arxiv
PublishedNovember 18, 2026 at 5:00 AM
From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
Publisher summary· verbatim
arXiv:2511.19218v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly power web-facing applications, including conversational assistants and content services, where open user interaction exposes them to diverse safety threats and adaptive attacks. In particular, jailbre
Stay posted· Newsletter
Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.
Your email is used only to send The Bubble Brief. Privacy policy
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivGradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees3harxivLimite 1B - Violetto: Technical Report3harxivMedGuardBench: A Patient-Oriented Benchmark for Personalized Guardrail Development3harxivCan You Undo It? Reversibility Classes for AI Agent Actions3hThe Bubble Brief
MON · WED · FRIRead AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.
Your email is used only to send The Bubble Brief. Privacy policy
Originally published on arxiv ↗