README.md

---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
library_name: transformers
---

# 🧠 A²FM: Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning

**A²FM (Adaptive Agent Foundation Model)** unifies reasoning-centric and agentic paradigms into a single framework that adaptively selects among **three execution modes** — *instant*, *reasoning*, and *agentic*.  
It follows a **route-then-align** training principle and introduces **Adaptive Policy Optimization (APO)** to jointly optimize accuracy and efficiency.

A²FM achieves **state-of-the-art performance** on major reasoning and agentic benchmarks:
- **13.4%** on *BrowseComp* (agentic)
- **70.4%** on *AIME25* (reasoning)
- **16.7%** on *HLE* (general)

Notably, its adaptive execution achieves a **cost of pass of only \$0.00487 per correct answer**, cutting cost by **45.2% vs. reasoning** and **33.5% vs. agentic**, delivering substantially higher cost efficiency while maintaining comparable accuracy.

📄 [**Paper**](https://arxiv.org/abs/2510.12838)  
💻 [**GitHub**](https://github.com/OPPO-PersonalAI/Adaptive_Agent_Foundation_Models)

---

## 🔑 Key Highlights

- ⚙️ **Unified reasoning & agentic modeling**  
  Integrates direct reasoning, chain-of-thought, and tool-augmented actions within a single backbone.  

- 🔄 **Route-then-Align supervised fine-tuning**  
  Trains task-aware routing followed by mode-aligned trajectory learning.  

- 🧩 **Adaptive Policy Optimization (APO)**  
  Reinforcement learning with adaptive sampling and cost-regularized reward for efficiency–accuracy balance.  

- 💡 **Substantially lower inference cost**  
  Adaptive routing cuts redundant reasoning/tool use while preserving correctness.

---

## 📘 Citation

```bibtex
@article{chen2025textsuperscript,
  title={A$\backslash$textsuperscript $\{$2$\}$ FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning},
  author={Chen, Qianben and Cao, Jingyi and Zhang, Jiayu and Qin, Tianrui and Li, Xiaowan and Zhu, King and Shi, Dingfeng and Zhu, He and Liu, Minghao and Liang, Xiaobo and others},
  journal={arXiv preprint arXiv:2510.12838},
  year={2025}
}