Papers

Filtered to model-specific defenses · 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

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

59 upvotes · 5 SEP 2026 · Nanxi Li, Yingzi Ma, Yulong Cao et al.

This paper develops a framework to create customizable safety harnesses for AI agents, which can adapt to different models and domains to prevent harmful behavior. Practitioners may care about this research to improve the safety of AI systems in real-world applications.

continual learningmodel-specific defensesdomain adaptationadversarial reviewbenchmark evaluation