中文
相关论文

相关论文: TrajAudit: Automated Failure Diagnosis for Agentic…

200 篇论文

Given that Large Language Models (LLMs) are increasingly applied to automate software development, comprehensive software assurance spans three distinct goals: regression prevention, reactive reproduction, and proactive discovery. Current…

软件工程 · 计算机科学 2026-02-24 Steven Liu , Jane Luo , Xin Zhang , Aofan Liu , Hao Liu , Jie Wu , Ziyang Huang , Yangyu Huang , Yu Kang , Scarlett Li

Fault Localization (FL) is an essential step during the debugging process. With the strong capabilities of code comprehension, the recent Large Language Models (LLMs) have demonstrated promising performance in diagnosing bugs in the code.…

软件工程 · 计算机科学 2025-02-25 Yihao Qin , Shangwen Wang , Yiling Lou , Jinhao Dong , Kaixin Wang , Xiaoling Li , Xiaoguang Mao

Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts.…

信息检索 · 计算机科学 2026-01-27 Xincheng You , Qi Sun , Neha Bora , Huayi Li , Shubham Goel , Kang Li , Sean Culatana

Formulating a treatment plan is inherently a complex reasoning and refinement task rather than a simple generation problem. However, existing large language models (LLMs) mainly rely on one-shot output without explicit verification, which…

人工智能 · 计算机科学 2026-05-08 Junkai Li , Yunghwei Lai , Tianyi Zhu , Zheng Long Lee , Weizhi Ma , Yang Liu

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not…

Effective incident management in large-scale IT systems relies on troubleshooting guides (TSGs), but their manual execution is slow and error-prone. While recent advances in LLMs offer promise for automating incident management tasks,…

Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…

Large language models are increasingly deployed as autonomous coding agents and have achieved remarkably strong performance on software engineering benchmarks. However, it is unclear whether such success transfers to computational…

Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large codebases. Existing repository-level approaches process…

软件工程 · 计算机科学 2026-05-15 Suyoung Bae , Jaehoon Lee , Changkyu Choi , YunSeok Choi , Jee-Hyong Lee

The rapid evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of…

密码学与安全 · 计算机科学 2026-03-03 Chuanming Tang , Ling Qing , Shifeng Chen

Integration testing is critical for the quality and reliability of complex software systems. However, diagnosing their failures presents significant challenges due to the massive volume, unstructured nature, and heterogeneity of logs they…

软件工程 · 计算机科学 2026-04-15 Celal Ziftci , Ray Liu , Spencer Greene , Livio Dalloro

Feature engineering remains a critical yet challenging bottleneck in machine learning, particularly for tabular data, as identifying optimal features from an exponentially large feature space traditionally demands substantial domain…

机器学习 · 计算机科学 2026-02-20 Keith Burghardt , Jienan Liu , Sadman Sakib , Yuning Hao , Bo Li

Optimization modeling stands as the engine of scientific decision-making in logistics and transportation, yet its adoption is hindered by a steep expertise threshold and the latency of manual workflows. Automating this process via Large…

人工智能 · 计算机科学 2026-04-21 Beinuo Yang , Qishen Zhou , Junyi Li , Chenxing Su , Panagiotis Angeloudis , Simon Hu

The rapid advancement of large language models (LLMs) has sparked growing interest in their integration into autonomous systems for reasoning-driven perception, planning, and decision-making. However, evaluating and training such agentic AI…

人工智能 · 计算机科学 2026-01-26 Mohamed Amine Ferrag , Abderrahmane Lakas , Merouane Debbah

Automated testing for REST APIs has become essential for ensuring the correctness and reliability of modern web services. While existing approaches primarily focus on detecting server crashes and error codes, they often overlook logical…

软件工程 · 计算机科学 2025-03-20 Ke Zhang , Chenxi Zhang , Chong Wang , Chi Zhang , YaChen Wu , Zhenchang Xing , Yang Liu , Qingshan Li , Xin Peng

Large Language Models (LLMs) have shown remarkable capabilities in automating software engineering tasks, spurring the emergence of coding agents that scaffold LLMs with external tools to resolve repository-level problems. However, existing…

软件工程 · 计算机科学 2026-02-10 Yue Pan , Zimin Chen , Siyu Lu , Zhaoyang Chu , Xiang Li , Han Li , Yang Feng , Claire Le Goues , Federica Sarro , Martin Monperrus , He Ye

The rapid shift from stateless large language models (LLMs) to autonomous, goal-driven agents raises a central question: When is agentic AI truly necessary? While agents enable multi-step reasoning, persistent memory, and tool…

人工智能 · 计算机科学 2025-12-03 Shubhi Asthana , Bing Zhang , Chad DeLuca , Ruchi Mahindru , Hima Patel

Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…

人工智能 · 计算机科学 2026-05-26 Jingwei Sun , Jianing Zhu , Yuanyi Li , Tongliang Liu , Xia HU , Bo Han

Emergency departments worldwide face rising patient volumes, workforce shortages, and variability in triage decisions that threaten the delivery of timely and accurate care. Current triage methods rely primarily on vital signs, routine…

定量方法 · 定量生物学 2025-10-21 Kerem Delikoyun , Qianyu Chen , Win Sen Kuan , John Tshon Yit Soong , Matthew Edward Cove , Oliver Hayden

Recent advancements in automatic code generation using large language models (LLMs) have brought us closer to fully automated secure software development. However, existing approaches often rely on a single agent for code generation, which…

软件工程 · 计算机科学 2024-11-06 Ana Nunez , Nafis Tanveer Islam , Sumit Kumar Jha , Peyman Najafirad