Related papers: WhyFlow: Interrogative Debugger for Sensemaking Ta…
Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed.…
Agentic systems are increasingly acting on users' behalf, accessing calendars, email, and personal files to complete everyday tasks. Privacy evaluation for these systems has focused on the input and output boundaries, but each task involves…
Dataflow analysis is a fundamental code analysis technique that identifies dependencies between program values. Traditional approaches typically necessitate successful compilation and expert customization, hindering their applicability and…
Scientific workflow management systems offer features for composing complex computational pipelines from modular building blocks, for executing the resulting automated workflows, and for recording the provenance of data products resulting…
Tens of thousands of engineers use Sourcegraph day-to-day to search for code and rely on it to make progress on software development tasks. We face a key challenge in designing a query language that accommodates the needs of a broad…
Static data-flow analysis has proven its effectiveness in assessing security of applications. One major challenge it faces is scalability to large software. This issue is even exacerbated when additional limitations on computing and storage…
Time series analysis underpins forecasting, monitoring, and decision making in domains such as finance and weather, where solving a task often requires both numerical accuracy and contextual reasoning. Recent progress has moved from…
Quantitative information flow (QIF) is concerned with measuring how much of a secret is leaked to an adversary who observes the result of a computation that uses it. Prior work has shown that QIF techniques based on abstract interpretation…
This paper introduces a case study that involves data leakage in a bank applying the so-called Thinging Machine (TM) model. The aim is twofold: (1) Presenting a systematic conceptual framework for the leakage problem that provides a…
The current hardware landscape and application scale is driving performance engineers towards writing bespoke optimizations. Verifying such optimizations, and generating minimal failing cases, is important for robustness in the face of…
Deep learning is a branch of artificial intelligence employing deep neural network architectures that has significantly advanced the state-of-the-art in computer vision, speech recognition, natural language processing and other domains. In…
As multi-agent systems powered by Large Language Models (LLMs) are increasingly adopted in real-world workflows, users with diverse technical backgrounds are now building and refining their own agentic processes. However, these systems can…
Artificial intelligence offers powerful new tools for scientific discovery, but the interaction paradigms required to effectively harness these systems remain underexplored. In this paper, we present findings from a formative user study…
Generative AI shifts interaction toward intent-based outcome specification, despite user intents being inherently vague, fluid, and evolving. While a growing body of HCI research has proposed diverse interaction techniques to support this…
The need for countering Advanced Persistent Threat (APT) attacks has led to the solutions that ubiquitously monitor system activities in each enterprise host, and perform timely abnormal system behavior detection over the stream of…
Understanding the relation of events plays an important role in different domains, such as identifying the reasons for users' certain actions from application logs as well as explaining sports players' behaviors according to historical…
Causal Machine Learning has emerged as a powerful tool for flexibly estimating causal effects from observational data in both industry and academia. However, causal inference from observational data relies on untestable assumptions about…
Smartphone apps usually have access to sensitive user data such as contacts, geo-location, and account credentials and they might share such data to external entities through the Internet or with other apps. Confidentiality of user data…
The predominant use of wireless access networks is for media streaming applications, which are only gaining popularity as ever more devices become available for this purpose. However, current access networks treat all packets identically,…
Language models have shown remarkable proficiency in code generation; nevertheless, ensuring type correctness remains a challenge. Although traditional methods, such as constrained decoding, alleviate this problem by externally rejecting…