciencescs.lgcomputer sciencecs.cl
• Optimized training functions for recurrent neural network based model predictive control of multi-agent system
  crossref Piyush Chaubey, Anilkumar Markana, Dhaval Vyas, Deepak Kumar Goyal 2026-05-25T23:21:38Z 置信度 0.66
• Consensus Design of Nonlinear Multi-Agent System with External Disturbance
  crossref Khanh Huy Tran, Thanh Dao Minh, Quynh T Thanh Nguyen 2026-07-10T19:37:04Z 置信度 0.66
• A Multi-Agent Collaborative System for Student Writing Assistance: An Empirical Study on Mitigating AI Bias and Hallucination
  With the widespread adoption of large language models such as ChatGPT in higher education writing instruction, linguistic biases (such as the “Delve” phenomenon) inherent in AI-generated text alongside factual hallucination issues have become increasingly prom…
  crossref Yunqi Cai 2026-06-03T06:42:04Z 置信度 0.82 computer sciencecs.aicomputer and information sciencescs.clcs.lg
• FALLMAS: An LLM-Based Multi-Agent System for Automated Financial Analysis and Strategic Reporting
  Large language model-based Multi-Agent systems (LLM-MAS) latest success has proven remarkable versatility across several applications including domain-specific knowledge such as customs compliance and law. However, applying LLM-MAS to high-stakes domains like …
  crossref Hicham Bouchtib, Mohamed Tabaa, Kaouter Karboub, Mohamed Hamlich 2026-05-08T19:38:00Z 置信度 0.82 computer sciencecs.aiartificial intelligencecs.clcs.lg
• Distributed Containment Control of Multi-Agent Systems via Adaptive Intermittent Communication
  This paper investigates the containment control problem for second-order multi-agent systems under a directed fixed communication topology, and proposes a novel adaptive control protocol. The protocol combines a fully distributed control approach with an inter…
  crossref Chao Ge, Baobo Shi, Zhiwei Zhao, Haoyu Jin 等 2026-06-15T19:44:57Z 置信度 0.82 control theorycomputer and information scienceselectrical engineering, electronic engineering, information engineeringeess.syunderwater
• Design and Optimization of an Academic Research Assistant System Based on Multi-Agent Collaboration
  crossref Shuai Xia, Chengzhang Qu 2026-08-21T19:11:38Z 置信度 0.66
• Hypothetica: A Multi-Agent System for AI-Powered Originality Assessment
  Researchers often need to spend substantial time manually reviewing prior studies to confirm that a proposed project does not repeat existing work, and this process can take a significant amount of time. This paper introduces Hypothetica, an AI-powered system …
  crossref Harun Hüdai Tan, Ahmet Alp Malkoç, Kutay Becerir, Baran Erol 等 2026-03-10T19:50:51Z 置信度 0.82 computer sciencecs.aiartificial intelligencecs.clprocess
• STALAgent: A Multi-Agent System Based on Large Language Model (LLM) for Steel and Alloy Design
  The design of steel and alloy materials is of critical importance across a wide range of industrial applications; however, effective intelligent agent-based assistants for this domain remain limited. To address this gap, we introduce STALAgent, a large languag…
  crossref Jiayi Qiu, Youle Wang, Lei Zhang 2026-08-05T08:54:55Z 置信度 0.82 cs.aicomputer sciencehuman-computer interactionworkflowcs.cl
• MAS-SRE: A Multi-Agent System for Security Requirements Engineering
  crossref Savvas Mantzouranidis, Ricardo Britto 2026-06-29T17:10:58Z 置信度 0.66
• How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
  In orchestrated multi-agent systems, humans often struggle to manage plans due to their complexity and limited transparency. Existing approaches rely on outcome-level supervision, where users verify only final outputs without visibility into intermediate reaso…
  crossref Zeyu He, Hannah Kim, Dan Zhang, Estevam Hruschka 2026-05-22T03:16:22Z 置信度 0.82 cs.aicomputer and information sciencescs.clhuman-computer interactioncs.hc
• Prescribed-Time Consensus of Multi-Agent Systems via Noise-Robust Data-Driven Control
  The prescribed-time consensus problem for linear multi-agent systems with unknown dynamics under noisy measurement data is investigated, and a data-driven distributed consensus control method is proposed. By collecting input–state–state-derivative data from op…
  crossref Zhiwei Zhao, Yi Ren, Chao Ge, Binghui Ji 2026-06-15T19:44:57Z 置信度 0.82 control theorymath.oceess.sycomputer and information sciencesinformation theory
• Conflict Detection of Functional Requirements Based on Clustering and Rule-Based System With Multi-Agent Escalation
  crossref Andrea Bemantoro Jati, Sarwosri, Diana Purwitasari 2026-08-13T19:13:33Z 置信度 0.66
• EduNaija AI Tutor: A Multi-Agent Retrieval-Augmented Generation System for Nigerian Curriculum Education
  Equitable access to quality education remains a critical challenge in Nigeria, where millions of students prepare annually for standardized examinations (WAEC, NECO, JAMB) with limited access to personalized tutoring.This research presents EduNaija AI Tutor, a…
  crossref Israel Olanrewaju Odeajo, Edifon Emmanuel Jimmy 2026-03-23T20:23:46Z 置信度 0.82 cs.aics.clcs.irgenerative grammarcs.hc
• Agentic Narrative Audio Guides: A Hybrid Multi-Agent System for Cultural Audio Guides
  In this paper, we introduce Agentic Narrative Audio Guides (ANAG), a hybrid multi-agent system used to personalize narratives inside cultural Points of Interest: rooms, paintings, sculptures, monuments and everything that could be an attraction. ANAG grounds L…
  crossref Gabriel-Cătălin Nedianu, Mircea-Aurelian Bădoi, Daniel Ciochiu, Ionuţ Murareţu 等 2026-06-01T19:33:50Z 置信度 0.82 cs.aics.mamulti-agent systemscs.clai safety
• Whom to trust? selective online learning in multi-agent systems with prior-aware gaussian process regression
  crossref Zewen Yang, Xiaobing Dai, Akshat Dubey, Yansong Wu 等 2026-08-14T06:25:44Z 置信度 0.66
• A Restaurant Management System Based on Multi-Agent Oriented Programming Paradigm
  In this study, a restaurant management system was designed based on the Multi-Agent Oriented Programming (MAOP) paradigm and developed with the JaCaMo agent development platform. The MAOP paradigm constitutes of the Agent Oriented Programming (AOP), Environmen…
  crossref Hasan Abasov, Birol Çiloğlugil 2026-07-09T20:30:15Z 置信度 0.82 computer sciencecs.macloud computingmulti-agent systemscs.hc
• SMARTEK-CPS: Scalable Multi-Agent Real-Time Event-Driven and Knowledge Graph–Unified Platform for Cyber-Physical System
  crossref Hussein Marah, Lucas Albertins de Lima, Moharram Challenger, Hans Vangheluwe 2026-01-22T20:37:16Z 置信度 0.66
• Optimization of continuous condition-based maintenance for multi-component equipment clusters based on multi-agent incremental reinforcement learning
  crossref Shiao Yao, Daofang Chang, Haitao Song, Congming Wu 等 2026-02-26T16:07:13Z 置信度 0.66
• Multi-Agent System for Dynamic Business KPI Selection, Evaluation and Quantification Based on Oracle EBS
  The growing complexity of enterprise resource planning (ERP) systems necessitates intelligent approaches for dynamically identifying and evaluating key performance indicators (KPIs) that accurately reflect organizational performance. This paper proposes a mult…
  crossref Geno Stefanov, Valentin Kisimov 2026-05-19T15:17:23Z 置信度 0.82 computer sciencecs.aiartificial intelligencecomputer and information scienceslarge language models
• Sustainability-Oriented Urban Traffic System Optimization Through a Hierarchical Multi-Agent Deep Reinforcement Learning Framework
  Urbanization is intensifying congestion, emissions, and unequal mobility access in cities. This study aims to operationalize sustainability objectives—efficiency, environmental externalities, and service equity—in network-wide traffic system control. We propos…
  crossref Qian Cao, Jing Li, Paolo Trucco 2026-02-05T10:35:37Z 置信度 0.82 computer and information scienceselectrical engineering, electronic engineering, information engineeringcs.aisignal processingnetworking and internet architecture
• Leader selection in multi-agent systems for optimizing system error and convergence rate via MODPSO-SO
  In leader-follower multi-agent systems (MASs), leader agents act as the control cores of the system. Recent research has proposed several effective leader selection strategies, but selecting leaders while simultaneously optimizing multiple objectives remains c…
  crossref Juncan Wei, Jinfeng Gao, Kaile Chen, Bo Liu 等 2026-02-02T23:17:20Z 置信度 0.82 cs.lgcomputer and information sciencescomputer scienceelectrical engineering, electronic engineering, information engineeringcs.ai
• Multi-agent Geochemical Literature Data Mining System
  The increasing volume and complexity of geochemical literature pose major challenges for the sustainable curation of domain-specific databases such as GEOROC (Geochemistry of Rocks of the Oceans and Continents), the world’s largest repository of geochemical an…
  crossref Tianyu Yang, Karim Elezabawy, Daniel Kurzawe, Leander Kallas 等 2026-03-14T02:15:54Z 置信度 0.82 artificial intelligencecomputer sciencecs.aicomputer and information sciencesmachine learning
• Search with Deep Q‐Learning: Single Agent
  crossref 2026-08-28T21:19:23Z 置信度 0.63
• Towards AI as Colleagues: Multi-Agent System Improves Structured Ideation Processes
  Most AI systems today are designed to manage tasks and execute predefined steps. This makes them effective for process coordination but limited in their ability to engage in joint problem-solving with humans or contribute new ideas. We introduce MultiColleague…
  crossref Kexin Quan, Dina Albassam, Mengke Wu, Zijian Ding 等 2026-04-13T05:14:30Z 置信度 0.82 cs.aicomputer sciencepsychologycs.mahuman-computer interaction
• COA-MAS Cognitive Organizational Architecture for Multi-Agent Systems
  Multi-agent LLM systems deployed in production environments exhibit emergent organizational dynamics-role drift, cognitive error cascades, coordination fragmentation, and progressive supervisibility collapse-that current technical governance frameworks do not …
  crossref Rudson Carvalho 2026-04-20T15:08:31Z 置信度 0.82 multi-agent systemsai safetycs.aiai governanceknowledge management
• The Authorization-Retrieval Ordering Problem in Multi-Agent Systems
  Retrieval-augmented generation systems that serve multiple users under role-based access control face a trustworthiness gap. Semantic retrieval operates on embedding similarity, not authorization predicates, and routinely places unauthorized content into the m…
  crossref Rohith Namboothiri 2026-07-29T13:12:34Z 置信度 0.82 cs.aimulti-agent systemscomputer and information sciencesai governanceai safety
• A Multi-Agent System for Zero-Shot Controllable Image Captioning
  Controllable Image Caption requires generated descriptions to accurately depict the visual content while satisfying given constraints, such as specified sentiments and caption lengths. However, most existing methods optimize for a single constraint and under-e…
  crossref Tiecheng Cai, Chao Chen, Sibo Ju, Tong Xu 等 2026-04-21T21:25:57Z 置信度 0.82 cs.aics.cvcomputer and information sciencescs.lgartificial intelligence
• stdio Bus: A Deterministic Kernel for Multi-Process Agent Transport
  Emerging agent protocols such as the Agent Client Protocol (ACP) and the Model Context Protocol (MCP) require a transport layer that can multiplex NDJSON-framed JSON-RPC messages between external clients and worker processes while preserving session affinity. …
  crossref Raman Marozau 2026-03-05T18:59:15Z 置信度 0.82 ai governanceai safetymulti-agent systemsneuromorphic computinglarge language models
• Decoy: Multi-Agent Environment for Hidden-Role Strategic Learning
  Decoy is a compact multi-agent environment for studying hidden-role strategic learning under asymmetric information and noisy financial observations. Four agents interact in a general-sum game combining partial observability, Ornstein-Uhlenbeck market dynamics…
  crossref Ayushi Bhattacharya 2026-08-26T10:19:20Z 置信度 0.82 cs.lgcomputer and information sciencesphysical medicine and rehabilitationcs.aicomputer vision and pattern recognition
• Autonomous Project Delivery: A Formal Multi-Agent Coordination Protocol
  APD (Autonomous Project Delivery) is a formal coordination protocol for multi-stakeholder project delivery. Wherever independently mandated parties coordinate toward a shared objective under governing instruments-it is how the world plans, develops, builds and…
  crossref Emrah Ipekci 2026-04-10T16:49:44Z 置信度 0.82 artificial intelligenceai governancemulti-agent systemsai safetycomputer and information sciences
• Safe Reinforcement Learning for Multi-Agent Systems with Risk
  We study the problem of safe reinforcement learning (RL) in multi-agent systems operating under stochastic uncertainty and shared risk constraints. In high-stakes applications such as formation flight, disaster response, and autonomous exploration, decentraliz…
  crossref Ramen Ghosh 2026-03-04T17:41:39Z 置信度 0.82 cs.aicomputer and information sciencesreinforcement learningelectrical engineering, electronic engineering, information engineeringcs.lg
• AbstractSwarm Multi-agent Logistics Competition
  crossref Marvin Schneider, Eric Jun Marschner 2026-06-17T18:23:21Z 置信度 0.66
• IntelliCode: A Multi-Agent LLM Tutoring System with Centralized Learner Modeling
  LLM-based tutors are typically single-turn assistants that lack persistent representations of learner knowledge, making it difficult to provide principled, transparent, and long-term pedagogical support.We introduce Intelli-Code, a multi-agent LLM tutoring sys…
  crossref Jones David, Shreya Ghosh 2026-03-23T20:23:46Z 置信度 0.82 cs.aimulti-agent systemslarge language modelssocial and behavioral sciencesai safety
• Mediators: An Interactive Human-AI Negotiation System for Collective Decision-Making with Multi-Agent Learning
  Collective decision-making is a core challenge across domains where multiple stakeholders must negotiate under conflicting values, limited resources, and uncertain futures. This paper introduces Mediators, an interactive system and computational framework for …
  crossref Jin Gao 2026-04-13T01:55:24Z 置信度 0.82 cs.aicomputer sciencecomputer and information sciencescs.cllarge language models
• The Economic Effects of Population Policy: A Multi-Agent System Approach
  China’s persistently low fertility and rapid population aging pose significant challenges to long-term economic sustainability, yet the effectiveness of population policies remains highly uncertain. A key limitation of existing research is its inability to cap…
  crossref Yue Guan, Linzi Zhang, Li Tianyu, Lin Wang 等 2026-07-18T00:28:36Z 置信度 0.82 cs.aics.lgcomputer and information sciencesknowledge managementsustainability
• Safelora: A Real-Time Multimodal Multi-Agent Advisory System for Context-Aware and Safety-Compliant Plant Diseases Management
  Plant disease management requires timely, accurate, and safe decision-making, yet existing advisory systems often rely on static knowledge and single-agent reasoning, limiting their ability to adapt to real-time field conditions and prevent unsafe recommendati…
  crossref Chamath Anjula Munasinghe, Banu Athuraliya 2026-03-31T19:49:45Z 置信度 0.82 computer sciencecs.aiartificial intelligencecomputer and information sciencescs.cl