Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act
A dense, decision-level reward is introduced in which an LLM judge evaluates the necessity of each tool call, which effectively suppresses cue-driven tool use while preserving task performance, providing a practical approach to improving the robustness of LLM agent tool-use policies.
Yi-Wei Yang, Haoxiang Zhang, Bing-Bing Wen et al.
· 0 citations