Search: “multi-hop”

arXiv:2512.01113v2 Announce Type: replace-cross Abstract: Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning

arXiv:2607.12527v1 Announce Type: new Abstract: Musculoskeletal diseases are among the leading causes of disability worldwide and create the greatest global need for rehabilitation. Because recovery,

arXiv:2607.11875v2 Announce Type: replace-cross Abstract: We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous wo

arXiv:2607.07820v1 Announce Type: new Abstract: Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajector

arXiv:2607.08269v1 Announce Type: new Abstract: Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML. We prese

arXiv:2602.23440v4 Announce Type: replace Abstract: Reinforcement learning has emerged as an effective paradigm for training large language models to interleave reasoning with search engine calls. How

arXiv:2607.08284v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. Ho

arXiv:2607.07383v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering (KB-VQA) requires models to retrieve visual entities matching the query image from large-scale encyclopedic kn

arXiv:2607.07548v1 Announce Type: new Abstract: Large language model based search agents increasingly adopt multi-agent architectures in which a main agent decomposes a complex question into sub-queri

arXiv:2607.05804v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework fo

arXiv:2601.18157v3 Announce Type: replace Abstract: The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual underst

arXiv:2602.04853v2 Announce Type: replace Abstract: Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. Whi

arXiv:2607.04625v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) streamlines long-document understanding by leveraging retrieval mechanisms to restrict input images to a highly c

arXiv:2607.02588v1 Announce Type: cross Abstract: Multimodal large language models excel on short clips but struggle on hour-long videos in an online setting, where frames are processed incrementally

arXiv:2607.02680v1 Announce Type: cross Abstract: MLLMs have shown strong zero-shot capabilities across diverse inputs such as across images, video, audio, and text. A crucial, yet underexplored, appl

arXiv:2602.22897v3 Announce Type: replace Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to i

arXiv:2607.01553v1 Announce Type: cross Abstract: Transformers have become general-purpose architectures, but their all-to-all self-attention is poorly matched to graph data, whose interactions are sp

arXiv:2607.00339v1 Announce Type: new Abstract: Conversational data is increasingly used as a persistent source of user state for long-running assistants and AI agents. However, querying this data rem

arXiv:2606.31285v1 Announce Type: new Abstract: Human reasoning is inherently multimodal: when problems become difficult, we rarely think in words alone. We often externalize our reasoning by sketchin

arXiv:2606.13669v2 Announce Type: replace Abstract: Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works

arXiv:2606.28361v1 Announce Type: cross Abstract: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative r

Businesses run on fast decisions, but the teams who hold the answers are often buried under a backlog of routine requests, leaving users waiting in line for insights they need now. Today, we are bring

arXiv:2606.28370v1 Announce Type: cross Abstract: Enterprise business intelligence queries span structured warehouses and unstructured document repositories -- modalities with fundamentally different

arXiv:2606.29328v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding. This assumption breaks dow

arXiv:2606.28780v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are widely applied to visual document understanding. However, comprehending long documents remains an issue b

arXiv:2502.11491v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown remarkable capabilities in natural language processing. However, in knowledge graph question answering

arXiv:2606.29296v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a default recipe for process-supervised reinforcement learning of LLM reasoners, and dense process supervis

arXiv:2606.18379v2 Announce Type: replace-cross Abstract: Graph-based retrieval at billion-node scale requires jointly solving three tightly coupled problems -- graph construction, representation lear

arXiv:2606.28134v1 Announce Type: cross Abstract: Graph-based fraud detection is essential for safeguarding large-scale transaction systems, where undetected anomalies may lead to substantial financia

arXiv:2606.28050v1 Announce Type: cross Abstract: LLM-as-a-Judge and self-evaluation pipelines implicitly assume that evaluation is easier than generation. We test this in a controlled in-context QA s

arXiv:2606.28011v1 Announce Type: cross Abstract: We propose an agentic Large Language Model (LLM) framework for active Fault-Tolerant Control (FTC) that transforms fault detection outputs into constr

arXiv:2606.17524v2 Announce Type: replace Abstract: Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings, where

arXiv:2606.26535v1 Announce Type: cross Abstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnos

arXiv:2606.26449v1 Announce Type: cross Abstract: Retrieval-augmented systems routinely present citations alongside generated answers, yet a citation does not confirm that the corresponding source mea

arXiv:2606.27009v1 Announce Type: new Abstract: Multi-agent large language model (LLM) loops, for example a Writer that drafts and a Critic that revises, are almost always terminated by a fixed iterat

Written by: Jordan Jones Introduction Google Threat Intelligence Group (GTIG) has conducted an in-depth analysis of a .NET backdoor, tracked as STOCKSTAY, that has been continually developed and deplo

arXiv:2606.24259v1 Announce Type: cross Abstract: Fine-tuned encoders deployed across heterogeneous NLP tasks face three compounding problems: mismatched inductive biases, class-imbalance corruption o

arXiv:2606.22030v1 Announce Type: cross Abstract: We present Nous, a novel agent memory architecture grounded in the principle that knowledge is prediction, not storage. Rather than persisting facts a

arXiv:2606.22694v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain unreliable when spatial reasoning requires composing relations whose meanings depend on frames of reference. Existi

arXiv:2606.12065v1 Announce Type: new Abstract: Automating compliance check for geometry-intensive regulations remains a significant technical bottleneck in Building Information Modeling (BIM), primar

arXiv:2606.11470v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across natural language processing tasks, yet reliable reasoning remains an open challenge

arXiv:2606.12385v1 Announce Type: new Abstract: Modern LLM training pipelines increasingly rely on other models to generate data, filter corpora, judge outputs, and guide development decisions. These

arXiv:2606.10554v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications that require access to up-to-date knowledge. However, retraining LLM

From foundational ETL and analytics to the frontier of generative AI, Apache Spark serves as the architectural backbone for global data processing. However, as data volumes scale, the trade-off betwee

arXiv:2606.10684v1 Announce Type: cross Abstract: Modern language agents which perform multi-step reasoning have shown strong performance in knowledge-intensive question answering. However, existing a

arXiv:2606.10709v1 Announce Type: cross Abstract: The use of GRPO-style algorithms has become the standard strategy for training LLM search agents under outcome-only rewards. With these algorithms, a