k
keynews.ai
keynews.ai
FrontierThe story, in brief

Hermes Agent Adds Asynchronous Subagents, So Delegated Work No Longer Blocks the Parent Chat

Hermes Agent just shipped async subagents. Parent chats no longer block on delegated work—here's what changes for agents-as-capability.

Reporting by MarkTechPost 1 min brief
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

Nous Research's Hermes Agent adds asynchronous delegation, a critical capability for production agent systems. This architectural improvement matters because it enables non-blocking task parallelization—a prerequisite for enterprise deployment where parent workflows can't stall waiting for background tasks.

The key facts

12 to know

  1. Hermes Agent (Nous Research) adds asynchronous subagents feature

  2. Delegate tool now spawns background agents without blocking parent chat

  3. async_delegation toolset tracked in issue #5586

  4. Covers spawn, check, steer, and collect task operations

  5. Addresses subagent isolation and sync vs. async tradeoffs

  6. Published June 16, 2026

  7. Hermes Agent now supports asynchronous subagents via delegate tool

  8. Parent chat no longer blocks on delegated work

  9. New async_delegation toolset with spawn, check, steer, and collect task functions

  10. Subagent isolation architecture implemented

  11. Synchronous vs. asynchronous tradeoff analysis available

  12. Published June 16, 2026 by Nous Research (via MarkTechPost)

Go to the source

MarkTechPostmarktechpost.com

Publisher excerpt: We look at Hermes Agent's new asynchronous subagents from Nous Research. The delegate tool can now spawn background agents that no longer block the parent chat. We walk through the async_delegation toolset tracked in issue #5586, covering how to spawn, check, steer, and collect tasks. We also cover…
Read original report
Back to today's editionMore frontier news

The wider picture

View all
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier01

Alibaba Unveils Zhenwu V900 — and Plans Qwen Models With Up to 10 Trillion Parameters

Alibaba is advancing on two fronts simultaneously: announcing a custom AI accelerator (Zhenwu V900) and committing to massive model scale (10T parameters for future Qwen releases). For practitioners, this matters as a credible third-party capability play outside the US-China licensing squeeze; for enthusiasts, it's a significant lab-race signal about training compute and parameter scaling as competitive levers.

TechRepublic
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier02

Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning

A new capability frontier: models that reason directly in speech without transcription bottlenecks. This changes how we think about multimodal reasoning and what's possible with open-weight releases at scale.

MarkTechPost
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier03

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war

Frontier labs are shipping upgraded reasoning and multimodal models in rapid succession, signaling acceleration in the capability race. Simultaneous price cuts reshape AI economics for practitioners.

Simon Willison