docs/research.md

Research Lists

A compilation of projects, papers, blogs in autonomous agents.

Table of Contents

• Introduction
• Projects
• Articles
• Talks

Projects

Developer tools

• [2023/8/10] ModelScope-Agent - An Agent Framework Connecting Models in ModelScope with the World
• [2023/05/25] Gorilla - An API store for LLMs
• [2023/03/31] BMTools - Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
• [2023/03/09] LMQL - A query language for programming (large) language models.
• [2022/10/25] Langchain - ⚡ Building applications with LLMs through composability ⚡

Applications

• [2023/07/08] ShortGPT - 🚀🎬 ShortGPT - An experimental AI framework for automated short/video content creation. Enables creators to rapidly produce, manage, and deliver content using AI and automation.
• [2023/07/05] gpt-researcher - GPT based autonomous agent that does online comprehensive research on any given topic
• [2023/07/04] DemoGPT - 🧩DemoGPT enables you to create quick demos by just using prompts. [demo]
• [2023/06/30] MetaGPT - 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
• [2023/06/11] gpt-engineer - Specify what you want it to build, the AI asks for clarification, and then builds it.
• [2023/05/16] SuperAGI - <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
• [2023/05/13] Developer - Human-centric & Coherent Whole Program Synthesis aka your own personal junior developer
• [2023/04/07] AgentGPT - 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser. [demo]
• [2023/04/03] BabyAGI - an example of an AI-powered task management system
• [2023/03/30] AutoGPT - An experimental open-source attempt to make GPT-4 fully autonomous.

Benchmarks

• [2023/08/07] AgentBench - A Comprehensive Benchmark to Evaluate LLMs as Agents. paper
• [2023/06/18] Auto-GPT-Benchmarks - A repo built for the purpose of benchmarking the performance of agents, regardless of how they are set up and how they work.
• [2023/05/28] ToolBench - An open platform for training, serving, and evaluating large language model for tool learning.

Articles

Research Papers

• [2023/08/11] BOLAA: Benchmarking and Orchestrating LLM-Augmented Autonomous Agents, Zhiwei Liu, et al.
• [2023/07/31] ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, Yujia Qin, et al.
• [2023/07/16] Communicative Agents for Software Development, Chen Qian, et al.
• [2023/06/09] Mind2Web: Towards a Generalist Agent for the Web, Xiang Deng, et al. [code] [demo]
• [2023/06/05] Orca: Progressive Learning from Complex Explanation Traces of GPT-4, Subhabrata Mukherjee et al.
• [2023/05/25] Voyager: An Open-Ended Embodied Agent with Large Language Models, Guanzhi Wang, et al. [code] [website]
• [2023/05/23] ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models, Binfeng Xu, et al. [code]
• [2023/05/17] Tree of Thoughts: Deliberate Problem Solving with Large Language Models, Shunyu Yao, et al.[code] [code-orig]
• [2023/05/12] MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers, Lili Yu, et al.
• [2023/05/19] FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance, Lingjiao Chen, et al.
• [2023/05/06] Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models, Lei Wang, et al.
• [2023/05/01] Learning to Reason and Memorize with Self-Notes, Jack Lanchantin, et al.
• [2023/04/24] WizardLM: Empowering Large Language Models to Follow Complex Instructions, Can Xu, et al.
• [2023/04/22] LLM+P: Empowering Large Language Models with Optimal Planning Proficiency, Bo Liu, et al.
• [2023/04/07] Generative Agents: Interactive Simulacra of Human Behavior, Joon Sung Park, et al. [code]
• [2023/03/30] Self-Refine: Iterative Refinement with Self-Feedback, Aman Madaan, et al.[code]
• [2023/03/30] HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace, Yongliang Shen, et al. [code] [demo]
• [2023/03/20] Reflexion: Language Agents with Verbal Reinforcement Learning, Noah Shinn, et al. [code]
• [2023/03/04] Towards A Unified Agent with Foundation Models, Norman Di Palo et al.
• [2023/02/23] Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection, Sahar Abdelnab, et al.
• [2023/02/09] Toolformer: Language Models Can Teach Themselves to Use Tools, Timo Schick, et al. [code]
• [2022/12/12] LMQL: Prompting Is Programming: A Query Language for Large Language Models, Luca Beurer-Kellner, et al.
• [2022/10/06] ReAct: Synergizing Reasoning and Acting in Language Models, Shunyu Yao, et al. [code]
• [2022/07/20] Inner Monologue: Embodied Reasoning through Planning with Language Models, Wenlong Huang, et al. [demo]
• [2022/04/04] Do As I Can, Not As I Say: Grounding Language in Robotic Affordances, Michael Ahn, e al. [demo]
• [2021/12/17] WebGPT: Browser-assisted question-answering with human feedback, Reiichiro Nakano, et al.
• [2021/06/17] LoRA: Low-Rank Adaptation of Large Language Models, Edward J. Hu, et al.

Blog Articles

• [2023/08/14] A Roadmap of AI Agents(Chinese) By Haojie Pan
• [2023/06/23] LLM Powered Autonomous Agents By Lilian Weng
• [2023/06/11] A CRITICAL LOOK AT AI-GENERATED SOFTWARE By JAIDEEP VAIDYAHAFIZ ASIF
• [2023/04/29] AUTO-GPT: UNLEASHING THE POWER OF AUTONOMOUS AI AGENTS By Akash Takyar
• [2023/04/20] Conscious Machines: Experiments, Theory, and Implementations(Chinese) By Jiang Zhang
• [2023/04/18] Autonomous Agents & Agent Simulations By Langchain
• [2023/04/16] 4 Autonomous AI Agents you need to know By Sophia Yang
• [2023/03/31] ChatGPT that learns to use tools(Chinese) By Haojie Pan

Talks

• [2023/06/05] Two Paths to Intelligence by Geoffrey Hinton
• [2023/05/24] State of GPT by Andrej Karpathy | OpenAI