SOURCE-LINKED INTELLIGENCE

CoBRA: Learning Tool-Use Boundaries via Counterfactual Margins

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

As large language models increasingly act through external tools, deciding when to call a tool has become a central problem alongside deciding how to use it. Unnecessary tool calls introduce latency, cost, retrieval noise, and error propagation, while missed calls hurt knowledge-intensive queries or questions requiring up-to-date evidence. Existing methods typically trigger tools from absolute query or generation signals, such as difficulty, confidence, or final task reward, and therefore lack an explicit estimate of the instance-level marginal benefit of tool use. We propose CoBRA, a counterf

Read original source ↗ Open in workspace

recordType

paper

region

Global