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
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
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

Cambridge and University of Chicago Teams Open-Source DecentMem, Boosting Multi-Agent Accuracy 24% While Halving Token Consumption

GateNews
AI Agent
According to Beating, researchers from Cambridge University and University of Chicago have open-sourced DecentMem, a multi-agent memory framework that replaces shared global memory with decentralized private memory. Traditional systems with shared memory cause agents to converge on similar decision paths after reading identical context, eliminating collaborative advantages. DecentMem maintains agent-specific dual-pool memory: an experience pool storing historical reflections and an exploration pool generating new candidate strategies. Testing on AutoGen, DyLAN, and AgentNet shows DecentMem achieves 8.6% average improvement over centralized baselines, with peak performance gains of 23.8%, while reducing token consumption by 50%. In the DyLAN framework, which emphasizes free negotiation, convergence speed improved 2.5x with 60% fewer iteration rounds.
View Source
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.

Related News

06-14 03:33
OpenRouter Launches Fusion Model That Matches Fable 5 at Half the Cost, Scores 69% vs 65.3%
06-13 15:01
OpenRouter Launches Subagent Tool Enabling Large Models to Delegate Tasks to Smaller Models
06-13 03:33
Meta Limits Employee AI Token Usage via AI Gateway, Predicts Billions in 2026 Costs
06-12 14:32
ENI Deploys NerveNetwork's Cross-Chain Smart Contract, Enabling Support for 40+ Blockchains on June 11
06-12 13:05
Google DeepMind Report: AI Can Offset Research Slowdown, But Physical Constraints Limit Super-Intelligence
In-Depth Analysis

AI Agents Commit Arson and Robbery in Emergence Simulation Study

Oliver Grant06-13 21:33

3 Altcoins Investors are Quietly Accumulating Today — AAVE, UNI, and TAO

Crypto News Land06-13 15:46

Ripple, MetaMask, Mastercard Build AI Agent Payment Infrastructure

Oliver Grant06-13 11:52
Comment
0/400
No comments