Related papers: SIADAFIX: issue description response for adaptive …
Correcting bugs using modern Automated Program Repair (APR) can be both time-consuming and resource-expensive. We describe a program repair approach that aims to improve the scalability of modern APR tools. The approach leverages program…
The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven…
Finding good configurations for a software system is often challenging since the number of configuration options can be large. Software engineers often make poor choices about configuration or, even worse, they usually use a sub-optimal…
In this work, we present a domain-independent approach for adaptive scaffolding in robotic explanation generation to guide tasks in human-robot interaction. We present a method for incorporating interdisciplinary research results into a…
As supercomputers grow in hardware complexity, their susceptibility to faults increases and measures need to be taken to ensure the correctness of results. Some numerical algorithms have certain characteristics that allow them to recover…
The rising popularity of declarative languages and the hard to debug nature thereof have motivated the need for applicable, automated repair techniques for such languages. However, despite significant advances in the program repair of…
Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce…
We consider the problem of learning to repair programs from diagnostic feedback (e.g., compiler error messages). Program repair is challenging for two reasons: First, it requires reasoning and tracking symbols across source code and…
Large language models (LLMs) are effective for automated program repair, but plausible patches that pass the full test suite often rewrite more code than necessary, increasing review and maintenance costs. This over-editing is common…
Static code analysis is a powerful approach to detect quality deficiencies such as performance bottlenecks, safety violations or security vulnerabilities already during a software system's implementation. Yet, as current software systems…
This paper introduces Project Synapse, a novel agentic framework designed for the autonomous resolution of last-mile delivery disruptions. Synapse employs a hierarchical multi-agent architecture in which a central Resolution Supervisor…
Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understanding of the underlying logic. While large language models…
Software plays a crucial role in our daily lives, and therefore the quality and security of software systems have become increasingly important. However, vulnerabilities in software still pose a significant threat, as they can have serious…
Aim. There are 10s of thousands of code review comments each week at Meta. We developed Metamate for Code Review (MetaMateCR) that provides AI-assisted fixes for reviewer comments in production at scale. Method. We developed an internal…
Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans…
Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily on manual trial-and-error processes, incur significant…
Program synthesis with Large Language Models (LLMs) suffers from a "near-miss syndrome": the generated code closely resembles a correct solution but fails unit tests due to minor errors. We address this with a multi-agent framework called…
Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…
Automated Program Repair (APR) has advanced rapidly with Large Language Models (LLMs), but most existing methods remain computationally expensive, and focused on a small set of languages. Ruby, despite its widespread use in web development…
Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a solution, but current approaches typically ignore the…