Qwen Code Adds Agent Team for Multi-Agent Coding Workflows
The June 18 Qwen Code weekly update introduces experimental Agent Team collaboration, durable /loop tasks and in-session /cd workspace switching.
Key takeaways
Qwen Code's June 18, 2026 weekly update says four official versions, v0.18.0 to v0.18.3, were released that week with more than 100 PRs merged. The main update is Agent Team, an experimental opt-in feature for multi-agent collaboration inside coding workflows.
Qwen Code published a weekly update on June 18, 2026, saying it released v0.18.0 to v0.18.3 during the week and merged more than 100 PRs. Key updates include Agent Team, durable /loop tasks, and an in-session /cd command.
Agent Team is experimental and opt-in. When enabled, the model can create named teams, spawn long-lived teammates, exchange messages, share task lists and consolidate a final report through a leader. This moves coding agents closer to structured team workflows rather than isolated one-shot subagents.
For ENHE users, the practical takeaway is to evaluate AI coding tools by workflow orchestration, permission handling, context recovery, logging and result consolidation, not only by model quality or code completion speed.
What this means for everyday users
The update shows AI coding tools moving toward multi-agent orchestration. Teams should review task persistence, project permissions, audit trails, API key handling and local deployment boundaries before adopting agentic coding workflows.
Tools you may use
Your AI account needs, covered. Contact customer service if you need assistance.
Value:Your AI account needs
AI Voice Generator — Flexible Edition
Value:AI Voice Generator — Flexible Edition is an AI software app in ai audio tool
AI Video Studio Omnipotent Edition | Local AI Video Workstation | Text-to-Video, Image-to-Video, Video Enhancement
Value:AI Video Studio Omnipotent Edition | Local AI Video Workstation | Text-to-Video
Related tutorials
Related reading
OpenAI Adds Spend Controls and Usage Analytics to ChatGPT Enterprise
OpenAI has added spend controls and enhanced usage analytics for ChatGPT Enterprise, according to Computerworld's June 19, 2026 report. The update helps administrators monitor adoption, track usage across teams, and understand ChatGPT and Codex credit consumption by user, product, and model.
AgentScope Java 2.0 brings enterprise AI agents closer to production deployment
AgentScope Java 2.0 is presented as an open-source framework for enterprise-grade AI agents. The update focuses on production deployment concerns such as state recovery, multi-tenant isolation, workspaces, event streams, permission controls and Java ecosystem integration.
HPE and NVIDIA Expand Private Cloud AI for Production AI Agents
HPE announced new HPE Private Cloud AI and AI Factory capabilities with NVIDIA on June 16, 2026. The updates target production AI agents with secure local agent registration, NVIDIA Agent Toolkit, Nemotron models, OpenShell runtime, Zerto rollback capabilities, data pipelines and confidential computing.
AWS Expands Bedrock AgentCore as Agent Knowledge Retrieval Becomes Managed Infrastructure
AWS announced several Amazon Bedrock AgentCore updates at AWS Summit New York on June 17, 2026. The releases include Managed Knowledge Base, Web Search on AgentCore, AgentCore harness general availability, policy integrations and optimization capabilities, showing that production AI agents are becoming managed infrastructure around knowledge, execution and governance.
PaddleOCR 3.7.0 brings document AI closer to local deployment workflows
PaddleOCR v3.7.0 was released on GitHub on June 11, 2026, while PaddleOCR-VL-1.6 is available on Hugging Face with document parsing, layout, table, formula and chart tags. For ENHE users, the practical angle is local document processing for RAG, knowledge bases and AI agent workflows.
Databricks launches Genie One as enterprise AI agents move into business workflows
Databricks announced Genie One on June 16, 2026. The product is positioned as an agentic coworker for business teams and is built around Genie Ontology, reusable Genie Agents and governed enterprise data.
Summary
Qwen Code's Agent Team feature is a practical signal that coding agents are becoming workflow systems. Its value depends on controlled task splitting, shared context, permission handling and final result consolidation.