Related papers: BUILD-AND-FIND: An Effort-Aware Protocol for Evalu…
Enterprise agents are increasingly expected to operate autonomously across tools and interfaces, yet production deployments require governance by construction. Systems must specify which actions are allowed, when human oversight is…
An essential part of software maintenance and evolution, refactoring is performed by developers, regardless of technology or domain, to improve the internal quality of the system, and reduce its technical debt. However, choosing the…
AI coding agents increasingly modify real software repositories and make dependency decisions, including adding, removing, or updating third-party packages. These choices can materially affect security posture and maintenance burden, yet…
We are interested in interactive agents that learn to coordinate, namely, a $builder$ -- which performs actions but ignores the goal of the task, i.e. has no access to rewards -- and an $architect$ which guides the builder towards the goal…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
Binary code similarity detection is a core task in reverse engineering. It supports malware analysis and vulnerability discovery by identifying semantically similar code in different contexts. Modern methods have progressed from manually…
Advancing reinforcement learning (RL) requires tools that are flexible enough to easily prototype new methods while avoiding impractically slow experimental turnaround times. To match the first requirement, the most popular RL libraries…
Free energy calculations are rapidly becoming indispensable in structure-enabled drug discovery programs. As new methods, force fields, and implementations are developed, assessing their expected accuracy on real-world systems…
Automated program synthesis lowers the cost of producing implementations but introduces a harder governance problem: determining which generated artifacts are admissible. Natural-language specifications are ambiguous, and example-based…
Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains…
Memory corruption vulnerabilities are still a severe threat for software systems. To thwart the exploitation of such vulnerabilities, many different kinds of defenses have been proposed in the past. Most prominently, Control-Flow Integrity…
Existing benchmarks for computational materials discovery primarily evaluate static predictive tasks or isolated computational sub-tasks. While valuable, these evaluations neglect the inherently iterative and adaptive nature of scientific…
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…
Well structured and readable source code is a pre-requisite for maintainable software and successful collaboration among developers. Static analysis enables the automated extraction of code complexity and readability metrics which can be…
Thanks to unprecedented language understanding and generation capabilities of large language model (LLM), Retrieval-augmented Code Generation (RaCG) has recently been widely utilized among software developers. While this has increased…
The problem of writing a specification which accurately reflects the intent of the developer has long been recognized as fundamental. We propose a method and a supporting tool to write and check a specification and an implementation using a…
AI code agents excel at isolated tasks yet struggle with multi-file software engineering requiring architectural understanding. We introduce Theory of Code Space (ToCS), a benchmark that evaluates whether agents can construct, maintain, and…
For the task of generating complex outputs such as source code, editing existing outputs can be easier than generating complex outputs from scratch. With this motivation, we propose an approach that first retrieves a training example based…
Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current…
In recent years, recommender systems have become a ubiquitous part of our daily lives, while they suffer from a high risk of being attacked due to the growing commercial and social values. Despite significant research progress in…