SAIL-Research-Lab
Open Resource for Safe AI and Robot Learning Research.
Built from SAIL-Research-Lab's public GitHub profile, United States of America. Not on Take My Repo yet, so there are no posts or updates here.
[IEEE TAI] Safe Multi-Agent Reinforcement Learning to Make decisions in Autonomous Driving.
[ICLR 2025] Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning.
[NeurIPS 2026]AgenticPay: A Multi-Agent LLM Negotiation System for Buyer–Seller Transactions
Benchmarking of Neural Network Architectures in Reinforcement Learning.
The repository is for Reinforcement-Learning Uncertainty research, in which we investigate various uncertain factors in RL.
[IEEE TPAMI] A Framework for Constrained Multi-Objective Reinforcement Learning
Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization
Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime
[TMLR] TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning.
AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
WolfSociety: Harmful-Agent Scaling and Collective Collapse in Financial Agent Societies
SafeClawBench: An Operating-System Perspective on Evaluating Self-Hosted AI Agent Safety.