CoBRA: Learning Tool-Use Boundaries via Counterfactual Margins
Experiments with retrieval as the main tool on Qwen3-4B show that CoBRA improves tool-use efficiency and boundary-sensitive answer accuracy while maintaining strong performance on tool-dependent out-of-distribution questions.
Wen-Hao Zou, Xiang-Long Liu, Wendong Bi et al.
· 0 citations