Longxu Dou

@LongxuDou

Researcher @TencentHunyuan | ex-@SeaAIL

longxudou.github.io

Joined February 2016

Replies Reposts Media

Pinned
Longxu Dou
@LongxuDou
Feb 19, 2025
🚀 Excited to share our technical report on the Southeast Asian multilingual model Sailor2 and its latest updates! Our 49-page report details Sailor2's development journey, including multilingual data cleaning, small model data mixture simulations, multi-stage continual
9
Longxu Dou
@LongxuDou
Jul 14
Grok 4.20 ranked last at 0.080. With Grok 4.5, it jumped to 0.505 — 13/46 tasks, from last to first on the long-duration agent track. Huge progress from the xAI team. Still plenty of headroom: 29 of 46 tasks remain unsolved by any model.
Yucheng Shi
@Yucheng__Shi
Jul 13
Most agent benchmarks end in minutes. Real terminal work doesn’t. We’re introducing Long-Horizon Terminal-Bench (LHTB), a benchmark designed to measure whether AI agents can sustain progress across hundreds of dependent actions, not just start a task and solve the easy first
00:00
Longxu Dou
@LongxuDou
Jul 12
Jason Zhu
00:00
Jason Zhu
Longxu Dou
@LongxuDou
Dec 17, 2025
🚀We propose Reptile, a Terminal Agent🤖️that enables interaction with an LLM agent directly in your terminal. The agent can execute any command or custom CLI tool to accomplish tasks, and users can define their own tools and commands for the agent to utilize. ✨What Makes
4
Longxu Dou
@LongxuDou
Aug 9, 2025
🚀 Diffusion Language Models are super Data Learners!
Jinjie Ni
@NiJinjie
Aug 9, 2025
Token crisis: solved. ✅ We pre-trained diffusion language models (DLMs) vs. autoregressive (AR) models from scratch — up to 8B params, 480B tokens, 480 epochs. Findings: > DLMs beat AR when tokens are limited, with >3× data potential. > A 1B DLM trained on just 1B tokens