English
Related papers

Related papers: Library Drift: Diagnosing and Fixing a Silent Fail…

200 papers

LLMs are commonly used in retrieval-augmented applications to execute user instructions based on data from external sources. For example, modern search engines use LLMs to answer queries based on relevant search results; email plugins…

Cryptography and Security · Computer Science 2025-03-07 Sahar Abdelnabi , Aideen Fay , Giovanni Cherubin , Ahmed Salem , Mario Fritz , Andrew Paverd

The integration of Large Language Models (LLMs) into the software development lifecycle (SDLC) masks a critical socio-technical failure: Cognitive-Systemic Collapse. This paper introduces "Epistemological Debt," the hidden carrying cost…

Software Engineering · Computer Science 2026-05-05 Frank Ginac

Vision-Language-Action (VLA) models for autonomous driving often hit a performance plateau during Reinforcement Learning (RL) optimization. This stagnation arises from exploration capabilities constrained by previous Supervised Fine-Tuning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yuechen Luo , Qimao Chen , Fang Li , Shaoqing Xu , Jaxin Liu , Ziying Song , Zhi-xin Yang , Fuxi Wen

In this concept paper, we discuss intricacies of specifying and verifying the quality of continuous and lifelong learning artificial intelligence systems as they interact with and influence their environment causing a so-called concept…

Machine Learning · Computer Science 2021-01-19 Anton Khritankov

Intent-Based Networking (IBN) simplifies network management, but its reliability is challenged by "intent drift", where the network's state gradually deviates from its intended goal, often leading to silent failures. Conventional approaches…

Networking and Internet Architecture · Computer Science 2026-02-17 Md. Kamrul Hossain , Walid Aljoby

The notion of concept drift refers to the phenomenon that the data generating distribution changes over time; as a consequence machine learning models may become inaccurate and need adjustment. In this paper we consider the problem of…

Machine Learning · Computer Science 2022-05-16 Fabian Hinder , André Artelt , Valerie Vaquet , Barbara Hammer

The increasing deployment of advanced digital technologies such as Internet of Things (IoT) devices and Cyber-Physical Systems (CPS) in industrial environments is enabling the productive use of machine learning (ML) algorithms in the…

Machine Learning · Computer Science 2021-12-21 Nicolas Jourdan , Sagar Sen , Erik Johannes Husom , Enrique Garcia-Ceja , Tobias Biegel , Joachim Metternich

Deep neural networks exhibit periodic loss spikes during unregularized long-term training, a phenomenon known as the "Slingshot Mechanism." Existing work usually attributes this to intrinsic optimization dynamics, but its triggering…

Machine Learning · Computer Science 2026-05-27 Liu Hanqing , Jianjun Cao , Yuanze Li , Zijian Zhou

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…

Multiagent Systems · Computer Science 2026-05-12 Tianxiao Li , Yixing Ma , Haiquan Wen , Zhenglin Huang , Qianyu Zhou , Zeyu Fu , Guangliang Cheng

Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that couples executable scripts, with non-executable guidance on…

Computation and Language · Computer Science 2026-05-19 Hongyi Liu , Haoyan Yang , Tao Jiang , Bo Tang , Feiyu Xiong , Zhiyu Li

Context: Technical lag accumulates when software systems fail to keep pace with technological advancements, leading to a deterioration in software quality. Objective: This paper aims to consolidate existing research on technical lag,…

Software Engineering · Computer Science 2026-01-21 Shane K. Panter , Nasir U. Eisty

A failure detection system is the first step towards predictive maintenance strategies. A popular data-driven method to detect incipient failures and anomalies is the training of normal behaviour models by applying a machine learning…

Machine Learning · Computer Science 2021-06-21 Iñigo Martinez , Elisabeth Viles , Iñaki Cabrejas

Large language models (LLMs) now play a central role in code generation, yet they continue to hallucinate, frequently inventing non-existent libraries. Such library hallucinations are not just benign errors: they can mislead developers,…

Software Engineering · Computer Science 2026-05-20 Lukas Twist , Jie M. Zhang , Mark Harman , Helen Yannakoudakis

Third-party libraries are essential in software development as they prevent the need for developers to recreate existing functionalities. However, vulnerabilities within these libraries pose significant risks to dependent projects.…

Software Engineering · Computer Science 2025-04-01 Zirui Chen , Xing Hu , Puhua Sun , Xin Xia , Xiaohu Yang

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be…

Computation and Language · Computer Science 2023-05-29 Minqian Liu , Lifu Huang

Risk decision systems in fraud detection and credit scoring operate under structural label absence: ground truth arrives weeks to months after decisions are made. During this blind period, model performance may degrade silently, eroding the…

Computers and Society · Computer Science 2026-04-21 Oleg Solozobov

With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes…

Artificial Intelligence · Computer Science 2026-03-10 Yonghong Deng , Zhen Yang , Ping Jian , Xinyue Zhang , Zhongbin Guo , Chengzhi Li

LLMs are increasingly used to draft academic text and to support software engineering (SE) evidence synthesis, but they often hallucinate bibliographic references that look legitimate. We study how deployment-motivated prompting constraints…

Information Retrieval · Computer Science 2026-03-10 Chen Zhao , Yuan Tang , Yitian Qian

Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabilities, behavioral profile, and internal failure mode. We study behavioral and mechanistic…

Cryptography and Security · Computer Science 2026-04-21 Md Rysul Kabir , Zoran Tiganj

Adaptive prompting mechanisms have been proposed to enhance vision-language models by dynamically tailoring prompts to inputs. However, in frozen few-shot prompt learning with CLIP-style backbones, we systematically observe that adaptive…

Machine Learning · Computer Science 2026-05-12 Yunxuan Fang , Ziwei Zhang , Xinhe Wang