研究人员推出了一种名为“LLM-as-a-Verifier”的新颖框架，该框架将验证视为大型语言模型的一个新的可扩展轴。这种方法超越了离散评分，通过计算基于token logit分布的连续分数来实现，从而为代理任务提供更细粒度的反馈。该框架在Terminal-Bench V2和SWE-Bench Verified等多个基准测试中展示了最先进的性能，并且还可以提供任务的进度估计。此外，它还被集成到Claude Code中，以帮助开发人员并提高强化学习的样本效率。 AI
影响 通过引入新的验证可扩展轴来增强LLM能力，可能提高代理性能和开发人员工具。
排序理由 该集群包含多篇详细介绍LLM新研究框架的学术论文。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
arXiv:2607.05391v1 Announce Type: new Abstract: Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as …
arXiv:2607.02668v1 Announce Type: new Abstract: Large language models are inconsistent: varying prompts or including unrelated information can lead to unexpected changes in model outputs. The generator-validator (G-V) gap is one manifestation of this phenomenon, where LLMs genera…
Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as a new scaling axis. To unlock this and demonstra…
Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as a new scaling axis. To unlock this and demonstra…
LLM-as-a-Verifier introduces a probabilistic verification framework that scales across multiple dimensions to improve solution correctness assessment and agent performance across various benchmarks.
<p>The rapid ascent of Large Language Models (LLMs) has been nothing short of transformative. From generating human-like text to assisting with complex problem-solving, their capabilities continue to expand at an astonishing pace. Historically, the primary drivers of this advance…