AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints

ArXi:2603.13348v1 Announce Type: new Tool use represents a critical capability for AI agents, with recent advances focusing on leveraging reinforcement learning (RL) to scale up the explicit reasoning process to achieve better performance. However, there are some key challenges for tool use in current RL-based scaling approaches: (a) direct RL