Search: “retrieval”

arXiv:2610.08527v1 Announce Type: new Abstract: Hybrid architectures combining linear sequence models with softmax attention provide an effective balance between efficient long-context modeling and pr

arXiv:2610.07385v1 Announce Type: new Abstract: Fine-tuning vision-language models (VLMs) is typically evaluated at a single downstream checkpoint, obscuring whether a semantic capability was never ac

arXiv:2610.07798v1 Announce Type: new Abstract: People increasingly ask large language models what to do with their money, yet seldom describe their finances in full. This paper asks what a model does

arXiv:2610.04864v1 Announce Type: new Abstract: Long-video embedding requires capturing sparse query-relevant evidence under a limited visual-token budget. Uniform sampling can miss brief events in vi

arXiv:2610.04911v1 Announce Type: cross Abstract: Existing deep research agents are designed primarily for text- and image-based web sources, while video reasoning systems typically assume that releva

arXiv:2610.02970v1 Announce Type: new Abstract: Large language models (LLMs) have shown promising potential for biomedical named entity recognition (BioNER) through instruction following and in-contex

arXiv:2610.02831v1 Announce Type: new Abstract: Vision-language models (VLMs) are powerful listwise rerankers for multimodal retrieval, but high inference costs restrict them to evaluating small local

arXiv:2610.02576v1 Announce Type: new Abstract: Systematic reviews condense clinical trials into evidence tables, yet clinicians can interrogate these tables only through database queries, and many qu

arXiv:2610.02510v1 Announce Type: new Abstract: Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dial

arXiv:2610.02521v1 Announce Type: new Abstract: Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observatio

arXiv:2610.01192v1 Announce Type: new Abstract: Streaming vision-language models must process continuously growing video streams under a bounded compute budget, creating a persistent tension between r

arXiv:2610.01884v1 Announce Type: new Abstract: We introduce an approach for collection-grounded B-roll sequence generation. Given a user's video collection, a directive given in natural language, and

arXiv:2610.01058v1 Announce Type: cross Abstract: Quantized large language models are increasingly deployed on edge devices for their low latency and energy efficiency. However, model quantization wea

arXiv:2609.36359v1 Announce Type: new Abstract: Graph-based approximate nearest neighbor search (ANNS) is widely used for large-scale semantic search. Its indices are constructed primarily based on ge

arXiv:2609.36322v1 Announce Type: cross Abstract: Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer

arXiv:2609.35808v1 Announce Type: cross Abstract: Experience reuse can reduce repeated exploration in embodied agents, but a trajectory that succeeded previously may be unsuitable for the current exec

arXiv:2609.34677v1 Announce Type: cross Abstract: World models predict future observations from current experience and actions, yet prediction can depend on observations seen far in the past. Episodic

arXiv:2609.30725v1 Announce Type: new Abstract: Although effective, coding agents often incur substantial monetary costs. Their recurring cost-inefficient behaviors remain underexplored. We conduct th

arXiv:2609.31460v1 Announce Type: new Abstract: Topic modeling is an effective technique for discovering hidden themes within documents and is widely used in text mining and data analysis across a var

arXiv:2609.30604v1 Announce Type: cross Abstract: Existing computer-use agent benchmarks do not fully evaluate agents acting as assistants. A useful assistant retrieves information across complex, mul

arXiv:2609.29933v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and comp

arXiv:2609.29144v1 Announce Type: new Abstract: Persistent memory lets language-model agents improve prompts and skills without updating model weights. We show that matching retrieval scope to certifi

arXiv:2609.29703v1 Announce Type: new Abstract: AI-agent evaluations usually inspect a final answer, yet error may enter through evidence, retrieval, prompting, generation or decision mapping. We intr

arXiv:2609.30134v1 Announce Type: new Abstract: Neural behavior cloning compresses demonstrations into large models, making individual actions difficult to trace and policy updates costly. Retrieval p

arXiv:2609.27784v1 Announce Type: cross Abstract: Semi-structured documents are ubiquitous in scientific reports, financial statements, and technical manuals. Question answering over such documents re

arXiv:2609.27286v1 Announce Type: new Abstract: Long horizon language model agents continuously accumulate interaction history, increasing computational cost while making relevant information harder t

arXiv:2609.24092v1 Announce Type: new Abstract: Real-world document processing systems rely on rigid, predefined schemas, yet critical target fields often lack direct visual counterparts on the page.

arXiv:2609.25441v1 Announce Type: new Abstract: Legal argument mining supports passage classification, retrieval, and argument completion. This work introduces an expert-annotated dataset of 42 U.S. f

arXiv:2509.26200v2 Announce Type: replace-cross Abstract: Agentic artificial intelligence is a candidate enabler of Level-4 autonomy in sixth-generation (6G) networks, but agents reasoning over a shar

arXiv:2609.22231v1 Announce Type: new Abstract: Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories.

arXiv:2609.19158v1 Announce Type: new Abstract: Knowledge graphs are usually integrated into question answering by encoding a retrieved subgraph with a graph neural network and fusing it with the lang

arXiv:2609.19059v1 Announce Type: cross Abstract: Multimodal large language model (MLLM) agents are increasingly used as personal assistants for long-running tasks. Their utility depends on continuity

arXiv:2609.17855v1 Announce Type: new Abstract: Standardizing clinical language to SNOMED CT supports interoperability, analytics, and reusable phenotyping, but concept recommendation remains difficul

arXiv:2609.16301v1 Announce Type: new Abstract: Medical knowledge evolves continuously, whereas the parametric knowledge encoded in large language models (LLMs) is fixed at training time. External ret

arXiv:2609.14646v1 Announce Type: cross Abstract: Multi-turn interactions with LLMs are becoming increasingly common in information-seeking scenarios. However, user queries are often ambiguous and con

arXiv:2609.13692v1 Announce Type: cross Abstract: LLM serving reuses KV cache by exact prefix match, so when a prompt is assembled from a set of reusable pieces -- retrieved passages, tool definitions

arXiv:2609.14412v1 Announce Type: new Abstract: Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmark

arXiv:2609.11493v1 Announce Type: new Abstract: Chemistry, Manufacturing and Controls (CMC) process development generates an enormous body of technical information across a multi-stage, knowledge-inte

arXiv:2609.11899v1 Announce Type: new Abstract: Long-video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual tokens loses te

arXiv:2609.10413v1 Announce Type: new Abstract: Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precision degrades. The core challenge is

arXiv:2604.04036v2 Announce Type: replace-cross Abstract: Novice math teachers often encounter students' mistakes that are difficult to diagnose and remediate. Misconceptions are especially challengin

arXiv:2609.11460v1 Announce Type: new Abstract: Reviewer comments naturally relate to specific parts of the reviewed paper, yet grounding these comments to the underlying evidence is difficult due to

arXiv:2609.08310v1 Announce Type: cross Abstract: The success of generative retrieval has largely been attributed to the use of Semantic IDs, which improve over arbitrary item-level identifiers such a

arXiv:2601.19275v2 Announce Type: replace-cross Abstract: Tactile memory, the ability to store and retrieve touch-based experience, is critical for contact-rich tasks such as key insertion under uncer

arXiv:2609.09372v1 Announce Type: cross Abstract: Although MMLU is widely adopted as a benchmark for calibrating general AI capabilities, we psychometrically demonstrate that its aggregate score prima

arXiv:2602.18613v2 Announce Type: replace Abstract: Standard reranking evaluations study how a reranker orders candidates returned by an upstream retriever. This setup couples ranking behavior with re