Related papers: WebNavigator: Global Web Navigation via Interactio…
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,…
Inspired by research in psychology, we introduce a behavioral approach for visual navigation using topological maps. Our goal is to enable a robot to navigate from one location to another, relying only on its visual input and the…
Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…
LLM-based agents often operate in a greedy, step-by-step manner, selecting actions solely based on the current observation without considering long-term consequences or alternative paths. This lack of foresight is particularly problematic…
Deploying autonomous agents in real world environments is challenging, particularly for navigation, where systems must adapt to situations they have not encountered before. Traditional learning approaches require substantial amounts of…
Autonomous robots exploring unknown environments face a significant challenge: navigating effectively without prior maps and with limited external feedback. This challenge intensifies in sparse reward environments, where traditional…
Object Navigation (ObjectNav) has made great progress with large language models (LLMs), but still faces challenges in memory management, especially in long-horizon tasks and dynamic scenes. To address this, we propose TopoNav, a new…
The current state of modern web interfaces, especially in regards to accessibility focused usage is extremely lacking. Traditional methods for web interaction, such as scripting languages and screen readers, often lack the flexibility to…
We introduce NNetNav, a method for unsupervised interaction with websites that generates synthetic demonstrations for training browser agents. Given any website, NNetNav produces these demonstrations by retroactively labeling action…
Understanding the geometric relationships between objects in a scene is a core capability in enabling both humans and autonomous agents to navigate in new environments. A sparse, unified representation of the scene topology will allow…
Many networks are used to transfer information or goods, in other words, they are navigated. The larger the network, the more difficult it is to navigate efficiently. Indeed, information routing in the Internet faces serious scalability…
Current evaluation of web agents largely reduces to binary success metrics or conformity to a single reference trajectory, ignoring the structural diversity present in benchmark datasets. We present WebGraphEval, a framework that abstracts…
With recent advancements in large language models, web agents have been greatly improved. However, dealing with complex and dynamic web environments requires more advanced planning and search abilities. Previous studies usually adopt a…
One of the fundamental problems in digital agents is their lack of understanding of their environment. For instance, a web browsing agent may get lost in unfamiliar websites, uncertain what pages must be visited to achieve its goals. To…
Navigation on graphs is the problem how an agent walking on the graph can get from a source to a target with limited information about the graph. The information and the way to exploit it can vary. In this paper, we study navigation on…
Object-goal visual navigation requires robots to reason over semantic structure and act effectively under partial observability. Recent approaches based on object-level topological maps enable long-horizon navigation without dense geometric…
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as…
Complex networks are ubiquitous in nature and play a role of paramount importance in many contexts. Internet and the cyberworld, which permeate our everyday life, are self-organized hierarchical graphs. Urban traffic flows on intricate road…
Graphical user interfaces (GUI) automation agents are emerging as powerful tools, enabling humans to accomplish increasingly complex tasks on smart devices. However, users often inadvertently omit key information when conveying tasks, which…
Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily text-centric, overlooking visual information in…