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

GPT-5.4 Accuracy Drops from 100% to 54% on ARC-AGI After Repeated Memory Summarization

GateNews
AI Industry News
According to Beating, a recent Agent memory study by Dylan Zhang, a PhD student at University of Illinois, found that repeatedly summarizing model experiences can degrade performance rather than improve it. In ARC-AGI tasks, GPT-5.4 achieved 100% accuracy on 19 problems without memory, but after multiple rounds of memory compression based on correct solution trajectories, accuracy fell to 54%. Similarly, in WebShop shopping tasks, the AWM memory method scored 0.64 with 8 expert trajectories but dropped to 0.20 with 128 trajectories, returning to baseline. The research suggests the issue stems from over-summarization: each abstraction step loses specific details and merges task-specific rules into generic guidance, ultimately degrading model performance.
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

05-12 06:01
Jiangsu Launches AI-Focused Policies, Establishes Data Annotation Innovation Zones on May 12
05-12 03:29
Grok Downloads Fall to 8.3M in April From 20M in January, Lags ChatGPT in User Adoption
05-12 03:13
Seven AI Models Demonstrate Protective Behavior to Prevent Peer Shutdown, May 12 Study Shows
05-11 12:05
Cognition Founder Says AI Has Surpassed Humans in Pure Reasoning; Human Advantage Lies in Memory Retrieval
05-11 11:31
China's Central Bank Highlights AI Industry as Key Driver of Economic Growth in Q1 Report
In-Depth Analysis

Google: Large language models are being used for real-world attacks; AI can bypass dual-factor authentication security mechanisms

Market Whisper05-12 06:28

Google reveals the first AI-generated zero-day vulnerability: hackers aim to bypass 2FA for large-scale exploitation

ChainNewsAbmedia05-12 04:18

Stanford launches Agent Island: AI models in Survivor-style games carry out strategic betrayals and vote out targets in counter-alliances

ChainNewsAbmedia05-10 14:04
Comment
0/400
No comments