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

🤖 AI·大模型 arXiv AI 2026-06-16

RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments

全新零售长时推理基准，测试LLM智能体在真实环境中的连贯决策能力。

arXiv:2606.15862v1 Announce Type: new Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet th…

llm 零售基准测试长时推理决策智能体

📝 深度技术 arXiv AI 2026-06-01

Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach

用遗憾最小化方法优化LLM后训练，让大模型在交互环境中做出更低遗憾的决策，破解基础在线决策难题。

arXiv:2511.04393v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as "agents" for decision-making (DM) in int…

llm 决策智能体遗憾最小化后训练在线决策

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments

Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach

📅 日期