SOURCE-LINKED INTELLIGENCE

Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling

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

Multi-turn tool calling is a core evaluation scenario for large language model (LLM) agents. On public tool-calling benchmarks, open-weight models now approach or even surpass closed-source frontier models in aggregate accuracy. However, this metric averages over many different multi-turn situations and obscures whether progress is balanced across them. We propose an action-class-oriented diagnostic framework that decomposes multi-turn failures into two orthogonal modes: action-class miscalibration and action-execution failure. The framework operates over a four-class action space (TOOL_CALL/A

Read original source ↗ Open in workspace

recordType

paper

region

Global