Search: “retrieval”

When you want to move from single agent SQLite on something like QMD, PostgreSQL is a great choice for multi agent and production quality, but not as snappy. So we made it much more snappy with BM25 &

$NBIS announced a partnership with LangChain to integrate Nebius Token Factory with LangChain’s Deep Agents. The goal is to make it easier for teams building AI agents on LangChain to run those worklo

toodles from mickey mouse clubhouse was weirdly ahead of its time wake phrase: mickey mouse clubhouse launched in 2006, and “oh toodles” trained toddlers on the assistant wake phrase years before siri

LangChain announced a partnership with Pinecone, a vector database platform, to integrate vector search capabilities with LangChain's framework for building applications with large language models. Th

Describe Seattle: I want to live near the sea and I want to live near the forest and I want to live near the mountains and I want to live near a café and I want to live near a library and I want to li

Here is a very common problem when building complex agents. Long-horizon agents (in particular) fail in two ways: the decision-maker can't decompose well, or the skill library goes stale. This new res

a bunch here where I’m saying ok Garry’s kinda right?! 👀…in some ways :) we’re making this loop much easier to close out of the box soon If more people get into evals & traces to ground self-improving

LiteParse: our open-source, layout-aware PDF parser for AI agents. The secret? Grid projection. Instead of heavy ML layout models or flat text extraction, it projects text onto a monospace grid so ali

One of the most jarring things about current AI is its lack of introspection ability and metacognition. It doesn't know what it doesn't know, how it knows, or how it could find out. It's a one-way sys

And yes, Lush/SN used a homegrown Lisp interpreter, to which a compiler was added in the early 1990s. @TradeTexasBig Oh, it wasn't even CL, it was its own language! https://lush.sourceforge.net/lush-m

in 1996 mitzenmacher showed that sampling two backends and picking the better one drops max load exponentially vs. random selection one extra comparison. that's the whole trick we built pinecone assis

ARC-AGI-3 is a new benchmark iteration designed so that any intelligent human applying genuine effort should achieve greater than 90% accuracy, maintaining the benchmark's core principle that tasks mu

Francois Chollet makes the observation that achieving a perfect score on certain AI benchmark games or tasks only requires surpassing the median performance of an unfiltered random population sample,

here’s a good application of harness permissions Programmatically Enforced Auto-Research: - auto-research loops usually expose a set of files that the agent is allowed to edit to hill climb a metric/e

In order to make sure ARC-AGI-3 games were solvable by humans we tested over 450 people If a game was too hard we either revised it or tossed it completely For maximum transparency we just open source

one problem with today’s markets is that even in an age of abundant information, distribution systems still concentrate attention and amplify consensus, turning price discovery into a coordinated resp

Each workflow in Thoth is a full LangGraph agent which can call subagents which themselves are LangGraph agents. Just describe what you want in plain English and it builds a full multi-step pipeline.

I just love the language of this study...it speaks of the shifting 'community language'...and that is so true...have you noticed the new 'community language' is 'harness', it was 'contextual prompting

I was unable to access the specific tweet at the provided URL (https://x.com/mayvencraft/status/2042362400146354295), and the web search did not return any results directly related to it. The accou...

NEW paper from Microsoft Every agent benchmark has the same hidden problem: how do you know the agent actually succeeded? Microsoft researchers introduce the Universal Verifier, which discusses lesson

Great paper on improving memory for AI agents. NEW paper: Memory Intelligence Agent (MIA) MIA boosts GPT-5.4 by up to 9% on LiveVQA. Quick summary: Most memory-augmented agents treat memory as a stati

Visually rich documents are especially challenging for agents. Tables, charts, and images often break traditional document pipelines, making complex reasoning difficult📄 So we teamed up with @lancedb

The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery Blog: https://pub.sakana.ai/agentic-scientist/ GitHub: https://github.com/SakanaAI/AI-Scientist-v3 arXiv: htt

Brilliant paper on agentic continual learning from Meta and MIT. (bookmark it) Agent memory harnesses usually only write forward. A lesson goes into the bank and is never checked against whether it he

wait so this feels a bit different too in a good way You already gave the LLM the answer. So why is it writing it out from scratch? Introducing a new AI model architecture: Constrained Decoding Models

Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap

Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transforme

Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu

People are underestimating the impact of ultrafast AI on business. Lemme ramble on this for a second. People are using Ultrafast for impressive game development and crazy fast coding, but business use

thank god for embed5. somehow Cohere is really good at not looking at your data while being the best at indexing it The Cohere Embeddings team has been cooking 🍳 Several key innovations in the model:

Banger report on building faster memory for AI Agents. If your agent's memory layer is slow, this design is worth a look. Great weekend read. It proposes a new agentic memory architecture, Jev-Mem, in

Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with LLM Wikis. Wikis are useful for agents because each page holds dense text and the

Natural language can act as an in-context control surface that streams rich, constrained UI and links users into deeper web views.

“Just-in-Time” OCR The latest agent harnesses (e.g. Cowork, Codex, Grok) do 2 passes of ad-hoc document processing when executing over a user-uploaded ‘data room’ of documents: 1️⃣ A fast and light pa

Interesting paper from Microsoft. If you run persistent memory for a production agent, this one is worth your time. (bookmark it) Memory curators usually read only the finished trajectory. That lets t

Nice paper to improve inference efficiency. It's been a while we haven't seen good work on efficiency. Here is why it matters: A long-running agent's workspace outgrows its context window long before

This work introduces diffusion-augmented LLMs, a new class of models. They first suggest that speculative decoding needs a separate draft model. Diffusion LLMs give up the quality of the model they re

Independent verifiers improve agent output - but frontier verifiers are expensive. So we trained our own. Results on @GoogleDeepMind's FACTS-Search: > No verifier: 89.4 (previously published SOTA) > W

There’s generally a massive difference in quality between specialized OCR providers, “simple” open-weight OCR models, and free/OSS solutions. 1️⃣ Specialized OCR models (including LlamaParse) solve fo

you can now build @LangChain agents w/ agentic video understanding! google is consistently at the forefront of multimodal processing; this is the video analog of 'agentic vision' token usage + cost is

My conversation with @jerryjliu0. He's building @llama_index: document infrastructure for AI agents, the layer underneath everything models need to work. Did you know he's the guy whose tool half the

Thanks @juliafedorin for a great conversation! Some tidbits from the podcast on the AI space: - We've pivoted from building a RAG framework towards building the document infrastructure for agents - Do

static embeddings are extremely fast/cheap compared to dense embeddings, and still quite powerful. one issue is that they lose accuracy over longer text, since the tokens get pooled and averaged late

// Automata from agent traces // How much of your agent's behavior comes from the model, and how much from the harness you wrapped around it? New work collapses an entire corpus of agent traces into a

Important read if you build with agent skills. Shared skill libraries are treated as a safe way for coding agents to reuse each other's work. New research shows they propagate malware. EvoMal plants a

The hottest neolabs are the application layer, who serve as an intermediary layer providing their customers the best intelligence per token per task/workflow across different underlying model provider