Related papers: Agint: Agentic Graph Compilation for Software Engi…

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…

We present NetGent, an AI-agent framework for automating complex application workflows to generate realistic network traffic datasets. Developing generalizable ML models for networking requires data collection from network environments with…

Computer-aided design (CAD) is a promising application area for emerging artificial intelligence methods. Traditional workflows for cyberphysical systems create detailed digital models which can be evaluated by physics simulators in order…

Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…

Graph Neural Networks (GNNs) have achieved remarkable success in graph-based learning by propagating information among neighbor nodes via predefined aggregation mechanisms. However, such fixed schemes often suffer from two key limitations.…

Deep learning accelerators address the computational demands of Deep Neural Networks (DNNs), departing from the traditional Von Neumann execution model. They leverage specialized hardware to align with the application domain's structure.…

Large Language Models (LLMs) have improved programming efficiency, but their performance degrades significantly as requirements scale; when faced with multi-modal documents containing hundreds of scenarios, LLMs often produce incorrect…

Designing realistic and adaptive networked threat scenarios remains a core challenge in cybersecurity research and training, still requiring substantial manual effort. While large language models (LLMs) show promise for automated synthesis,…

Transformers have revolutionized performance in Natural Language Processing and Vision, paving the way for their integration with Graph Neural Networks (GNNs). One key challenge in enhancing graph transformers is strengthening the…

Code localization--identifying precisely where in a codebase changes need to be made--is a fundamental yet challenging task in software maintenance. Existing approaches struggle to efficiently navigate complex codebases when identifying…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

This paper presents GraphAGILE, a domain-specific FPGA-based overlay accelerator for graph neural network (GNN) inference. GraphAGILE consists of (1) \emph{a novel unified architecture design} with an \emph{instruction set}, and (2) \emph{a…

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…

We present a novel graph neural network we call AgentNet, which is designed specifically for graph-level tasks. AgentNet is inspired by sublinear algorithms, featuring a computational complexity that is independent of the graph size. The…

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…

Large Language Model (LLM)-based UI agents show great promise for UI automation but often hallucinate in long-horizon tasks due to their lack of understanding of the global UI transition structure. To address this, we introduce AGENT+P, a…

We present a self-certifying compiler for the COGENT systems language. COGENT is a restricted, polymorphic, higher-order, and purely functional language with linear types and without the need for a trusted runtime or garbage collector. It…

The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent…

Agentic workflows invoked by Large Language Models (LLMs) have achieved remarkable success in handling complex tasks. However, optimizing such workflows is costly and inefficient in real-world applications due to extensive invocations of…