Related papers: Model-based Test Generation for Robotic Software: …
Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy…
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…
Traditional network experiments focus on validation through either simulation or emulation. Each approach has its own advantages and limitations. In this work, we present a new tool for next-generation network experiments created through…
AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties…
Test cases are valuable assets for maintaining software quality. State-of-the-art automated test generation techniques typically focus on maximizing program branch coverage or translating focal methods into test code. However, in contrast…
Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms,…
In this paper we outline a software development process for safety-critical systems that aims at combining some of the specific strengths of model-based development with those of programming language based development using safety-critical…
We investigate using reinforcement learning agents as generative models of images (extending arXiv:1804.01118). A generative agent controls a simulated painting environment, and is trained with rewards provided by a discriminator network…
Machine learning enables systems to build and update domain models based on runtime observations. In this paper, we study statistical model checking and runtime verification for systems with this ability. Two challenges arise: (1) Models…
In order for agents trained by deep reinforcement learning to work alongside humans in realistic settings, we will need to ensure that the agents are \emph{robust}. Since the real world is very diverse, and human behavior often changes in…
A challenge that machine learning practitioners in the industry face is the task of selecting the best model to deploy in production. As a model is often an intermediate component of a production system, online controlled experiments such…
Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy…
Limit order books are a fundamental and widespread market mechanism. This paper investigates the use of conditional generative models for order book simulation. For developing a trading agent, this approach has drawn recent attention as an…
Coding agents can generate web applications from natural-language descriptions, yet a recent benchmark study shows that generated applications fail to meet functional requirements in over 70% of cases. The core difficulty is that web…
Large language models possess impressive capabilities in generating programs (e.g., Python) from natural language descriptions to execute robotic tasks. However, these generated programs often contain errors that violate externally given…
Context: LLM-based multi-agent systems enable automation and decision support in software development, yet existing studies rely on benchmark datasets offering only binary pass-or-fail results, limiting insight into real-world…
The rapid advancements in large language models and generative artificial intelligence (AI) capabilities are making their broad application in the high-stakes testing context more likely. Use of generative AI in the scoring of constructed…
When agents interact with humans, either through embodied agents or because they are embedded in a robot, it would be easy if they could use fixed interaction protocols as they do with other agents. However, people do not keep fixed…
The emergence of the Industrial Internet results in an increasing number of complicated temporal interdependencies between automation systems and the processes to be controlled. There is a need for verification methods that scale better…
Virtual Reality (VR) applications are increasingly being integrated across a wide range of domains, including surgical training and industrial marketing. However, the long-term adoption and maintenance of VR applications remain limited,…