Related papers: DualResearch: Entropy-Gated Dual-Graph Retrieval f…

Deep Research agents predominantly optimize search policies to maximize retrieval probability. However, we identify a critical bottleneck: the retrieval-utilization gap, where models fail to use gold evidence even after it is retrieved, due…

This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft…

Multi-hop question answering over hybrid table-text data requires retrieving and reasoning across multiple evidence pieces from large corpora, but standard Retrieval-Augmented Generation (RAG) pipelines process documents as flat ranked…

Reasoning, the ability to logically draw conclusions from existing knowledge, is a hallmark of human. Together with perception, they constitute the two major themes of artificial intelligence. While deep learning has pushed the limit of…

Graph-based RAG methods like GraphRAG have shown promising global understanding of the knowledge base by constructing hierarchical entity graphs. However, they often suffer from inefficiency and rely on manually pre-defined query modes,…

Retrieval-Augmented Generation (RAG) over Knowledge Graphs (KGs) suffers from the fact that indexing approaches may lose important contextual nuance when text is reduced to triples, thereby degrading performance in downstream…

As scientific literature grows rapidly, automated survey generation has become a key capability for AI scientists and human researchers. However, existing systems suffer from limited analytical depth due to reliance on abstracts and…

Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant…

While generative retrieval (GR) demonstrates competitive performance on standard retrieval benchmarks, existing approaches directly map queries to document identifiers (docids) without intermediate deliberation, limiting their effectiveness…

Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of…

In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop…

A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even…

Large language models (LLMs) have demonstrated strong performance in natural language generation but remain limited in knowle- dge-intensive tasks due to outdated or incomplete internal knowledge. Retrieval-Augmented Generation (RAG)…

We propose a new CogQA framework for multi-hop question answering in web-scale documents. Inspired by the dual process theory in cognitive science, the framework gradually builds a \textit{cognitive graph} in an iterative process by…

Transformer-based models have advanced the field of question answering, but multi-hop reasoning, where answers require combining evidence across multiple passages, remains difficult. This paper presents a comprehensive evaluation of…

Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across a document. In this paper, we propose…

The growing demand for automated graph algorithm reasoning has attracted increasing attention in the large language model (LLM) community. Recent LLM-based graph reasoning methods typically decouple task descriptions from graph data,…

Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA) remains limited by two fundamental limitations: (i) global…

We introduce DeepResearch$^{\text{Eco}}$, a novel agentic LLM-based system for automated scientific synthesis that supports recursive, depth- and breadth-controlled exploration of original research questions -- enhancing search diversity…

Polymer literature contains a large and growing body of experimental knowledge, yet much of it is buried in unstructured text and inconsistent terminology, making systematic retrieval and reasoning difficult. Existing tools typically…