Content
Introduction
LLM augmented autonomous agents have the potential to transform various applications by enhancing accuracy, efficiency, and automation in problem-solving. This repository contains a curated list of resources related to agent, agent planning, memory, multi-agent prompting, mimicking, and evaluation benchmarks.
Agent Survery
- The Rise and Potential of Large Language Model Based Agents: A Survey
- A Survey on Large Language Model based Autonomous Agents
- Lilian Wang’s Blog
CodeBase
- Stable-alignment ***
- AgentVerse **
- Camel **
- MetaGPT **
- LangChain
- AgentChain
- AgentChain uses Large Language Models (LLMs) for planning and orchestrating multiple Agents or Large Models (LMs) for accomplishing sophisticated tasks. AgentChain is fully multimodal: it accepts text, image, audio, tabular data as input and output.
- AutoGPT
- GPTeam
- SocraticAI
- Langroid
- Generative agents
- Light
- AutoAgents
- SuperAGI
- AI-waves:Agents
Agent Planning
- Reasoning with Language Model is Planning with World Model
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- Large Language Model as Autonomous Decision Maker
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Agent Memory and Single Agent
- A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
- TPTU: Task Planning and Tool Usage of Large Language Model-based AI Agents
- LARGE LANGUAGE MODEL AS AUTONOMOUS DECISION MAKER
- Cognitive Architectures for Language Agents
- ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
Multi-agent prompting & mimicking
- Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
- CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
- ExpertPrompting: Instructing Large Language Models to be Distinguished Experts
- Examining the Inter-Consistency of Large Language Models: An In-depth Analysis via Debate
- Communicative Agents for Software Development
- Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
- Generative Agents: Interactive Simulacra of Human Behavior
- Co-Writing Screenplays and Theatre Scripts with Language Models An Evaluation by Industry Professionals
- Training Socially Aligned Language Models in Simulated Human Society
- MULTI-AGENT COLLABORATION: HARNESSING THE POWER OF INTELLIGENT LLM AGENTS
- Blind Judgement: Agent-Based Supreme Court Modelling With GPT
- METAGPT: META PROGRAMMING FOR MULTI-AGENT COLLABORATIVE FRAMEWORK
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
- Building Cooperative Embodied Agents Modularly with Large Language Models
- Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models
- LLM as DB
- BOLAA: BENCHMARKING AND ORCHESTRATING LLM-AUGMENTED AUTONOMOUS AGENTS
- AgentSims: An Open-Source Sandbox for Large Language Model Evaluation
- AutoGen
- AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents
- S3: Social-network Simulation System with Large Language Model-Empowered Agents
- CGMI: Configurable General Multi-Agent Interaction Framework
Evaluation-Benchmarks
Welcome-Contributions
We need your help to build a better paper list! You can fork this repo and make a pull request if you find more exciting papers!