Reflexion = Verbal Reinforcement Learning
论文:Shinn et al., 2023, Northeastern + MIT + Princeton
原文链接:https://arxiv.org/abs/2303.11366
代码:https://github.com/noahshinn024/reflexion
本文记录我的论文学习过程与核心理解
AgentBench: Evaluating LLMs as Agents
论文:Liu, Xu et al., 清华 + 上交 + UC Berkeley + Microsoft + Stanford 等
原文链接:https://arxiv.org/abs/2308.03688
发表:2023.8 | 引用:1000+(Semantic Scholar)
开源:https://github.com/alibabaagents/agentbench
本文记录我的论文学习过程与核心理解
ChatDev: Communicative Agents for Software Development
论文:Chen Qian, Liu Wei et al., 清华 + 北大 + 微软亚洲研究院
原文链接:https://arxiv.org/abs/2307.07924
发表:2023.8 | 引用:500+(Semantic Scholar)
开源:https://github.com/OpenBMB/ChatDev
本文记录我的论文学习过程与核心理解
Generative Agents: Interactive Simulacra of Human Behavior
论文:Stanford University + Google DeepMind
原文链接:https://arxiv.org/abs/2304.03442
发表:2023.4(arXiv)| UIST 2023 正式发表 | 引用:1000+
本文记录我的论文学习过程与核心理解
Agentic RAG: Combining Retrieval-Augmented Generation with Agent Capabilities
本文记录我的论文学习过程与核心理解
Computer Use: Anthropic's Breakthrough in Native GUI Control for AI Agents
论文:Anthropic,2024
本文记录我的论文学习过程与核心理解
Self-Discover: Large Language Models Self-Compose Reasoning Structures
论文:Google DeepMind(Zhou et al.),2024
原文链接:https://arxiv.org/abs/2402.03620
本文记录我的论文学习过程与核心理解
MemGPT: Towards LLMs as Operating Systems
论文:UC Berkeley Packer, Wooders, Lin, Fang, Patil, Stoica, Gonzalez,2023
本文记录我的论文学习过程与核心理解
Toolformer: Language Models Can Teach Themselves to Use Tools
论文:Timo Schick et al., Meta AI, 2023
本文记录我的论文学习过程与核心理解
ReAct = Reasoning + Acting
论文:Yao et al., 2022, Google Research + Princeton
原文链接:https://arxiv.org/abs/2210.03629
本文记录我的论文学习过程与核心理解