The paper investigates multi‑hop question answering systems and identifies two distinct failure modes: retrieval failures, where the necessary passage is not retrieved, and extraction failures, where the passage is retrieved but the required fact cannot be extracted—a phenomenon termed the fact‑grounding gap. Across three standard benchmarks, extraction failures account for nearly half of all per‑hop deficiencies and are invisible to standard retrieval metrics, remaining unresolved by retrieval‑only interventions. The study shows that these two bottlenecks require different solutions, a distinction currently missing from evaluation practices.
arXiv:2606. 28337v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are often evaluated using final answer accuracy, even though their failures can originate from preprocessing, retrieval, context packing, or generation.
arXiv:2606. 02488v1 Announce Type: new Abstract: Multi-hop question-answering systems often use expensive retrieval on every question.
arXiv:2609.13768v1 Announce Type: new Abstract: Multi-hop question answering often fails when retrieval treats evidence as isolated matches to the original question, since the facts needed to answer...
arXiv:2609.07050v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective reasoning. However, this remains particularl...
Hi-Q is a new framework for multi‑hop question answering that refines queries hierarchically based on evidence retrieved from a corpus. At each node it tests whether the current query unit is supported by evidence; if not, the node is expanded using a dependency‑preserving binary operator and verified for semantic coverage. The resulting query tree grows according to corpus support signals, and Hi‑Q achieves state‑of‑the‑art performance on three multi‑hop QA benchmarks, outperforming both iterative retrieval and graph‑based baselines without constructing a corpus‑wide graph.
PRISM is an agentic retrieval framework that uses large language models in a structured loop to improve evidence gathering for multi‑hop question answering. It splits retrieval into three specialized agents—a Question Analyzer, a Selector focused on precision, and an Adder focused on recall—whose iterative interaction yields a compact yet comprehensive evidence set. Experiments on HotpotQA, 2WikiMultiHopQA, MuSiQue, and MultiHopRAG show that PRISM consistently outperforms strong baselines by achieving higher retrieval accuracy and filtering out distracting content.
arXiv:2607. 10795v1 Announce Type: new Abstract: In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning.
arXiv:2603.16654v3 Announce Type: replace-cross Abstract: Evaluating the reasoning abilities of large language models (LLMs) solely from final answers can obscure failures in intermediate steps, espe...
arXiv:2607. 10562v1 Announce Type: new Abstract: Evaluating the multi-hop reasoning capabilities of large language models remains a significant challenge.
Clarify-Then-Search is a benchmark that tests whether large language models can ask clarification questions to improve the usefulness of deep search results. It uses 518 real-world query pairs from Baidu, where each intent query is paired with an underspecified version. The evaluation involves a clarifier asking up to three questions, a user answerer providing only explicit information, and a rewriter generating a new query that is then searched; performance is measured by a weighted nugget-recall score.
arXiv:2606. 04646v1 Announce Type: cross Abstract: Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text.
arXiv:2606. 10460v1 Announce Type: cross Abstract: Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved.