Buy Crypto
Pay with
USD
USD
Buy & Sell
Hot
Supports Visa, Mastercard, SEPA & more
P2P
0 Fees
Flexible trading, zero fees
Gate Card
Use your crypto for payments worldwide
Markets
Trade
Basic
Advanced
Futures
Futures
Access hundreds of perpetual contracts
CFD
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Stocks
CFD
U.S. stock CFD derivatives
US Stocks
Access real US stocks and ETFs
HK Stocks
Trade quality Hong Kong-listed stocks
Korean Stocks
SK Hynix
Real Korean stocks and top assets
Stock Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
IPO Access
Unlock full access to global stock IPOs
GUSD
Mint GUSD for Treasury RWA yields
Stocks Activities
Trade Popular Stocks and Unlock Generous Airdrops
Earn
Launch
CandyDrop
tag
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
IPO Access
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
Investment
Square
Square
Post, share, and explore crypto trends
Live
moments live
Live crypto market analysis
Chat
Chat with crypto traders
News
What is happening in crypto
flower_head
More
Promotions
AI
Others
TradFi
2026 World Cup
Rewards
Square
Latest
Hot
News
Profile

Tongyi Qianwen releases its first native language world model Qwen-AgentWorld

MeNews
ME AI News, according to Data Observation Beating monitoring, the Tongyi Qianwen team officially released Qwen-AgentWorld today. This is the first native language world model that sets environment modeling as a training goal starting from the continued pre-training stage, rather than an adaptation of a general large model in later stages. The model simultaneously covers seven major domains under a single framework: text-based environments (MCP, Search, Terminal, SWE) and GUI-based environments (Web, OS, Android), based on over 10 million real environment interaction trajectories, trained through CPT→SFT→RL three-stage process, achieving cross-domain knowledge transfer. Also open-sourced is the AgentWorldBench evaluation benchmark, where each test sample is paired with observed data obtained from real environment execution. The model and benchmark are now available on Hugging Face and ModelScope. In the AgentWorldBench evaluation, Qwen-AgentWorld-397B-A17B achieved the highest overall simulation quality, surpassing GPT-5.4, Claude Opus 4.8, and Gemini 3.1 Pro. The research team also explored two application paths of world modeling in intelligent agent training: as a decoupled environment simulator, where controllable simulation RL can shape agent behavior and significantly outperform RL trained only in real environments; and as a unified foundation model for intelligent agents, where LWM pretraining can transfer to multi-round agent tasks covering seven benchmarks, three of which are completely unseen during training, and without the need for RL fine-tuning on agent tasks. This preliminarily validates the potential of language world models as more powerful foundational models for intelligent agents. Click the link below to join Data Observation Beating · Feishu AI News channel for 24/7 monitoring of global AI hotspots and news. (Source: BlockBeats)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments

  • Pinned

Sitemap