Related papers: AutoSurfer -- Teaching Web Agents through Comprehe…

Integrating textual graphs into Large Language Models (LLMs) is promising for complex graph-based QA. However, a key bottleneck is retrieving informative yet compact subgraphs that fit the LLM context. Existing retrievers often struggle,…

Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical…

Large language models (LLMs) have enabled remarkable advances in automated task-solving with multi-agent systems. However, most existing LLM-based multi-agent approaches rely on predefined agents to handle simple tasks, limiting the…

Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables autonomous reasoning and decision-making. While prior…

The exponential growth of data-driven systems and AI technologies has intensified the demand for high-quality web-sourced datasets. While existing datasets have proven valuable, conventional web data collection approaches face significant…

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…

Large language models (LLMs) have been successfully adapted for interactive decision-making tasks like web navigation. While achieving decent performance, previous methods implicitly assume a forward-only execution mode for the model, where…

Efficiently solving real-world problems with LLMs increasingly hinges on their ability to interact with dynamic web environments and autonomously acquire external information. While recent research like Search-R1 and WebDancer demonstrates…

Large language models (LLMs) are increasingly being used to generate synthetic datasets for the evaluation and training of downstream models. However, prior work has noted that such generated data lacks diversity. In this paper, we propose…

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…

This paper addresses fine-tuning Large Language Models (LLMs) for function calling tasks when real user interaction data is unavailable. In digital content creation tools, where users express their needs through natural language queries…

To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated machine learning (AutoML) methods have been developed to automatically search for good models. Due to the huge model search space,…

Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual…

In this paper, we introduce Auto-Intent, a method to adapt a pre-trained large language model (LLM) as an agent for a target domain without direct fine-tuning, where we empirically focus on web navigation tasks. Our approach first discovers…

Simulation-based testing is crucial for validating autonomous vehicles (AVs), yet existing scenario generation methods either overfit to common driving patterns or operate in an offline, non-interactive manner that fails to expose rare,…

Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, removing the…

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 generation of corner cases has become increasingly crucial for efficiently testing autonomous vehicles prior to road deployment. However, existing methods struggle to accommodate diverse testing requirements and often lack the ability…

Implementing an autonomous vehicle that is able to output feasible, smooth and efficient trajectories is a long-standing challenge. Several approaches have been considered, roughly falling under two categories: rule-based and learning-based…

Human drivers can recognise fast abnormal driving situations to avoid accidents. Similar to humans, automated vehicles are supposed to perform anomaly detection. In this work, we propose the spatio-temporal graph auto-encoder for learning…