Search: “persistence”

If you build agent skills in production, check out this great paper from Alibaba. You can think of a production agent skill as a directory. The root loads on activation, and references, schemas, scrip

Impressive work from Alibaba. (bookmark it) If you build long-running agents and keep rewriting your memory schema, take a look at this approach. It basically treats agent context management as a prog

We will continue to offer Zero Data Retention for frontier models. As AI takes on longer, more autonomous work and delivers greater value to businesses, safety systems also need to identify risks acro

As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for

Its interesting to see the experiments on how to give AI a computer: Codex & Claude Code use your local machine, ChatGPT Work on the web (as well as Claude and ChatGPT) give the AI a one-time machine

Recommended paper for agent skill builders. There are 56,804 public agent skills today, all competing for fewer than 100 reliable trigger slots in the system prompt. Your own playbooks compete for tha

This is part of working with the EU AI Act, other labs are adding similar watermarking. It’s hard to identify AI-generated text, and this gives people better tools to do that. We’ll also be a shipping

ChatGPT Work is OpenAI's fighter in the highest stake product category in history: bringing the power of coding agents to the masses. It's also how a billion users will soon use ChatGPT by default. I

'OCR is just a feature now. Frontier models will eat it.' We hear this constantly. The data says otherwise. Across three GPT generations, parsing accuracy gained ~24 points, while cost per page 4x'd.

one of the top cybersecurity models, post-trained from open weights by @depthfirstlabs on @FireworksAI_HQ long-horizon RL is as much an infra problem as a research one: 100+ turn rollouts, async/pipel

i'll say it plainly, hermes agent desktop is the best agentic app i've used, and i'm a little mad i didn't find it sooner. it auto see the models i'm serving, laguna s 2.1 sitting on my dgx spark and

The openai agent sandbox escape actually has very real implications for the diffusion of AI in the enterprise. The incident showed the power and capability of agents, and the need to harden systems an

New research from Meta and CMU. This one is on agentic context management for long horizon tasks. (bookmark it) Production agents accumulate context every turn. The usual fix compresses on a token thr

the paper: babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems' https://

Today we’re releasing Poolside Laguna S 2.1 It is a 118B-total, 8B-active open-weight model built for agentic coding and long-horizon work, with context up to 1M tokens https://poolside.ai/blog/introd

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

1/ I watched LangChain’s webinar on LLM wikis and agent memory and wrote up a working paper from my own small agent-fleet experiments: Soft-Cache: A Human-Supervisable Coherence Protocol for Persisten

Claude Code on desktop now has an in-app browser. Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers. It's s

'Ghost memory' is a real problem with agents. You might have seen the issue where a long-running agent still confidently repeats a user fact that stopped being true weeks ago? New research names the f

LiteParse runs anywhere, including inside agent runtimes. To prove it, we built an email processing assistant using @flueai (the agentic framework by @astrodotbuild), @resend webhooks, and @tursodatab

// Neural procedural memory // Good paper on agent memory beyond prompt retrieval. NPM stores procedural skills as activation steering vectors distilled from contrastive historical experience. Textual

Project gallery and whitepaper: https://research.nvidia.com/labs/gear/aspire/ ASPIRE is a great collaboration between NVIDIA GEAR lab, UMich, Berkeley, and CMU. Kudos to all the coauthors who pour the

Agents are easy to demo locally. The hard part is shipping them inside a real app. We published a deployment cookbook for @LangChain agents: full-stack examples with streaming UI, subagents, thread hi

deployment cookbook for langchain agents! Agents are easy to demo locally. The hard part is shipping them inside a real app. We published a deployment cookbook for @LangChain agents: full-stack exampl

This is a new paradigm for interacting with Claude that is significantly more 'inline' with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this '

context engineering docs for agentic engineering - plans, research, etc SHOULD NOT be stored in version control: A good docs management system keeps them: > outside your repo > accesible to agent via

Great report on LLM agent communication protocols. Communication is a huge bottleneck in multi-agent systems. (worth bookmarking) The report builds a five-dimensional taxonomy (counterparty, payload,

paper #1 for context: https://x.com/yoheinakajima/status/2057812713045377055?s=20 babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-So

This is exactly right. People are starting to look for cheaper model alternatives and realizing two things at once: open-source models are already very good, and the ability to train and serve them ef

Gary Marcus comments on AI systems that exhibit scam-like or deceptive behaviors while remaining too commercially important or integrated to face meaningful consequences. The post likely critiques how

Sometimes you need to start over. But that decision is hard. @llama_index had to make that call: they built one of the most popular AI frameworks in the world, but saw the agent harness and frontier l

Teach an agent a workflow once. Have it remember after every rebuild. This tutorial shows how to deploy @nousresearch Hermes Agent with NVIDIA NemoClaw and OpenShell, connect it to Slack, Outlook, Git

all agents in the future are going to need to write and execute code LangSmith Sandboxes are GA - try them out today https://docs.langchain.com/langsmith/sandboxes .@MukilLoganathan’s Interrupt keynot

This post likely argues that an individual's upbringing and early life experiences function similarly to a system prompt for an AI model—shaping foundational values, behaviors, and responses that infl

okay i think this is a much better visualization of what i mean by 'log-centric agent architecture' babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is t

Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu

This post likely announces or discusses an open-source AI agent framework that incorporates memory and continual learning capabilities, enabling the system to retain information across interactions an

// Language Models Need Sleep // Let your agents 'sleep', folks. On a serious note, this is a fascinating paper on getting the most from long-horizon agents. Here is the problem with agents today: Att

Star Citizen, an ambitious space simulation game in development by Cloud Imperium Games, has reached $1 billion in crowdfunding, making it one of the most funded projects ever. The milestone reflects

Active Graph is the best, most 'correct' knowledge/context engine I've come across so far (and I've tried or at least researched most of them.) babyagi has ~200 citations, but 0 papers... i just publi

Elon Musk posted a motivational message emphasizing perseverance and determination, likely encouraging people not to surrender in the face of challenges or setbacks. The post reflects Musk's known phi

babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems' https://arxiv.org/a

Highlights: 👉 Long-horizon autonomy: maintained coherent execution across a 35-hour autonomous kernel optimization run 👉 Agentic coding: leading Terminal-Bench 2.0-Terminus performance for terminal-ba

Replit Agent can automatically add authentication features to web applications with a single prompt, solving the common problem of apps losing user sessions. This tool helps developers quickly impleme

recommended reading. babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems

Gary Marcus discusses the current state of large language models (LLMs), likely covering their capabilities, limitations, and practical applications in AI. The post probably addresses key challenges s