How to Build a Model-Native Agent That Learns Internal Planning, Memory, and Multi-Tool Reasoning Through End-to-End Reinforcement Learning
"Tool Use" 相关文章
解密prompt系列63. Agent训练方案:RStar2 & Early Experience etc
Agent 一年半开发复盘：大家对 Agent 的理解有错位，有效的「认知流程」很关键
LLMs Inside the Product: A Practical Field Guide
她把黑猩猩当作“人”，也教人类学会谦卑丨逝者
播客推荐| Context Engineering for AI Agents with LangChain and Manus
Under the hood of AI agents: A technical guide to the next frontier of gen AI
Building a Context-Folding LLM Agent for Long-Horizon Reasoning with Memory Compression and Tool Use
Andrej Karpathy Releases ‘nanochat’: A Minimal, End-to-End ChatGPT-Style Pipeline You Can Train in ~4 Hours for ~$100
一篇关于AI Agent设计理念的深度思考
一篇关于AI Agent设计理念的深度思考
Stanford Researchers Released AgentFlow: In-the-Flow Reinforcement Learning RL for Modular, Tool-Using AI Agents
Anthropic AI Releases Petri: An Open-Source Framework for Automated Auditing by Using AI Agents to Test the Behaviors of Target Models on Diverse Scenarios
Anthropic AI Releases Petri: An Open-Source Framework for Automated Auditing by Using AI Agents to Test the Behaviors of Target Models on Diverse Scenarios
A New Agency-Focused Supervision Approach Scales Software AI Agents With Only 78 Examples
A New Agency-Focused Supervision Approach Scales Software AI Agents With Only 78 Examples
Dr. Jane Goodall, groundbreaking chimpanzee expert and conservationist, has died
美团发布高效推理模型LongCat-Flash-Thinking：部分性能接近GPT5
清华团队提出DeepDive：深度搜索Agent再迎新突破
SimpleTIR：让大模型“边写代码边思考”不再崩溃
