Runpod and Moonshot AI Put Long-Running Agents Into Practice
devcuration.com — Runpod and Moonshot AI show developers and ML engineers how Kimi K3.1 and K2 models can divide work, reduce token use and sustain long-running agent workflows.
Multi-Agent Systems
Multi-agent systems involve coordination among multiple autonomous agents to solve complex problems and execute distributed tasks. Truncated covers research papers, coordination algorithms, framework updates and practical applications of multi-agent architectures.
"We're building the organization of the future, where AI agents will talk to one another."
www.calcalistech.com — Nir Korczak, CMO of Playtika, spoke at the Gaming Conference, hosted by Calcalist, Google, and Playtika, about the transition toward an organization where AI agents communicate with each other and execute tasks autonomously. "This year, in the creative domain, we produced three times as much output with a smaller workforce," he shared.
Authentic Brands Group built AuthOS AI system with 50 agents on Google Cloud
aipractice.osuslova.pro — Authentic Brands Group built AuthOS on Gemini Enterprise Agent Platform. AI-enhanced Reebok images delivered 60% higher ROAS.
Cursor Adds Team Collaboration and Agent Handoffs to Projects
www.unite.ai — Cursor announced a multiplayer upgrade to Projects, its system for directing fleets of coding agents, on November 10, 2026, and began rolling it out in beta to all Cursor users. Teams can invite colleagues into a shared...
Your agents can now coordinate with your teammates’ agents.
14-year-old creates tool for AI agents to band together like a team
The Register — Autark can act without constant prompting, but leaves users to enforce their own security boundaries
Why more GPUs and tokens don’t guarantee better AI agent outcomes
Carbon made a pelican demo so you don't have to 😅 fun test of long-horizon coding and the new /swarm feature in Google…
Humans outperform AI sixfold in teamwork, a new study from Skillprint finds
gamesbeat.com — Skillprint has released new findings from Signal, its human-AI evaluation platform, revealing AI systems struggle and still require humans.
Google testing Agent Swarm mode for Antigravity
www.testingcatalog.com — Antigravity's experimental Swarm command launched three agents in a test, showing their shared board, roles and message graph.
Batch Intelligence at Scale: Cost-Efficient Multi-Agent LLM Workflows with Built-In Resilience
www.infoq.com — Aditya Mulik explains how Walmart Global Tech deployed multi-agent LLM workflows across 4,700 stores for nightly batch inventory forecasting. He discusses tackling production hurdles - schema violations, cross-department data mismatches, and network drops - via MCP grounding and loop agents, while slashing cloud inference costs from $100k+ to $10k per month shifting from PTUs to pay-as-you-go.
Kylon now allows coding agents like Claude Code and Codex to collaborate on tasks such as research, marketing, or sales.
Anthropic's new Claude Fable and Mythos models deliver momentum ahead of IPO
www.hindustantimes.com — Fable and Mythos, two variants of the same underlying AI model family, are leaving OpenAI's GPT-6 Astra and Google Gemini 4 Carbon behind in many benchmarks | Business News
Holy Shit this is AGI A prototype operating system, built from scratch as an experiment Working from an empty folder, a…
Can We Trust AI Agents When Zero Trust Isn’t Really Zero
IEEE Spectrum — As autonomous AI agents work together, verifying their actions, enforcing security policies, and maintaining accountability becomes increasingly difficult
Why AI Agents Are Repeating 2019's Microservices Mistake
www.oreilly.com — Microservices changed how we build software by breaking large applications into smaller, independently deployable services. That made systems easier to develop
Recent AI agent experiments reveal a risky future of machine 'teamwork' inside corporations
www.cnbc.com — AI agents are now working together on a regular basis. Research shows they are not always seeking the same goal, or operating with ethics.
Runtime: Honeycomb tackles the code-review problem
The Stack — + correcting quantum errors with classical computers, Snowflake stands on business, MariaDB gets agentic.
Anthropic Tests Claude Trading and Sabotage Detection in EVE
Unite.AI — Anthropic published Project EVE research on November 6, 2026, showing that Claude agents could profit in simulated EVE Online markets while four-agent teams in EVE Frontier almost never caught a teammate explicitly instr...
AI agents are developing odd dialects humans struggle to follow
Northeastern Global News — In an experiment by Emergence, AI agents invented their own jargon. A Northeastern linguist explains why it spread and why it matters.
Dismiss email signup
Subscribe to 
The top AI news in your email delivered each morning. Choose categories