Yunkai's Blog Lab
Agent
Tag - Agent
2026
2026-07-18
ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability
2026-07-14
如何在智能体时代管理 AI 投资
2026-07-13
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
2026-07-13
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
2026-07-13
Neuro-Agentic Control：用 LLM 智能体控制安全控制器的深度学习框架
2026-07-08
Prompt-to-Paper：面向生物信息学的智能体AI论文生成系统
1
2
Yunkai Huang
嗨，这里是云开~
Articles
107
Tags
312
Categories
5
Follow Me
Announcement
This is my Blog
Recent Posts
两项 API 设置让 ARC-AGI-3 分数翻三倍——OpenAI 深度解析
2026-07-29
OpenAI 面向学术研究者推出 ChatGPT，加速科学发现
2026-07-29
Beyond Memory: LLM Agent 的异构协作知识工作模板
2026-07-29
模型无需明确后果也能“伪装对齐”？最新研究揭示AI安全新挑战
2026-07-29
GPT-5.6：前沿智能与前沿效率的融合
2026-07-29
Categories
[技术动态]
2
技术动态
102
技术探索
1
随笔
1
随笔
1
Tags
Place Recognition
UAV
Knowledge Management
Red-Teaming
OpenAI
Codex
Software Quality
Narrative Generation
MLP
ROI
Quantum Computing
Time-Series
反思
Deep Learning
Social Epistemology
Graph Neural Network
形式化验证
Cancer Genomics
媒体技术
经济研究
模拟器
Optimization
Robustness
隐私保护
Claude Code
Football
Teens
大语言模型
Multi-Agent Systems
ChatGPT
PostgreSQL
扩散模型
Drug Discovery
Safety
Business Leadership
Adversarial Resilience
Rust
农业韧性
Debate
Interpretability
Archives
July 2026
104
February 2026
3
Website Info
Article Count :
107
Unique Visitors :
Page Views :
Last Update :
