Gate News message, April 27 — Alibaba’s PAI team has released and open-sourced AgenticQwen, a small-scale agentic language model designed for industrial-grade tool-calling applications. The model comes in two versions: 8B and 30B-A3B. Trained through an innovative “dual data flywheel” reinforcement learning framework, AgenticQwen achieves near-trillion-parameter model-level agentic capabilities while significantly reducing inference costs.
The dual data flywheel mechanism addresses the homogenization problem in traditional synthetic data. The reasoning flywheel automatically generates harder variants from model errors, while the agentic flywheel expands simple linear workflows (such as single booking processes) into multi-branch behavior trees with constraints, rejections, and adversarial conditions, simulating real-world complex decision scenarios. Benchmarks show AgenticQwen-8B scored 47.4 on real tool environment benchmarks (TAU-2 and BFCL-V4), far exceeding the base Qwen3-8B (23.8) and approaching Qwen3-235B (52.0). AgenticQwen-30B-A3B (with only 3B parameters activated) achieved 50.2.
The model has been deployed in internal production systems similar to Manus, significantly narrowing the gap with 235B models in end-to-end inference time. However, the model is limited by a native context length of 40K tokens, which constrains its performance on deep search tasks.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
Related Articles
Alphea Launches AI-Native Layer 1 Blockchain with Autonomous Agent Execution
Gate News message, April 27 — Alphea, a newly unveiled Layer 1 blockchain platform designed for AI infrastructure, officially presented its decentralized execution environment at Hong Kong Web3 Festival 2026. The platform integrates execution, persistent memory, and verifiable computation as
GateNews32m ago
Gate to Host AI Trading Space Roundtable on April 28: Exploring AI as the Next Web3 Cycle Driver
Gate News message, April 27 — Gate will host a live Space roundtable discussion on AI Trading on April 28 at 8 p.m., bringing together industry experts to explore whether AI's deep integration into trading workflows marks the true starting point of the next Web3 cycle.
The discussion will examine A
GateNews4h ago
Ant Group Launches Ling-2.6-1T: Trillion-Parameter Model Optimized for Token-Efficient Task Execution
Gate News message, April 27 — Ant Group's inclusionAI has released Ling-2.6-1T, a new trillion-parameter flagship instruction model in the Ling series. Unlike long-chain reasoning models, Ling-2.6-1T employs a "Fast-Thinking" mechanism designed for precise task execution with minimal token
GateNews4h ago
Nansen API Now Supports Tempo's MPP Protocol, Enabling AI Agents to Pay Per Call
Gate News message, April 27 — Nansen API now supports the Machine Payments Protocol (MPP), a standard for autonomous machine-to-machine payments backed by Tempo and Stripe. The integration allows AI agents to pay directly from their wallets on a per-call basis.
The feature operates alongside
GateNews5h ago
OpenAI's Greg Brockman: AI Shifting from Chat to Autonomous Task Execution
Gate News message, April 27 — Greg Brockman, president and co-founder of OpenAI, says the next wave of artificial intelligence will move users from chatting with AI bots to assigning real-world tasks. This shift requires enterprises to rethink operational workflows and establish new protocols for se
GateNews6h ago
Major CEX Launches Smart Money Signal Suite with 1,000+ Trader Data
Gate News message, April 27 — A major centralized exchange has launched a "Smart Money Signal Suite" that integrates real-time holdings, win rates, and profit/loss data from over 1,000 popular traders. The toolkit, accessible through the platform's Agent Trade Kit, encapsulates trader signals as
GateNews6h ago
