VectifyAI/PageIndex

stevedylan.dev/docs.surf

A fullstack app for indexing standard.site documents

Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki

LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when evidence is sufficient. Yet current Retrieval-Augmented Generation (RAG) systems organize external knowledge as flat chunks retrieved by embedding similarity, exposing a retrieval-as-lookup interface ill-suited to iterative reasoning agents. We propose LLM-Wiki, an agent-native retrieval system that operationalizes the Retrieval-as-Reasoning paradigm by treating external knowledge as a compilable, composable, and self-evolving structure rather than a static retrieval index. LLM-Wiki compiles documents into structured Wiki pages with bidirectional links, exposes search, read, and link-following operations through standard tool-calling interfaces, and introduces an Error Book for persistent structural and semantic self-correction. LLM-Wiki achieves state-of-the-art results on HotpotQA, MuSiQue, and 2WikiMultiHopQA, outperforming HippoRAG 2, LightRAG, and GraphRAG by 2.0-8.1 F1 points. On AuthTrace, LLM-Wiki achieves the best overall accuracy, with especially strong gains on multi-document structured queries, confirming that compilation-based retrieval generalizes beyond chain-style multi-hop reasoning.

Introduction

A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.

🚀 Announcing readwise-vector-db: Supercharge Your Readwise Library with Local, Semantic Search

Interface Experimentation | Projects

This page indexes the files currently present in interface-experiments.

Paper page - Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature

Join the discussion on this paper page

Big Indexing - at:// pizza thoughts

elvis on Twitter / X

arXiv Papers → LLM ArtifactsThis is how I keep up with AI research now.It's like having access to the most personalized arXiv feed.Automations run everyday to curate papers based a set of rules and insights.Curated papers are indexed and power the artifacts.Agent… pic.twitter.com/5UCxF8ZsT0— elvis (@omarsar0) May 6, 2026

Fast regex search: indexing text for agent tools · Cursor

How we're building indexes for regular expression search so agents can find text in large monorepos without the 15-second ripgrep waits.

Glossary

LlamaIndex is a simple, flexible framework for building knowledge assistants using LLMs connected to your enterprise data.

XRPCifying your life

I recently used Jacquard to write an ~AppView~ Index for Weaver. I alluded in my posts about my devlog about that experience how easy I had made the actual w...

Indexing Standard Site - AT Protocol

This guest post from Steve Simkins, creator of Sequoia and docs.surf, outlines the strategy he used to index standard.site records.

Index

Index is a mixed-use community center for non-conforming ideas and methods of creative exchange.

Vector RAG vs LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research

We preregistered a comparison of two ways to help an LLM answer questions over a small research corpus: a single-round Vector RAG system and an LLM-compiled markdown wiki. Both systems answered the same 13 questions over 24 papers using the same answer-generating model, and their answers were scored by blinded LLM judges. The wiki scored much better at connecting findings across papers, but its advantage in answer organization was not strong after judge adjustment. RAG met the preregistered test for single-fact lookup questions. The clean query-side cost result went against the expected wiki advantage: under the tested setup, the wiki used far more query tokens than RAG, so it could not recover any upfront build cost through cheaper queries. Two exploratory analyses changed how we interpret the result. First, claim-level citation checking favored the wiki: its cited pages more often supported the exact claims being made, even though RAG scored better on the overall groundedness rubric. Second, a decomposition-based RAG variant recovered most of the wiki's advantage on cross-paper synthesis at lower LLM-token cost, but it did not recover the wiki advantage in claim-by-claim citation support. The main conclusion is that grounded research synthesis is not a single capability. Systems can differ in how well they organize evidence, how well their citations support each claim, and how much they cost to run. In this study, no architecture was best on all three.

Karpathy shares 'LLM Knowledge Base' architecture that bypasses RAG with an evolving markdown library maintained by AI

Karpathy proposes something simpler and more loosely, messily elegant than the typical enterprise solution of a vector database and RAG pipeline.