Related papers: Windows Agent Arena: Evaluating Multi-Modal OS Age…
With the rapid advancement of Vision-Language Models (VLMs), GUI-based mobile agents have emerged as a key development direction for intelligent mobile systems. However, existing agent models continue to face significant challenges in…
Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual…
Recent advances in large language models (LLMs) have opened new avenues for applying multi-agent systems in very large-scale simulations. However, there remain several challenges when conducting multi-agent simulations with existing…
While individual components of agentic architectures have been studied in isolation, there remains limited empirical understanding of how different design dimensions interact within complex multi-agent systems. This study aims to address…
LMMs have shown impressive visual understanding capabilities, with the potential to be applied in agents, which demand strong reasoning and planning abilities. Nevertheless, existing benchmarks mostly assess their reasoning abilities in…
Language agents based on large language models (LLMs) have demonstrated great promise in automating web-based tasks. Recent work has shown that incorporating advanced planning algorithms, e.g., tree search, is advantageous over reactive…
Large Language Models (LLMs)-based agents have made impressive progress in reasoning and tool use, enabling them to solve complex tasks. However, their ability to proactively collaborate with users, especially when goals are vague,…
Nowadays, research on GUI agents is a hot topic in the AI community. However, current research focuses on GUI task automation, limiting the scope of applications in various GUI scenarios. In this paper, we propose a formalized and…
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…
The emergence of large language models (LLMs) opens new frontiers for unmanned aerial vehicle (UAVs), yet existing systems remain confined to predefined tasks due to hardware-software co-design challenges. This paper presents the first…
Despite recent advances, LLM-based web agents still struggle with limited exploration, omission of critical steps, and sensitivity to task constraints. Prior work suggests that many of these failures stem from weaknesses in planning, yet…
For decades, human-computer interaction has fundamentally been manual. Even today, almost all productive work done on the computer necessitates human input at every step. Autonomous virtual agents represent an exciting step in automating…
Large language models (LLMs) have demonstrated remarkable capabilities in natural language tasks, yet their performance in dynamic, real-world financial environments remains underexplored. Existing approaches are limited to historical…
Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-horizon planning and reasoning. To address this, we propose an…
Unlike traditional automation tools or static LLM-based systems, agents combine decision-making and tool utilization to accomplish complex tasks, showing great potential in software engineering. However, existing studies largely focus on…
The integration of Large Language Models (LLMs) with specialized tools presents new opportunities for intelligent automation systems. However, orchestrating multiple LLM-driven agents to tackle complex tasks remains challenging due to…
As large language model (LLM)-based agents become increasingly integrated into daily digital interactions, their ability to reason across long interaction histories becomes crucial for providing personalized and contextually aware…
We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representations of classic Atari games into rich textual descriptions,…
Graphical User Interface (GUI) agents offer cross-platform solutions for automating complex digital tasks, with significant potential to transform productivity workflows. However, their performance is often constrained by the scarcity of…
Large Language Model (LLM) Agents have demonstrated remarkable capabilities in task automation and intelligent decision-making, driving the widespread adoption of agent development frameworks such as LangChain and AutoGen. However, these…