LLMAgentPapers and awesome-llm-powered-agent

These are complementary resources: one curates foundational research papers on LLM agents while the other aggregates a broader ecosystem of papers, repositories, blogs, and implementations, making them best used together for comprehensive understanding of the field.

LLMAgentPapers
49
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 8/25
Community 18/25
Maintenance 2/25
Adoption 10/25
Maturity 16/25
Community 19/25
Stars: 2,911
Forks: 174
Downloads:
Commits (30d): 2
Language:
License:
Stars: 2,207
Forks: 196
Downloads:
Commits (30d): 0
Language:
License: MIT
No License No Package No Dependents
Stale 6m No Package No Dependents

About LLMAgentPapers

zjunlp/LLMAgentPapers

Must-read Papers on LLM Agents.

This resource provides a curated collection of must-read academic papers focused on Large Language Model (LLM) agents, covering various aspects like agent personality, memory, planning, tool use, and multi-agent systems. It helps AI researchers and practitioners stay updated with the latest advancements in designing and implementing intelligent agents powered by LLMs. The input is a topic within LLM agents, and the output is a list of relevant research papers.

AI Research Natural Language Processing Machine Learning Engineering Agent Systems Cognitive AI

About awesome-llm-powered-agent

hyp1231/awesome-llm-powered-agent

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

This project offers a comprehensive collection of resources related to Large Language Model (LLM)-powered agents, which are AI systems capable of autonomously solving complex tasks or simulating human interactions. It provides a curated list of research papers and open-source projects. Researchers, AI developers, and academics can use this to explore the latest advancements, discover new frameworks, and identify potential applications in areas like web agents, robotics, and gaming.

AI research LLM development autonomous systems multi-agent simulation AI applications

Scores updated daily from GitHub, PyPI, and npm data. How scores work