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

Continuous improvements in quantum computing hardware are exposing the need for simultaneous advances in software. Large-scale implementation of quantum algorithms requires rapid and automated compilation routines such as circuit synthesis…

Intelligent assistants like Cortana, Siri, Alexa, and Google Assistant are trained to parse information when the conversation is synchronous and short; however, for email-based conversational agents, the communication is asynchronous, and…

Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse…

A Just-In-Time (JIT) defect prediction model is a classifier to predict if a commit is defect-introducing. Recently, CC2Vec -- a deep learning approach for Just-In-Time defect prediction -- has been proposed. However, CC2Vec requires the…

Regression testing ensures a System Under Test (SUT) still works as expected after changes to it. The simplest approach for regression testing consists of re-running the entire test suite against the changed version of the SUT. However,…

Tracing just-in-time compilation is a popular compilation technique for the efficient implementation of dynamic languages, which is commonly used for JavaScript, Python and PHP. We provide a formal model of tracing JIT compilation of…

Increasing technological sophistication and widespread use of smartphones and wearable devices provide opportunities for innovative and highly personalized health interventions. A Just-In-Time Adaptive Intervention (JITAI) uses real-time…

While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal,…

The complexity of embedded application design is increasing with growing user demands. In particular, automotive embedded systems are highly complex in nature, and their functionality is realized by a set of periodic tasks. These tasks may…

AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…

State-of-the-art sequential reasoning in Large Language Models (LLMs) has expanded the capabilities of Copilots beyond conversational tasks to complex function calling, managing thousands of API calls. However, the tendency of compositional…

Autonomous agents powered by multimodal large language models have been developed to facilitate task execution on mobile devices. However, prior work has predominantly focused on atomic tasks -- such as shot-chain execution tasks and…

This paper presents a fully automated procedure for controller synthesis for multi-agent systems under coupled constraints. Each agent has dynamics consisting of two terms: the first one models the coupled constraints and the other one is…

The advancement of large language models (LLMs) has enabled the construction of multi-agent systems to solve complex tasks by dividing responsibilities among specialized agents, such as a planning agent for subgoal generation and a…

Recent advances in large language models (LLMs) have substantially accelerated the development of embodied agents. LLM-based multi-agent systems mitigate the inefficiency of single agents in complex tasks. However, they still suffer from…

Intelligent agents powered by AI planning assist people in complex scenarios, such as managing teams of semi-autonomous vehicles. However, AI planning models may be incomplete, leading to plans that do not adequately meet the stated…

The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance and efficiency, particularly for model deployment on…

We introduce CollabToolBuilder, a flexible multiagent LLM framework with expert-in-the-loop (HITL) guidance that iteratively learns to create tools for a target goal, aligning with human intent and process, while minimizing time for…

Large vision-language models are generally applicable to many downstream tasks, but come at an exorbitant training cost that only large institutions can afford. This paper trades generality for efficiency and presents Curation in Training…

Autonomous agent systems such as OpenClaw introduce significant efficiency challenges due to long-context inputs and multi-turn reasoning. This results in prohibitively high computational and monetary costs in real-world development. While…