How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs

arXiv:2610.02557v1 Announce Type: new Abstract: As powerful AI systems reach and sometimes surpass the abilities of human experts across a range of cognitively demanding tasks,

arXiv:2609.29189v1 Announce Type: new Abstract: Scalable oversight aims to verify the behaviour of agents whose capabilities exceed those of their overseers. AI debate has been

arXiv:2608.19002v1 Announce Type: new Abstract: Debates have recently emerged as a useful methodology for agentic AI to improve performance as well as to aid explainability and

arXiv:2605.12963v1 Announce Type: new Abstract: As AI systems become increasingly capable, safety strategies must be evaluated not only by how much they reduce present risk, but

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical

arXiv:2603.25747v1 Announce Type: new Abstract: The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their

arXiv:2604.22117v1 Announce Type: cross Abstract: Aligned large language models(LLMs) remain vulnerable to adversarial manipulation, and their dependence on web-scale pretraining

arXiv:2606.20068v1 Announce Type: new Abstract: While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic