Related papers: Atomic-to-Compositional Generalization for Mobile …
Agent applications are increasingly adopted to automate workflows across diverse tasks. However, due to the heterogeneous domains they operate in, it is challenging to create a scalable evaluation framework. Prior works each employ their…
Preparing high-quality instructional materials remains a labor-intensive process that often requires extensive coordination among teaching faculty, instructional designers, and teaching assistants. In this work, we present Instructional…
While Large Language Model (LLM) agents show great potential for automated UI navigation such as automated UI testing and AI assistants, their efficiency has been largely overlooked. Our motivating study reveals that inefficient UI…
Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer interaction. However, current evaluation practices for GUI agents face two fundamental…
The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological…
General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…
Recent advances in agentic frameworks have enabled AI agents to perform complex reasoning and decision-making. However, evidence comparing their reasoning performance, efficiency, and practical suitability remains limited. To address this…
Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requires agents to process transient audio cues and temporal video dynamics that are…
Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…
Large language models deployed for MAPDL finite-element simulation face practical reliability challenges: without structured execution control, tool encapsulation, and fault recovery, outputs may be inconsistent and task failures are…
Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often…
A mobile agent is a program that is not bound to the system on which it began execution, but rather travels amongst the hosts in the network with its code and current execution state (i.e. Distributed Environment).The implementation of…
Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existing methods largely rely on static or graph-based inter-agent…
This paper introduces \textsc{InfantAgent-Next}, a generalist agent capable of interacting with computers in a multimodal manner, encompassing text, images, audio, and video. Unlike existing approaches that either build intricate workflows…
Large language models hold considerable promise for various applications, but their computational requirements create a barrier that many institutions cannot overcome. A single session using a 70-billion-parameter model can cost around $127…
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…
Full-duplex voice agents--systems that listen and speak simultaneously--are rapidly moving from research to production. However, existing evaluations address conversational dynamics and task completion in isolation. We introduce…
Large Language Models (LLMs) have achieved high accuracy on complex commonsense and mathematical problems that involve the composition of multiple reasoning steps. However, current compositional benchmarks testing these skills tend to focus…
Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models…
Multi-agent systems powered by large language models have demonstrated remarkable capabilities across diverse domains, yet existing automated design approaches seek monolithic solutions that fail to adapt resource allocation based on query…