Papers

Filtered to black-box policy · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

252 upvotes · 1 AUG 2026 · Yunhao Chen, Xin Wang, Yixu Wang et al.

This paper introduces OpenART, a platform for testing AI agents in open-ended environments, to evaluate their safety in complex and evolving scenarios. Practitioners can use OpenART to identify potential risks and improve the robustness of their AI systems.

agent red teamingcontinual learningopen-ended environment evolutionstateful scenariosblack-box policyevolutionary Markov hypergraph attack