Related papers: DeepFix: Debugging and Fixing Machine Learning Wor…
Debugging ML software (i.e., the detection, localization and fixing of faults) poses unique challenges compared to traditional software largely due to the probabilistic nature and heterogeneity of its development process. Various methods…
Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative interviews with five AI…
The rapid escalation of applying Machine Learning (ML) in various domains has led to paying more attention to the quality of ML components. There is then a growth of techniques and tools aiming at improving the quality of ML components and…
The existing deep learning (DL)-based automated program repair (APR) models are limited in fixing general software defects. % We present {\tool}, a DL-based approach that supports fixing for the general bugs that require dependent changes…
With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…
Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provided in one deep learning framework. However, this conversion…
The rapid proliferation of synthetic media, presentation attacks, and document forgeries has created significant vulnerabilities in Know Your Customer (KYC) workflows across financial services, telecommunications, and digital-identity…
This paper describes AutoFix, an automatic debugging technique that can fix faults in general-purpose software. To provide high-quality fix suggestions and to enable automation of the whole debugging process, AutoFix relies on the presence…
Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may…
Software development life cycle is profoundly influenced by bugs: their introduction, identification, and eventual resolution account for a significant portion of software cost. This has motivated software engineering researchers and…
Compilers are critical to modern computing, yet fixing compiler bugs is difficult. While recent large language model (LLM) advancements enable automated bug repair, compiler bugs pose unique challenges due to their complexity, deep…
The increasing realism of AI-Generated Images (AIGI) has created an urgent need for forensic tools capable of reliably distinguishing synthetic content from authentic imagery. Existing detectors are typically tailored to specific forgery…
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…
Large Language Models (LLMs) frequently generate buggy code with complex logic errors that are challenging to diagnose. While existing LLM-based self-repair approaches conduct intensive static semantic analysis or reply on superficial…
Computational notebooks became indispensable tools for research-related development, offering unprecedented interactivity and flexibility in the development process. However, these benefits come at the cost of reproducibility and an…
Software development agents powered by large language models (LLMs) have shown great promise in automating tasks like environment setup, issue solving, and program repair. Unfortunately, understanding and debugging such agents remain…
The quality of underlying training data is very crucial for building performant machine learning models with wider generalizabilty. However, current machine learning (ML) tools lack streamlined processes for improving the data quality. So,…
In recent years, more vulnerabilities have been discovered every day, while manual vulnerability repair requires specialized knowledge and is time-consuming. As a result, many detected or even published vulnerabilities remain unpatched,…
Software issue resolution aims to address real-world issues in software repositories (e.g., bug fixing and efficiency optimization) based on natural language descriptions provided by users, representing a key aspect of software maintenance.…
Process mining provides powerful insights into organizational workflows, but extracting these insights typically requires expertise in specialized query languages and data science tools. Large Language Models (LLMs) offer the potential to…