Related papers: Go-Browse: Training Web Agents with Structured Exp…
With advances in generative AI, there is now potential for autonomous agents to manage daily tasks via natural language commands. However, current agents are primarily created and tested in simplified synthetic environments, leading to a…
The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although…
We present a scalable pipeline for automatically generating high-quality training data for web agents. In particular, a major challenge in identifying high-quality training instances is trajectory evaluation - quantifying how much progress…
Recent advancements in GUI agents have significantly expanded their ability to interpret natural language commands to manage software interfaces. However, acquiring GUI data remains a significant challenge. Existing methods often involve…
Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of training data. Large language models (LLMs) have recently…
Existing web agents typically initiate exploration from the root URL, which is inefficient for complex websites with deep hierarchical structures. Without a global view of the website's structure, agents frequently fall into navigation…
LLM web agents now browse and take actions on the open web, yet current agent evaluations are constrained to sandboxed environments or artificial tasks. We introduce BrowserArena, a live open-web agent evaluation platform that collects…
Powered by a large language model (LLM), a web browsing agent operates web browsers in a human-like manner and offers a highly transparent path toward automating a wide range of everyday tasks. As web agents become increasingly capable and…
Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical…
The paradigm of Large Language Models (LLMs) has increasingly shifted toward agentic applications, where web browsing capabilities are fundamental for retrieving information from diverse online sources. However, existing open-source web…
Autonomous agents must know how to explore user interfaces (UIs) for reliable task solving, yet systematic evaluation of this crucial phase is lacking. We introduce UIExplore-Bench, the first benchmark explicitly dedicated to UI…
Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this limitation stems from Topological Blindness, where agents are forced to…
Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs, primarily optimized for natural language…
Deep research agents integrate fragmented evidence through multi-step tool use. BrowseComp offers a text-only testbed for such agents, but existing multimodal benchmarks rarely require both weak visual cues composition and BrowseComp-style…
The predominant approach for training web navigation agents is to gather human demonstrations for a set of popular websites and hand-written tasks, but it is becoming clear that human data is an inefficient resource. We develop a pipeline…
Large language model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long horizon navigation, large scale information…
We propose a goal-driven web navigation as a benchmark task for evaluating an agent with abilities to understand natural language and plan on partially observed environments. In this challenging task, an agent navigates through a website,…
When deployed, AI agents will encounter problems that are beyond their autonomous problem-solving capabilities. Leveraging human assistance can help agents overcome their inherent limitations and robustly cope with unfamiliar situations. We…
Web AI agents such as ChatGPT Agent and GenSpark are increasingly used for routine web-based tasks, yet they still rely on text-based input prompts, lack proactive detection of user intent, and offer no support for interactive data analysis…
Information-seeking (IS) agents have achieved strong performance across a range of wide and deep search tasks, yet their tool use remains largely restricted to API-level snippet retrieval and URL-based page fetching, limiting access to the…