Search: “retrieval”

What a fascinating paper on AI agents. A lot of the issues we see with AI agents today revolve around wrong assumptions the LLMs make. This leads to problems like hallucination, cost inefficiencies, u

Banger paper from Google DeepMind. It's on the very hot topic of model routing. Routers assume the value estimate is free. Working out which specialist handles a query best costs money too, and it is

Great paper if you are building production-grade agents. It's a good way to understand what is actually incurring costs in your agents, which involve more complex components and decisions. This works

Last week, hundreds of founders and builders gathered for AGENT NIGHT. If you weren't there, here's what you missed including the preview launch of WorkOS Airlock: 01:25 Why agents need a new access c

Very interesting new paper from Microsoft and colleagues. (bookmark it) Skill libraries are used in every major harness on the assumption that more guidance is free. This work measures what a bad skil

Most semantic search queries leave something unstated. The user knows what they mean. The system doesn't. Pinecone's text match filters scope a vector search to a lexical condition (a machine number,

Finally a good paper testing if file-system based memory for LLM agents is worth it. First, what does this look like? Deployed agents keep long-term memory as a folder of markdown files they read and

Great technical paper from Harvard and MIT. It's on role drift in compound LLM systems. (bookmark it) End-to-end RL improves the accuracy of a multi-module LLM pipeline without constraining how the mo

// Agentic Context Management // Great read for the weekend. (bookmark it) Production agents fail less on reasoning and more on what sits in their context. Conversation history, big prompts, huge tool

// Programmatic Memory Enables Long-Horizon Reasoning // Keep the entire interaction log and search it. It works great and beats bespoke memory harnesses on long-horizon tasks. New research introduces

🎨 Meet Qwen-Image-3.0 — the third generation of our foundational image generation model. If 1.0 was about 'Precision,' and 2.0 added 'Variety, Completeness, Beauty & Authenticity,' then 3.0 comes down

Progressive disclosure in agents doesn't scale. And its benefits seems agent harness dependent. (bookmark this one) Finally there is a proper study on using agent skills and the effect of progressive

Last month we hosted an AI Nerd Meetup @Workato HQ featuring builders tackling the hardest problems in agentic AI. Highlights: @yuan_sihan of Fireworks - how open-source agents can use a frontier mode

Pinecone has introduced Nexus, a knowledge engine built specifically for AI agents. Instead of repeatedly searching documents with traditional RAG, Nexus compiles knowledge once from sources like data

New research from Meta. (bookmark it) It's on how to fix agents that forget previously made decisions. It's well know that long-horizon agents keep forgetting decisions they already made. Meta researc

LlamaIndex is inviting users to process large-scale document collections through its cloud platform at cloud.llamaindex.ai. The post, from LlamaIndex founder Jerry Liu, highlights the platform's capab

// Memory becomes an action space // Great paper on long-term memory for agents. (bookmark it) In short, it's discusses the use of a learned policy for using memory at the right granularity. Most memo

// MetaSkill-Evolve // Great paper on self-improving agents. Most self-improving agents rewrite what the agent does and leave how it improves frozen and hand-authored. That improvement procedure never

Building the Document Context Layer for AI Agents AI Agents are the new knowledge workers, but the vast majority of knowledge work depends on unstructured documents. If you don’t build the proper tool

// ReContext // Models now support 128K context windows and still fail to use evidence that is already in the prompt. Where is the gap? New paper introduces ReContext, a training-free inference harnes

Great overview of always-on agents. (bookmark it) It's a new 130+ pages survey on always-on agents. Simply put it, always-on agents are systems whose future behavior depends on durable state built up

This post discusses using deep agents and OpenKeyFlow (OKF) for a wiki project built with LangGraph, a framework for constructing agent-based applications. The developer is leveraging LangGraph's capa

There is a massive demand for processing files *in the agent loop*. The number of users submitting agent queries with file attachments is exponentially increasing over time. Our mission is to make Lit

3 years ago I gave a talk at the first @aiDotEngineer conference on 'Advanced RAG' techniques in order to work around the limitations of naive RAG. It's insane how much the world has changed since the

// AutoMem // I quite like this idea of metamemory. (bookmark it) This new research from Stanford treats agent's memory management as a trainable skill instead of a fixed module. The model decides wha

@hwchase17 s “wiki memory” really resonates with how we’ve been thinking about Enterprise Knowledgebases. Agent memory is still early, but one pattern we observe consistently: enterprises don’t need a

Harrison Chase suggests using a wiki structure as the foundation for building AI agents with memory systems, citing its simplicity and extensibility as key advantages. This approach would organize age

This post describes a common architectural pattern for integrating memory components into AI systems, illustrated through examples like DeepWiki and AutoWiki that automatically generate and maintain k

We just made it a lot easier for AI agents to work with your documents. LlamaParse MCP now does more than parse or classify files: it can pull structured data out of contracts, invoices, and reports a

I cannot provide an accurate summary without access to the actual content of this X/Twitter post. The URL provided appears to have an invalid status ID format, and I don't have the ability to browse e

If your benchmark relies on a static dataset or sampling from a static distribution densely known at training time, then it is fundamentally measuring memorization/retrieval. Which might be fine if yo

New paper on giving LLM agents experience that improves the weights and stays readable at the same time. Agent-experience methods split into two camps. Externalized natural-language rules stay interpr

You can now equip your n8n workflows with the world's best parsing/extraction over your most complex documents 📃💫 We're excited to announce that LlamaParse is now an officially verified community node

I decided to run my knowledge base inside a @Cloudflare Worker👀 How? Surprisingly easily: • Spin up a @qdrant_engine cluster and grab the credentials • Process incoming files at the edge: parse with @

pretty sick that i get to work with Jake every day on making continual learning + memory accessible at scale for every single agent one common thread here is...the Trace a large part of Continual Lear

Here is a thought that might sounds odd/wrong the first time you hear it: recorded media is a phase. A long one, but a phase. For most of human history, media was live. Stories were told around fires

This post describes an AI research agent built on ActiveGraph that provides complete visibility into its reasoning process through detailed graphs and traces of claims, sources, and internal agent act

We've made a breakthrough in self-evolving AI scientists moving from 'search' to 'principled discovery': Scientific discovery requires that the search space itself changes, and an AI scientist must pe

Your AI chatbot is only as good as the data behind it. This n8n template from our friends at @apify shows you how to wire up a RAG pipeline using Apify + Pinecone + Gemini so your chatbot can answer q

@swyx and I are curating the AI in GTM track at @aiDotEngineer on June 30. The thing every AI engineer must realize: GTM just became an engineering problem. Outbound = agent design. Enrichment = retri

@jerryjliu0 — Founder & CEO of @llama_index — on Venture with Grace, sharing why data is at the center of the agentic AI boom. AI agents are proliferating rapidly — and with them comes an explosion of

// State-Externalizing Harnesses // A new paradigm is emerging on how to effectively build agents and harnesses. If there is a state that the environment can maintain reliably, it probably doesn't bel

Demo3 showcases Qwen's browser agent capabilities, likely demonstrating an AI system's ability to autonomously interact with web browsers to perform tasks such as navigation, form filling, or informat

i know it's backwards order, but experiment #2: https://x.com/ActiveGraphAI/status/2061106299748909090?s=20 [New Technical Blog Post] In our second longmemeval experiment, we introduce semantic ingest

The Perplexity Agent API documentation includes a 'Search as Code' feature accessible through the sandbox tools section, enabling developers to integrate search functionality programmatically within a

[New Technical Blog Post] In our second longmemeval experiment, we introduce semantic ingestion into recall leveraging the ActiveGraph runtime. We started from a 60.6% baseline and improved to 83.4%/8