Search: “multi-hop”

arXiv:2604.12487v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit strong abilities in natural language understanding and generation, yet they struggle with knowledge-intensive rea

arXiv:2604.02460v2 Announce Type: replace Abstract: Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation.

arXiv:2609.22726v1 Announce Type: new Abstract: Efficient coordination under limited communication remains a key challenge in decentralized multi-robot exploration. While centralized approaches benefi

arXiv:2609.22880v1 Announce Type: cross Abstract: LLM rerankers add of the order of $0.2-0.3 per 1,000 queries and about a second of tail latency on top of a graph-augmented dense pipeline such as Hip

arXiv:2609.16012v1 Announce Type: new Abstract: Despite significant progress in general visual question answering and cross-modal understanding, multimodal large language models still face a pronounce

arXiv:2609.05518v1 Announce Type: new Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, moti

arXiv:2609.02059v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question a

arXiv:2608.21558v1 Announce Type: cross Abstract: Recent advances in LLMs and the adoption of RAG systems in industry have created a need for domain-specific question-answer datasets that can assess R

arXiv:2608.22872v1 Announce Type: new Abstract: Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline a

arXiv:2608.12282v1 Announce Type: new Abstract: Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities

arXiv:2608.01463v2 Announce Type: replace Abstract: Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Mul

arXiv:2608.00705v1 Announce Type: cross Abstract: Reported verdicts on GraphRAG versus vector RAG disagree, and the evidence is typically tied to a single corpus, embedder, and judge -- and, we show,

arXiv:2607.00972v1 Announce Type: new Abstract: Trustworthy deployment of Agentic Retrieval-Augmented Generation (RAG) systems requires mechanisms for estimating when multi-stage reasoning pipelines m

arXiv:2607.00341v1 Announce Type: cross Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). How

arXiv:2607.00725v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) under a fixed reader-context budget forces a selection problem: of the evidence retrieved, only a fraction can be s

arXiv:2508.15851v2 Announce Type: replace Abstract: Despite rapid progress in large language models (LLMs), current QA benchmarks still overlook the core challenge of real-world scientific information

arXiv:2606.03280v1 Announce Type: new Abstract: Recent work shows that language models can transmit behavioural traits through hidden signals in generated data during training. We ask whether a more d

arXiv:2603.16654v2 Announce Type: replace-cross Abstract: Evaluating the reasoning abilities of large language models (LLMs) solely from final answers can obscure failures in intermediate steps, espec

arXiv:2601.23224v2 Announce Type: replace Abstract: Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting th

arXiv:2505.09246v4 Announce Type: replace-cross Abstract: In many real-world settings, machine learning models and interactive systems have access to both structured knowledge, e.g., knowledge graphs

arXiv:2601.21699v2 Announce Type: replace Abstract: Multi-turn reasoning agents solve complex questions by decomposing them into intermediate retrieval or tool-use steps, for accumulating supporting e

arXiv:2605.07593v1 Announce Type: new Abstract: Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams,

arXiv:2602.13595v2 Announce Type: replace Abstract: Neural scaling laws provide a predictable recipe for AI advancement: reducing numerical precision should linearly improve computational efficiency a

arXiv:2601.19827v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-re

arXiv:2603.28886v2 Announce Type: replace-cross Abstract: Graph-augmented retrieval combines dense similarity with graph-based relevance signals such as Personalized PageRank (PPR), but these scores h

arXiv:2510.20505v4 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against late

arXiv:2607.09678v2 Announce Type: replace Abstract: When LLM agents hand information to one another, does the message format matter? Two literatures disagree: format-optimization work reports that str

arXiv:2608.05153v1 Announce Type: cross Abstract: GraphRAG underperforms vector RAG on citation precision in many reports, but where and why have remained corpus-bound. We present a triple-robustness

arXiv:2608.00712v1 Announce Type: new Abstract: Multi hop question generation (MQG) aims to generate questions from multiple given documents and target answers, whereas question answering (QA) focuses

arXiv:2607.14561v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge

arXiv:2606.27909v1 Announce Type: cross Abstract: Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden

arXiv:2605.27596v1 Announce Type: new Abstract: Recently, there has been increased interest in Small Language Models (SLMs), which are fast, show good performance, and have lower hardware demands than

SAG retrieves structured multi-hop evidence via event-entity hyperedges and query-time joins, without a maintained global knowledge graph.

arXiv:2609.10239v1 Announce Type: cross Abstract: Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversiz

arXiv:2609.01658v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances Large Language Models by grounding responses in external knowledge, but multi-hop reasoning remains vulnerable

arXiv:2604.23783v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterativ

arXiv:2604.11741v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer

arXiv:2608.22479v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enables LLMs to access external knowledge for answering knowledge-intensive questions. For complex multi-hop questi

arXiv:2607.05577v1 Announce Type: new Abstract: Long-form fiction writers need memory that answers multi-hop questions about evolving story state: who knows a secret and when they learned it, whether

arXiv:2606.11770v1 Announce Type: new Abstract: Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate s

arXiv:2605.03598v2 Announce Type: cross Abstract: Understanding how biological and artificial neural networks implement computation from connectivity is a central problem in neuroscience and machine l

arXiv:2604.17458v2 Announce Type: replace Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) enhances LLMs by structuring corpus into graphs to facilitate multi-hop reasoning. While recen

arXiv:2609.37661v1 Announce Type: new Abstract: Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs. However, existing relation-free gr

arXiv:2609.36700v1 Announce Type: cross Abstract: When conversing with large language models (LLMs), users often begin with a simple question and build towards a multi-hop question through follow-up t

arXiv:2608.25115v1 Announce Type: new Abstract: Existing methods for improving Retrieval-Augmented Generation (RAG) efficiency mainly optimize downstream LLM generation, such as context compression or

arXiv:2608.21252v1 Announce Type: cross Abstract: Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationship