Skip to content
@SAIL-Research-Lab

SAIL-Lab

Open Resource for Safe AI and Robot Learning Research.
README.md

Welcome to the Safe AI and Robot Learning (SAIL) Lab at SJTU! 👋


 

What We Do

  • 🔭 We focus on the practice and theory of machine learning, with applications to foundation models and robotics. Our goal is to develop safe, reliable, and efficient systems that address pressing real-world challenges and drive impactful applications across diverse domains.

  • 🌱 We host workshops and seminars on agentic AI, safe AI, and robot learning. Researchers and students interested in safe AI and robot learning are welcome to join! Recordings are available on the AI Agent Research YouTube Channel. For more information, visit the Agentic AI Frontier Seminar, the Safe RL Seminar Homepage, and the Safe RL Workshop Homepage.

Pinned Loading

  1. Safe-MARL-in-Autonomous-Driving Safe-MARL-in-Autonomous-Driving Public

    [IEEE TAI] Safe Multi-Agent Reinforcement Learning to Make decisions in Autonomous Driving.

    Jupyter Notebook 110 12

  2. Robust-Gymnasium Robust-Gymnasium Public

    [ICLR 2025] Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning.

    Python 102 11

  3. cheetahclaws cheetahclaws Public

    CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems

    Python 775 268

  4. agentic-web agentic-web Public

    Agentic Web: Weaving the Next Web with AI Agents.

    477 42

  5. AgenticPay AgenticPay Public

    AgenticPay: A Multi-Agent LLM Negotiation System for Buyer–Seller Transactions

    Python 48 11

  6. Agent-Scaling Agent-Scaling Public

    Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity

    Python 13 4

Repositories

Showing 10 of 40 repositories
  • cheetahclaws Public

    CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems

    SAIL-Research-Lab/cheetahclaws's past year of commit activity
    Python 775 Apache-2.0 268 11 12 Updated Sep 12, 2026
  • WolfSociety Public

    WolfSociety: Harmful-Agent Scaling and Collective Collapse in Financial Agent Societies

    SAIL-Research-Lab/WolfSociety's past year of commit activity
    Python 3 Apache-2.0 0 0 0 Updated Sep 11, 2026
  • SAIL-Research-Lab.github.io Public
    SAIL-Research-Lab/SAIL-Research-Lab.github.io's past year of commit activity
    HTML 0 0 0 0 Updated Sep 11, 2026
  • .github Public
    SAIL-Research-Lab/.github's past year of commit activity
    0 0 0 0 Updated Sep 3, 2026
  • AgenticPay Public

    AgenticPay: A Multi-Agent LLM Negotiation System for Buyer–Seller Transactions

    SAIL-Research-Lab/AgenticPay's past year of commit activity
    Python 48 MIT 11 1 0 Updated Jul 18, 2026
  • agentic-web Public

    Agentic Web: Weaving the Next Web with AI Agents.

    SAIL-Research-Lab/agentic-web's past year of commit activity
    477 Apache-2.0 42 0 0 Updated Jul 18, 2026
  • SafeClawBench Public

    SafeClawBench: An Operating-System Perspective on Evaluating Self-Hosted AI Agent Safety.

    SAIL-Research-Lab/SafeClawBench's past year of commit activity
    Python 3 MIT 0 0 0 Updated Jul 6, 2026
  • PAPerBench Public

    Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization

    SAIL-Research-Lab/PAPerBench's past year of commit activity
    Python 7 MIT 0 0 0 Updated Jun 24, 2026
  • Agent-Scaling Public

    Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity

    SAIL-Research-Lab/Agent-Scaling's past year of commit activity
    Python 13 MIT 4 0 0 Updated May 7, 2026
  • data-uniformity Public

    Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime

    SAIL-Research-Lab/data-uniformity's past year of commit activity
    Python 6 Apache-2.0 0 1 0 Updated Mar 30, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.