Related papers: Improving and Evaluating Open Deep Research Agents

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…

As an embodiment of intelligence evolution toward interconnected architectures, Deep Research Agents (DRAs) systematically exhibit the capabilities in task decomposition, cross-source retrieval, multi-stage reasoning, information…

We present ORCA (Omni Research on Calculation in AI) Benchmark - a novel benchmark that evaluates large language models (LLMs) on multi-domain, real-life quantitative reasoning using verified outputs from Omni's calculator engine. In 500…

This survey examines the rapidly evolving field of Deep Research systems -- AI-powered applications that automate complex research workflows through the integration of large language models, advanced information retrieval, and autonomous…

This paper presents an analysis of open-source large language models (LLMs) and their application in Retrieval-Augmented Generation (RAG) tasks, specific for enterprise-specific data sets scraped from their websites. With the increasing…

Agentic Retrieval Augmented Generation (RAG) and 'deep research' systems aim to enable autonomous search processes where Large Language Models (LLMs) iteratively refine outputs. However, applying these systems to domain-specific…

Edge-scale deep research agents based on small language models are attractive for real-world deployment due to their advantages in cost, latency, and privacy. In this work, we study how to train a strong small deep research agent under…

In the field of software operations, Large Language Models (LLMs) have attracted increasing attention. However, existing research has not yet achieved efficient and effective end-to-end intelligent operations due to low-quality data,…

We present \textbf{Deep Researcher Agent}, an open-source framework that enables large language model (LLM) agents to autonomously conduct deep learning experiments around the clock. Unlike existing AI research assistants that focus on…

Reading comprehension by machine has been widely studied, but machine comprehension of spoken content is still a less investigated problem. In this paper, we release Open-Domain Spoken Question Answering Dataset (ODSQA) with more than three…

Large language models (LLMs) have excelled in various natural language processing tasks, but challenges in interpretability and trustworthiness persist, limiting their use in high-stakes fields. Causal discovery offers a promising approach…

Search engines answer users' queries by listing relevant items (e.g. documents, songs, products, web pages, ...). These engines rely on algorithms that learn to rank items so as to present an ordered list maximizing the probability that it…

The paradigm of large language model (LLM) reasoning is shifting from parameter scaling to test-time compute scaling, yet many existing approaches still rely on uniform brute-force sampling (for example, fixed best-of-N or self-consistency)…

Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent search agents further cast RAG as an autonomous, multi-turn…

Large Language Models (LLMs) equipped with web search capabilities have demonstrated impressive potential for deep research tasks. However, current approaches predominantly rely on either manually engineered prompts (prompt…

Recent advancements in Large Reasoning Models (LRMs), such as OpenAI's o1/o3 and DeepSeek-R1, have demonstrated remarkable performance in specialized reasoning tasks through human-like deliberative thinking and long chain-of-thought…

Large Language Models (LLMs) have recently demonstrated remarkable performance in various Natural Language Processing (NLP) applications, such as sentiment analysis, content generation, and personalized recommendations. Despite their…

Long-context multiple-choice question answering tasks require robust reasoning over extensive text sources. Since most of the pre-trained transformer models are restricted to processing only a few hundred words at a time, successful…

Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the challenges in DR is the lack of domain-specific training data. While DR models…

Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such settings due to limited long-horizon…