Related papers: Argus: Evidence Assembly for Scalable Deep Researc…

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…

Reliable retrieval-augmented generation (RAG) systems depend fundamentally on the retriever's ability to find relevant information. We show that neural retrievers used in RAG systems have blind spots, which we define as the failure to…

Retrieval-augmented generation (RAG) combines document retrieval with large language models to produce responses grounded in external evidence. While several R packages support core components of RAG workflows, integrated evaluation of RAG…

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…

Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in parallel. However, progress in this field is impeded by the…

Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG)…

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,…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks when equipped with external tools. However, current frameworks predominantly rely on sequential processing, leading to inefficient execution…

Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reasoning by grounding generation in external knowledge. However, most existing RAG and GraphRAG…

Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search…

Compiler diagnostics for type inference failures are notoriously bad, and type classes only make the problem worse. By introducing a complex search process during inference, type classes can lead to wholly inscrutable or useless errors. We…

Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based…

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…

With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing…

Retrieval-Augmented Generation (RAG) grounds large language model outputs in external evidence, but remains challenged on multi-hop question answering that requires long reasoning. Recent works scale RAG at inference time along two…

Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such…

Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aesthetic anxiety) create severe label inconsistencies and…

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…

Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains…

Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRAG approaches face two core limitations: shallow retrieval…