AI Agent

RLHF Workflow: From Reward Modeling to Online RLHF

Hanze Dong, Wei Xiong, Bo Pang, Haoxiang Wang, Han Zhao, Yingbo Zhou, Nan Jiang, Doyen Sahoo, Caiming Xiong, Tong Zhang

专题命中 工作流自动化 ：workflow(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments Published in Transactions on Machine Learning Research (09/2024)

An Integrated Epidemic Simulation Workflow for Submodular Intervention Strategies

Reet Barik, Marco Minutoli, Mahantesh Halappanavar, Ananth Kalyanaraman

专题命中 工作流自动化 ：workflow(title,abstract)；agent(abstract)

Automated test generation to evaluate tool-augmented LLMs as conversational AI agents

Samuel Arcadinho, David Aparicio, Mariana Almeida

专题命中 工作流自动化 ：AI agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments 14 pages, 5 figures, Submitted to GenBench@EMNLP2024

dZiner: Rational Inverse Design of Materials with AI Agents

Mehrad Ansari, Jeffrey Watchorn, Carla E. Brown, Joseph S. Brown

专题命中 工作流自动化 ：AI agent(title,abstract)；agent(abstract)

On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms

Richard Yue, John E. Ortega, Kenneth Ward Church

专题命中 工作流自动化 ：workflow(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments AMTA 2024 - The Association for Machine Translation in the Americas organizes biennial conferences devoted to researchers, commercial users, governmental and NGO users

Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement

Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, Sujian Li

专题命中 工作流自动化 ：agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments Accepted to EMNLP 2024 (Main Conference)

A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples

Lihang Pan, Yuxuan Li, Chun Yu, Yuanchun Shi

专题命中 工作流自动化 ：agent(title,abstract)；workflow(abstract)

An Agent-Centric Perspective on Norm Enforcement and Sanctions

Elena Yan, Luis G. Nardin, Jomi F. Hübner, Olivier Boissier

专题命中 工作流自动化 ：agent(title,abstract)；multi-agent(abstract)

Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chat

John Chen, Xi Lu, Michael Rejtig, David Du, Ruth Bagley, Michael S. Horn, Uri J. Wilensky

专题命中 工作流自动化 ：agent(title,abstract)；workflow(abstract)

Comments Conditionally accepted (with minor revisions) by Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI '24)

Causal Asymmetry of Classical and Quantum Autonomous Agents

Spiros Kechrimparis, Mile Gu, Hyukjoon Kwon

专题命中 工作流自动化 ：autonomous agent(title,abstract)；agent(abstract)

Comments 12 pages, 4 figures

Joint Estimation and Control for Multi-Target Passive Monitoring with an Autonomous UAV Agent

Savvas Papaioannou, Christos Laoudias, Panayiotis Kolios, Theocharis Theocharides, Christos G. Panayiotou

专题命中 工作流自动化 ：agent(title,abstract)；planning(abstract)

Journal ref 31st Mediterranean Conference on Control and Automation (MED), 2023

Agent Miner: An Algorithm for Discovering Agent Systems from Event Data

Andrei Tour, Artem Polyvyanyy, Anna Kalenkova, Arik Senderovich

专题命中 工作流自动化 ：agent(title,abstract)；autonomous agent(abstract)

A Tractable Truthful Profit Maximization Mechanism Design with Autonomous Agents

Mina Montazeri, Hamed Kebriaei, Babak N. Araabi

专题命中 工作流自动化 ：autonomous agent(title,abstract)；agent(abstract)

Warlock: an automated computational workflow for simulating spatially structured tumour evolution

Maciej Bak, Blair Colyer, Veselin Manojlović, Robert Noble

专题命中 工作流自动化 ：workflow(title,abstract)；agent(abstract)

Comments 5 pages, 2 figures

Estimating the Long-term Behavior of Biologically Inspired Agent-based Models

Daniel A. Cruz, Jack Toppen, Eunbi Park, Melissa L. Kemp, Elena S. Dimitrova

专题命中 工作流自动化 ：agent(title,abstract)；autonomous agent(abstract)

Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?

Pradip Pramanick, Chayan Sarkar

专题命中 工作流自动化 ：agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments Accepted in EMNLP '22

Automatic 2D-3D Registration without Contrast Agent during Neurovascular Interventions

Robert Homan, René van Rijsselt, Daniel Ruijters

专题命中 工作流自动化 ：agent(title,abstract)；workflow(abstract)

Verification of an agent-based disease model of human mycobacterium tuberculosis infection

Cristina Curreli, Francesco Pappalardo, Giulia Russo, Marzio Pennisi, Dimitrios Kiagias, Miguel Juarez, Marco Viceconti, .

专题命中 工作流自动化 ：agent(title,abstract)；workflow(abstract)

Simulation and computational analysis of multiscale graph agent-based tumor model

Ghazal Tashakor, Remo Suppi

专题命中 工作流自动化 ：agent(title,abstract)；workflow(abstract)

Comments 7 pages, 7 figures

Journal ref A Publication of The IEEE, New Jersey, USA 2019 ISBN: 978-1-7281-4483-2

Agent-based (BDI) modeling for automation of penetration testing

Ge Chu, Alexei Lisitsa

专题命中 工作流自动化 ：agent(title,abstract)；planning(abstract)

Automatizing a non-scripting TPS for optimizing clinical workflow and re-optimization of IMRT/VMAT plans

Rafael Ayala, Gema Ruiz, Teresa Valdivielso

专题命中 工作流自动化 ：workflow(title,abstract)；planning(abstract)

Comments 11 pages, 7 figures

Model Exploration Using OpenMOLE - a workflow engine for large scale distributed design of experiments and parameter tuning

Romain Reuillon, Mathieu Leclaire, Jonathan Passerat-Palmbach

专题命中 工作流自动化 ：workflow(title,abstract)；agent(abstract)

Comments IEEE High Performance Computing and Simulation conference 2015, Jun 2015, Amsterdam, Netherlands

Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX framework

面向执行约束的自主AI自动化：一种可复现的AIBOM驱动的CSAF-VEX框架

Petar Radanliev, Omar Santos, Carsten Maple, Kay Atefi

机构 * University of Oxford（牛津大学） ； Cisco Systems（思科系统） ； The Alan Turing Institute（艾伦·图灵研究所） ； University of Warwick – WMG（沃里克大学 – WMG） ； University of Hull（哈罗德大学） 纠错

专题命中 工作流自动化 ：agentic(title,abstract)；分类 cs.AI、cs.SE

AI总结 提出一种协议驱动框架，通过绑定SBOM和AIBOM工件与确定性环境捕获及结构化运行时遥测，结合静态与运行时证据生成CSAF VEX公告，经密码签名和确定性重放验证，在合成自主AI工作负载上评估。

Journal ref Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX framework. Front Artif Intell 9, (May 2026), 1826384

ADT: Agent-based Dynamic Thresholding for Anomaly Detection

Xue Yang, Enda Howley, Micheal Schukat

专题命中 工作流自动化 ：agent(title,abstract)；分类 cs.AI、cs.LG；autonomous agent(journal_ref)

Journal ref Adaptive Learning Agents Workshop @ International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2023, London, UK

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents

SkillJect：有效自动化基于技能的提示注入以针对具备技能的代理

Xiaojun Jia, Jie Liao, Simeng Qin, Jindong Gu, Wenqi Ren, Xiaochun Cao, Yang Liu, Philip Torr

机构 * Nanyang Technological University, Singapore（南洋理工大学，新加坡） ； Chongqing University, China（重庆大学） ； Northeastern University, China（东北大学） ； Sun Yat-sen University, China（中山大学） ； University of Oxford, UK（牛津大学） 纠错

专题命中 工作流自动化 ：agent(abstract)；tool use(abstract)；workflow(abstract)；multi-agent(abstract)

AI总结 SkillJect 是首个自动化生成有效中毒技能的框架，通过隐藏恶意负载和重写指令通道，提升攻击效果，揭示可重用技能生态中的持久性攻击向量。

ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation

ClawTrace: 面向LLM智能体技能蒸馏的成本感知追踪

Boqin Yuan, Yue Su, Renchu Song, Sen Yang, Jing Qin

机构 * University of California San Diego（加州大学圣地亚哥分校） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 工作流自动化 ：agent(title,abstract)；分类 cs.AI；agentic(comments)

AI总结 针对技能蒸馏管道缺乏每步成本信号的问题，提出ClawTrace记录成本归因轨迹并生成TraceCard，通过CostCraft生成保留、剪枝和修复三类技能补丁，发现剪枝补丁作为质量护栏而保留补丁导致回归，主张按规则类型评估可复用技能。

Comments Accepted at Agent Skills '26 Workshop, ACM Conference on AI and Agentic Systems (CAIS 2026), San José, CA, May 26, 2026

AutomationBench

Daniel Shepard, Robin Salimans

机构 * Zapier 纠错

专题命中 工作流自动化 ：agent(abstract)；AI agent(abstract)；workflow(abstract)；agentic(abstract)

Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining

通过重构理解：为LLM预训练反转软件开发过程

Zhiyuan Zeng, Yichi Zhang, Yong Shan, Kai Hua, Siyuan Fang, Zhaiyu Liu, Jiaheng Liu, Haozhe Wang, Yining Zheng, Ming Ding, Ke Shen, Ge Zhang, Wenhao Huang, Xipeng Qiu

专题命中 工作流自动化 ：agent(abstract)；planning(abstract)；agentic(abstract)；multi-agent(abstract)

AI总结 本文提出通过重构软件开发过程来提升LLM性能，通过模拟多智能体轨迹生成更丰富的监督信号，实验显示在多个基准测试中效果显著。

EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis

EpidemIQs: 用于流行病建模与分析的提示到论文LLM代理

Mohammad Hossein Samaei, Faryad Darabi Sahneh, Lee W. Cohnstaedt, Caterina Scoglio

机构 * Department of Electrical and Computer Engineering, Kansas State University（电气与计算机工程系，堪萨斯州立大学） 纠错

专题命中 工作流自动化 ：agent(abstract)；planning(abstract)；workflow(abstract)；multi-agent(abstract)

AI总结 EpidemIQs是一种多代理LLM框架，通过五个阶段实现流行病建模与分析的自动化，利用科学家代理和任务专家代理提高效率和准确性。

AuraGenome: An LLM-Powered Framework for On-the-Fly Reusable and Scalable Circular Genome Visualizations

Chi Zhang, Yu Dong, Yang Wang, Yuetong Han, Guihua Shan, Bixia Tang

机构 * Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心） ； University of Chinese Academy of Sciences（中国科学院大学） ； Hangzhou Institute for Advanced Study, UCAS（杭州先进研究所） ； National Genomics Data Center, China National Center for Bioinformation（国家基因组科学数据中心） ； Beijing Institute of Genomics, Chinese Academy of Sciences（中国科学院北京基因组研究所） 纠错

专题命中 工作流自动化 ：agent(abstract)；planning(abstract)；workflow(abstract)；multi-agent(abstract)