A Framework for Robust, Self-Recovering Tool-Using Language Model Agents — trained on 50K+ failure-annotated trajectories for fault-tolerant reasoning and recovery.
-
Updated
Nov 10, 2025 - Python
A Framework for Robust, Self-Recovering Tool-Using Language Model Agents — trained on 50K+ failure-annotated trajectories for fault-tolerant reasoning and recovery.
Add a description, image, and links to the toolbench topic page so that developers can more easily learn about it.
To associate your repository with the toolbench topic, visit your repo's landing page and select "manage topics."