直击扩散语言模型预训练与生成阶段的不匹配痛点，提出改进方法，值得算法研究者细读。
arXiv:2608.09424v1 Announce Type: new Abstract: Autoregressive language models align training and use: generation conditions on a clean prompt, and tr…
OpenAI两大改进让GPT-5.6 Sol在ARC-AGI-3提分188%，最严苛交互推理测试背后的关键突破。
IT之家 7 月 31 日消息，OpenAI 公司今天（7 月 31 日）发布公告，宣布通过改进框架， 让 GPT-5.6 Sol 模型的 ARC-AGI-3 提高了 188%。 IT之家注：ARC-AGI-3 由 ARC Prize 团队推出的全新交互式推理基准测试，是目前全球公认衡量 AI 通用…
LLM 生成的临床试验摘要能否兼顾医生与患者需求？这项研究系统评估并改进了多受众场景下的忠实性问题，附有公开方法与分析。
arXiv:2607.09932v1 Announce Type: cross Abstract: Large language models are increasingly used to summarize clinical trial results for healthcare provi…
用两个Qwen模型打造无降级群智能系统，实现长上下文、持久记忆与深度推理，周末项目也能颠覆AI订阅模式！
I recently started a weekend project—partly because I was thinking about cancelling my AI subscriptions—with the goal of creating a system capable of …
首次验证无标准答案的强化学习也能提升LLM，颠覆传统监督范式。
arXiv:2606.27369v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth…
LLM互教互学新范式：通过同伴反馈实现策略共蒸馏，让两个模型在训练中相互提升。
arXiv:2606.14368v1 Announce Type: new Abstract: We study multi-domain LLM training in which two models, each stronger in a different domain, co-evolve…
利用解空间结构改进扩散模型，为旅行商问题带来新解法，值得关注。
arXiv:2412.13858v2 Announce Type: replace-cross Abstract: We investigate diffusion models to solve the Traveling Salesman Problem. Building on the rec…
几何感知强化学习后训练，精准修复多模态大模型在医学影像中的几何盲点。
arXiv:2601.23220v2 Announce Type: replace-cross Abstract: Despite recent Multimodal Large Language Models (MLLMs)' linguistic prowess in medical diagn…
破解大模型出错规律，为模型优化提供新视角的科研论文
arXiv:2605.28328v1 Announce Type: cross Abstract: When generating outputs for domains with specific validity constraints (e.g., a program should compi…
即使噪声很大的LLM评估器，也能有效改进AI智能体的性能，打破传统认知。
Article URL: https://www.tensorzero.com/blog/even-very-noisy-llm-evaluators-are-useful-for-improving-ai-agents/ Comments URL: https://news.ycombinator…