牛哥精选 · 所有

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

📝 深度技术 arXiv AI 2026-06-09

AI Scientists Are Only as Good as Their Evidence: A Stratified Ablation of Proprietary Data and Reasoning Skills in Drug-Asset Valuation

颠覆认知：AI科学家的能力瓶颈不在模型，而在证据质量——药物估值的深层剖析

arXiv:2606.09556v1 Announce Type: new Abstract: AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prom…

ai科学家药物估值证据基础科学决策模型评估

🤖 AI·大模型 arXiv AI 2026-05-29

GrepSeek: Training Search Agents for Direct Corpus Interaction

提出GrepSeek方法训练LLM搜索代理直接与语料库交互，摆脱传统检索器限制，提升知识密集型任务效率。

arXiv:2605.29307v1 Announce Type: cross Abstract: Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language …

grepseek llm搜索代理语料库直接交互信息检索知识密集型任务

📝 深度技术 arXiv NLP 2026-05-20

Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains

探索强化学习与可验证奖励在知识密集型领域对LLM推理能力的提升，填补研究空白。

arXiv:2605.18261v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance …

rlvr llm 知识密集型强化学习可验证奖励

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

AI Scientists Are Only as Good as Their Evidence: A Stratified Ablation of Proprietary Data and Reasoning Skills in Drug-Asset Valuation

GrepSeek: Training Search Agents for Direct Corpus Interaction

Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains

📅 日期