Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
| Date | Stars |
|---|---|
| 2026-07-24 | 2372 |
| 2026-07-25 | 2374 |
| 2026-07-28 | 2374 |
| 2026-07-30 | 2374 |
| 2026-07-31 | 2384 |
| 2026-08-06 | 2384 |
Today
— stars today
This week
+10 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.42%/day
<!-- <h1 align="center"> <strong>A Comprehensive Survey of Self-Evolving AI Agents<br>A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems</strong> </h1> --> <h1 align="center"> <strong>Awesome-Self-Evolving-Agents</strong> </h1> <div align="center"> [](https://awesome.re) [](https://arxiv.org/abs/2508.07407) [](https://github.com/EvoAgentX/Awesome-Self-Evolving-Agents/pulls) [](https://star-history.com/#EvoAgentX/Awesome-Self-Evolving-Agents) [](LICENSE) <h3 align="center"> <strong>🤖 We're still cooking — Stay tuned! 🤖<br>⭐ Give us a star if you like it! ⭐</strong> </h3> <img src="./assets/evolve-tree.jpg" alt="Evolve Tree"> <br> <em>Figure: A visual taxonomy of AI agent evolution and optimisation techniques, categorised into three major directions: single-agent optimisation, multi-agent optimisation, and domain-specific optimisation. The tree structure illustrates the development of these approaches from 2023 to 2025, including representative methods within each branch.</em> </div> ## AI Agents Development Path <p align="center"> <img src="./assets/evolve-path.png" alt="Development Path", width="500"> </p> ## Conceptual Framework of the Self-Evolving AI Agents <p align="center"> <img src="./assets/evolve-framework.png" alt="Conceptual Framework", width="500"> </p> ## Open-Source Framework - (*EMNLP'25 Demo*) **EvoAgentX**: An Automated Framework for Evolving Agentic Workflows [[💻 Code](https://github.com/EvoAgentX/EvoAgentX)] [[📝 Paper](https://arxiv.org/abs/2507.03616)] - (*Arxiv'25*) MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems [[📝 Paper](https://arxiv.org/abs/2505.16988)] [[💻 Code](https://github.com/MASWorks/MASLab)] ## 1. Single-Agent Optimisation ### 1.1 🤖 LLM Behaviour Optimisation #### 1.1.1 📌 Training-Based Behaviour Optimisation ##### (1) 🔧 Supervised Fine-Tuning Approaches - (*ICLR'24*) ToRA: A tool-integrated reasoning agent for mathematical problem solving [[📝 Paper](https://arxiv.org/abs/2309.17452)] [[💻 Code](https://github.com/microsoft/ToRA)] - (*NeurIPS'22*) STaR : Bootstrapping reasoning with reasoning [[📝 Paper](https://arxiv.org/abs/2203.14465)] [[💻 Code](https://github.com/ezelikman/STaR)] - (*Arxiv'24*) NExT: Teaching large language models to reason about code execution [[📝 Paper](https://arxiv.org/abs/2404.14662)] - (*EMNLP'24*) MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning [[📝 Paper](https://arxiv.org/abs/2405.07551)] - (*ICML'25*) MAS-GPT: Training LLMs to build LLM-based multi-agent systems [[📝 Paper](https://arxiv.org/abs/2503.03686)] [[💻 Code](https://github.com/MASWorks/MAS-GPT)] ##### (2) 🔧 Reinforcement Learning Approaches - (*ICML'24*) Self-Rewarding Language Models [[📝 Paper](https://arxiv.org/abs/2401.10020)] [[💻 Code](https://github.com/lucidrains/self-rewarding-lm-pytorch)] - (*Arxiv'24*) Tulu 3: Pushing Frontiers in Open Language Model Post-Training [[📝 Paper](https://arxiv.org/abs/2411.15124)] [[💻 Code](https://github.com/allenai/open-instruct)] - (*EMNLP'24*) Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing [[📝 Paper](https://arxiv.org/abs/2402.00658)] [[💻 Code](https://github.com/SparkJiao/dpo-trajectory-reasoning)] - (*Arxiv'24*) Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents [[📝 Paper](https://arxiv.org/abs/2408.07199)] - (*Arxiv'24*) DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data [[📝 Paper](https://ar
Excerpt of 42,219 characters
Read on GitHub
22
14
8
5
Zhmin Zhao · Software Analysis and Intelligence Lab (SAIL) & Lab on Maintenance, Construction and Intelligence of Software (MCIS) · Canada
4
LeaderOnePro · China
4
3
3
3
Rui Pan
1
Zijian Zhou · National University of Singapore · Singapore
1
1
Zhengyao Jiang · University College London · United Kingdom
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:486be8ff52be58d6, topic:multi-agent-systems, topic:agentic-ai, readme:ai agent