牛哥精选 · 一年

📋 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 2026-07-08

Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design

别急着微调，研究证明奖励函数才是决定LLM生成流程模型质量的关键变量

arXiv:2607.06175v1 Announce Type: cross Abstract: Large language models (LLMs) can generate BPMN process models from natural-language descriptions, ye…

llm 强化学习奖励函数 bpmn 流程建模

🤖 AI·大模型 arXiv AI 2026-06-01

REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge

ICML 2026新作：用回归感知的强化学习，让LLM当裁判更精准可靠

arXiv:2603.17145v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as automated evaluators that assign n…

强化学习 llm-as-a-j 回归感知模型评估 icml 2026

🤖 AI·大模型 arXiv AI 2026-05-26

PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning

用大语言模型自动设计奖励函数，为程序化内容生成强化学习提供新范式，突破人工奖励建模瓶颈。

arXiv:2502.10906v2 Announce Type: replace Abstract: Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-speci…

大语言模型强化学习程序化内容生成奖励函数设计 pcg

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design

REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge

PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning

📅 日期