Add ATBench 2026 paper reference
Browse files
README.md
CHANGED
|
@@ -26,6 +26,8 @@ pipeline_tag: text-classification
|
|
| 26 |
|
| 27 |
Visit our GitHub, Hugging Face or ModelScope organization (click links above), search checkpoints with names starting with `AgentDoG-`, and you will find all you need! Enjoy!
|
| 28 |
|
|
|
|
|
|
|
| 29 |
# AgentDoG
|
| 30 |
|
| 31 |
|
|
@@ -678,4 +680,4 @@ If you use AgentDoG in your research, please cite:
|
|
| 678 |
|
| 679 |
## 🤝 Acknowledgements
|
| 680 |
|
| 681 |
-
This project builds upon prior work in agent safety, trajectory evaluation, and risk-aware AI systems.
|
|
|
|
| 26 |
|
| 27 |
Visit our GitHub, Hugging Face or ModelScope organization (click links above), search checkpoints with names starting with `AgentDoG-`, and you will find all you need! Enjoy!
|
| 28 |
|
| 29 |
+
The latest ATBench benchmark release is introduced in [ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis](https://arxiv.org/abs/2604.02022).
|
| 30 |
+
|
| 31 |
# AgentDoG
|
| 32 |
|
| 33 |
|
|
|
|
| 680 |
|
| 681 |
## 🤝 Acknowledgements
|
| 682 |
|
| 683 |
+
This project builds upon prior work in agent safety, trajectory evaluation, and risk-aware AI systems.
|