8000 sc2musa (Weiyu Ma (马纬彧)) · GitHub
[go: up one dir, main page]

Skip to content
View sc2musa's full-sized avatar
  • UCAS
  • Beijing ,China
  • X @meisah111

Block or report sc2musa

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sc2musa/README.md

Weiyu Ma · 马纬彧

Agentic RL · Game AI · World Model
Former StarCraft II pro (KR Grandmaster) turned AI researcher

Homepage Google Scholar Email

Tip

Open to work — looking for research or engineering roles in Agentic RL, LLM/VLM agents and game AI. Reach me at sc2meisah@gmail.com.

正在求职:Agentic RL、LLM/VLM Agent 与游戏 AI 方向的研究 / 算法岗位,欢迎邮件联系。

My research asks how AI can perceive, decide and keep learning from interaction the way people do. I use games and multi-step agent tasks as testbeds for LLM/VLM agents, Agentic RL, world models and multi-agent decision-making.

Selected work

Work What it is Venue Links
⭐ LLM Play SC2 (TextStarCraft II) The world's first work to put LLMs in charge of real-time decision-making in a complex environment — pioneering LLM research on complex real-time decision-making, with StarCraft II as the benchmark. 10+ LLMs benchmarked; >50% win rate vs. Harder (Lv5) AI NeurIPS 2024 Paper · Code
AVA The world's first VLM-based multi-agent system for complex real-time decision-making — VLM micro from raw frames; CCF-A ACL 2026 Findings Paper · Code
EvoCurr The world's first recursive self-improvement (RSI) in complex decision-making — 72 h unattended self-evolution; 100% win rate with 100+ units, beyond human Grandmasters EMNLP 2026 Findings Paper · Code
LLM-SMAC The world's first Agentic RL in complex multi-agent decision-making (StarCraft II) — far deeper multi-turn interaction than Search-R1-style tool use; 7B model beats DeepSeek-V3 AAMAS 2026 Paper · Code
FreshPER The world's first general replay-buffer framework for LLM post-training — NQ Search +20 pts, Sokoban +39 pts, MathVista +15 pts (absolute) Under review Paper · Code
JEV-Star SOTA for direct LLM control of StarCraft II — 9/10 real-time wins vs. Lv7, the strongest non-cheating AI Preprint 2026 Paper · Code
eSports World Model Dataset The world's first open-source, multi-game dataset for long-horizon, multi-agent world modeling in eSports — complete matches with synchronized per-player views (SC2 / Dota 2 / CS2) Released 2026.10 Dataset · Code

More papers, projects and demos → weiyu.page


中文简介

我关注一个核心问题:如何让 AI 像人一样感知、决策,并从交互中持续学习。我以游戏和多步智能体任务为试验场,研究 LLM/VLM Agent、Agentic RL、World Model 与多智能体决策。本科期间是星际争霸 II 职业选手(韩服宗师)。

代表作

  • ⭐ LLM Play SC2(TextStarCraft II,NeurIPS 2024,引用 170+):全球首个将大模型用于复杂场景实时决策的工作,开创了以星际争霸 II 为标杆的大模型复杂实时决策方向;系统评测 10+ 主流大模型,对战困难(Lv5)AI 胜率 >50%
  • AVA(ACL 2026 Findings):全球首个基于 VLM 的多智能体复杂实时决策系统,CCF-A
  • EvoCurr(EMNLP 2026 Findings):全球首个在复杂决策场景实现递归自我改进(RSI)的工作,无人干预自主进化 72 小时,百余单位协同 100% 胜率、超越人类宗师
  • LLM-SMAC(AAMAS 2026):全球首个在星际争霸 II 这类复杂多智能体决策场景下的 Agentic RL 工作,多轮交互深度远超 Search-R1 类工作,7B 模型超越 DeepSeek-V3
  • FreshPER:全球首个通用的大模型后训练经验回放(Replay Buffer)框架,NQ Search、Sokoban、MathVista 分别提升 20、39、15 个百分点
  • JEV-Star:大模型直接决策在星际争霸 II 上的 SOTA,实时对战最高非作弊难度 Lv7 AI 10 局 9 胜
  • 电子竞技世界模型数据集:全球首个开源的多游戏、长时程、多智能体电竞世界模型数据集,以完整对局为单位提供逐玩家同步视角

完整论文、项目与演示视频见个人主页:weiyu.page

Popular repositories Loading

  1. Large-Language-Models-play-StarCraftII Large-Language-Models-play-StarCraftII Public

    TextStarCraft2,a pure language env which support llms play starcraft2

    Python 392 28

  2. Jev_Star Jev_Star Public

    Python 55 10

  3. esports-worldmodel-datasets esports-worldmodel-datasets Public

    5

  4. Search_r1_multinode Search_r1_multinode Public

    Multinode reimplement for search-r1

    Python 4 1

  5. sc2ai-project sc2ai-project Public

    this a simple project for sc2 ai

    Python 3

  6. Python-100-Days Python-100-Days Public

    Forked from jackfrued/Python-100-Days

    Python - 100天从新手到大师

    Jupyter Notebook 2 1

0