Search: “retrieval”

arXiv:2610.08452v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a

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 a

arXiv:2609.15800v1 Announce Type: new Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers models to navigate and answer queries about visually rich documents by retrieving relevant page im

arXiv:2609.08188v1 Announce Type: new Abstract: Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers

arXiv:2609.08180v1 Announce Type: new Abstract: Retrieval-augmented personalization enables large language models to produce more accurate and preference-aligned outputs using relevant records retriev

arXiv:2609.08228v1 Announce Type: new Abstract: Modern LLM agents increasingly rely on reusable skills, yet as skill libraries scale to thousands of entries, effective retrieval becomes a bottleneck.

arXiv:2608.27470v1 Announce Type: new Abstract: Entity Disambiguation (ED) is a key task for constructing and using knowledge graphs. State-of-the-art neural approaches commonly model ED as a single t

arXiv:2608.25123v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language models by incorporating external knowledge without retraining, but existing methods often u

arXiv:2608.25717v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is widely assumed to mitigate factual errors in large language models (LLMs), but it remains unclear whether retrie

arXiv:2608.18988v1 Announce Type: cross Abstract: Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLM

arXiv:2608.02583v1 Announce Type: cross Abstract: Sparse retrieval underpins modern search systems, from web search to retrieval-augmented generation. Existing work has introduced Learned Sparse Retri

arXiv:2603.12572v5 Announce Type: replace Abstract: Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchm

Building search across text, images, audio, and video? Multimodal search uses vector embeddings to retrieve content based on meaning, not just keywords or metadata. Less manual tagging. More flexible

We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages with a shared embedding space for cross-model querying. Both models achieve frontier per

arXiv:2511.04093v2 Announce Type: replace Abstract: Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge. How

arXiv:2608.04527v1 Announce Type: new Abstract: Frozen vision-language-action (VLA) policies generate temporally extended action chunks, but long-horizon manipulation remains vulnerable to accumulated

We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the internet or git history. When we apply a s

arXiv:2606.07909v1 Announce Type: new Abstract: Modern large language model (LLM) agents can use external tools to help users solve complex tasks. However, for problems that require learning from long

arXiv:2606.06036v1 Announce Type: new Abstract: Despite recent progress, LLM agents still struggle with reasoning over long interaction histories. While current memory-augmented agents rely on a stati

arXiv:2606.03247v1 Announce Type: new Abstract: Document-grounded dialogue systems (DGDS) utilize knowledge from external documents to answer domain-specific user questions. Existing solutions typical

arXiv:2605.22247v1 Announce Type: new Abstract: Idioms pose a fundamental challenge for language models, as their meaning cannot be inferred from surface form alone. Understanding such expressions, th

// Memory as a Model // The paper augments any LLM with a separate trained memory model that stores, retrieves, and integrates facts on its behalf. It decouples memory updates from base-model weight u

arXiv:2605.15701v1 Announce Type: cross Abstract: Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'

arXiv:2403.13805v2 Announce Type: replace-cross Abstract: CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of c

arXiv:2605.10094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades u

Finance Search is now available in the Perplexity Agent API. In one tool call, developers can now retrieve licensed financial datasets, real-time market data, and cited web sources for agents that nee

arXiv:2604.10695v1 Announce Type: new Abstract: Recent Audio-Visual Question Answering (AVQA) methods have advanced significantly. However, most AVQA methods lack effective mechanisms for handling mis

Simply retrieving a reasoning trace looks a lot like human reasoning, until it's time to navigate uncharted territory. If you memorized all reasoning traces of humans from 10,000 BC, you could automat

Memory is where the harness stops being a wrapper and becomes an ownership layer. Once it controls what gets remembered, retrieved, compressed, and acted on, it starts shaping the agent’s judgment, no

arXiv:2601.02978v3 Announce Type: replace-cross Abstract: Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models

arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ

arXiv:2610.12932v1 Announce Type: new Abstract: Search agents extend large reasoning models with multi-round access to external knowledge, yet most existing systems largely conflate retrieving evidenc

arXiv:2610.11218v1 Announce Type: cross Abstract: Dense associative memory (DAM) provides an energy-based framework for memory retrieval with close connections to attention mechanisms in modern artifi

arXiv:2609.25028v1 Announce Type: new Abstract: QMSum provides no scorer, making query-focused meeting summarization results difficult to compare. We rescore or generate 15 systems under one implement

arXiv:2609.22977v1 Announce Type: cross Abstract: Similarity-based retrieval is the dominant rule for conditioning large language models (LLMs) in in-context learning, retrieval-augmented generation,

arXiv:2609.22441v1 Announce Type: new Abstract: In large-scale recommendation systems like the LinkedIn Feed, content generated by a member's network (connections and follows) makes up over 70% of imp

arXiv:2609.14174v1 Announce Type: cross Abstract: Asked to describe what one of six speakers in a recording talks about, audio language models describe the right one on 6 to 16% of trials, below the 1

arXiv:2602.14941v2 Announce Type: replace-cross Abstract: Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory

arXiv:2609.03100v1 Announce Type: new Abstract: Geostationary atmospheric motion vectors (AMVs) provide the dense horizontal wind vectors (u,v) and heights ingested into data assimilation systems. Tra

arXiv:2608.24753v1 Announce Type: cross Abstract: Evaluating Retrieval-Augmented Generation (RAG) systems requires assessing not only end-to-end correctness but also how individual components interact

arXiv:2608.22118v1 Announce Type: new Abstract: LLM responses are based on the internet (via training or RAG), and AI is now used to generate a significant amount of content online (Paredes et al., 20

arXiv:2608.13708v1 Announce Type: cross Abstract: Automatically generating textbook-grounded assessment items can reduce science teachers' workload, but existing retrieval-augmented generation (RAG) s

arXiv:2608.00585v1 Announce Type: new Abstract: Verification for retrieval-augmented generation usually scores each retrieved chunk and drops the ones that fail. We show this cannot work for multi-hop

arXiv:2607.24803v1 Announce Type: cross Abstract: Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle

arXiv:2607.08397v1 Announce Type: new Abstract: Referring Image Segmentation (RIS) aims to segment image regions specified by natural language, enabling fine-grained and controllable visual understand

arXiv:2607.06843v1 Announce Type: new Abstract: Diffusion-based text-to-motion models synthesize realistic human motions but often exhibit semantic drift from the input text. Motion is inherently temp