Related papers: WebSTAR: Scalable Data Synthesis for Computer Use …
Addressing intricate real-world problems necessitates in-depth information seeking and multi-step reasoning. Recent progress in agentic systems, exemplified by Deep Research, underscores the potential for autonomous multi-step research. In…
Scaling up high-quality trajectory data has long been a critical bottleneck for developing human-like computer use agents. We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale…
Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operations, but this hybrid action space often leaves them uncertain about when to continue with…
Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity…
We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning.…
Although many AI applications of interest require specialized multi-modal models, relevant data to train such models is inherently scarce or inaccessible. Filling these gaps with human annotators is prohibitively expensive, error-prone, and…
One major barrier to advancing aerial autonomy has been collecting large-scale aerial datasets for training machine learning models. Due to costly and time-consuming real-world data collection through deploying drones, there has been an…
The rapid growth of dataset scales has been a key driver in advancing deep learning research. However, as dataset scale increases, the training process becomes increasingly inefficient due to the presence of low-value samples, including…
Computer use agents represent an emerging area in artificial intelligence, aiming to operate computers autonomously to fulfill user tasks, attracting significant attention from both industry and academia. However, the performance of…
While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of real-world workflows that require exploring multiple sources and synthesizing open-ended insights. In…
Visual grounding is the task of localising image regions from natural language queries and is critical for reasoning capable Graphical User Interface agents. Many existing methods rely on massive, noisy synthetic datasets. This work…
Computer Use Agents (CUAs) operate interfaces by pointing, clicking, and typing -- mirroring interactions of sighted users (SUs) who can thus monitor CUAs and share control. CUAs do not reflect interactions by blind and low-vision users…
Real-world software engineering tasks require coding agents that can operate on massive repositories, sustain long-horizon sessions, and reliably coordinate complex toolchains at test time. Existing research-grade coding agents offer…
Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools. These tasks remain challenging, as the underlying language models are often not optimized for long-horizon…
Verifying the success of computer use agent (CUA) trajectories is a critical challenge: without reliable verification, neither evaluation nor training signal can be trusted. In this paper, we present lessons learned from building a…
Simulated user agents are increasingly used in usability testing to support fast, iterative UX workflows, as they generate rich data such as action logs and think-aloud reasoning, but the unstructured nature of this output often obscures…
Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by…
Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive. Small open computer-use agents are more practical specialization targets, but they remain…
Recursive query processing has experienced a recent resurgence, as a result of its use in many modern application domains, including data integration, graph analytics, security, program analysis, networking and decision making. Due to the…
Static timing analysis (STA) is crucial for Electronic Design Automation (EDA) flows but remains a computational bottleneck. While existing GPU-based STA engines are faster than CPU, they suffer from inefficiencies, particularly intra-warp…