Multi Source Iterative Research With Llm Driven Query Refinement

via “multi-step reasoning search with iterative refinement”

AI search engine — direct answers with citations, Pro Search, Focus modes, research Spaces.

Unique: Implements explicit query decomposition and iterative refinement where the model generates its own follow-up searches based on intermediate results, rather than executing a single retrieval pass. This mirrors human research behavior (asking follow-up questions based on initial findings) and is architecturally distinct from single-pass RAG systems that retrieve once and generate once.

vs others: Outperforms single-pass search engines and basic RAG systems on complex research questions by dynamically identifying information gaps and filling them, whereas Google Search requires manual query reformulation and ChatGPT lacks real-time web access for iterative refinement.

via “multi-stage query transformation and expansion”

<p align="center"> <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" /> </p> <h1 align="center">LlamaIndex.TS</h1> <h3 align="center"> Data framework for your LLM application. </h3>

Unique: Implements query transformation as a composable pipeline where decomposition, expansion, and rewriting stages can be chained and combined, with built-in deduplication and result merging across multiple query variants

vs others: More flexible than LangChain's query transformation because it supports multiple transformation strategies in sequence (not just expansion), and provides automatic result merging across variants

via “deep-search-with-multi-step-reasoning”

Neural search API — meaning-based search, full content retrieval, similarity search for AI agents.

Unique: Combines web search with multi-step reasoning and structured output extraction in a single API call. Returns citation-backed results with extracted structured data, eliminating need for separate LLM calls to parse and organize search results. Latency up to 60 seconds allows for iterative refinement within the search process.

vs others: More cost-effective than chaining standard search + separate LLM calls for research tasks; provides structured outputs with citations built-in, whereas competitors require post-processing with additional LLM calls.

via “multi-stage query planning and decomposition”

Autonomous agent for comprehensive research reports.

Unique: Uses a dedicated planner agent with context compression to intelligently decompose queries into parallel sub-queries, rather than simple keyword expansion or fixed templates. The three-tier LLM strategy allows different models for planning vs execution, optimizing cost and latency.

vs others: More intelligent than keyword-based query expansion (e.g., Perplexity's approach) because it uses reasoning to identify conceptual gaps; faster than sequential search because parallelization reduces wall-clock time despite planning overhead.

via “query transformation and expansion for improved retrieval”

LlamaIndex starter pack for common RAG use cases.

Unique: LlamaIndex's query transformation modules are composable, enabling chaining of multiple transformation strategies (expansion, decomposition, rewriting) in a single pipeline, whereas most RAG systems apply a single transformation

vs others: More sophisticated than simple query expansion because LlamaIndex supports query decomposition for multi-part questions, enabling retrieval of context for each sub-question separately before synthesis

via “query expansion and reformulation for improved retrieval”

LangChain reference RAG implementation from scratch.

Unique: Implements query expansion using LLM-based rewriting that generates semantically equivalent query variants (e.g., 'What is X?' → 'Explain X', 'How does X work?', 'Define X'), and merges results from all variants to improve recall without requiring manual expansion rules.

vs others: More flexible than fixed expansion rules because LLM-based rewriting adapts to query content; more practical than single-query retrieval because it captures multiple valid interpretations of ambiguous queries.

via “query rewriting for improved retrieval”

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

Unique: Integrates query rewriting as a first-class pipeline step in the LangGraph workflow rather than an optional post-processing layer, ensuring all queries benefit from optimization before retrieval and enabling conditional routing based on rewrite confidence

vs others: More transparent than implicit query expansion in vector databases because the rewritten query is visible and debuggable, allowing developers to understand and tune retrieval behavior

via “retrieval-with-feedback-loops-and-iteration”

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Unique: Implements explicit feedback loops where retrieval results are evaluated and used to trigger query refinement and re-retrieval, enabling iterative improvement without requiring perfect initial retrieval — a feedback-driven approach that's more robust for complex queries

vs others: More effective for complex queries than single-shot retrieval because it allows refinement based on intermediate results, and more practical than requiring users to formulate perfect queries upfront

via “query transformation and expansion”

A data framework for building LLM applications over external data.

Unique: Provides LLM-based query transformation as a first-class pipeline stage with support for multiple strategies (expansion, decomposition, rewriting) and pluggable custom transformers. Integrates seamlessly with retrieval pipelines to improve end-to-end relevance without manual query engineering.

vs others: More sophisticated than simple query expansion; built-in decomposition and rewriting strategies reduce manual prompt engineering compared to implementing custom LLM calls.

via “deep-search-with-iterative-refinement”

Search the web and codebases to get precise, up-to-date context for programming and research. Find examples, API usage, and documentation from real repositories and sites to ship faster with fewer mistakes. Extend investigations with deep search, crawling, and business or profile lookups when needed

Unique: Supports search result caching and context preservation across multiple queries, allowing agents to reference previous findings when formulating follow-up searches. Enables stateful research workflows where each search builds on prior knowledge.

vs others: More effective than single-query search for complex research because it allows agents to refine understanding iteratively, similar to how human researchers conduct investigations by following leads and validating findings.

via “multi-query retrieval with llm-generated query variants”

Everything you need to know to build your own RAG application

Unique: Leverages LLM-in-the-loop query expansion with parallel retrieval and union-based deduplication, avoiding hand-crafted query expansion rules and adapting dynamically to domain-specific terminology

vs others: More effective than single-query retrieval for sparse corpora, and more flexible than static query expansion templates because the LLM adapts variants to the specific query context

via “idea discovery through llm interaction”

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Unique: Employs a structured interaction model with multiple LLMs to iteratively refine ideas, enhancing the creative process beyond single-model approaches.

vs others: More comprehensive than single-LLM brainstorming tools, as it leverages diverse insights for idea generation.

via “comprehensive parallel search with llm-based reranking and reflection loops”

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Unique: Implements parallel semantic search with LLM-based reranking and reflection loops for iterative answer refinement. The agent uses the LLM to evaluate document relevance and answer quality, enabling more sophisticated reasoning than similarity-based ranking alone.

vs others: More comprehensive than single-pass RAG; LLM-based reranking and reflection loops enable higher-quality answers for complex research tasks, especially when using reasoning models

via “llm-powered query refinement for dark web search optimization”

AI-Powered Dark Web OSINT Tool

Unique: Integrates domain-specific prompt engineering for dark web terminology expansion rather than generic query expansion; supports four LLM providers via unified abstraction layer (llm_utils.get_llm()) enabling provider switching without code changes, and contextualizes refinement within OSINT investigation workflows rather than generic search

vs others: Outperforms generic query expansion tools (e.g., Elasticsearch query DSL) by leveraging LLM semantic understanding of dark web marketplace conventions, payment tracking terminology, and threat actor naming patterns specific to OSINT investigations

via “multi-source iterative research with llm-driven query refinement”

Local Deep Research achieves ~95% on SimpleQA benchmark (tested with Qwen 3.6). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and your private documents. Everything Local & Encrypted.

Unique: Implements LLM-driven query refinement loop where each research iteration analyzes gaps in current results and reformulates queries, rather than executing a static search plan. This is coordinated through a Research Service that manages execution lifecycle with thread-safe context management, enabling concurrent research tasks with per-user isolation via SQLCipher encrypted databases.

vs others: Outperforms single-pass research tools (Perplexity, traditional RAG) by iteratively deepening search based on LLM reasoning about gaps, achieving ~95% accuracy on SimpleQA benchmark while maintaining full local deployment and encryption for sensitive research.

via “deep research tool with iterative llm-driven investigation”

A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows. Now with Deep Research.

Unique: Implements research as an iterative, agent-driven process with feedback loops where the LLM refines search queries based on findings, rather than a single-shot search-and-summarize pattern. Integrates findings back into the Neo4j knowledge base as structured entities.

vs others: More thorough than simple search-and-summarize because it enables agents to reason about gaps and refine queries; more autonomous than manual research because the agent drives the iteration loop without human intervention.

via “query expansion and refinement for improved retrieval”

Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 30 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).

Unique: Integrates query expansion into the MCP server's search interface, allowing agents to benefit from improved retrieval without explicitly requesting expansion, and supporting both LLM-based and rule-based expansion strategies

vs others: More effective than single-query retrieval for complex information needs, and more efficient than requiring agents to manually reformulate queries because expansion happens transparently

via “contextual query refinement”

Paste in my prompt to Claude Code with an embedded API key for accessing my public readonly SQL+vector database, and you have a state-of-the-art research tool over Hacker News, arXiv, LessWrong, and dozens of other high-quality public commons sites. Claude whips up the monster SQL queries that safel

Unique: Utilizes a dynamic feedback mechanism that adapts to user interactions, enhancing the relevance of search results through contextual understanding.

vs others: Offers a more interactive and adaptive search experience compared to static query systems that do not learn from user input.

via “contextual llm-based information retrieval”

Andrej Karpathy's LLM wiki concept just became a real Mac app

Unique: Utilizes a hybrid approach combining LLMs with a structured knowledge base for enhanced retrieval accuracy.

vs others: More intuitive and context-aware than traditional search tools, providing richer responses to nuanced queries.

via “deep research mode with iterative refinement”

Open Source AI Platform - AI Chat with advanced features that works with every LLM

Unique: Implements autonomous query refinement where the LLM generates structured search queries, retrieves results, and decides whether to continue researching or synthesize. Maintains conversation state across iterations and prevents redundant retrievals by tracking previously-fetched documents in PostgreSQL conversation records.

vs others: More sophisticated than single-turn RAG because it enables iterative exploration; more controlled than open-ended web search because retrieval is bounded to indexed documents and the LLM must explicitly request additional searches.