Author

Xiang-Long Liu

h-index 0 View on Semantic Scholar

We have 1 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

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