Search AI news

Faster Retrieval for Better, More Efficient RAG

Maximum inner product search (MIPS) sits at the core of recommendation systems, search, and retrieval-augmented generation (RAG). Given a query vector, MIPS systems search within a database of millions of candidate key vectors for the one that best matches the query. The original data point associated with that best-matching key is then used to handle the query: in RAG, the document that is best suited to answer the question is typically prefixed to the query. As the number of keys grows to millions and vector dimensions reach thousands, the computational cost of running an exhaustive…

Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB

UC Berkeley’s LEANN vector index stores a pruned graph and recomputes embeddings at query time. It matches HNSW accuracy at 90% recall using 4 GB instead of 188 GB, at the cost of seconds-level search. The post Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB appeared first on MarkTechPost.

Multi-Agent Retrieval-Augmented Causality Assessment (MARCA) of Individual Case Safety Reports in Pharmacovigilance

arXiv:2610.33279v1 Announce Type: new Abstract: Introduction: Increasing volumes of individual case safety reports (ICSRs) challenge expert-led causality assessment in pharmacovigilance. We developed MARCA (Multi-Agent Retrieval-Augmented Causality Assessment), a four-agent framework for Naranjo-based assessment, and evaluated agreement with human experts and exploratory differences between non-RAG and RAG-labelled scores. Methods: MARCA combined scientific literature retrieval, drug-label assessment, objective-evidence classification, and clinical causality reasoning using Gemini 2.5 Pro and DeepSeek-V3.2. Agent-generated rationales informed human-assisted scoring. A consensus expert reference standard covered 215 ICSRs and 1,562 drug-event combinations (DECs) from FAERS (Q1-Q2 2025). Agr

SUDO: From Scientific Publications to Global Scholarly Discourse

arXiv:2610.33018v1 Announce Type: new Abstract: Scholarly Knowledge Graphs (SKGs) support literature search, scientific discovery, and agent-assisted research. Yet, most approaches to SKG construction pre-specify the knowledge unit to be represented, typically named scholarly entities or contribution-level statements, and retain only the publication content expressible through that unit. This choice produces two dominant yet distinct paradigms: concept-centric SKGs that preserve entities and local relations, and statement-centric SKGs that capture high-level discourse in sentences. In both cases, the graph reflects a chosen extraction target rather than how a paper constructs and communicates knowledge. We introduce SUDO, the Scholarly Upper Discourse Ontology, which defines how knowledge

Parametric Session States Recover Retrieval Intent without Replaying History

arXiv:2610.33047v1 Announce Type: new Abstract: Long-running assistants often interpret follow-up requests whose referents, constraints, and active goals were established many turns earlier. The central challenge is therefore not only context length, but retrieval intent: a current query such as ``use the previous configuration'' may omit the project, entity, and version terms needed to locate relevant evidence. Long-context models can recover those terms by replaying the interaction, but repeatedly pay the cost of processing history. Conventional retrieval-augmented generation (RAG) is cheaper, yet assumes an information-sufficient query; conversational rewriting either rereads the history or depends on an explicitly maintained textual memory. We introduce \emph{Parametric Session State}

The study proposes to control the compilation of autoregressive large models into strategy-precise parallel inference, thereby enhancing the efficiency of hierarchical RAG.

A research paper published on October 24, 2026, on arXiv (ID 2610.30664v1) proposes a new method that compiles the autoregressive control logic of large language models in Hierarchical RAG into a policy-exact parallel inference pipeline, achieving a 35–47% reduction in control latency on MetaX devices while maintaining 84–89% policy consistency.

Why it matters：This work addresses the bottleneck inherent in LLMs when used as structured decision‑making controllers—namely, their reliance on sequential text decoding—by proposing a theoretically provable parallelization compilation scheme. Experiments conducted on real hardware (MetaX, H800) and with multiple data partitions demonstrate strong efficiency and clear technical details, positioning this research as cutting‑edge optimization for trustworthy AI systems.