arXiv Artificial IntelligenceA decodability criterion predicts when hidden-state selection beats majority voting in large language models
arXiv:2608.17124v1 Announce Type: new Abstract: Combining the answers a large language model (LLM) samples…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2608.17124v1 Announce Type: new Abstract: Combining the answers a large language model (LLM) samples…
arXiv Artificial IntelligencearXiv:2608.17067v1 Announce Type: new Abstract: As text-to-image generative models advance, they raise…
arXiv Artificial IntelligencearXiv:2608.17053v1 Announce Type: new Abstract: A bounded agent may obtain information for a decision from…
arXiv Artificial IntelligencearXiv:2608.16977v1 Announce Type: new Abstract: AI systems are increasingly capable of contributing to…
arXiv Artificial IntelligencearXiv:2608.16971v1 Announce Type: new Abstract: Radiology reports describe findings and locations in free…
arXiv Artificial IntelligencearXiv:2608.16956v1 Announce Type: new Abstract: API buyers purchase a dated contract, not a model name alone…
arXiv Artificial IntelligencearXiv:2608.16891v1 Announce Type: new Abstract: Agentic AI systems request tool actions that can modify…
arXiv Artificial IntelligencearXiv:2608.16890v1 Announce Type: new Abstract: Clinical trial programming -- transforming study protocols…
arXiv Artificial IntelligencearXiv:2501.06286v3 Announce Type: replace-cross Abstract: Multi-hop question answering requires a system to…
arXiv Artificial IntelligencearXiv:2503.00992v3 Announce Type: replace Abstract: Background. Evidence that large language models (LLMs)…
arXiv Artificial IntelligencearXiv:2608.16373v2 Announce Type: replace-cross Abstract: Despite comprising over 70% of its surface, the…
arXiv Artificial IntelligencearXiv:2608.16185v2 Announce Type: replace-cross Abstract: LLM agents increasingly answer questions over…