zjunlp/KnowSelf
[ACL 2025] Agentic Knowledgeable Self-awareness
This project helps improve how Large Language Models (LLMs) make decisions, especially in complex planning tasks. It allows an LLM to dynamically assess situations and decide when and how to use its knowledge, similar to human self-awareness. It takes an existing LLM, along with task-specific knowledge and examples of good problem-solving steps, and produces an enhanced LLM that can choose the best strategy (fast, slow, or knowledgeable thinking) for a given situation. This is ideal for AI researchers or developers building intelligent agents.
No commits in the last 6 months.
Use this if you are developing AI agents with Large Language Models and want them to make more nuanced, human-like decisions about when to apply knowledge or engage in 'slow thinking' for complex problems.
Not ideal if you need a simple, off-the-shelf solution for basic LLM applications without advanced agentic planning or self-awareness capabilities.
Stars
92
Forks
9
Language
Python
License
MIT
Category
Last pushed
Jun 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/zjunlp/KnowSelf"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lealone/Lealone
一个安全的能够自我进化的 AI 应用开发平台
business-science/ai-data-science-team
An AI-powered data science team of agents to help you perform common data science tasks 10X faster.
langchain-ai/open-swe
An Open-Source Asynchronous Coding Agent
microsoft/UFO
UFO³: Weaving the Digital Agent Galaxy
camel-ai/oasis
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.