Related papers: Mango: Multi-Agent Web Navigation via Global-View …

Retrieval Augmented Generation (RAG) has proven to be highly effective in boosting the generative performance of language model in knowledge-intensive tasks. However, existing RAG framework either indiscriminately perform retrieval or rely…

Multi-Agent Path Finding (MAPF) aims to move agents from their start to goal vertices on a graph. Lifelong MAPF (LMAPF) continuously assigns new goals to agents as they complete current ones. To guide agents' movement in LMAPF, prior works…

Agentic reinforcement learning has enabled large language models to perform complex multi-turn planning and tool use. However, learning in long-horizon settings remains challenging due to sparse, trajectory-level outcome rewards. While…

Autonomous web navigation requires agents to perceive complex visual environments and maintain long-term context, yet current Large Language Model (LLM) based agents often struggle with spatial disorientation and navigation loops. In this…

Recent advances in autonomous digital agents from industry (e.g., Manus AI and Gemini's research mode) highlight potential for structured tasks by autonomous decision-making and task decomposition; however, it remains unclear to what extent…

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…

Retrieval-augmented generation (RAG) demonstrates remarkable performance across tasks in open-domain question-answering. However, traditional search engines may retrieve shallow content, limiting the ability of LLMs to handle complex,…

How can we make use of information parallelism in online decision making problems while efficiently balancing the exploration-exploitation trade-off? In this paper, we introduce a batch Thompson Sampling framework for two canonical online…

Recommendation systems must optimize multiple objectives while satisfying hard business constraints such as fairness and coverage. For example, an e-commerce platform may require every recommendation list to include items from multiple…

Consider the scenario where multiple agents have to move in an optimal way through a network, each one towards their ending position while avoiding collisions. By optimal, we mean as fast as possible, which is evaluated by a measure known…

Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and…

With the World Wide Web's ubiquity increase and the rapid development of various online businesses, the complexity of web sites grow. The analysis of web user's navigational pattern within a web site can provide useful information for…

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…

In this paper, we consider a novel variant of the multi-armed bandit (MAB) problem, MAB with cost subsidy, which models many real-life applications where the learning agent has to pay to select an arm and is concerned about optimizing…

Autonomy via agents using large language models (LLMs) for personalized, standardized tasks boosts human efficiency. Automating web tasks (like booking hotels within a budget) is increasingly sought after. Fulfilling practical needs, the…

Safe navigation is essential for autonomous systems operating in hazardous environments. Traditional planning methods excel at long-horizon tasks but rely on a predefined graph with fixed distance metrics. In contrast, safe Reinforcement…

Mobile device agent based on Multimodal Large Language Models (MLLM) is becoming a popular application. In this paper, we introduce Mobile-Agent, an autonomous multi-modal mobile device agent. Mobile-Agent first leverages visual perception…

Phishing attacks are a major threat to online security, exploiting user vulnerabilities to steal sensitive information. Various methods have been developed to counteract phishing, each with varying levels of accuracy, but they also face…

Large Language Models (LLMs) have achieved great success in many real-world applications, especially the one serving as the cognitive backbone of Multi-Agent Systems (MAS) to orchestrate complex workflows in practice. Since many deployment…

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…