15 Oct 2026 · 15 articles
Open models like GLM-5 and MiniMax M2.7 now match closed frontier models on core agent tasks — file operations, tool use, and instruction following — at a fraction of the cost and latency. Here's what our evals show and how to start using them in Deep Agents.
Summary published by LangChain Blog · 13 Oct 2026 · Read the original ↗
Where to start with agent evals, offline vs online evals, evaluator types, LLM judges, benchmarks with Harbor, multi-turn evals, and keeping costs down.
Summary published by LangChain Blog · 15 Oct 2026 · Read the original ↗
Long-running agents degrade as context piles up. Learn how offloading, summarization, skills, subagents, and memory keep your agent's context window focused.
Summary published by LangChain Blog · 14 Oct 2026 · Read the original ↗
Google DeepMind and Google Cloud are providing up to 200 top European scientific researchers with direct access to our frontier models, together with $3 million in compu…
Summary published by Google DeepMind · 14 Oct 2026 · Read the original ↗
Interesting piece from Anthropic describing why and how they built their own custom alternative to Git, based on the dramatic increase in rate of changes to their code after the past six months. In May 2026, Anthropic averaged around 2,500 code changes merged per day; as of September, we merged over 30,000 per day. They included a chart showing those changes. I had Claude modify their chart (…
Summary published by Simon Willison's Weblog · 13 Oct 2026 · Read the original ↗
Release: llm-gemini 0.35 I added support to llm-gemini for the new Gemini 4 Argon model, made available today via the Gemini API and for customers of their $100/month subscription plan. Here are the low, medium and high pelicans . As expected, they are all excellent: Gemini has a track record of producing great SVGs, and are the only lab where I know their staff have invested in SVG specifically…
Summary published by Simon Willison's Weblog · 13 Oct 2026 · Read the original ↗
Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way to deploy a model agnostic, open source agent harness in a production ready way.
Summary published by LangChain Blog · 13 Oct 2026 · Read the original ↗
Learn how Orange Business used LangChain and LangSmith to build Live Intelligence, a governed AI platform for agents, evals, observability, and production scale.
Summary published by LangChain Blog · 13 Oct 2026 · Read the original ↗
Learn how Deep Agents SDK manages context for long-running AI tasks through offloading, summarization, and filesystem abstraction to prevent context rot.
Summary published by LangChain Blog · 13 Oct 2026 · Read the original ↗
Built on Deep Agents and LangGraph, Open SWE provides the core architectural components for internal coding agents.
Summary published by LangChain Blog · 13 Oct 2026 · Read the original ↗
Use ScaleDown's constrained decoding models with LangChain and Deep Agents to summarize history, compress tool results, and extract data faster and cheaper.
Summary published by LangChain Blog · 13 Oct 2026 · Read the original ↗
Article URL: https://arxiv.org/abs/2610.13928 Comments URL: https://news.ycombinator.com/item?id=50065692 Points: 279 # Comments: 143
Summary published by Hacker News - Newest: "AI" · 13 Oct 2026 · Read the original ↗
Release: llm-meta-ai 0.2 Meta AI release Muse Wonder (and Muse Wonder Full), their new "most capable models". These look like they may be Meta's first Fable class models - Artificial Analysis scores Muse Wonder (Max) as equivalent to GPT-6.1 Sol. I updated my llm-meta-ai plugin for the new model. Here are pelicans for Muse Wonder for the six reasoning levels: minimal, low, medium, high, xhigh…
Summary published by Simon Willison's Weblog · 12 Oct 2026 · Read the original ↗
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe. Subscribe now New benchmark shows how AI models lack intuitive visual reasoning:…Humanity’s Sixth Sense highlights some shortcomings of current AI systems…AI startups Elorian and Scale AI have built
Summary published by Import AI · 12 Oct 2026 · Read the original ↗
MCP support now lives in langchain.mcp, built on FastMCP for the 2026-07-28 spec, with elicitation handled as a LangGraph interrupt and tool lists cached.
Summary published by LangChain Blog · 4 Sep 2026 · Read the original ↗