Related papers: AI Coding Agents Need Better Compiler Remarks
Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…
Integration, composition, mechanization, and AI assisted development are the driving themes in the future of software development. At their core these concepts are rooted in the increasingly important role of computing in our world, the…
Developing AI models that are useful in clinical practice, requires efficient collaboration between clinicians and AI developers. This poses a practical challenge: clinicians must repeatedly communicate and refine their requirements with AI…
Vast improvements in natural language understanding and speech recognition have paved the way for conversational interaction with computers. While conversational agents have often been used for short goal-oriented dialog, we know little…
Automatic code optimization remains a difficult challenge, particularly for complex loop nests on modern hardware. This paper investigates a novel approach to code optimization where Large Language Models (LLMs) guide the process through a…
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…
Although coding agents have introduced new coordination dynamics in collaborative software development, detailed interactions in practice remain underexplored, especially for the code review process. In this study, we mine agent-authored PR…
Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable decision rules. While machine-learning models achieve strong performance, many fail to translate…
As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced,…
This survey paper examines the recent advancements in AI agent implementations, with a focus on their ability to achieve complex goals that require enhanced reasoning, planning, and tool execution capabilities. The primary objectives of…
The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…
Conversational agents have been gaining increasing popularity in recent years. Influenced by the widespread adoption of task-oriented agents such as Apple Siri and Amazon Alexa, these agents are being deployed into various applications to…
Modern scientific discovery increasingly relies on high-performance computing for complex modeling and simulation. A key challenge in improving parallel program performance is efficiently mapping tasks to processors and data to memory, a…
Agents, as user-centric tools, are increasingly deployed for human task delegation, assisting with a broad spectrum of requests by generating thoughts, engaging with user proxies, and producing action plans. However, agents based on large…
The human-agent team, which is a problem in which humans and autonomous agents collaborate to achieve one task, is typical in human-AI collaboration. For effective collaboration, humans want to have an effective plan, but in realistic…
AI agents are increasingly being deployed to automate tasks, often based on underspecified user instructions. Making unwarranted assumptions to compensate for the missing information and failing to ask clarifying questions can lead to…
Large Language Model (LLM) Agents are advancing quickly, with the increasing leveraging of LLM Agents to assist in development tasks such as code generation. While LLM Agents accelerate code generation, studies indicate they may introduce…
LLM-based software engineering is influencing modern software development. In addition to correctness, prior studies have also examined the performance of software artifacts generated by AI agents. However, it is unclear how exactly the…
The promise of Large Language Models in automated software engineering is often measured by functional correctness, overlooking the critical issue of long term maintainability. This paper presents a systematic audit of technical debt in…
The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable agents for a given task. Unlike traditional tools, agent capabilities are often…