MachinoAI Research

Papers

Browse the full research library.

Ten papers per page, with summaries, diagrams, formulas, concepts and citations kept close to the source.

All papers

82 research papers / Page 3 of 9

AI Agents/12 min read

Voyager: An Open-Ended Embodied Agent with Large Language Models

Voyager: An Open-Ended Embodied Agent with Large Language Models: Long-term learning and skill library.

Read this paper to understand long-term learning and skill library in LLM-agent design.

Guanzhi Wang

Read paper

AI Agents/12 min read

MemGPT: Towards LLMs as Operating Systems

MemGPT: Towards LLMs as Operating Systems: Long-term contextual memory.

Read this paper to understand long-term contextual memory in LLM-agent design.

Charles Packer

Read paper

AI Agents/12 min read

AgentBench: Evaluating LLMs as Agents

AgentBench: Evaluating LLMs as Agents: General agent evaluation.

Read this paper to understand general agent evaluation in LLM-agent design.

Xiao Liu

Read paper

AI Agents/12 min read

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face: LLM as orchestrator.

Read this paper to understand llm as orchestrator in LLM-agent design.

Yongliang Shen

Read paper

AI Agents/12 min read

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation: Multi-agent collaboration.

Read this paper to understand multi-agent collaboration in LLM-agent design.

Qingyun Wu

Read paper

AI Agents/12 min read

CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society: Role-playing multi-agent systems.

Read this paper to understand role-playing multi-agent systems in LLM-agent design.

Guohao Li

Read paper

AI Agents/12 min read

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework: Agents organized around workflows and SOPs.

Read this paper to understand agents organized around workflows and sops in LLM-agent design.

Sirui Hong

Read paper

AI Agents/12 min read

MRKL Systems: A Modular, Neuro-Symbolic Architecture That Combines Large Language Models, External Knowledge Sources and Discrete Reasoning

MRKL Systems: A Modular, Neuro-Symbolic Architecture That Combines Large Language Models, External Knowledge Sources and Discrete Reasoning: LLM + external tools/modules.

Read this paper to understand llm + external tools/modules in LLM-agent design.

Ehud Karpas

Read paper

AI Agents/12 min read

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Tree of Thoughts: Deliberate Problem Solving with Large Language Models: Search and planning over reasoning paths.

Read this paper to understand search and planning over reasoning paths in LLM-agent design.

Shunyu Yao

Read paper

AI Agents/12 min read

Reflexion: Language Agents with Verbal Reinforcement Learning

Reflexion: Language Agents with Verbal Reinforcement Learning: Self-reflection and episodic memory.

Read this paper to understand self-reflection and episodic memory in LLM-agent design.

Noah Shinn

Read paper