Related papers: Beyond Text-to-SQL: Autonomous Research-Driven Dat…

We present a new benchmark for evaluating Deep Search--a realistic and complex form of retrieval-augmented generation (RAG) that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. These include documents,…

Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving…

Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance. LLMs have difficulty reasoning about and integrating all relevant information. We propose a…

Supervised Deep Learning (DL) models are currently the leading approach for sensor-based Human Activity Recognition (HAR) on wearable and mobile devices. However, training them requires large amounts of labeled data whose collection is…

Conventional biomedical research is increasingly labor-intensive due to the exponential growth of scientific literature and datasets. Artificial intelligence (AI), particularly Large Language Models (LLMs), has the potential to…

Modern analytics systems are fundamentally reactive, requiring users to define queries over increasingly complex and continuously evolving data. In real-time streaming environments, this paradigm breaks down, as the space of potential…

The D0 experiment at Fermilab relies on a central Oracle database for storing all detector calibration information. Access to this data is needed by hundreds of physics applications distributed worldwide. In order to meet the demands of…

Generating regulatorily compliant Suspicious Activity Report (SAR) remains a high-cost, low-scalability bottleneck in Anti-Money Laundering (AML) workflows. While large language models (LLMs) offer promising fluency, they suffer from…

Retrieval-Augmented Generation (RAG) is a framework for grounding Large Language Models (LLMs) in external, up-to-date information. However, recent advancements in context window size allow LLMs to process inputs of up to 128K tokens or…

Retrieving proper domain knowledge from an external database lies at the heart of end-to-end task-oriented dialog systems to generate informative responses. Most existing systems blend knowledge retrieval with response generation and…

Processing sequential multi-sensor data becomes important in many tasks due to the dramatic increase in the availability of sensors that can acquire sequential data over time. Human Activity Recognition (HAR) is one of the fields which are…

Designing a generalist scientific agent capable of performing tasks in laboratory settings to assist researchers has become a key goal in recent Artificial Intelligence (AI) research. Unlike everyday tasks, scientific tasks are inherently…

Relational databases are valuable resources for learning novel and interesting relations and concepts. In order to constraint the search through the large space of candidate definitions, users must tune the algorithm by specifying a…

We introduce DABstep, a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks. DABstep comprises over 450 real-world challenges derived from a financial analytics platform, requiring models to combine…

Large Language Models (LLMs) trained on large volumes of data excel at various natural language tasks, but they cannot handle tasks requiring knowledge that has not been trained on previously. One solution is to use a retriever that fetches…

Given a user's complex information need, a multi-agent Deep Research system iteratively plans, retrieves, and synthesizes evidence across hundreds of documents to produce a high-quality answer. In one possible architecture, an orchestrator…

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing…

Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world problems. To sustain this capability on long-horizon tasks,…

Causal analysis on relational databases is challenging, as analysis datasets must be repeatedly queried from complex schemas. Recent LLM systems can automate individual steps, but they hardly manage dependencies across analysis stages,…

Dense retrievers have made significant strides in text retrieval and open-domain question answering. However, most of these achievements have relied heavily on extensive human-annotated supervision. In this study, we aim to develop…