AI Agent

Model-Based Trace-Checking

Y. Howard, S. Gruner, A. Gravell, C. Ferreira, J. C. Augusto

专题命中 软件智能体 ：agent(abstract)；分类 cs.SE

Journal ref UK Software Testing Research Workshop 2003

8-Valent Fuzzy Logic for Iris Recognition and Biometry

N. Popescu-Bodorin, V. E. Balas, I. M. Motoc

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments 6 pages, 2 figures, 5th IEEE Int. Symp. on Computational Intelligence and Intelligent Informatics (Floriana, Malta, September 15-17), ISBN: 978-1-4577-1861-8 (electronic), 978-1-4577-1860-1 (print), 2011

Journal ref Proc. 5th IEEE Int. Symp. on Computational Intelligence and Intelligent Informatics, pp. 149-154, ISBN: 978-1-4577-1861-8 (electronic), 978-1-4577-1860-1 (print), IEEE Press, 2011

An Expressive Language and Efficient Execution System for Software Agents

G. Barish, C. A. Knoblock

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Journal ref Journal Of Artificial Intelligence Research, Volume 23, pages 625-666, 2005

Logic-Based Decision Support for Strategic Environmental Assessment

Marco Gavanelli, Fabrizio Riguzzi, Michela Milano, Paolo Cagnoli

专题命中 软件智能体 ：planning(abstract)；分类 cs.AI

Comments 17 pages, 1 figure, 26th Int'l. Conference on Logic Programming (ICLP'10)

Journal ref Theory and Practice of Logic Programming, 26th Int'l. Conference on Logic Programming (ICLP'10) Special Issue, 10(4-6), 643-658, 2010

File Managing and Program Execution in Web Operating Systems

Mario Bravetti

专题命中 软件智能体 ：workflow(abstract)；分类 cs.SE

Spatio-Temporal Graphical Model Selection

Patrick L. Harrington, Alfred O. Hero

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Improvement in RUP Project Management via Service Monitoring: Best Practice of SOA

Sheikh Muhammad Saqib, Shakeel Ahmad, Shahid Hussain, Bashir Ahmad, Arjamand Bano

专题命中 软件智能体 ：planning(abstract)；分类 cs.SE

Journal ref Journal of Computing, Volume 2, Issue 2, February 2010, https://sites.google.com/site/journalofcomputing/

Documenting Spreadsheets with Pseudo-Code: an Exercise with Cash-Flow and Loans

Jocelyn Paine

专题命中 软件智能体 ：planning(abstract)；分类 cs.SE

Comments 12 Pages

Journal ref Proc. European Spreadsheet Risks Int. Grp. (EuSpRIG) 2009 173-183 ISBN 978-1-905617-89-0

Managing Requirement Volatility in an Ontology-Driven Clinical LIMS Using Category Theory. International Journal of Telemedicine and Applications

Arash Shaban-Nejad, Olga Ormandjieva, Mohamad Kassab, Volker Haarslev

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments 36 Pages, 16 Figures

Journal ref International Journal of Telemedicine and Applications, Volume 2009, Article ID 917826, 14 pages, PubMed ID: 19343191

Towards an Intelligent System for Risk Prevention and Management

Fahem Kebair, Frederic Serin

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments 11 pages

Journal ref Proceedings of the 5th International ISCRAM Conference. 526-535, Washington, DC, USA May 2008

Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity

Juergen Schmidhuber

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments 15 pages, 3 highly compressible low-complexity drawings. Joint Invited Lecture for Algorithmic Learning Theory (ALT 2007) and Discovery Science (DS 2007), Sendai, Japan, 2007

The role of behavior modifiers in representation development

Carlos R. de la Mora B., Carlos Gershenson, Angelica Garcia-Vega

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments 8 pages

Logic-Based Specification Languages for Intelligent Software Agents

Viviana Mascardi, Maurizio Martelli, Leon Sterling

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments 67 pages, 1 table, 1 figure. Accepted for publication by the Journal "Theory and Practice of Logic Programming", volume 4, Maurice Bruynooghe Editor-in-Chief

Software Agents: Completing Patterns and Constructing User Interfaces

J. C. Schlimmer, L. A. Hermens

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments See http://www.jair.org/ for an online appendix and other files accompanying this article

Journal ref Journal of Artificial Intelligence Research, Vol 1, (1993), 61-89

Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models

再试一次，不要回头：小型代码模型中盲重采样优于自我修复

Yuvraj Verma

专题命中 软件智能体 ：分类 cs.AI、cs.LG、cs.SE；agent(comments)

AI总结 该研究针对MBPP+数据集在三种规模代码模型上发现，盲重采样在7B以下表现最优，成本远低于其他重试方法，而基于自身失败尝试的自我修复存在锚定效应导致的性能损失。

Comments Code, pre-registrations and run traces: https://github.com/vermayuvraj/self-improving-agent

Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents

信任但要验证？揭示自主编码代理的安全债务

A H M Nazmus Sakib, Dipayan Banik, Murtuza Jadliwala

专题命中 软件智能体 ：agent(abstract)；agentic(comments)

AI总结 本文利用AIDev数据集，通过大语言模型评判框架和人工分析，研究自主编码代理生成拉取请求中的安全代码异味。发现38.9%的请求含安全异味，供应链问题和硬编码凭证占比高，揭示了安全风险及开发者警惕性降低问题，强调需实施上下文感知安全护栏。

Comments Accepted at the KDD 2026 Workshop on Agentic Software Engineering (AgenticSE)

Demonstrating chart-plot: Closing the Last Mile of Academic Chart Generation

展示chart-plot：弥合学术图表生成的最后一英里

Yinghao Tang, Yupeng Xie, Yingchaojie Feng, Jiale Lao, Tingfeng Lan, Wei Chen

专题命中 软件智能体 ：agentic(abstract,comments)

AI总结 提出chart-plot系统，通过风格感知代码生成、部署感知渲染循环和结构化编辑层，解决学术图表从代码到发表的质量差距问题。

Comments 7 pages, 6 figures. Submitted to the VLDB ADS 2026 Workshop: The Joint Workshop on Agentic Data Systems and Data-Centric AI

Extending Agents by Transmitting Protocols in Open Systems

Lavindra de Silva, Michael Winikoff, Wei Liu

专题命中 软件智能体 ：agent(abstract,journal_ref)

Journal ref In Proceedings of the 2003 AAMAS-Workshop on Challenges in Open Agent Systems, Melbourne, Australia, 2003

Winning at Any Cost -- Infringing the Cartel Prohibition With Reinforcement Learning

Michael Schlechtinger, Damaris Kosack, Heiko Paulheim, Thomas Fetzer

专题命中 软件智能体 ：分类 cs.AI、cs.LG；agent(comments)；multi-agent(comments)

Comments accepted at the 19th International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS 2021)

Why Do Prefetchers Fail? Let Agents Answer

预取器为何失效？让智能体来解答

Xiangfeng Sun, Ceyu Xu, Ningzhi Ai, Zeyu Zhu, Yiyang Yuan, Yuan Xie

专题命中 软件智能体 ：agent(abstract)

AI总结 该研究提出智能体驱动的自动研究流程构建预取器混合模型MoP，在SPEC CPU2006/2017上实现61.1%几何平均IPC加速，超越多款人工设计预取器，为硬件预取器设计提供新路径。

Comments Fixed a minor typo in Fig. 4

When "Do Not" Is Not Deny: Security Rules in CLAUDE.md vs Built-In Controls

当“不要”并非“拒绝”：CLAUDE.md中的安全规则与内置控制

Ting Yan

专题命中 软件智能体 ：agent(abstract)

AI总结 该研究对比CLAUDE.md的自然语言安全规则与Claude Code内置控制的匹配度，发现仅4%-16%的规则有匹配控制，揭示开发者无法获知规则是否被强制执行的安全问题。

Comments 11 pages, 5 figures

When Can Agents Safely Checkpoint, Fork, Restore, and Merge? Exact Checking for Execution Edits

智能体何时能安全地进行检查点、分叉、恢复与合并？执行编辑的精确检查

Yusheng Zheng, Xiaoyu Song, Yanpeng Hu, Lebin Cheng, Yuxi Huang, Wei Zhang

专题命中 软件智能体 ：agent(abstract)

AI总结 该研究针对智能体的检查点、分叉等执行编辑操作，提出一种精确判定编辑安全性的算法，通过形式化方法验证，相关成果已在 Lean 中实现并开源。

Comments 24 pages

Latent Reasoning Guidance for Parallel Code Translation

并行代码翻译的潜在推理引导

Tomer Bitan, Erel Kaplan, Roee Bar-Yadin, Lian Ghrayeb, Le Chen, Samyak Jhaveri, Niranjan Hasabnis, Gal Oren

专题命中 软件智能体 ：autonomous agent(abstract)

AI总结 提出一种在测试时使用过程奖励模型（PRM）对连续潜在前缀进行评分，以在最终代码解码前选择替代隐藏状态轨迹的方法，从而提升并行代码翻译的成功率。

Revealed Social Networks

揭示的社会网络

Christopher P. Chambers, Yusufcan Masatlioglu, Christopher Turansick

专题命中 软件智能体 ：agent(abstract)

AI总结 本文针对线性均值模型开发显示偏好式检验，研究其识别特性，发现结果变量维度与识别密切相关，一维时识别失效普遍，多维时识别普遍存在。

Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding

Stream3Dv2：几何-语义融合增强的流式零样本3D场景理解

Jie Xu, Na Zhao

机构 * Singapore University of Technology and Design（新加坡科技设计大学） 纠错

专题命中 软件智能体 ：agent(abstract)

AI总结 针对现有开放词汇零样本3D场景理解模型难以处理流式RGB-D输入、易受2D分割掩码噪声影响的问题，提出无训练框架Stream3Dv2，通过几何-语义融合等策略提升性能，在相关任务上优于基准，可与LLM智能体集成用于开放世界具身智能。

Understanding as an Explicit and Assessable Component of Frontier AI Safety Decisions

将理解作为前沿AI安全决策的明确且可评估的组成部分

Stephen Barrett, Robin Bloomfield, Alexandra Chirilă, Mamoon Masud, David Meredith Hardy, Phillip Mulvana

专题命中 软件智能体 ：agent(abstract)

AI总结 该研究提出一种基于Assurance 2.0框架的临时方法，用于明确且可评估前沿AI安全决策中的理解，经两种场景测试，该方法可应用且能驱动工程工作。

Comments Changed first line of abstract

Simulation-Optimization of Systems of Optimizers: Exploiting the Inner Optimization's Geometry

优化器系统的模拟优化：利用内部优化的几何结构

Zhou He

专题命中 软件智能体 ：agent(abstract)

AI总结 该研究针对优化器系统（SOSO）的模拟优化，提出利用内部优化几何结构的 PRIME 求解器，在多类测试平台上实现了优异性能，大幅降低了方差，为模拟优化提供了新方向。

r2py: AI-Assisted Conversion of R Statistical Packages to Python

r2py：用于AI辅助将R统计包转换为Python的框架

Yufei Cai, Jun Li

专题命中 软件智能体 ：agentic(abstract)

AI总结 本文提出r2py，这是Claude Code环境中首个七阶段AI辅助方法，可将R包系统转换为数值保真的原生Python库，在KernSmooth包上实现的r2py_kernsmooth通过518项测试，有效数字一致性达6-10位。

Comments v2: substantially extended. Adds a second case study (rpart) reached through R's .Call() interface, and a five-phase prologue reconstructing the portion of R's C API the package uses so its original C compiles without R. v1 covered KernSmooth only. Title shortened

Quantum-Safe Web Service Architecture Using Time-Based One-Time Passwords

使用基于时间的一次性密码的量子安全Web服务架构

Abel C. H. Chen

专题命中 软件智能体 ：agent(abstract)

AI总结 本研究开发了一种量子安全Web服务架构，采用基于后量子密码学的TLS与HTTPS保障传输安全，通过HMAC驱动的TOTP保障服务安全，并实验对比了四种哈希算法的性能以支撑部署。

The Roman Coronagraph Community Participation Program: corgisim - a simulation suite for the Nancy Grace Roman Space Telescope Coronagraph Instrument

罗马日冕仪社区参与计划：corgisim——南希·格蕾丝·罗马空间望远镜日冕仪的模拟套件

Jingwen Zhang, Sophie Noiret, Maxwell A. Millar Blanchaer, Jason Wang, Alexis Lau, Neil Zimmerman, Jessica Gersh-Range, Eric Shen, Kevin Ludwick, Taichi Uyama, Chen Xie, Vanessa P. Bailey, John Krist, Elodie Choquet, Julien Girard, Alexis Bidot, Arthur Vigan

专题命中 软件智能体 ：planning(abstract)

AI总结 该研究开发了开源模拟包corgisim，作为罗马日冕仪社区参与计划的一部分，用于南希·格蕾丝·罗马空间望远镜日冕仪观测的端到端模拟，为相关任务提供数据支持与应用指导。

Comments Proceedings of SPIE Astronomical Telescopes + Instrumentation 2026 (Paper No.14145-182)