Related papers: WebNavigator: Global Web Navigation via Interactio…
This paper solves the planar navigation problem by recourse to an online reactive scheme that exploits recent advances in SLAM and visual object recognition to recast prior geometric knowledge in terms of an offline catalogue of familiar…
Navigating and visualizing multilayered knowledge graphs remains a challenging, unresolved problem in information systems design. Building on our earlier study, which engaged end users in both the design and population of a domain-specific…
ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are to navigate to an object instance in an unseen environment. Prior works have shown that end-to-end ObjectNav agents that use vanilla visual and recurrent modules, e.g.…
Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) \textit{Ineffective…
Language agents have demonstrated remarkable potential in web search and information retrieval. However, these search agents assume user queries are complete and unambiguous, an assumption that diverges from reality where users begin with…
Navigation is believed to be controlled by at least two partially dissociable systems in the brain. The cognitive map informs an organism of its location and bearing, updated by integrating vestibular self-motion or predicting distances to…
We carry out a comparative study on the problem for a walker searching on several typical complex networks. The search efficiency is evaluated for various strategies. Having no knowledge of the global properties of the underlying networks…
Autonomous navigation in unknown environments requires multi-scale spatial understanding that captures geometric details, topological connectivity, and global structure to support high-level decision making under partial observability.…
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…
Graph Retrieval-Augmented Generation (GRAG or Graph RAG) architectures aim to enhance language understanding and generation by leveraging external knowledge. However, effectively capturing and integrating the rich semantic information…
Achieving fully autonomous exploration and navigation remains a critical challenge in robotics, requiring integrated solutions for localisation, mapping, decision-making and motion planning. Existing approaches either rely on strict…
Web browsers are a portal to the internet, where much of human activity is undertaken. Thus, there has been significant research work in AI agents that interact with the internet through web browsing. However, there is also another…
In recent years, mobile robot navigation approaches have become increasingly important due to various application areas ranging from healthcare to warehouse logistics. In particular, Deep Reinforcement Learning approaches have gained…
Robust obstacle avoidance is one of the critical steps for successful goal-driven indoor navigation tasks.Due to the obstacle missing in the visual image and the possible missed detection issue, visual image-based obstacle avoidance…
We humans can impeccably search for a target object, given its name only, even in an unseen environment. We argue that this ability is largely due to three main reasons: the incorporation of prior knowledge (or experience), the adaptation…
The irreducible complexity of natural phenomena has led Graph Neural Networks to be employed as a standard model to perform representation learning tasks on graph-structured data. While their capacity to capture local and global patterns is…
RAG (Retrieval-Augmented Generation) systems and web agents are increasingly evaluated on multi-hop deep search tasks, yet current practice suffers from two major limitations. First, most benchmarks leak the reasoning path in the question…
When the navigational environment is known, it can be represented as a graph where landmarks are nodes, the robot behaviors that move from node to node are edges, and the route is a set of behavioral instructions. The route path from source…
Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…
Conventional Retrieval Augmented Generation (RAG) approaches are common in text-based applications. However, they struggle with structured, interconnected datasets like knowledge graphs, where understanding underlying relationships is…