Related papers: Efficient Agent Training for Computer Use
In order to reduce the cost of experimental evaluation for agents, we introduce a computational theory of evaluation for mini agents: build evaluation model to accelerate the evaluation procedures. We prove upper bounds of generalized error…
Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and…
The task of building general agents that perform well over a wide range of tasks has been an important goal in reinforcement learning since its inception. The problem has been subject of research of a large body of work, with performance…
As AI deployments become more complex and high-stakes, it becomes increasingly important to be able to estimate their risk. AI control is one framework for doing so. However, good control evaluations require eliciting strong attack…
Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration…
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the…
Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel…
While much work on web agents emphasizes the promise of autonomously performing tasks on behalf of users, in reality, agents often fall short on complex tasks in real-world contexts and modeling user preference. This presents an opportunity…
Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…
The recent rapid advancement of machine learning has been driven by increasingly powerful models with the growing availability of training data and computational resources. However, real-time decision-making tasks with limited time and…
Large Language Model (LLM) agents are increasingly deployed in complex, multi-step workflows involving planning, tool use, reflection, and interaction with external knowledge systems. These workflows generate rapidly expanding contexts that…
Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often…
With the increasing of computer capabilities, Computer aided ergonomics (CAE) offers new possibilities to integrate conventional ergonomic knowledge and to develop new methods into the work design process. As mentioned in [1], different…
Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification, we evaluate Claude Code in an agentic proving…
External knowledge has played a crucial role in the recent development of computer use agents. We identify a critical knowledge-execution gap: retrieved knowledge often fails to translate into effective real-world task execution. Our…
Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle execution chains prone to cascading failures. While API-driven agents harness rich capabilities…
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…
Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to…
Graphical user interface (GUI) agents have advanced rapidly but still struggle with complex tasks involving novel UI elements, long-horizon actions, and personalized trajectories. In this work, we introduce Instruction Agent, a GUI agent…
Existing Graphical User Interface (GUI) agents operate through step-by-step calls to vision language models--taking a screenshot, reasoning about the next action, executing it, then repeating on the new page--resulting in high costs and…