AI Agent 生态 · 全部实体（第 77 / 100 页）

本页收录第 7601–7700 条，共 10000 条 · 返回 AI Agent 生态 首页

• ADAM: A Governed Operating Machine for AI-Native Software and Multi-Agent Systems
  Large language models are rapidly moving software development from code completion toward workflow-level agency. Contemporary coding agents can inspect repositories, formulate plans, modify files, execute tools, diagnose failures, and revise implementations. Y…
  crossref Surendra Reddy 2026-08-12T06:00:26Z 置信度 0.70
• Nikolas: AI Agent for Semi-Autonomous Catalyst Discovery Using the PRISM Meta-Cognitive Architecture
  The discovery of efficient catalysts for CO 2 reduction is critical for addressing climate change, yet traditional approaches rely on expensive noble metals and time consuming trial-and-error experimentation. We present Nikolas, a semi-autonomous AI agent for …
  crossref Pandurang Mopgar 2026-02-20T06:56:03Z 置信度 0.70
• Author response for "Masgent: An AI-assisted Materials Simulation Agent"
  crossref Guangchen Liu, Songge Yang, Yu Zhong 2026-04-17T21:06:04Z 置信度 0.70
• Adaptive Multi-Agent Role Reassignment over Model Context Protocol for Resilient AI Orchestration
  Multi-agent systems powered by large language models (LLMs) can automate complex workflows by dividing tasks among specialised roles such as research, critique and summarisation. Existing orchestration frameworks typically assign these roles statically through…
  crossref Manish Shukla 2025-09-05T13:21:31Z 置信度 0.70
• Artificial Intelligent Agent
  In AI, an agent is a computer program or system that is designed to perceive its environment, make decisions, and take actions to achieve a specific goal or set of goals. The agent operates autonomously, meaning it is not directly controlled by a human operato…
  crossref Radhika Ranjan Roy 2024-09-04T15:11:33Z 置信度 0.70
• A Comprehensive Survey of AI Agent Frameworks and Their Applications in Financial Services
  crossref Satyadhar Joshi 2025-05-14T18:46:46Z 置信度 0.70
• AI-Powered Personal Diary with Intelligent Conversational Agent
  In the modern digital era, individuals increasingly seek tools that not only help them document their daily experiences but also provide meaningful insights and guidance. Traditional diary systems, whether physical or digital, primarily function as passive sto…
  crossref Mansi Agrawal 2026-06-06T11:34:44Z 置信度 0.70
• Project Risk Assessment of a Multi-Agent AI Platform: Measured Failure Rates and Contingency
  Artificial Intelligence (AI) software is entering construction project delivery without the failure-rate evidence a project risk assessment requires, because suppliers publish none. This paper carries a five-agent AI platform through an ordinary construction r…
  crossref Reihaneh Samsami 2026-08-29T12:35:56Z 置信度 0.70
• Beyond AEO: The AI Visibility Stack and the Era of Agent Discovery Optimization
  The emergence of autonomous AI agents as active participants in B2B commerce requires a fundamental revision of how enterprises conceptualize digital visibility. Existing disciplines-Search Engine Optimization (SEO), Answer Engine Optimization (AEO), and Gener…
  crossref Gabriela Marco 2026-04-09T13:09:38Z 置信度 0.70
• Systemic Governance Risk in AI Agent Networks: Cross-Institutional Contagion and Topological Vulnerability
  <p>Financial institutions deploy AI agents through shared technology vendors, creating cross-institutional governance dependencies invisible to bilateral regulation. This paper constructs the first empirical map of that dependency surface using 239 finan…
  crossref William Collins 2026-04-10T20:26:36Z 置信度 0.70
• A Guardrail-Driven Multi-Agent Architecture for AI-Assisted Public Administration Workflows
  crossref Ciprian Paduraru, Bogdan Dumitru, Alin Stefanescu 2026-05-26T00:00:20Z 置信度 0.70
• Leading Human-Agent Teams: The ORCHESTRA Framework for Accountable AI Work
  Artificial intelligence is moving from a tool that assists individual tasks to an organizational actor that participates in workflows, decision processes, and service delivery. This shift creates a new leadership problem. Managers can no longer focus only on w…
  crossref Arkapravo Sarkar, Shashwat Mohapatra 2026-05-14T03:39:27Z 置信度 0.70
• Design of Hybrid Human-AI Agent Organizations: A Mathematical Framework for Organizational Dynamics
  This work develops a mathematically closed, fully identifiable, and empirically falsifiable theory of hybrid Human-AI organizational design. The research introduces a unified probabilistic representation in which classical and AI-native organizational dimensio…
  crossref Usman Zafar 2026-05-25T04:59:32Z 置信度 0.70
• Cognitive Attestation: Signing Interpretable Decompositions of Latent Model State in AI Agent Governance
  An AI agent denies a loan application. It signs a record of what it did: the decision, the applicant, the delegation under which it acted. An auditor can verify the record. The auditor cannot ask which learned features engaged, at what intensity, during the to…
  crossref Tymofii Pidlisnyi 2026-07-29T13:26:26Z 置信度 0.70
• ATLASky-AI: An Adaptive Multi-Agent Framework for Autonomous 4D Knowledge Verification in Aerospace
  Accurate integration of heterogeneous spatiotemporal data into knowledge graphs is paramount for ensuring safety and efficiency in aerospace operations. While recent research has advanced knowledge graph construction through large language models (LLMs), verif…
  crossref RAED AWILL 2025-04-17T23:07:01Z 置信度 0.70
• The Effect of Appearance of Virtual Agents in Human-Agent Negotiation
  Artificial Intelligence (AI) changed our world in various ways. People start to interact with a variety of intelligent systems frequently. As the interaction between human and AI systems increases day by day, the factors influencing their communication have be…
  crossref Berkay Türkgeldi, Cana Su Özden, Reyhan Aydoğan 2022-08-16T23:44:25Z 置信度 0.70
• Two Paths of AI in Social Science Research: Super Agent and Human Mirror
  Large language models (LLMs) are being applied across the social sciences along two qualitatively different trajectories. The *super-agent* path optimizes models to reason correctly and solve problems as an idealized rational agent; the *human-mirror* path rep…
  europepmc Jihong Zhang 2026 置信度 0.80
• Large Batch Sharing
  crossref Thibault Lahire 2026-07-12T22:10:29Z 置信度 0.70
• The Practical AI Agent Framework  <div> An Architectural Framework and Design Principles for Building Reliable AI Agents </div>
  AI agent systems use language models, information sources, external capabilities, and execution processes to complete work for users. Teams can select from many models, retrieval methods, memory designs, protocols, SDKs, and orchestration frameworks. These tec…
  crossref Abhilash Bhagat 2026-08-12T04:45:36Z 置信度 0.70
• Social Simulation of COVID-19 with AI in Japan
  This book offers vital insights from researchers on COVID-19 prevention strategies, helping readers navigate future outbreaks effectively
  crossref 2025-09-26T06:40:37Z 置信度 0.70
• A Multi-agent Security Framework for AI-Assisted Software Development
  AI-enabled tools for code generation have drastically changed software development, but security holes in the code created by AI are still significant. Several new studies show security vulnerabilities could increase by 37.6% after five rounds of iterative sof…
  crossref Deepanjan Mukherjee 2026-02-03T11:01:25Z 置信度 0.70
• AI-Agent-Based Autonomous Defense Against DoS/DDoS in AI Data Centers
  Artificial intelligence (AI) data centers host large-scale inference and training workloads that generate high volumes of legitimate network and compute traffic[1],[2]. This operational intensity makes it challenging to distinguish between normal usage spikes …
  crossref Rama Rao Katta, Venkateshwaran Dorai 2026-03-17T20:18:48Z 置信度 0.70
• Reinforcement Learning Your Way: Agent Characterization through Policy Regularization
  The increased complexity of state-of-the-art reinforcement learning (RL) algorithms has resulted in an opacity that inhibits explainability and understanding. This has led to the development of several post hoc explainability methods that aim to extract inform…
  crossref Charl Maree, Christian Omlin 2022-03-25T00:05:18Z 置信度 0.70
• Agent-to-Agent -MCP Architecture for Intelligent Enterprise Payroll Management
  crossref John Selvaraj Arulappan, Velu Natarajan, Santosh Vasudevan 2026-07-22T19:25:18Z 置信度 0.70
• Med-Agent: A Hybrid AI Agent for Multimodal Cancer Diagnosis
  Recent advances in artificial intelligence (AI) and multimodal learning have enabled new possibilities for holistic clinical decision support in the area of oncology. In this paper, we introduce MedAgent, an AI system that operates on three-dimensional dynamic…
  crossref Wojciech Dąbrowicki, Andrzej Rusiecki, Łukasz Jeleń 2025-11-06T22:13:24Z 置信度 0.70
• The AI Agent Economy
  crossref Lisa J. Y. Tan, Ken Huang 2025-06-09T13:13:04Z 置信度 0.70
• Multi-Agent AI assisted Multimodal Content Synthesis: Knowledge Sharing across Barriers
  Enabling cross-pollination of ideas across geographies can unlock new possibilities among communities. While video based knowledge exchange has proven effective within local communities, its potential for global impact remains unrealized due to barriers in lan…
  crossref Aradhana R, Rajagopal A 2026-05-05T20:00:49Z 置信度 0.70
• The <scp>AI</scp> Agent Economy
  This chapter explores the economic and ethical implications of AI agents, software that is increasingly facilitating economic activity. The economic potential of AI agents lies in their ability to optimize resource allocation, reduce friction in various econom…
  crossref 2025-10-06T07:37:41Z 置信度 0.70
• Specification and Evaluation of Multi-Agent LLM Systems - Prototype and Cybersecurity Applications
  Recent advancements in LLMs indicate potential for novel applications, as evidenced by the reasoning capabilities in the latest OpenAI and DeepSeek models. To apply these models to domain-specific applications beyond text generation, LLM-based multi-agent syst…
  crossref Felix Härer 2025-11-14T18:47:04Z 置信度 0.70
• A Compound AI Agent for Conversational Grant Discovery
  Research funding discovery remains fundamentally fragmented: researchers navigate disparate agency portals (e.g., in the United States, NSF, NIH, DARPA, Grants.gov, and many others) with heterogeneous interfaces, search capabilities, and data schemas. We prese…
  crossref Zhisheng Tang, Mayank Kejriwal 2026-05-22T03:16:22Z 置信度 0.70
• Technology for teams: the use of agent technology for self-organisation
  crossref Philippa Collins 2004-03-18T20:59:06Z 置信度 0.70
• Multi-Agent AI Architectures for Automated Customer Service Management Systems
  An increasing number of companies have recently adopted automated systems to manage their Customer Service Department. Such systems typically consist of software applications capable of supporting operations such as online booking or client support. More recen…
  crossref Ganesh Pambala 2026-03-19T07:47:40Z 置信度 0.70
• An autonomous multimodal AI agent for evidence-grounded ophthalmic diagnosis.
  Multimodal ophthalmic diagnosis requires integrating fundus photography, B-scan ultrasonography, and medical evidence, yet most artificial intelligence (AI) systems remain single-task or weakly grounded. AgentEYE is an auditable multimodal agent that routes oc…
  pubmed Zhao K, Sun Q, Kang D, Yu T 等 2026 置信度 0.82
• Benefits of co-learning with an AI agent
  The advent of effective machine learning techniques raises the question of how such procedures might benefit human learning. In this paper we study how humans solve a type of classification puzzle—the Game of Hidden Rules (GOHR)—with vs. without the assistance…
  europepmc Jacob Feldman, Lazaros Gallos, Hao Wang, Vladimir Menkov 等 2026 置信度 0.80
• Local AI agent brings tumor board expertise to hematological malignancies.
  pubmed Yu S, Sha Yu 2026 置信度 0.82
• Construction and Application of an AI-Agent-Based Workflow for the Rapid Survey of Building Damage and Functionality
  Abstract For a building's occupants, the assessment of its post-earthquake function is the most precise feedback available, and it governs the recovery strategy that follows. It nevertheless remains manual and subjective, and both conventional appraisal and in…
  europepmc Xu Zheng, Jin Liu 2026 置信度 0.80
• HABIT: A Self-Evolving AI-Agent Harness for GUI-Based CAE Software---Application to Aerospace
  Abstract GUI-based CAE software sits at the center of aerospace analysis workflows, yet interacting with it remains a labor-intensive bottleneck. Embedding foundation-model agents inside such software demands two capabilities that existing work lacks. The firs…
  europepmc Shaoqi WU, Jingyi LI, Jiayi YAO, Xingyuan JU 2026 置信度 0.80
• Developing a Generative AI Agent to Support Science Curiosity: A Theory-Informed Development and Initial Evaluation Study
  Science curiosity is a key motivational driver of learning, yet higher education often provides limited opportunities for students to pursue scientific questions through sustained and individualized support. Generative artificial intelligence (GenAI) creates n…
  europepmc 2026 置信度 0.80
• Toward a Self-Learning AI Agent for Drug Repurposing: Building Human-Scale Representations for Virtual Patients
  Virtual patients need a useful coordinate system before they can model patient-specific dynamics. Most models in AI for science operate at molecular, cellular, or organ-specific scales. However, treatment decisions are made across a whole person and across dif…
  europepmc Jianghui Xiong, Qianchen Xia 2026 置信度 0.80
• A Dynamic Written Corrective Feedback Framework Integrating AI Agent Delivery for Structured and Iterative Essay Support.
  Automated writing feedback systems are prevalent, yet most deliver static, fragmented comments that provide limited scaffolding for revision. This study evaluates the STEP-DWCF-R framework (Structured, Tiered, Evidence-driven Process for Dynamic Written Correc…
  pubmed Sheng Y, Ganapathy M, Gao Y, Zeren Y 等 2026 置信度 0.82
• A large language model-driven multidisciplinary AI agent system predicts delirium in emergency critically ill patients.
  Delirium occurs frequently in emergency departments and is associated with poor outcomes and increased burden. Early delirium risk prediction is crucial for timely prevention and intervention in emergency care, but most existing models focus on intensive care …
  pubmed Shang W, Shi T, Ma Q, Kong G 2026 置信度 0.82
• Vision-Based Digital Twin and AI Agent Framework for Low-Cost, Explainable Indoor Building Inspection and Safety Assessment.
  Aging residential buildings constructed under outdated design standards create an urgent need for scalable, evidence-based indoor safety assessment methods. Conventional manual inspections rely on subjective checklists, lack audit trails, and are impractical f…
  pubmed Jing Z, Zhu L, Chen T, Hovestadt L 等 2026 置信度 0.82
• AI Agent Prevalence and Data Quality Across Multiple Online Sample Providers
  Online recruitment platforms have become the dominant infrastructure for behavioral research, yet data quality concerns have acquired new urgency with the emergence of large language models (LLMs). Recent work showing that LLM-based agents can complete surveys…
  europepmc 2026 置信度 0.80
• HEA-Bench: An AI-Agent-Optimized Calculator of High-Entropy Alloy and Oxide Descriptors and Phase-Prediction Rules
  The empirical descriptors of high-entropy alloys and oxides, from the mixing entropy and atomic-size mismatch to the Miedema enthalpies and the Ω, Φ, and φ stability parameters, are quoted in nearly every design study, yet they are reimplemented ad hoc by indi…
  europepmc 2026 置信度 0.80
• AI Agent Adoption in Banking_A Quantitative Analysis with Focus on Bangladeshi Customer Services
  Abstract This study examines determinants of AI agent adoption in banking through secondary data analysis of 35 Bangladeshi commercial banks over 2020–2024, complemented by global comparative benchmarking. Using panel data regression and the Technology-Organiz…
  europepmc Kafe Mohammad 2026 置信度 0.80
• AutoPsychDx: An LLM Agent Framework for Automated Psychometric Diagnosis Using Multi-Method Classification
  Clinical screening with self-report instruments such as the PHQ-9 typically relies on a single psychometric method — most commonly, a sum-score cut-off. Yet this "one-size-fits-all" approach treats all items as equally informative, ignores measurement error, a…
  europepmc 2026 置信度 0.80
• An LLM-Agent-Based Framework for Calculating Node Carbon Intensity in Regional Power Systems
  Abstract Regional carbon-aware operation requires nodal carbon intensity (NCI) signals that remain valid under heterogeneous operational inputs, topology changes, and network congestion; however, existing workflows for carbon-flow tracing and marginal-emission…
  europepmc Junpeng Zhao, Rouyi Chen, Hui Jiang, Yanlu Huang 等 2026 置信度 0.80
• An Integrated Observability Intelligence Framework: Bridging Semantic Data Modeling, Caching, and LLM-Powered Multi-Agent Root Cause Analysis
  Abstract Modern cloud-native systems generate heterogeneous observability data at unprecedented scale, yet two critical gaps persist in operational intelligence. First, distributed analytical consumers independently reconstruct metric definitions from physical…
  europepmc Chris Zhang, Kevin Coleman 2026 置信度 0.80
• A multimodal LLM-agent framework for personalized clinical decision-making in hepatocellular carcinoma.
  Hepatocellular carcinoma (HCC) treatment is challenging due to tumor heterogeneity and patient variability. Current guidelines often overlook individual factors, limiting treatment precision. We developed an integrated framework combining radiomics, deep learn…
  europepmc 2025 置信度 0.80
• An LLM-Agent Framework for Adaptive Task Decomposition and Continual Strategy Updating in Non-Stationary Environments
  The study addresses the challenges faced by agents in dynamic and uncertain environments, where decision-making is easily disrupted, task structures are difficult to maintain, and strategies lack continuous adaptability. It proposes an adaptive task decomposit…
  europepmc 2026 置信度 0.80
• LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
  We present the LLM Economist, a novel framework that uses agent-based modeling to design and assess economic policies in strategic environments with hierarchical decision-making. At the lower level, bounded rational worker agents -- instantiated as persona-con…
  arxiv Seth Karten, Wenzhe Li, Zihan Ding, Samuel Kleiner 等 2025-07-21T17:21:14Z 置信度 0.78 cs.MAcs.LG
• Predicting the expected behavior of agents that learn about agents: the CLRI framework
  We describe a framework and equations used to model and predict the behavior of multi-agent systems (MASs) with learning agents. A difference equation is used for calculating the progression of an agent's error in its decision function, thereby telling us how …
  arxiv Jose M. Vidal, Edmund H. Durfee 2000-01-12T20:57:59Z 置信度 0.78 cs.MAcs.LG
• GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation
  Before letting an agent operate over real context, can you prove it used the right evidence? GroundEval turns that question into a deterministic test of what the agent searched, fetched, cited, and was permitted to access. In one case study, two frontier LLM j…
  arxiv Jeffrey Flynt 2026-06-22T00:41:16Z 置信度 0.78 cs.AIcs.CLcs.SE
• Real-Time Detection and Repair of LLM Agent Failures
  LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the standard remedy, judging every step with a second LLM, costs more than the agent itself. We ask how much detection…
  arxiv Sunny Dubey 2026-08-03T16:34:46Z 置信度 0.78 cs.AIcs.LGcs.SE
• An Adaptive, Data-Integrated Agent-Based Modeling Framework for Explainable and Contestable Policy Design
  Multi-agent systems often operate under feedback, adaptation, and non-stationarity, yet many simulation studies retain static decision rules and fixed control parameters. This paper introduces a general adaptive multi-agent learning framework that integrates: …
  arxiv Roberto Garrone 2025-11-24T21:41:45Z 置信度 0.78 cs.MAcs.AIcs.LGeess.SY
• S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination
  We address concurrency control for LLM agents sharing mutable state over HTTP, where agents cannot be modified to declare read sets. S-Bus is an HTTP middleware whose central mechanism, a server-side DeliveryLog, reconstructs each agent's read set at commit ti…
  arxiv Sajjad Khan 2026-05-16T16:46:27Z 置信度 0.78 cs.LGcs.AIcs.DCcs.MA
• Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation
  Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative delivery, character development, and emotional engagement. Producing cutscenes is inherently complex: it deman…
  arxiv Lanshan He, Haozhou Pang, Qi Gan, Xin Shen 等 2026-04-28T07:28:14Z 置信度 0.78 cs.GRcs.AIcs.CL
• astra-langchain4j: Experiences Combining LLMs and Agent Programming
  Given the emergence of Generative AI over the last two years and the increasing focus on Agentic AI as a form of Multi-Agent System it is important to explore both how such technologies can impact the use of traditional Agent Toolkits and how the wealth of exp…
  arxiv Rem Collier, Katharine Beaumont, Andrei Ciortea 2026-01-29T15:46:13Z 置信度 0.78 cs.AIcs.MA
• HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language Models
  Recent research on instructable agents has used memory-augmented Large Language Models (LLMs) as task planners, a technique that retrieves language-program examples relevant to the input instruction and uses them as in-context examples in the LLM prompt to imp…
  arxiv Gabriel Sarch, Sahil Somani, Raghav Kapoor, Michael J. Tarr 等 2024-04-29T19:12:42Z 置信度 0.78 cs.AIcs.CLcs.CVcs.LG
• MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion
  Existing text-to-image models still struggle to generate images of multiple objects, especially in handling their spatial positions, relative sizes, overlapping, and attribute bindings. To efficiently address these challenges, we develop a training-free Multim…
  arxiv Sen Li, Ruochen Wang, Cho-Jui Hsieh, Minhao Cheng 等 2024-02-20T06:14:30Z 置信度 0.78 cs.CV
• Agora: A Drive-Based Framework for Agent Difffferentiation in Multi-Agent LLM Systems
  Abstract Current multi-agent LLM systems difffferentiate agents through hand-crafted roles or layer-stacking architectures. We propose Agora, a framework that difffferentiates agents through six continuous drives (boredom, curiosity, stress, anxiety, empathy, …
  europepmc Zihan Lin 2026 置信度 0.80
• WirelessLLM-Agent: A Unified LLM-Based Agent Framework for Multi-Task Wireless Communication Decision-Making
  The integration of large language models into wireless communication has shown promising results for individual tasks. However, existing approaches are typically designed for single-task scenarios and rely on supervised fine-tuning that fails to optimize for l…
  europepmc 2026 置信度 0.80
• MALTopic: Multi-Agent LLM Topic Modeling Framework
  Topic modeling is a crucial technique for extracting latent themes from unstructured text data, particularly valuable in analyzing survey responses. However, traditional methods often only consider free-text responses and do not natively incorporate structured…
  crossref Yash Sharma 2025-08-12T17:51:53Z 置信度 0.70
• An LLM-Based Multi-Agent Framework for Autonomous Business Lead Intelligence Using Public Web Data
  Business lead intelligence-the task of discovering commercial entities, resolving their identity, enriching them with contact and firmographic attributes, and prioritising them for outreach-is today served either by proprietary contact databases with opaque pr…
  crossref Nikunj Patel 2026-08-04T16:31:02Z 置信度 0.70
• Persistent Identity in LLM Multi-Agent Systems: A Semantic Consensus Framework for Heterogeneous AI Swarms
  Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of persistent memory, role specialization, and collaborative reasoning. While recent work has explored multi-agent LLM systems, most architectures treat agents as stateless par…
  crossref Bright Sunu 2026-04-24T19:16:14Z 置信度 0.70
• NeuroSync-Agent: A Real-Time Multimodal Fusion and LLM Reasoning Framework for Cognitive-State Inference
  crossref Basma Jalloul, Bassem Bouaziz, Siwar Chaabene, Walid Mahdi 2026-03-13T04:54:23Z 置信度 0.70
• A Multi-Agent LLM Framework with RAG for Shipbuilding Engineering Documents
  crossref Boris Galvan, George Drakoulas, Bram Cals, Tayfun Kucukyilmaz 等 2026-03-14T11:36:09Z 置信度 0.70
• CCoRe: Cooperative-Competitive Reasoning LLM-based Multi-Agent Framework
  Abstract Large Language Model-based Multi-Agent systems (LLM-MAS) emerged as a promising approach for solving complex tasks and queries that go beyond Single-Agent systems’ abilities. Cooperative-Competitive Reasoning LLM-based Multi-Agent Framework (CCoRe) is…
  crossref Hicham Bouchtib, Kaouter Karboub, Mohamed Tabaa, Mohamed Hamlich 2025-08-13T19:13:19Z 置信度 0.70
• GraphShield: A Graph-Structured Defense Framework for Prompt Injection in RAG and Multi-Agent LLM Systems
  GraphShield is a graph-structured defense framework for LLMs that represents system prompts, retrieved knowledge, agents, and parsed instructions as directed Trust-Knowledge Graph (TKG). Security is formalized as reachability from an instruction node to policy…
  crossref Shreya Singh 2026-07-08T22:00:37Z 置信度 0.70
• Autonomous Planetary Modeling Layer (APML): A Multi-Agent LLM Framework for Continuous Socio-Political System Identification
  Understanding large-scale socio-political dynamics remains among the most challenging problems in computational social science. Existing forecasting systems typically rely on econometric models, agent-based simulations, or machine learning architectures that o…
  crossref Angelito Malicse 2026-07-29T13:47:05Z 置信度 0.70
• LLM Agent Development Lifecycle (LADL): A Structured Engineering Framework for Probabilistic Autonomous Systems Beyond Agile Methodologies
  Standard software engineering practices-like Agile, Scrum, and DevOps-are built on the premise of deterministic systems. They work because we expect the same input to produce the same output every single time. However, these methodologies struggle when applied…
  crossref Arzoo Taj 2026-07-29T13:51:04Z 置信度 0.70
• Before You Build a Multi-Agent System: An Escalation Framework for LLM Adaptation
  Multi-agent systems (MAS) have become a popular framework for deploying large language models (LLMs), yet their operational complexity—increased latency, compounding errors, and difficult-to-optimize orchestration—is often unnecessary. Beyond MAS, a rich ecosy…
  crossref Junhyeong Lee, Joon-Young Kim, Seunghwa Ryu 2026-07-09T12:25:41Z 置信度 0.70
• Multi-Agent Robotic Assembly for Industrialized Construction: A Hierarchical, LLM-Based BIM-to-BOT Framework
  Robotics in construction is often hindered by the high cost of project-specific reprogramming and the specialized knowledge gap between construction experts and designers and robotic systems. This study introduces a multi-agent robotic assembly for industriali…
  crossref Amirpooya Shirazi, Aladdin Alwisy 2026-03-26T12:37:04Z 置信度 0.70
• Human–Agent Joint Diagnosis with ValidLLP4LLM: A Labeled Logic Framework for Validating LLM Reasoning
  Large language models (LLMs) can generate fluent diagnostic explanations that appear coherent while containing unsupported claims, omitted premises, or logically invalid inferences. Such hallucinations are especially dangerous in human–machine collaborative en…
  europepmc 2026 置信度 0.80
• Red-Agent: A Practical Multi-Provider Framework for LLM Red Teaming with Operational Reachability and Artifact-Complete Reporting
  We present Red-Agent, a practical multi-provider framework for LLM red teaming focused on reliable cross-model execution, artifact completeness, and reproducible reporting. The empirical results in this paper come from a curated 11-model run using a stable cam…
  crossref Nathan Heath 2026-05-02T11:09:33Z 置信度 0.70
• Synthetic Managerial Agents: A Multi-LLM Ensemble Framework for Computational Agent-Based Theory Exploration
  We introduce Synthetic Managerial Agents (SMA), a novel computational methodology that advances agentbased modeling (ABM) by replacing rigid behavioral rules with Large Language Model (LLM)-powered agents capable of flexible theoretical reasoning. Traditional …
  crossref Dequn Teng, Chen Ye, Veronica Martinez 2026-02-03T11:17:37Z 置信度 0.70
• CausLab: LLM-driven Multi-agent Bayesian Framework for Causal Discovery and Inference
  Randomized controlled trials (RCTs), known as A/B tests in industry, reliably estimate treatment effects. However, uncovering causal mechanisms underlying observed lifts and transferring those insights to guide future product decisions remain major challenges …
  crossref Chen Wang, Shan Huang, Shichao Han, Yong Wang 2026-03-13T09:07:18Z 置信度 0.70
• A Multi-Agent Large Language Model (Llm) Framework for Code-Complying Design Automation of Concrete Structures
  crossref Jinxin Chen, Yi Bao 2025-03-26T03:04:10Z 置信度 0.70
• A Methodological Framework for Self-Evolving Multi-Agent Systems: Toward Adaptive and Continuous Learning in LLM-Based Architectures
  Abstract This study proposes the Self-Evolving Multi-Agent Framework (SEMAF) to address the prevalent issues of rigidity and knowledge drift in current Large Language Model (LLM)-based multi-agent systems. While existing frameworks rely on static, role-based c…
  preprints Cheonsu Jeong 2025 置信度 0.74
• LLM as Agent: A Reinforcement Learning Framework for Interactive Voice Response Systems
  crossref Zhe FU, Guoqing Song, Frank (Youhua) Chen, Mengzhuo Guo 2025-08-04T20:06:16Z 置信度 0.70
• A Self-Correcting Multi-Agent LLM Framework for Language-Based Physics Simulation and Explanation
  Abstract Physics-based simulations are essential in science and engineering, yet creating them typically requires expert knowledge of numerical solvers and governing equations. Large language models (LLMs) offer new possibilities for natural language-based sim…
  preprints Donggeun Park, Hyeonbin Moon, Seunghwa Ryu 2025 置信度 0.74
• A Retrospective and Adaptive Framework to Improve LLMs
  crossref 2025-12-12T16:55:26Z 置信度 0.70
• Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP
  Modern LLM-agent frameworks increasingly interoperate via emerging standards-Anthropic's Model Context Protocol (MCP) for agent-to-tool access and Google's Agent2Agent (A2A) protocol for agent-toagent delegation and negotiation. Yet these protocols specify tra…
  crossref Wael S. Albayaydh, Rui Zhao 2026-08-06T05:29:43Z 置信度 0.70
• FTDI: A Budget-Aware Self-Healing Framework for Resilient LLM Multi-Agent Code Generation
  LLM-driven multi-agent systems remain vulnerable in executable-feedback code generation. Minor perturbations propagate through long interaction chains and amplify in feedback loops, while existing robustness defenses often lack a budget-aware recovery loop, wh…
  crossref Sixue Men, Qinyue Tong, Rui Zuo, Zheming Lu 2026-03-10T16:52:18Z 置信度 0.70
• FraudDebate-Agent: A Multi-Agent LLM Framework with an Evidence-Based Debate Mechanism for Financial Statement Fraud Detection
  Financial statement fraud inflicts large and recurring losses on capital markets, yet the dominant detection paradigm still relies on single, black-box classifiers (e.g., RUSBoost) trained on structured accounting ratios alone. Two limitations follow: (i) the …
  crossref Xinran Yue, Jingyun Yang, Wenhe Liu 2026-07-27T05:49:27Z 置信度 0.70
• Multi-Agent RAG Framework for Entity Resolution: Advancing Beyond Single-LLM Approaches with Specialized Agent Coordination
  Entity resolution in real-world datasets remains a persistent challenge, particularly in identifying households and detecting co-residence patterns within inconsistent and incomplete data. Recent advances using Large Language Models (LLMs) show promise but con…
  preprints Aatif Muhammad, Muzakkiruddin Ahmed Mohammed, Mariofanna Milanova, John R. Talburt 等 2025 置信度 0.74
• Democratizing Scientific Publishing: A Local, Multi-Agent LLM Framework for Objective Manuscript Editing
  Abstract Manuscript preparation is a critical bottleneck in scientific publishing, yet existing AI writing tools require cloud transmission of sensitive content, creating data-confidentiality barriers for clinical researchers. We introduce the Paper Analysis T…
  europepmc Rohan Bhansali, Alon Gorenshtein, Brandon Westover, Daniel M. Goldenholz 2026 置信度 0.80
• A Knowledge Graph-Enhanced Dual-Agent LLM Framework for Synthetic Aviation Safety Report Generation under Class Imbalance
  Aviation safety reports constitute a rich database from which advanced language technologies extract actionable operational intelligence. Aviation safety analytics has grown substantially as machine learning (ML) models have been developed to perform diverse i…
  crossref Xiao Jing, Zhenyu Gao, Dimitri Mavris 2026-06-16T11:54:23Z 置信度 0.70
• Automating Situational Judgment Tests from Likert Scales: A Multi-Agent LLM Framework for Literacy Assessment_supp1-3720406.docx
  crossref Fucheng Guo 2026-08-05T19:04:11Z 置信度 0.70
• From Model to Agent: A Modular LLM-Based Framework for Multi-Agent Systems
  crossref Tomás Loureiro, Filipa Ferrada, Thais Baldissera 2026-07-27T19:15:54Z 置信度 0.70
• A multi-agent ensemble framework for enhancing task performance using specialized LLM
  Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informujące swoich czytelników o najnowszych osiągnięciach naukowych i nowoczesnych rozwiązaniach technicznych w Polsce i na świecie, popularyzuje problemy techniczne oraz poszerza wiedzę i kulturę techniczną.
  crossref Michał MAJ 2026-03-30T09:15:32Z 置信度 0.70
• Data-Driven Meets Knowledge-Driven: An LLM‐Agent Framework for Quality Control in Metal Additive Manufacturing
  Quality prediction in metal additive manufacturing (AM) has conventionally relied on data-driven models that map process parameters to defect classes or quality metrics. However, these models often fail to generalize across different machines, materials, and p…
  crossref Jianzhang Li, Dachuan Shi, Zhidong Zhang, Thomas Bauernhansl 2026-03-11T10:41:19Z 置信度 0.70
• Autonomous Multi-Agent Systems for Global Market Expansion: An LLM-Based Framework for Scaling Strategic Internationalization in Small and Medium Enterprises
  Traditional internationalization strategies for Small and Medium Enterprises (SMEs) are often hindered by high consultancy costs, information asymmetry, and steep learning curves. This paper proposes a novel computational framework based on Autonomous Multi-Ag…
  crossref Claudio Massimo Onorato 2026-07-29T13:57:19Z 置信度 0.70
• Harnessing Language for Coordination: A Framework and Benchmark for LLM-Driven Multi-Agent Control_supp1-3564042.pdf
  crossref Timothee ANNE 2025-05-30T13:48:40Z 置信度 0.70
• A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
  crossref 2025-12-12T16:55:26Z 置信度 0.70
• LLM-Based Multi-Agent Framework for Troubleshooting Distributed Systems
  Effectively configuring distributed systems, particularly those orchestrated by Kubernetes, remains challenging due to inherent complexity. This paper introduces KubeLLM, an LLM-based multi-agent framework designed to automate the troubleshooting of Kubernetes…
  crossref Mario De Jesus, Perfect Sylvester, William Clifford, Aaron Perez 等 2025-08-13T17:27:09Z 置信度 0.70
• Bridging LLM Reasoning and Chemical Knowledge via an Evolutionary Multi-Agent Framework for Molecular Synthesis
  Motivation Molecular design faces the dual challenge of navigating a vast chemical space while ensuring experimental synthesizability. Traditional models are constrained by small datasets, restricting their scalability and broader chemical context. In contrast…
  europepmc 2026 置信度 0.80
• AutoCoSim: An LLM-RAG-based Multi-agent Framework for Automating Building Energy and CFD Co-simulation
  Achieving carbon neutrality in the built environment requires advanced heating, ventilation, and air conditioning (HVAC) control strategies that optimize both energy efficiency and occupant thermal comfort. Co-simulation frameworks integrating building energy …
  crossref Yu Li, Yijun Huang, Xi Chen, Ben M. Chen 2026-02-03T09:38:28Z 置信度 0.70
• PentestMCP: LLM and MCP Based Multi-Agent Framework for Automated Penetration Testing
  Abstract As information systems grow increasingly complex and cyberattack techniques continue to evolve, traditional penetration testing heavily dependent on manual expertise and operations---faces serious challenges in both efficiency and scalability. To over…
  europepmc Jiqiang Zhai, Xinyi Zhou, Hong Miao, Zekun Li 等 2025 置信度 0.80
• Strategic Learning Under Linguistic and Contextual Constraints: A Theoretical Framework for LLM-Based Multi-Agent Coordination
  Modern AI systems increasingly employ multiple language-based agents to solve complex problems. However, these systems face coordination challenges that traditional game theory cannot adequately address. AI agents have limited memory and must communicate throu…
  crossref Sungwook Yoon 2025-11-04T18:37:10Z 置信度 0.70