SOURCE-LINKED INTELLIGENCE

Toolcompass: Guiding Tool Trialing, Not Suppressing It

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Large language model (LLM) agents must generalize from tools seen during training to unseen tools at deployment. A key challenge is tool trialing, i.e., excessive trials waste the interaction budget, whereas selective trials enable exploration of unfamiliar tools. Existing outcome-based post-training leaves wasteful trials unguided, while turn-level supervision may suppress necessary exploration. We introduce ToolCompass, a post-training framework that guides tool trialing by organizing tool-call representations according to shared functions. Specifically, ToolCompass models each function clas

Read original source ↗ Open in workspace

recordType

paper

region

Global