讀紙 ReadPaper

由 Claude Code Max 翻譯的 AI 論文繁體中文版 · 101 篇

標籤 願望清單
篩選標籤： MCP 3 篇 × 清除
2608.26133v1 CC BY 4.0 Anthropic

Agent Seer：從規格理解合成評測情境

Agent Seer: Synthesizing Scenarios from Specification Understanding

Harish Karumuri、Mahesh Vemula、David Lopes Pegna（Apple）

AI AgentTool UseMCPEvaluationSynthetic DataLLM-as-JudgeBenchmark
arXiv 25
Liang-Hsun Huang 許願
2604.15034v2 CC BY 4.0 Google

Autogenesis：自我演化的智能體協定

Autogenesis A Self-Evolving Agent Protocol

Wentao Zhang, Zhe Zhao, Haibin Wen, Yingcheng Wu, Ming Yin, Bo An, Mengdi Wang

AgentSelf-EvolutionProtocolLLMMulti-AgentTool UseMCP
arXiv 58
Teds Lin 許願
2604.08224v1 CC BY 4.0

LLM 代理的外部化：記憶體、技能、協定與 harness 工程的統一綜述

Externalization in LLM Agents A Unified Review of Memory Skills Protocols and Harness Engineering

Chenyu Zhou, Huacan Chai, Wenteng Chen, Zihan Guo, Rong Shan, Yuanyi Song, Tianyi Xu, Yingxuan Yang,...

LLM AgentMemorySkillsProtocolsHarness EngineeringSurveyTool UseMCP
arXiv 204
Teds Lin 許願