AI Agent

Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models

Siqiao Xue, Danrui Qi, Caigao Jiang, Wenhui Shi, Fangyin Cheng, Keting Chen, Hongjun Yang, Zhiping Zhang, Jianshan He, Hongyang Zhang, Ganglin Wei, Wang Zhao, Fan Zhou, Hong Yi, Shaodong Liu, Hongjun Yang, Faqiang Chen

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

The Foundations of Computational Management: A Systematic Approach to Task Automation for the Integration of Artificial Intelligence into Existing Workflows

Tamen Jadad-Garcia, Alejandro R. Jadad

专题命中 工作流自动化 ：agent(abstract)；workflow(abstract)；分类 cs.AI、cs.SE

Comments 29 pages, 3 appendices

Whom to Trust? Elective Learning for Distributed Gaussian Process Regression

Zewen Yang, Xiaobing Dai, Akshat Dubey, Sandra Hirche, Georges Hattab

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

Comments 9 pages, conference preprint

How the level sampling process impacts zero-shot generalisation in deep reinforcement learning

Samuel Garcin, James Doran, Shangmin Guo, Christopher G. Lucas, Stefano V. Albrecht

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

Comments Currently under review, 9 pages

Automated Bioinformatics Analysis via AutoBA

Juexiao Zhou, Bin Zhang, Xiuying Chen, Haoyang Li, Xiaopeng Xu, Siyuan Chen, Xin Gao

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

Exploring MLOps Dynamics: An Experimental Analysis in a Real-World Machine Learning Project

Awadelrahman M. A. Ahmed

专题命中 工作流自动化 ：planning(abstract)；workflow(abstract)；分类 cs.LG、cs.SE

Comments 9 figures

Sensitivity Analysis of High-Dimensional Models with Correlated Inputs

Juraj Kardos, Wouter Edeling, Diana Suleimenova, Derek Groen, Olaf Schenk

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

Waypoint Generation in Row-based Crops with Deep Learning and Contrastive Clustering

Francesco Salvetti, Simone Angarano, Mauro Martini, Simone Cerrato, Marcello Chiaberge

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

Comments Accepted at ECML PKDD 2022

Journal ref Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13718, Springer

Learning to Forecast Aleatoric and Epistemic Uncertainties over Long Horizon Trajectories

Aastha Acharya, Rebecca Russell, Nisar R. Ahmed

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

Comments Accepted to ICRA 2023

Imitation from Observation With Bootstrapped Contrastive Learning

Medric Sonwa, Johanna Hansen, Eugene Belilovsky

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

Layout-aware Dreamer for Embodied Referring Expression Grounding

Mingxiao Li, Zehao Wang, Tinne Tuytelaars, Marie-Francine Moens

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

Broad-persistent Advice for Interactive Reinforcement Learning Scenarios

Francisco Cruz, Adam Bignold, Hung Son Nguyen, Richard Dazeley, Peter Vamplew

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

Comments Extended abstract accepted at the 2nd RL-CONFORM Workshop at IEEE/RSJ IROS'22 Conference. 5 pages, 7 figures. arXiv admin note: substantial text overlap with arXiv:2102.02441, arXiv:2110.08003

Reinforcement Learning for Hardware Security: Opportunities, Developments, and Challenges

Satwik Patnaik, Vasudev Gohil, Hao Guo, Jeyavijayan, Rajendran

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

Comments To Appear in 2022 19th International SoC Conference (ISOCC 2022), October 2022

Reinforcement Learning Guided by Provable Normative Compliance

Emery Neufeld

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

Comments 12 pages, 2 figures. Extended version, March 2022

Journal ref In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART (2022)

Reshaping Robot Trajectories Using Natural Language Commands: A Study of Multi-Modal Data Alignment Using Transformers

Arthur Bucker, Luis Figueredo, Sami Haddadin, Ashish Kapoor, Shuang Ma, Rogerio Bonatti

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

Deep reinforcement learning for smart calibration of radio telescopes

Sarod Yatawatta, Ian M. Avruch

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

Comments MNRAS Accepted 2021 May 12. Received 2021 May 11; in original form 2021 February 5

Grounding Open-Domain Instructions to Automate Web Support Tasks

Nancy Xu, Sam Masling, Michael Du, Giovanni Campagna, Larry Heck, James Landay, Monica S Lam

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

Comments To be published in NAACL 2021

A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost

Minbo Gao, Tianle Xie, Simon S. Du, Lin F. Yang

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

PathVQA: 30000+ Questions for Medical Visual Question Answering

Xuehai He, Yichen Zhang, Luntian Mou, Eric Xing, Pengtao Xie

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

A Human Mixed Strategy Approach to Deep Reinforcement Learning

Ngoc Duy Nguyen, Saeid Nahavandi, Thanh Nguyen

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

Journal ref 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

Parenting: Safe Reinforcement Learning from Human Input

Christopher Frye, Ilya Feige

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

Comments 9 pages, 4 figures, 1 table

Grounded autonomous scrutiny at scale: emergent critique from reproduction of published computational physics papers

迈向有根的自主研究：一个端到端的LLM微型研究循环在已发表的计算物理学中的应用

Haonan Huang

机构 * Department of Physics, Princeton University（普林斯顿大学物理系） 纠错

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

AI总结 本文提出一个端到端的LLM微型研究循环，用于在已发表的计算物理学中进行自主研究，通过大规模和深度测试展示其在复现、批评和扩展研究中的能力。

Comments v2: camera-ready version, accepted at ICML 2026 AI for Science Workshop. Corrects the phase-classification statistics and adds a coding-sensitivity analysis (Methods M6); the agent-produced six-page Comment is reproduced as-is in the final appendix. 24 pages, 4 figures

PackingGPT: 3D Packing Agent for Real Furniture in Last-Mile Delivery

PackingGPT：面向最后一公里配送中真实家具的3D装箱智能体

Yi You, Hui Li

专题命中 工作流自动化 ：agent(title)

AI总结 该研究针对最后一公里配送中家具车内装箱的现实复杂条件，构建了基准数据集与PackingGPT框架，训练的LLP模型使装箱失败率降至0.67%，为该任务提供了可行方案。

Agentic AI Orchestration of Heterogeneous Economic Models for Rapid, Multi-scenario Analysis of Energy Crises

用于能源危机快速多场景分析的异构经济模型的智能人工智能编排

Dana Golden, Brett Indelicato, Lav R. Varshney, Carlos D. Messina, Suzanne Thornsbury

专题命中 工作流自动化 ：agentic(title)

AI总结 研究针对能源危机下政策制定者需快速决策但经济模型整合困难的问题，利用大语言模型开发框架，协调多个异构经济模型，通过构建场景、转化输入、执行模型和合成输出，快速评估霍尔木兹海峡关闭等情况，避免单一模型假设主导结论。

AEGISS -- Atomic orbital and Entropy-based Guided Inference for Space Selection -- A novel semi-automated active space selection workflow for quantum chemistry and quantum computing applications

AEGISS——基于原子轨道和熵的空间选择引导推理——一种用于量子化学和量子计算应用的新型半自动活性空间选择工作流程

Fabio Tarocco, Pi A. B. Haase, Fabijan Pavošević, Vijay Krishna, Leonardo Guidoni, Stefan Knecht, Martina Stella

专题命中 工作流自动化 ：workflow(title)

AI总结 针对多参考量子化学计算中活性空间选择问题，提出受AVAS和AutoCAS启发的新方法，结合轨道熵分析与原子轨道投影构建活性空间，经验证适用于经典和量子计算框架，还开发出便于使用且可对接多种应用的软件包。

Inunda: A GPU-Native, Agent-enabled, Differentiable Solver for High-Resolution Flood Inundation Modeling

Inunda：用于高分辨率洪水淹没建模的GPU原生、支持智能体、可微求解器

Zhi Li

专题命中 工作流自动化 ：agent(title)

AI总结 研究针对洪水淹没建模难题，提出Inunda这一GPU原生、支持智能体、可微的求解器，用质量守恒局部惯性方案求解二维浅水方程，通过案例研究展示其在洪水后报、概率性预报及火灾后应用中的优势，结合物理水力学与可微编程优势。

Stochastic simulators based optimization by Gaussian process metamodels -- Application to maintenance investments planning issues

基于高斯过程元模型的随机模拟器优化方法——应用于维护投资规划问题

Thomas Browne, Bertrand Iooss, Loïc Le Gratiet, Jérôme Lonchampt, Emmanuel Remy

专题命中 工作流自动化 ：planning(title)

AI总结 本文提出基于高斯过程元模型的随机模拟器优化方法，用于解决维护投资规划问题，通过自适应设计方法优化NPV分位数。

dpti: An Automated Thermodynamic Integration Workflow for Phase Diagram Calculations with Machine Learning Interatomic Potentials

dpti：一种使用机器学习原子间势进行相图计算的自动化热力学积分工作流程

Fengbo Yuan, Xin Zhong, Donghao Zheng, Jinzhe Zeng, Linfeng Zhang, Han Wang, Yifan Li

专题命中 工作流自动化 ：workflow(title)

AI总结 研究针对机器学习原子间势的热力学积分计算难题，开发dpti开源Python包，通过可逆积分路径连接参考系统与目标体系，自动化相图计算流程，给出示例验证其有效性。

Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference

Omni-Flow：面向多模态推理的统一工作流编排与分布式KV缓存共享框架

Bin Xiao, Jingfu Dong, Changran Wang, Yitian Chen, Xiaoyu Zhao, Yuqi Peng, Jianping Lin, Yuchen Xie

专题命中 工作流自动化 ：workflow(title)

AI总结 提出Omni-Flow框架，通过三层抽象（控制流、数据流、计算流）统一编排多模态推理工作流，实现异构单元协同、分布式KV缓存共享与高效传输，支持多种多模态场景。

Comments 19 pages

Vibe Calibration: Autonomous Bring-up of a 112-Qubit Superconducting Quantum Processor by a Skill-Orchestrating Language Agent

Vibe Calibration：通过技能编排语言代理自主启动112量子比特超导量子处理器

Huikai Xu, Jiaxiu Han, Shigang Ou, Cheng Ye, Zisong Shen, Jing Gao, Yijia Wang, Tianrui Che, Yu Song, Weiyang Liu, Lei Wang, Lin-Feng Zhang, Pan Zhang, Hai-Feng Yu

专题命中 工作流自动化 ：agent(title)

AI总结 提出Vibe Calibration系统，利用大语言模型代理将专家隐性知识转化为可复用的技能，在112量子比特处理器上实现4.7小时内自主校准108个量子比特，速度提升4-5倍，并跨设备迁移。