相关论文: Agent JIT Compilation for Latency-Optimizing Web A…

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

The demand for real-time cloud applications has seen an unprecedented growth over the past decade. These applications require rapidly data transfer and fast computations. This paper considers a scenario where multiple IoT devices update…

Multi-Agent Systems (MAS) built using AI agents fulfill a variety of user intents that may be used to design and build a family of related applications. However, the creation of such MAS currently involves manual composition of the plan,…

Just-in-time (JIT) defect prediction refers to the technique of predicting whether a code change is defective. Many contributions have been made in this area through the excellent dataset by Kamei. In this paper, we revisit the dataset and…

Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic, multi-step tasks remains less well-understood: small per-step errors can compound over long…

Multi-agent systems (MAS) enable complex reasoning by coordinating multiple agents, but often incur high inference latency due to multi-step execution and repeated model invocations, severely limiting their scalability and usability in…

We present XPath Agent, a production-ready XPath programming agent specifically designed for web crawling and web GUI testing. A key feature of XPath Agent is its ability to automatically generate XPath queries from a set of sampled web…

AI agents are increasingly deployed in real-world applications, including systems such as Manus, OpenClaw, and coding agents. Existing research has primarily focused on server-side efficiency, proposing methods such as caching, speculative…

Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent. Nevertheless, the heterogeneity of edge devices, combined with the underdeveloped…

We give a prompt online mechanism for minimizing the sum of [weighted] completion times. This is the first prompt online algorithm for the problem. When such jobs are strategic agents, delaying scheduling decisions makes little sense.…

KTA (KTH's timing analyzer) is a research tool for performing timing analysis of program code. The currently available toolchain can perform two different kinds of analyses: i) exhaustive fine-grained timing analysis, where timing…

AI systems are continually evolving and advancing, and user expectations are concurrently increasing, with a growing demand for interactions that go beyond simple text-based interaction with Large Language Models (LLMs). Today's…

The integration of Large Language Models (LLMs) into applications ranging from interactive chatbots to multi-agent systems has introduced a wide spectrum of service-level objectives (SLOs) for responsiveness. These include latency-sensitive…

Multi-agent applications utilize the advanced capabilities of large language models (LLMs) for intricate task completion through agent collaboration in a workflow. Under this situation, requests from different agents usually access the same…

Due to the importance of Android app quality assurance, many automated GUI testing tools have been developed. Although the test algorithms have been improved, the impact of GUI rendering has been overlooked. On the one hand, setting a long…

Awkward Array is a library for performing NumPy-like computations on nested, variable-sized data, enabling array-oriented programming on arbitrary data structures in Python. However, imperative (procedural) solutions can sometimes be easier…

Generative AI is being leveraged to solve a variety of computer-use tasks involving desktop applications. State-of-the-art systems have focused solely on improving accuracy on leading benchmarks. However, these systems are practically…

Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world…

The ability to execute the test suite of a project is essential in many scenarios, e.g., to assess code quality and code coverage, to validate code changes made by developers or automated tools, and to ensure compatibility with…

In this paper the problem of cooperative task planning of multi-agent systems when timed constraints are imposed to the system is investigated. We consider timed constraints given by Metric Interval Temporal Logic (MITL). We propose a…