
Large language models can effectively learn to use external tools through cooperation and interaction with the ConAgents framework.


coremsg

cooperative-and-interactive-agents-for-tool-learning-conagents-framework


Cooperative and Interactive Agents for Tool Learning: ConAgents Framework


title_rewrite


ConAgents framework enhances tool learning by enabling cooperative and interactive agents to adaptively calibrate themselves, improving task performance.



The author proposes the ConAgents framework to address limitations in tool learning by modularizing the workflow into three agents and enabling adaptive calibration based on feedback from the tool environment.


Learning-to-Use-Tools-via-Cooperative-and-Interactive-Agents-ConAgents-Framework


Learning to Use Tools via Cooperative and Interactive Agents: ConAgents Framework
