https://github.com/xlang-ai/xlang-paper-reading

Paper collection on building and evaluating language model agents via executable language grounding
https://github.com/xlang-ai/xlang-paper-reading

agent code-generation complex-reasoning language-agent large-language-models llm-robotics neural-symbolic reinforcement-learning tool-use web-grounding

Last synced: 9 days ago
JSON representation

Paper collection on building and evaluating language model agents via executable language grounding

• Host: GitHub
• URL: https://github.com/xlang-ai/xlang-paper-reading
• Owner: xlang-ai
• Created: 2023-07-08T16:07:38.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-29T04:23:11.000Z (6 months ago)
• Last Synced: 2024-08-01T19:55:35.760Z (3 months ago)
• Topics: agent, code-generation, complex-reasoning, language-agent, large-language-models, llm-robotics, neural-symbolic, reinforcement-learning, tool-use, web-grounding
• Homepage: https://www.xlang.ai/project
• Size: 269 KB
• Stars: 327
• Watchers: 10
• Forks: 11
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-gpt - Paper collection on building and evaluating language model agents via executable language grounding

README

        
# XLang Paper Reading

![](https://img.shields.io/github/last-commit/xlang-ai/xlang-paper-reading?color=green)

![](https://img.shields.io/badge/PRs-Welcome-red) 

[![Twitter Follow](https://img.shields.io/twitter/follow/XLangNLP)](https://twitter.com/XLangNLP)

[![Join Slack](https://img.shields.io/badge/Slack-join-blueviolet?logo=slack&amp)](https://join.slack.com/t/xlanggroup/shared_invite/zt-20zb8hxas-eKSGJrbzHiPmrADCDX3_rQ)

[![](https://dcbadge.vercel.app/api/server/4Gnw7eTEZR?compact=true&style=flat)](https://discord.gg/4Gnw7eTEZR)

## Introduction

**Exe**cutable **Lang**uage **G**rounding ([XLANG](https://xlang.ai)) focuses on building language model agents that transform (“grounding”) language instructions into code or actions executable in real-world environments, including databases (data agent), web applications (plugins/web agent), and the physical world (robotic agent) etc,. It lies at the heart of language model agents or natural language interfaces that can interact with and learn from these real-world environments to facilitate human interaction with data analysis, web applications, and robotic instruction through conversation. Recent advances in XLang incorporate techniques such as LLM + external tools, code generation, semantic parsing, and dialog or interactive systems.



  

    

  



Here we make a paper list for you to keep track of the research in this track. Stay tuned and have fun!

### Paper Group

- [LLM code generation](https://github.com/xlang-ai/xlang-paper-reading/blob/main/llm-code-generation.md)

- [LLM agents (with tool use)](https://github.com/xlang-ai/xlang-paper-reading/blob/main/llm-tool-use.md)

- [LLM web grounding](https://github.com/xlang-ai/xlang-paper-reading/blob/main/llm-web-grounding.md)

- [LLM robotics](https://github.com/xlang-ai/xlang-paper-reading/blob/main/llm-robotics-and-embodied-ai.md)