·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
How Endava is redesigning software delivery around AI agents-168m◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning5h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning5h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models5h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents5h◆Why Muon Outperforms Adam: A Curvature Perspective5h◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies5h◆Efficient Reasoning on the Edge5h◆MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models5h◆Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories5h◆Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems5h◆Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach5h◆Belief-Aware VLM Model for Human-like Reasoning5h◆Binary Spiking Neural Networks as Causal Models5h◆SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems5h◆Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning5h◆Unlocking Proactivity in Task-Oriented Dialogue5h◆The Illusion of Opting in AI-Mediated Consequential Decisions5h◆SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition5h◆Subliminal Learning Is Steering Vector Distillation5h◆How Endava is redesigning software delivery around AI agents-168m◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning5h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning5h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models5h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents5h◆Why Muon Outperforms Adam: A Curvature Perspective5h◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies5h◆Efficient Reasoning on the Edge5h◆MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models5h◆Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories5h◆Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems5h◆Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach5h◆Belief-Aware VLM Model for Human-like Reasoning5h◆Binary Spiking Neural Networks as Causal Models5h◆SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems5h◆Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning5h◆Unlocking Proactivity in Task-Oriented Dialogue5h◆The Illusion of Opting in AI-Mediated Consequential Decisions5h◆SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition5h◆Subliminal Learning Is Steering Vector Distillation5h◆
News/Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?
arxiv
PublishedMay 28, 2026 at 4:00 AM

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.27494v1 Announce Type: cross Abstract: Modern retrieval-augmented generation(RAG) deployments increasingly rely on caching to reduce token cost and time-to-first-token(TTFT). Prefix-level KV reuse is now standard in serving stacks such as vLLM, and chunk-level and position-independent reu

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning5harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning5harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models5harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents5h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews