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.
Repo for "Adaptation of Agentic AI"
| Date | Stars |
|---|---|
| 2026-07-31 | 677 |
| 2026-08-06 | 679 |
Today
+2 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Adaptation of Agentic AI
[](https://github.com/sindresorhus/awesome)
[](https://img.shields.io/github/stars/pat-jj/Awesome-Adaptation-of-Agentic-AI?style=social)
[](https://creativecommons.org/licenses/by-nc-nd/4.0/)
[](https://img.shields.io/badge/PRs-Welcome-red)
[](https://arxiv.org/abs/2512.16301)
<p align="center">
<img src="images/intro.png" width="100%" style="align:center;"/>
</p>
A curated list of papers on adaptation strategies of agentic AI systems. This repository accompanies the paper "Adaptation of Agentic AI" (Ongoing Work).
**Cite this paper:**
```
@article{jiang2025adaptation,
title={Adaptation of Agentic AI},
author={Jiang, Pengcheng and Lin, Jiacheng and Shi, Zhiyi and Wang, Zifeng and He, Luxi and Wu, Yichen and Zhong, Ming and Song, Peiyang and Zhang, Qizheng and Wang, Heng and others},
journal={arXiv preprint arXiv:2512.16301},
year={2025}
}
```
## Table of Contents
- [Agent Adaptation](#agent-adaptation)
- [A1: Tool Execution Signaled](#a1-tool-execution-signaled)
- [A2: Agent Output Signaled](#a2-agent-output-signaled)
- [Tool Adaptation](#tool-adaptation)
- [T1: Agent-Agnostic Tool Adaptation](#t1-agent-agnostic-tool-adaptation)
- [T2: Agent-Supervised Tool Adaptation](#t2-agent-supervised-tool-adaptation)
---
## Agent Adaptation
### A1: Tool Execution Signaled Agent Adaptation
<p align="center">
<img src="images/a1_illustrate.png" width="100%" style="align:center;"/>
</p>
Development Timeline:
<p align="center">
<img src="images/a1_timeline.png" width="100%" style="align:center;"/>
</p>
#### RL-based Methods
| Time | Method | Venue | Task(s) | Tool(s) | Agent Backbone | Tuning |
|------|--------|-------|---------|---------|----------------|--------|
| 2025.11 | Orion | arXiv<br><img src="images/paper_icon.png" width="16" height="16"> [Paper](https://arxiv.org/abs/2511.07581) | IR | Retrievers | LFM2 | GRPO |
| 2025.10 | olmOCR2 | arXiv<br><img src="images/paper_icon.png" width="16" height="16"> [Paper](https://arxiv.org/abs/2510.19817)<br><img src="images/code_icon.png" width="16" height="16"> [Code](https://github.com/allenai/olmocr) | Document OCR | Synthetic Document Verifier | Qwen2.5-VL | SFT, GRPO |
| 2025.10 | AlphaProof | Nature’25<br><img src="images/paper_icon.png" width="16" height="16"> [Paper](https://www.nature.com/articles/s41586-025-09833-y) | Formal Theorem Proving | Lean Compiler | Transformer (3B Enc-Dec) | SFT, AlphaZero, TTRL |
| 2025.10 | ToolExpander | arXiv<br><img src="images/paper_icon.png" width="16" height="16"> [Paper](https://arxiv.org/abs/2510.07737) | Tool-Calling | Various APIs | Qwen2.5 | SFT, GRPO |
| 2025.09 | BFS-Prover-V2 | arXiv<br><img src="images/paper_icon.png" width="16" height="16"> [Paper](https://arxiv.org/abs/2509.06493)<br><img src="images/code_icon.png" width="16" height="16"> [Code](https://github.com/ByteDance-Seed/BFS-Prover-V2) | Formal Theorem Proving | Lean Compiler | Qwen2.5 | BFS-Guided AlphaZero-like EI |
| 2025.09 | WebGen-Agent | arXiv<br><img src="images/paper_icon.png" width="16" height="16"> [Paper](https://arxiv.org/abs/2509.22644)<br><img src="images/code_icon.png" width="16" height="16"> [Code](https://github.com/mnluzimu/WebGen-Agent) | Website Generation | VLM, GUI Agent, Code Executor | Various Models | SFT, Step-GRPO |
| 2025.09 | Tool-R1 | arXiv<br><img src="images/paper_icon.png" width="16" height="16"> [Paper](https://arxiv.org/abs/2509.12867)<br><img src="images/code_icon.png" width="16" height="16"> [Code](https://github.com/YBYBZhang/Tool-R1) | General TExcerpt of 38,383 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:463a223a502d83aa, topic:agentic-ai, name:agentic, desc:agentic
matched fp:463a223a502d83aa, topic:large-language-models
