arXiv Artificial IntelligenceWhen LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals
arXiv:2607.08065v2 Announce Type: replace Abstract: LLM-as-judge (Zheng et al., 2023) is increasingly the…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2607.08065v2 Announce Type: replace Abstract: LLM-as-judge (Zheng et al., 2023) is increasingly the…
arXiv Artificial IntelligencearXiv:2607.05682v2 Announce Type: replace Abstract: LLM systems for scientific discovery increasingly assist…
arXiv Artificial IntelligencearXiv:2606.30555v3 Announce Type: replace Abstract: The rapid integration of Large Language Models (LLMs) has…
arXiv Artificial IntelligencearXiv:2606.27814v4 Announce Type: replace Abstract: Training small language-model agents for long-horizon…
arXiv Artificial IntelligencearXiv:2606.25176v3 Announce Type: replace Abstract: Chess engines have evolved from search-based systems…
arXiv Artificial IntelligencearXiv:2606.22916v3 Announce Type: replace Abstract: Tool-using AI agents commonly operate under integration…
arXiv Artificial IntelligencearXiv:2606.19651v2 Announce Type: replace Abstract: Three-dimensional (3D) brain MRI is central to clinical…
arXiv Artificial IntelligencearXiv:2606.06256v3 Announce Type: replace Abstract: As the input length of large language model (LLM) serving…
arXiv Artificial IntelligencearXiv:2605.19576v3 Announce Type: replace Abstract: Self-evolving skill libraries face a silent failure mode…
arXiv Artificial IntelligencearXiv:2605.17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs)…
arXiv Artificial IntelligencearXiv:2604.22455v2 Announce Type: replace Abstract: A core component of any AI-Augmented Business Process…
arXiv Artificial IntelligencearXiv:2604.18584v2 Announce Type: replace Abstract: Mathematical problem solving remains a challenging test…