AI Agent 生态 · 全部实体（第 87 / 100 页）

本页收录第 8601–8700 条，共 10000 条 · 返回 AI Agent 生态 首页

• Game-theoretic LLM: Agent Workflow for Negotiation Games
  This paper investigates the rationality of large language models (LLMs) in strategic decision-making contexts, specifically within the framework of game theory. We evaluate several state-of-the-art LLMs across a spectrum of complete-information and incomplete-…
  openalex Wenyue Hua, Ollie Liu, Lingyao Li, Alfonso Amayuelas 等 2024-11-08 置信度 0.72 NegotiationWorkflowComputer scienceGame theoryMathematical economics
• GeoFlow: Agentic Workflow Automation for Geospatial Tasks
  We present GeoFlow, a method that automatically generates agentic workflows for geospatial tasks. Unlike prior work that focuses on reasoning decomposition and leaves API selection implicit, our method provides each agent with detailed tool-calling objectives …
  openalex Amulya Bhattaram, Justin Chung, Stanley Chung, Ranit Gupta 等 2025-11-03 置信度 0.72 Geospatial analysisWorkflowComputer scienceInvocationAutomation
• An Agent-Based Workflow Management System
  In this paper we discuss the architecture of an agent-based workflow management system built around the Bond agent framework. We address the problem of mapping a workflow description into the Blueprint language used for agent description. Bond agents can be mo…
  openalex Krzysztof Palacz, Dan C. Marinescu 1999-01-01 置信度 0.72 WorkflowWorkflow management systemComputer scienceWorkflow technologyBlueprint
• A novel approach for enacting the distributed business workflows using BPEL4WS on the multi-agent platform
  This paper describes the development of a distributed multi-agent workflow enactment mechanism using BPEL4WS specification. It demonstrates that a multi-agent protocol (lightweight coordination calculus (LCC)) can be used to interpret a BPEL4WS specification t…
  openalex Li Guo, David Robertson, Y.-H. Chen-Burger 2005-01-01 置信度 0.72 Computer scienceWorkflowBusiness Process Execution LanguageSoftware engineeringBusiness process
• Dynamic change within workflow systems
  Dynamic change is a large and pervasive unsolved problem which surfaces within office systems as well as within software engineering, manufacturing, and numerous other domains. Procedural changes, performed in an ad hoc manner, can cause inefficiencies, incons…
  openalex Clarence A. Ellis, Karim Keddara, Grzegorz Rozenberg 1995-01-01 置信度 0.72 Computer scienceWorkflowWorkflow management systemDatabase
• Agentic Workflows for Improving LLM Reasoning in Robotic Object-Centered Planning
  Large Language Models (LLMs) provide cognitive capabilities that enable robots to interpret and reason about their workspace, especially when paired with semantically rich representations like semantic maps. However, these models are prone to generating inaccu…
  openalex Jesus Moncada-Ramirez, Jose-Luis Matez-Bandera, Javier González-Jiménez, José-Raúl Ruiz-Sarmiento 2025-01-03 置信度 0.72 WorkflowComputer scienceContext (archaeology)Reflection (computer programming)Workspace
• WorkWeb system---multi-workflow management with a multi-agent system
  Current office systems independently manage workflows and personal schedules. However, they cannot be managed independently, because of resource constraints. The "WorkWeb System" is an expanded workflow system that is able to manage and contr…
  openalex Hiroyuki Tarumi, Koji Kida, Yoshihide Ishiguro, Kenji Yoshifu 等 1997-01-01 置信度 0.72 Workflow management systemComputer scienceWorkflowMulti-agent systemManagement system
• Declarative workflows: Balancing between flexibility and support
  Today’s process-aware information systems tend to either support business processes or provide flexibility. Classical workflow management systems offer good process support as long as the processes are structured and do not require much flexibility. Informatio…
  openalex Wil M. P. van der Aalst, M. Pesic, Helen Schonenberg 2009-03-09 置信度 0.72 Flexibility (engineering)WorkflowComputer scienceProcess (computing)Business process
• An agent-based cross-organizational workflow architecture in support of Web services
  The latest trend in system interoperability is the emerging concept of Web services. Web services promote the use of the Extensible Markup Language (XML) to represent services (Web Service Description Language (WSDL)) and their locations and interactions (Simp…
  openalex M. Brian Blake 2003-06-25 置信度 0.72 Computer scienceWS-I Basic ProfileWeb serviceWS-PolicyWorld Wide Web
• Software Agents in Data and Workflow Management
  CMS currently uses a number of tools to transfer data which, taken together, form the basis of a heterogeneous datagrid. The range of tools used, and the directed, rather than optimized nature of CMS recent large scale data challenge required the creation of a…
  openalex T. Wildish, S. Metson, A. Fanfani, Michael D. Ernst 等 2005-01-01 置信度 0.72 WorkflowComputer scienceSoftwareSoftware engineeringWorkflow management system
• Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows
  Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but optimizing LLM-based agentic systems remains challenging due to the vast search space of agent configurations, prompting strategies, and communication patterns. Ex…
  arxiv Patara Trirat, Wonyong Jeong, Sung Ju Hwang 2025-05-26T09:46:50Z 置信度 0.78 cs.LGcs.AI
• Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture
  Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent systems due to increased…
  arxiv Sunil Kumar Jang Bahadur, Gopala Dhar 2025-06-10T07:36:54Z 置信度 0.78 cs.CR
• Progressive Crystallization: Turning Agent Exploration into Deterministic, Lower-Cost Workflows in Production
  AI agents deployed for IT operations are typically permanent cost centers because every execution requires full LLM inference, even for previously solved problems. This paper introduces progressive crystallization, a lifecycle that treats agent exploration as …
  arxiv Arun Malik 2026-07-08T06:27:36Z 置信度 0.78 cs.SEcs.AIcs.DCcs.ETcs.MA
• MolSSI and BioExcel Workflow Workshop 2018 Report
  Workflows in biomolecular science are very important as they are intricately intertwined with the scientific outcomes, as well as algorithmic and methodological innovations. The use and effectiveness of workflow tools to meet the needs of the biomolecular scie…
  arxiv Levi N. Naden, Sam Ellis, Shantenu Jha 2019-05-28T14:48:25Z 置信度 0.78 cs.SE
• Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use
  Retrieval-Augmented Generation (RAG) and agentic AI systems are increasingly prevalent in enterprise AI deployments. However, real enterprise environments introduce challenges largely absent from academic treatments and consumer-facing APIs: multiple tenants w…
  arxiv Francisco Javier Arceo, Varsha Prasad Narsing 2026-05-06T17:59:21Z 置信度 0.78 cs.CRcs.AIcs.IRcs.SE
• KubeAdaptor: A Docking Framework for Workflow Containerization on Kubernetes
  As Kubernetes becomes the infrastructure of the cloud-native era, the integration of workflow systems with Kubernetes is gaining more and more popularity. To our knowledge, workflow systems employ scheduling algorithms that optimize task execution order of wor…
  arxiv Chenggang Shan, Guan Wang, Yuanqing Xia, Yufeng Zhan 等 2022-07-04T06:17:34Z 置信度 0.78 cs.DC
• Don't Vibe Code, Do Skele-Code: Interactive No-Code Notebooks for Subject Matter Experts to Build Lower-Cost Agentic Workflows
  Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, designed especially for less or non-technical users. It supports incremental, interactive notebook-style development, and each step is converted to code with a re…
  arxiv Sriram Gopalakrishnan 2026-03-18T16:37:29Z 置信度 0.78 cs.AIcs.HCcs.PLeess.SY
• Flow-Bench: A Dataset for Computational Workflow Anomaly Detection
  A computational workflow, also known as workflow, consists of tasks that must be executed in a specific order to attain a specific goal. Often, in fields such as biology, chemistry, physics, and data science, among others, these workflows are complex and are e…
  arxiv George Papadimitriou, Hongwei Jin, Cong Wang, Rajiv Mayani 等 2023-06-16T15:59:23Z 置信度 0.78 cs.DC
• Exploring Agentic Workflows for Generating High Quality Math Visual Aids
  Mathematical diagrams play a crucial role in K 12 education, both as problem components and as scaffolding for student comprehension. However, current AI tools, including Large Language Models (LLMs), struggle to reliably generate accurate and pedagogically so…
  arxiv Rizwaan Malik, Ashna Khetan, Isabel Sieh, Samin Khan 2026-07-10T17:12:38Z 置信度 0.78 cs.AIcs.CVcs.HC
• LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology
  Modern scientific discovery increasingly relies on workflows that process data across the Edge, Cloud, and High Performance Computing (HPC) continuum. Comprehensive and in-depth analyses of these data are critical for hypothesis validation, anomaly detection, …
  arxiv Renan Souza, Timothy Poteet, Brian Etz, Daniel Rosendo 等 2025-09-17T13:51:29Z 置信度 0.78 cs.DCcs.AIcs.DB
• AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows
  Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task. As skill repositories grow, developers need automated quality signals on every change, yet evaluation today …
  arxiv Tejas Singh Anand, Yuet Ying Christina Wang, Wanting Jiang, Steve Masson 等 2026-07-16T21:33:05Z 置信度 0.78 cs.SEcs.AIcs.LGcs.PF
• GNNs as Predictors of Agentic Workflow Performances
  Agentic workflows invoked by Large Language Models (LLMs) have achieved remarkable success in handling complex tasks. However, optimizing such workflows is costly and inefficient in real-world applications due to extensive invocations of LLMs. To fill this gap…
  arxiv Yuanshuo Zhang, Yuchen Hou, Bohan Tang, Shuo Chen 等 2025-03-14T11:11:00Z 置信度 0.78 cs.CLcs.MA
• Low-level I/O Monitoring for Scientific Workflows
  While detailed resource usage monitoring is possible on the low-level using proper tools, associating such usage with higher-level abstractions in the application layer that actually cause the resource usage in the first place presents a number of challenges. …
  arxiv Joel Witzke, Ansgar Lößer, Vasilis Bountris, Florian Schintke 等 2024-08-01T09:29:24Z 置信度 0.78 cs.DC
• An Ecosystem of Services for FAIR Computational Workflows
  Computational workflows represent major investments of effort and expertise. As first-class, publishable research objects of their own, they are key to sharing methodological know-how for reuse, reproducibility, and transparency. Thus, the application of the F…
  arxiv Sean R. Wilkinson, Johan Gustafsson, Finn Bacall, Khalid Belhajjame 等 2025-05-21T20:11:58Z 置信度 0.78 cs.DC
• A Workflow for Offline Model-Free Robotic Reinforcement Learning
  Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any costly or unsafe online…
  arxiv Aviral Kumar, Anikait Singh, Stephen Tian, Chelsea Finn 等 2021-09-22T16:03:29Z 置信度 0.78 cs.LG
• A Workflow for Lipid Nanoparticle (LNP) Formulation Optimization Using Designed Mixture-Process Experiments and Self-Validated Ensemble Models (SVEM)
  We present a Quality by Design (QbD) styled approach for optimizing lipid nanoparticle (LNP) formulations, aiming to offer scientists an accessible workflow. The inherent restriction in these studies, where the molar ratios of ionizable, helper, and PEG lipids…
  arxiv Andrew T. Karl, Sean Essex, James Wisnowski, Heath Rushing 2022-12-21T18:56:26Z 置信度 0.78 stat.AP
• Agentic Large Language Models, a survey
  Background: There is great interest in agentic LLMs, large language models that act as agents. Objectives: We review the growing body of work in this area and provide a research agenda. Methods: Agentic LLMs are LLMs that (1) reason, (2) act, and (3) interact.…
  arxiv Aske Plaat, Max van Duijn, Niki van Stein, Mike Preuss 等 2025-03-29T11:02:20Z 置信度 0.78 cs.AIcs.CLcs.LG
• Runtime-Structured Task Decomposition for Agentic Coding Systems
  Agentic coding systems increasingly use large language models (LLMs) for software engineering tasks such as debugging, root cause analysis, and code review. However, many existing systems encode task logic, execution flow, and output generation inside monolith…
  arxiv Shubhi Asthana, Bing Zhang, Chad DeLuca, Hima Patel 等 2026-05-14T21:16:23Z 置信度 0.78 cs.SEcs.AI
• Agentic Reasoning for Large Language Models
  Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and dynamic environments…
  arxiv Tianxin Wei, Ting-Wei Li, Zhining Liu, Xuying Ning 等 2026-01-18T18:58:23Z 置信度 0.78 cs.AIcs.CL
• Agentic-J: An AI Agent for Biological Microscopy Image Analysis
  Biological image analysis increasingly demands integration across heterogeneous tools, programming environments, and domain knowledge that few researchers can command simultaneously. We present Agentic-J, a containerised, multi-agent AI assistant, primarily fo…
  arxiv Lukas Johanns, Marilin Moor, Davide Panzeri, Yu Zhou 等 2026-06-01T11:10:28Z 置信度 0.78 cs.MAcs.AIcs.CV
• LLM-as-Code: Agentic Programming for Agent Harness
  Every major LLM agent framework gives the LLM the role of orchestrator; the model decides what to do next, when to call tools, and when to stop. We argue that token explosion, control-flow hallucination, and unreliable completion are not implementation bugs bu…
  arxiv Junjia Qi, Zichuan Fu, Jingtong Gao, Wenlin Zhang 等 2026-06-14T15:47:27Z 置信度 0.78 cs.AIcs.SE
• POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation
  Enterprise back office workflows require agentic systems that are auditable, policy-aligned, and operationally predictable, capabilities that generic multi-agent setups often fail to deliver. We present POLARIS (Policy-Aware LLM Agentic Reasoning for Integrate…
  arxiv Zahra Moslemi, Keerthi Koneru, Yen-Ting Lee, Sheethal Kumar 等 2026-01-16T22:38:21Z 置信度 0.78 cs.AI
• Flow: Modularized Agentic Workflow Automation
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An effective workflow ad…
  arxiv Boye Niu, Yiliao Song, Kai Lian, Yifan Shen 等 2025-01-14T04:35:37Z 置信度 0.78 cs.AIcs.LGcs.MA
• Agint: Agentic Graph Compilation for Software Engineering Agents
  LLM-based coding agents are increasingly common but still face challenges in context management, latency, reliability, reproducibility, and scalability. We present Agint, an agentic graph compiler, interpreter, and runtime that incrementally and hierarchically…
  arxiv Abhi Chivukula, Jay Somasundaram, Vijay Somasundaram 2025-11-24T19:10:47Z 置信度 0.78 cs.SEcs.LG
• An Agentic AI Workflow for Detecting Cognitive Concerns in Real-world Data
  Early identification of cognitive concerns is critical but often hindered by subtle symptom presentation. This study developed and validated a fully automated, multi-agent AI workflow using LLaMA 3 8B to identify cognitive concerns in 3,338 clinical notes from…
  arxiv Jiazi Tian, Liqin Wang, Pedram Fard, Valdery Moura Junior 等 2025-02-03T20:08:33Z 置信度 0.78 cs.AIcs.MA
• Cortex: Workflow-Aware Resource Pooling and Scheduling for Agentic Serving
  We introduce Cortex, a prototype workflow-aware serving platform designed for agentic workloads. The core principle of Cortex is stage isolation: it provisions dedicated resource pools for each distinct stage of an agentic workflow. This simple yet powerful st…
  arxiv Nikos Pagonas, Yeounoh Chung, Kostis Kaffes, Arvind Krishnamurthy 2025-10-15T21:49:38Z 置信度 0.78 cs.DC
• Optimizing Agentic Workflows using Meta-tools
  Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant operational expense, end-to-end latency and…
  arxiv Sami Abuzakuk, Anne-Marie Kermarrec, Rishi Sharma, Rasmus Moorits Veski 等 2026-01-29T17:43:08Z 置信度 0.78 cs.AIcs.LG
• RobustFlow: Towards Robust Agentic Workflow Generation
  The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical, unaddressed challenge. Curren…
  arxiv Shengxiang Xu, Jiayi Zhang, Shimin Di, Yuyu Luo 等 2025-09-26T03:49:41Z 置信度 0.78 cs.MA
• Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows
  Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hinder reliability and maintainability. Unlike traditional software systems, failu…
  arxiv Xuyan Ma, Xiaofei Xie, Yawen Wang, Junjie Wang 等 2025-09-28T08:30:03Z 置信度 0.78 cs.AIcs.SE
• Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
  Agentic workflows commonly coordinate multiple models and tools with complex control logic. They are quickly becoming the dominant paradigm for AI applications. However, serving them remains inefficient with today's frameworks. The key problem is that they exp…
  arxiv Gohar Irfan Chaudhry, Esha Choukse, Haoran Qiu, Íñigo Goiri 等 2025-08-22T17:41:27Z 置信度 0.78 cs.MAcs.AIcs.SE
• SEW: Self-Evolving Agentic Workflows for Automated Code Generation
  Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on crafting multi-agent systems with agentic workflows, where complex coding tasks ar…
  arxiv Siwei Liu, Jinyuan Fang, Han Zhou, Yingxu Wang 等 2025-05-24T11:12:14Z 置信度 0.78 cs.SEcs.AIcs.CL
• FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
  In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-dependent workflow construction, the lack of graph-level execution feedback, and the i…
  arxiv Mingda Zhang, Wenjin Liu, Tiesunlong Shen, Qika Lin 等 2026-02-02T05:30:42Z 置信度 0.78 cs.AIcs.LG
• Mining Event Logs to Support Workflow Resource Allocation
  Workflow technology is widely used to facilitate the business process in enterprise information systems (EIS), and it has the potential to reduce design time, enhance product quality and decrease product cost. However, significant limitations still exist: as a…
  arxiv Tingyu Liu, Yalong Cheng, Zhonghua Ni 2012-06-28T03:36:28Z 置信度 0.78 cs.SEcs.DB
• Architectural Implications of Agentic AI Workflows
  Agentic AI is emerging in datacenters, but its architectural implications remain unexplored. We organize agentic workflows in a taxonomy and present its first architectural characterization with a production study at Microsoft Azure and a controlled study of o…
  arxiv Jirong Yang, Peizhe Liu, Chaojie Zhang, Jovan Stojkovic 2026-08-05T05:31:33Z 置信度 0.78 cs.AIcs.ARcs.OS
• Early Adoption of Agentic Coding Tools by GitHub Projects
  Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to software projects, introducing new forms of human-agent collaboration in software development. While prior studies have examined PR-level outcomes of agent-genera…
  arxiv Maliha Noushin Raida, Daqing Hou 2026-07-15T17:05:06Z 置信度 0.78 cs.SEcs.AIcs.CYcs.LG
• JudgeFlow: Agentic Workflow Optimization via Block Judge
  Optimizing LLM-based agentic workflows is challenging for scaling AI capabilities. Current methods rely on coarse, end-to-end evaluation signals and lack fine-grained signals on where to refine, often resulting in inefficient or low-impact modifications. To ad…
  arxiv Zihan Ma, Zhikai Zhao, Chuanbo Hua, Federico Berto 等 2026-01-12T12:30:14Z 置信度 0.78 cs.AI
• Memory as a Service (MaaS): Purpose-Bound Memory Mediation for Cooperative Agents
  Agentic programming is code-centered, while its useful memory context extends beyond code. A programming agent may draw on memory from test, review, build, and release agents; design, product, security, operations, and compliance agents; meeting, finance, cale…
  arxiv Haichang Li 2025-06-28T08:33:17Z 置信度 0.78 cs.HC
• Integrated Digital Management System for Railway Workshops: A Modular Multi-Workflow Architecture for Machine, Permit, Contract, and Incident Management
  Indian Railway workshops form a critical component of rolling stock maintenance infrastructure, employing more than 2.5 lakh personnel across 44 major workshops nationwide. However, safety management in many workshops still relies on fragmented manual processe…
  arxiv Sharvari Kamble, Arjun Dangle, Gargi Khurud, Om Kendre 等 2026-04-05T18:18:23Z 置信度 0.78 cs.CY
• Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents
  The increasing adoption of autonomous coding agents accelerates software development but also introduces scoped security risks within high-impact file paths that can outpace traditional human review capacity. While prior research has primarily evaluated these …
  arxiv A H M Nazmus Sakib, Dipayan Banik, Murtuza Jadliwala 2026-07-14T06:59:41Z 置信度 0.78 cs.CR
• Sherlock: Reliable and Efficient Agentic Workflow Execution
  With the increasing adoption of large language models (LLM), agentic workflows, which compose multiple LLM calls with tools, retrieval, and reasoning steps, are increasingly replacing traditional applications. However, such workflows are inherently error-prone…
  arxiv Yeonju Ro, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca 等 2025-11-01T00:17:57Z 置信度 0.78 cs.MAcs.SE
• Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training
  Corpus distillation for biomedical large language models (LLMs) seeks to address the pressing challenge of insufficient quantity and quality in open-source annotated scientific corpora, which remains a bottleneck for effective LLM training in biomedical resear…
  arxiv Meng Xiao, Xunxin Cai, Qingqing Long, Chengrui Wang 等 2025-04-28T08:18:24Z 置信度 0.78 cs.CLcs.AIq-bio.QM
• Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens
  In recent years, using predefined agentic workflows to guide large language models (LLMs) for literature classification and review has become a research focus. However, writing research introductions is more challenging. It requires rigorous logic, coherent st…
  arxiv Meicong Zhang, Tiancheng su, Guoxiu He 2025-12-28T12:51:36Z 置信度 0.78 cs.CLcs.AI
• Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows
  Agentic workflows -- where multiple large language model (LLM) instances interact to solve tasks -- are increasingly built on feedback mechanisms, where one model evaluates and critiques another. Despite the promise of feedback-driven improvement, the stabilit…
  arxiv Yifei Ming, Zixuan Ke, Xuan-Phi Nguyen, Jiayu Wang 等 2025-06-03T19:26:23Z 置信度 0.78 cs.AI
• Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
  GitHub Actions is increasingly used to deploy LLM-based agents for repository-centric tasks such as issue triage, pull-request review, code modification, and release assistance. These agentic workflows extend traditional CI/CD automation with agentic capabilit…
  arxiv Shenao Wang, Xinyi Hou, Zhao Liu, Yanjie Zhao 等 2026-05-08T02:13:04Z 置信度 0.78 cs.CR
• A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring
  Robotic manipulation systems that follow language instructions often execute grasp primitives in a largely single-shot manner: a model proposes an action, the robot executes it, and failures such as empty grasps, slips, stalls, timeouts, or semantically wrong …
  arxiv Wenze Wang, Mehdi Hosseinzadeh, Feras Dayoub 2026-04-08T08:01:35Z 置信度 0.78 cs.ROcs.AIcs.CV
• Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models
  We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public cybersecurity sources and 35,02…
  arxiv Ron F. Del Rosario 2025-12-29T09:41:22Z 置信度 0.78 cs.AIcs.CR
• Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows
  Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multi-agent frameworks often rely on static or task-level workflows, which either over-process simple queries or underperform on complex one…
  arxiv Jinwei Su, Qizhen Lan, Yinghui Xia, Lifan Sun 等 2025-09-14T03:57:43Z 置信度 0.78 cs.AI
• WirelessAgent++: Automated Agentic Workflow Design and Benchmarking for Wireless Networks
  The integration of large language models (LLMs) into wireless networks has sparked growing interest in building autonomous AI agents for wireless tasks. However, existing approaches rely heavily on manually crafted prompts and static agentic workflows, a proce…
  arxiv Jingwen Tong, Zijian Li, Fang Liu, Wei Guo 等 2026-02-28T06:52:52Z 置信度 0.78 cs.NIcs.AIeess.SP
• Agentic Workflow for Education: Concepts and Applications
  With the rapid advancement of Large Language Models (LLMs) and Artificial Intelligence (AI) agents, agentic workflows are showing transformative potential in education. This study introduces the Agentic Workflow for Education (AWE), a four-component model comp…
  arxiv Yuan-Hao Jiang, Yijie Lu, Ling Dai, Jiatong Wang 等 2025-09-01T14:39:48Z 置信度 0.78 cs.CYcs.AIcs.ET
• Agentic Scene Policies: Unifying Space, Semantics, and Affordances for Robot Action
  Executing open-ended natural language queries is a core problem in robotics. While recent advances in imitation learning and vision-language-actions models (VLAs) have enabled promising end-to-end policies, these models struggle when faced with complex instruc…
  arxiv Sacha Morin, Kumaraditya Gupta, Mahtab Sandhu, Charlie Gauthier 等 2025-09-23T20:56:00Z 置信度 0.78 cs.ROcs.CV
• Optimizing FaaS Platforms for MCP-enabled Agentic Workflows
  Agentic workflows that use autonomous AI Agents powered by Large Language Models (LLMs) and Model Context Protocol (MCP) servers is rapidly rising. This introduces challenges in scalable cloud deployment and state management. Traditional hosting on Virtual Mac…
  arxiv Varad Kulkarni, Vaibhav Jha, Nikhil Reddy, Anand Eswaran 等 2026-01-21T07:46:25Z 置信度 0.78 cs.DC
• Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow
  Large language models (LLMs) excel at solving complex tasks by executing agentic workflows composed of detailed instructions and structured operations. Yet, building general-purpose agents by manually embedding foundation models into agentic systems such as Ch…
  arxiv Chia-Tung Ho, Jing Gong, Xufeng Yao, Yunsheng Bai 等 2025-08-04T23:50:02Z 置信度 0.78 cs.AIcs.LG
• An Agentic Workflow for Detecting Personally Identifiable Information in Crash Narratives
  Crash narratives in crash reports provide crucial contextual information for traffic safety analysis. Yet, their broader use is hindered by the presence of personally identifiable information (PII), including names, home addresses, and license plate numbers. B…
  arxiv Junyi Ma, Pei Li, Rui Gan, Kai Cheng 等 2026-04-15T05:03:20Z 置信度 0.78 cs.CR
• Automotive Engineering-Centric Agentic AI Workflow Framework
  Engineering workflows such as design optimization, simulation-based diagnosis, control tuning, and model-based systems engineering (MBSE) are iterative, constraint-driven, and shaped by prior decisions. Yet many AI methods still treat these activities as isola…
  arxiv Tong Duy Son, Zhihao Liu, Piero Brigida, Yerlan Akhmetov 等 2026-04-09T04:22:18Z 置信度 0.78 cs.AIcs.MAeess.SY
• Security in a Workflow: Exploring Role-Based Agentic Architectures for Vulnerability Handling
  Secure software engineering in practice is a multi-stage workflow involving vulnerability analysis, remediation, and fix verification. However, current LLM-based software security approaches often focus on isolated tasks such as detection or patch generation, …
  arxiv Srijita Basu, Miroslaw Staron 2026-06-12T08:45:24Z 置信度 0.78 cs.CRcs.SE
• Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needs
  Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilities behind unified interfaces. However, today's agent systems typically rely on hard-coded agent architectures…
  arxiv Giuseppe Arbore, Andrea Sillano, Luigi De Russis 2026-04-30T14:01:06Z 置信度 0.78 cs.AIcs.HC
• Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare
  Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary users, introducing signif…
  arxiv Liam Kearns 2026-06-27T01:00:39Z 置信度 0.78 cs.CRcs.AI
• AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction
  Large Language Models have shown strong capabilities in complex problem solving, yet many agentic systems remain difficult to interpret and control due to opaque internal workflows. While some frameworks offer explicit architectures for collaboration, many dep…
  arxiv Ruijie Shi, Houbin Zhang, Yuecheng Han, Yuheng Wang 等 2026-02-05T06:24:15Z 置信度 0.78 cs.AIcs.CL
• A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows
  Agentic AI marks a major shift in how autonomous systems reason, plan, and execute multi-step tasks. Unlike traditional single model prompting, agentic workflows integrate multiple specialized agents with different Large Language Models(LLMs), tool-augmented c…
  arxiv Eranga Bandara, Ross Gore, Peter Foytik, Sachin Shetty 等 2025-12-09T16:23:05Z 置信度 0.78 cs.AI
• Agent-S: LLM Agentic workflow to automate Standard Operating Procedures
  AI agents using Large Language Models (LLMs) as foundations have shown promise in solving complex real-world tasks. In this paper, we propose an LLM-based agentic workflow for automating Standard Operating Procedures (SOP). For customer care operations, an SOP…
  arxiv Mandar Kulkarni 2025-02-03T09:04:48Z 置信度 0.78 cs.HC
• MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking
  We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamental challenges of tool retrieval in agents. MagicSelector is a specialized framewo…
  arxiv HONOR Agentic Search Team, Zhengzong Chen, Lei Tang, Lijun Liu 等 2026-07-20T09:44:01Z 置信度 0.78 cs.IRcs.AIcs.CL
• Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design
  We present Agentic AI Translate, an agentic translator prototype that operationalises the thesis of Yamada (forthcoming) -- that the metalanguage of Translation Studies has become an instruction code for generative AI. The system replaces the dominant text-in …
  arxiv Masaru Yamada 2026-05-16T15:21:23Z 置信度 0.78 cs.CLcs.AIcs.HC
• A Workflow-Aware Serving Layer for Agentic Applications
  Agentic AI applications form an emerging serving workload in which a request creates a workflow: a directed acyclic graph of LLM and tool calls that exposes per-node model choices and optional quality operators such as verifiers. This workload falls between tw…
  arxiv Jiayi Qian, Zishen Wan, Hanchen Yang, Chun Tao 等 2026-07-03T04:28:49Z 置信度 0.78 cs.DCcs.MA
• Procedural Knowledge Improves Agentic LLM Workflows
  Large language models (LLMs) often struggle when performing agentic tasks without substantial tool support, prom-pt engineering, or fine tuning. Despite research showing that domain-dependent, procedural knowledge can dramatically increase planning efficiency,…
  arxiv Vincent Hsiao, Mark Roberts, Leslie Smith 2025-11-10T19:27:57Z 置信度 0.78 cs.AI
• Batch Query Processing and Optimization for Agentic Workflows
  Large Language Models (LLMs) in agentic workflows combine multi-step reasoning, heterogeneous tool use, and collaboration across multiple specialized agents. Existing LLM serving engines optimize individual calls in isolation, while multi-agent frameworks focu…
  arxiv Junyi Shen, Noppanat Wadlom, Yao Lu 2025-09-02T09:17:40Z 置信度 0.78 cs.DBcs.DC
• Towards an Agentic Workflow for Internet Measurement Research
  Internet measurement research faces an accessibility crisis: complex analyses require custom integration of multiple specialized tools that demands specialized domain expertise. When network disruptions occur, operators need rapid diagnostic workflows spanning…
  arxiv Alagappan Ramanathan, Eunju Kang, Dongsu Han, Sangeetha Abdu Jyothi 2025-11-13T18:44:09Z 置信度 0.78 cs.NIcs.AI
• AEMA: Verifiable Evaluation Framework for Trustworthy and Controlled Agentic LLM Systems
  Evaluating large language model (LLM)-based multi-agent systems remains a critical challenge, as these systems must exhibit reliable coordination, transparent decision-making, and verifiable performance across evolving tasks. Existing evaluation approaches oft…
  arxiv YenTing Lee, Keerthi Koneru, Zahra Moslemi, Sheethal Kumar 等 2026-01-17T04:09:02Z 置信度 0.78 cs.AI
• HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling
  Agentic LLM applications increasingly execute user requests as multi-step workflows involving planning, tool use, branching, refinement, and synthesis. In such settings, users experience the end-to-end latency of an entire workflow, not the latency of any sing…
  arxiv You Peng, Youhe Jiang, Wenshuang Li, Xu Xu 等 2026-05-15T21:09:34Z 置信度 0.78 cs.DC
• Testing Agentic Workflows with Structural Coverage Criteria
  Multi-agent systems increasingly expose explicit workflow structure: agents, tools, tool-access rules, restrictions, and delegation paths. Existing evaluations rely largely on end-to-end task success, benchmark scores, final-response quality, or prompt-level c…
  arxiv Nafiseh Kahani, Mojtaba Bagherzadeh 2026-05-26T04:07:55Z 置信度 0.78 cs.SE
• MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
  Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the agentic search space…
  arxiv Chengqi Zheng, Jianda Chen, Yueming Lyu, Wen Zheng Terence Ng 等 2025-05-29T01:08:36Z 置信度 0.78 cs.LGcs.MA
• Learning to Compose for Cross-domain Agentic Workflow Generation
  Automatically generating agentic workflows -- executable operator graphs or codes that orchestrate reasoning, verification, and repair -- has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably handle. Yet what con…
  arxiv Jialiang Wang, Shengxiang Xu, Hanmo Liu, Jiachuan Wang 等 2026-02-11T18:27:22Z 置信度 0.78 cs.MAcs.AIcs.LGcs.SE
• Architectures for Building Agentic AI
  This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges from principled compo…
  arxiv Sławomir Nowaczyk 2025-12-10T09:28:40Z 置信度 0.78 cs.AIcs.LG
• Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference
  Platform-orchestrated agentic workflows have become a popular paradigm for developing LLM-based applications. However, their reliability remains a major challenge due to the uncertainty of LLM outputs, complex inter-node dependencies, and heterogeneous tool in…
  arxiv Xuyan Ma, Yawen Wang, Junjie Wang, Xiaofei Xie 等 2026-07-03T02:28:32Z 置信度 0.78 cs.SE
• LARA: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling
  Large language models (LLMs) and agentic systems have recently demonstrated potential for automating scientific workflows, including atomistic simulations. However, their deployment in high-performance computing (HPC) environments remains limited by the lack o…
  arxiv William Dawson, Louis Beal, Yoann Curé, Giuseppe Fisicaro 等 2026-04-24T14:03:42Z 置信度 0.78 physics.comp-ph
• Robust Agent Compensation (RAC): Teaching AI Agents to Compensate
  We present Robust Agent Compensation (RAC), a log-based recovery paradigm (providing a safety net) implemented through an architectural extension that can be applied to most Agent frameworks to support reliable executions (avoiding unintended side effects). Us…
  arxiv Srinath Perera, Kaviru Hapuarachchi, Frank Leymann, Rania Khalaf 2026-05-05T06:27:34Z 置信度 0.78 cs.AI
• On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
  Agentic systems increasingly solve complex user requests by executing orchestrated workflows, where subtasks are assigned to specialized models or tools and coordinated according to their dependencies. While recent work improves agent efficiency by optimizing …
  arxiv Xinglin Wang, Zishen Liu, Shaoxiong Feng, Peiwen Yuan 等 2026-05-07T12:24:21Z 置信度 0.78 cs.AIcs.CL
• EvoFlow: Evolving Diverse Agentic Workflows On The Fly
  The past two years have witnessed the evolution of large language model (LLM)-based multi-agent systems from labor-intensive manual design to partial automation (\textit{e.g.}, prompt engineering, communication topology) and eventually to fully automated desig…
  arxiv Guibin Zhang, Kaijie Chen, Guancheng Wan, Heng Chang 等 2025-02-11T08:48:46Z 置信度 0.78 cs.LGcs.CLcs.MAcs.NE
• Agentic Workflows for Economic Research: Design and Implementation
  This paper introduces a methodology based on agentic workflows for economic research that leverages Large Language Models (LLMs) and multimodal AI to enhance research efficiency and reproducibility. Our approach features autonomous and iterative processes cove…
  arxiv Herbert Dawid, Philipp Harting, Hankui Wang, Zhongli Wang 等 2025-04-13T21:54:47Z 置信度 0.78 econ.GN
• AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
  Designing multi-agent workflows is especially difficult in open-ended scientific settings where tasks lack curated training sets, reliable scalar evaluation metrics, and standardized interfaces between existing tools and agents. We propose AgentCo-op, a retrie…
  arxiv Shuaike Shen, Wenduo Cheng, Shike Wang, Mingqian Ma 等 2026-05-19T19:22:21Z 置信度 0.78 cs.AI
• AgentX: Towards Orchestrating Robust Agentic Workflow Patterns with FaaS-hosted MCP Services
  Generative Artificial Intelligence (GenAI) has rapidly transformed various fields including code generation, text summarization, image generation and so on. Agentic AI is a recent evolution that further advances this by coupling the decision making and generat…
  arxiv Shiva Sai Krishna Anand Tokal, Vaibhav Jha, Anand Eswaran, Praveen Jayachandran 等 2025-09-09T11:07:50Z 置信度 0.78 cs.DC
• Workflow is All You Need: Escaping the "Statistical Smoothing Trap" via High-Entropy Information Foraging and Adversarial Pacing
  Central to long-form text generation in vertical domains is the "impossible trinity" confronting current large language models (LLMs): the simultaneous achievement of low hallucination, deep logical coherence, and personalized expression. This study establishe…
  arxiv Zhongjie Jiang 2025-12-10T22:13:55Z 置信度 0.78 cs.CLcs.AIcs.CYq-fin.GN
• TDFlow: Agentic Workflows for Test Driven Development
  We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes, revises, and debugs rep…
  arxiv Kevin Han, Siddharth Maddikayala, Tim Knappe, Om Patel 等 2025-10-27T18:44:59Z 置信度 0.78 cs.SEcs.AIcs.MA
• Inference-Time Agentic Decision Rules Beat Longer Evolving Search for Multi-Image Medical Reasoning
  Multi-image medical VQA is not merely a prompt-length problem; it is a fundamental challenge of agentic decision-making. Medical vision-language agents must aggregate evidence across ordered images, remain robust to answer-order perturbations, and avoid overfi…
  arxiv Site Li, Jianyi Hao, Xiaofeng Liu 2026-07-30T01:16:32Z 置信度 0.78 cs.CV
• A Process Harness for Uplifting Legacy Workflows to Agentic BPM: Design and Realization in CUGA FLO
  We introduce the process harness, a new mechanism for uplifting legacy workflows into Agentic Business Process Management (Agentic BPM) without replacing the underlying workflow engine. A process harness places a policy-governed agentic layer around a determin…
  arxiv Fabiana Fournier, Lior Limonad 2026-06-25T15:50:42Z 置信度 0.78 cs.AI
• IFCMemoryBench: Evaluating Long-Term Memory of LLM-Based Agents in BIM Information Retrieval
  Long-term memory is becoming a core capability of LLM-based agents, but existing evaluations largely test conversational recall in open-domain or persona-grounded settings. We argue that a stronger test is whether an agent can reuse information from prior sess…
  arxiv Changyu Du, Alexander Vosseler, Filippo Mazza, André Borrmann 2026-07-13T08:45:00Z 置信度 0.78 cs.IRcs.AI
• Aligning Audio-Visual Joint Representations with an Agentic Workflow
  Visual content and accompanied audio signals naturally formulate a joint representation to improve audio-visual (AV) related applications. While studies develop various AV representation learning frameworks, the importance of AV data alignment is usually under…
  arxiv Shentong Mo, Yibing Song 2024-10-30T17:18:53Z 置信度 0.78 cs.CVcs.AIcs.LGcs.MMcs.SD
• Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution
  Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model (LLM) agents for tasks such as code review and data synchronization. While bringing convenience for developers, this…
  arxiv Neil Fendley, Zhengyu Liu, Aonan Guan, Jiacheng Zhong 等 2026-05-11T20:45:31Z 置信度 0.78 cs.CRcs.AIcs.SE
• Foam-Agent: Towards Automated Intelligent CFD Workflows
  Computational fluid dynamics (CFD) has been the main workhorse of computational physics. Yet its steep learning curve and fragmented, multi-stage workflow create significant barriers. To address these challenges, we present Foam-Agent, a multi-agent framework …
  arxiv Ling Yue, Nithin Somasekharan, Tingwen Zhang, Yadi Cao 等 2025-05-08T07:05:51Z 置信度 0.78 cs.AIcs.MA
• Global Optimization and Inference-Time Region Grafting for Agentic Workflows
  Recent advances in agentic workflow optimization automate workflow design through task-specific workflow search or input-conditioned architecture selection. However, they determine the workflow before execution and cannot adapt failed workflow regions using ex…
  arxiv Donghyeok Koh, Gyuwan Kim, Jinyeong Bak, Seung-Hoon Na 等 2026-08-03T15:04:26Z 置信度 0.78 cs.CL
• Agentic Observability: Automated Alert Triage for Adobe E-Commerce
  Modern enterprise systems exhibit complex interdependencies that make observability and incident response increasingly challenging. Manual alert triage, which typically involves log inspection, API verification, and cross-referencing operational knowledge base…
  arxiv Aprameya Bharadwaj, Kyle Tu 2026-01-31T20:20:02Z 置信度 0.78 cs.SEcs.AI