Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking

arXiv:2608.20820v1 Announce Type: new Abstract: Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context.

arXiv:2607.20472v1 Announce Type: new Abstract: When a user asks a language model something harmful, is it a genuine attack or a misunderstood but well-meaning question? This

arXiv:2605.01327v1 Announce Type: new Abstract: Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of

arXiv:2604.22748v1 Announce Type: new Abstract: As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment

arXiv:2605.19447v1 Announce Type: new Abstract: Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a