Tencent's T1 Team Specializes in Agent Long Tasks: Over 300 Consecutive Operation Rounds, Benchmark Score Rises by 20 Points
46 minutes ago
Beating AI Express News: Tencent has dedicated its Qwen3.5-122B-A10B model to training a terminal agent, resulting in T1. The agent is designed to handle complex tasks in Linux terminals, with each task capable of calling tools consecutively for over 300 rounds at maximum. Its score on Terminal-Bench 2.1 rose from 43.8% for the base model to 64.0%, an increase of 20.2 percentage points. The bulk of this gain came from reinforcement learning: SFT alone lifted the score to 49.4%, while subsequent reinforcement learning added another 14.6 points. The team prepared around 15,000 terminal tasks, each paired with an automated test. Even if the agent does not complete the entire task, it can earn corresponding rewards for meeting partial requirements. Long tasks present another challenge: when the agent performs actual work and later uses that experience for training, the same content may be re-split into different tokens, and the Mixture of Experts (MoE) may switch to a different set of experts. T1 records both the tokens generated at the time and the selected experts, and replicates these during training, reducing this training-inference gap by approximately one-third.
Nvidia adds an enhancement to Pi: AI agents independently identified four optimizations, cutting token usage by up to 64%.
5 minutes ago
Standard Chartered bullish on SKY: Target price of $0.325 by end-2028, with 5x upside potential from current levels.
5 minutes ago
Driven by the rapid development of Robinhood Chain, research and investment institutions have raised Robinhood’s stock price target to $165.
5 minutes ago
More Uncertainty Over Interest Rate Hikes? Majority of Economists in Bloomberg Survey Expect Fed to Skip Rate Hikes This Year
5 minutes ago
The community of STARLINK, a meme coin in the X Layer ecosystem, has opened a donation-based charity fund to deploy network services to disaster-hit areas and network deserts.
5 minutes ago
4D Labs, a real-world embodied data layer protocol for physical AI, secures investment from YZi Labs.
5 minutes ago
Hot feeds
A trader profits $448K by monitoring #Binance's new listings!
2024.12.13 17:37:29
Last week, funds have flowed into #Bitcoin, #Ethereum, and #Hyperliquid.
2024.12.16 14:48:36
A $PEPE whale that had been dormant for 600 days transferred all 2.1T $PEPE($52M) to a new address.
2024.12.14 10:35:27
When Elon Musk tweeted about Moltbook, the meme coin MOLT experienced a short-term 30% price surge, hitting a new all-time high of $114 million.
2026.01.31 18:37:29
A smart #AI coin trader made $17.6M on $GOAT, $ai16z, $Fartcoin,$arc.
2025.01.05 16:05:18
A sniper earned 2,277 $ETH ($8.3M) trading $SHIRO within 18 hours!
2024.12.03 23:09:08
MoreHot Articles

How did I turn $1,000 into $30,000 with smart money?
2024.12.09

10 promising AI Agent cryptos
2024.12.05

The 30-Year-Old Entrepreneur Behind Virtual, a Multi-Million Dollar AI Agent Society
2025.01.22

10 smart traders specializing in MEMEcoin trading on Solana
2024.12.09

A trader lost $73.9K trading memecoins in just 3 minutes — a lesson for us all!
2024.12.13

What is $SPORE? Let us take you through the on-chain records to show you how it works.
2024.12.25

