Related papers: Theory of Code Space: Do Code Agents Understand So…
AI coding agents operate directly on users' filesystems, where they regularly corrupt data, delete files, and leak secrets. Current approaches force a tradeoff between safety and autonomy: unrestricted access risks harm, while frequent…
Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…
General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…
GenAI-based coding assistants have disrupted software development. The next generation of these tools is agent-based, operating with more autonomy and potentially without human oversight. Like human developers, AI agents require contextual…
We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates…
Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols. Existing systems are assessed using different…
Recent progress in autonomous code generation has fueled excitement around AI agents capable of accelerating scientific discovery by running experiments. However, there is currently no benchmark that evaluates whether such agents can…
Theoretical computer science (TCS) is a subdiscipline of computer science that studies the mathematical foundations of computational and algorithmic processes and interactions. Work in this field is often recognized by its emphasis on…
Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual style, product experience, or manufacturability into solver settings that are not directly tied…
Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially…
While AI shows promise for enhancing the efficiency of qualitative analysis, the unique human-AI interaction resulting from varied coding strategies makes it challenging to develop a trustworthy AI-assisted qualitative coding system (AIQCs)…
Neural Language Models of Code, or Neural Code Models (NCMs), are rapidly progressing from research prototypes to commercial developer tools. As such, understanding the capabilities and limitations of such models is becoming critical.…
Large Language Models (LLMs) have demonstrated substantial progress in task automation and natural language understanding. However, without domain expertise in geographic information science (GIS), they continue to encounter limitations…
Context: Scientific open-source software (SciOSS) plays a foundational role in research and engineering, yet its long-term sustainability has often been overlooked and remains a significant concern. Objective: This study investigates the…
Implementing large software, as software analyzers which aim to be used in industrial settings, requires a well-engineered software architecture in order to ease its daily development and its maintenance process during its lifecycle. If the…
Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic…
Artificial Intelligence is moving from models that only generate text to Agentic AI, where systems behave as autonomous entities that can perceive, reason, plan, and act. Large Language Models (LLMs) are no longer used only as passive…
\textbf{Context:} Policy-as-Code (PaC) has become a foundational approach for embedding governance, compliance, and security requirements directly into software systems. While organizations increasingly adopt PaC tools, the software…
Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…
As artificial intelligence (AI) tools become increasingly embedded in software development workflows, questions persist about their true impact on developer productivity and experience. This paper presents findings from a mixed-methods…