SOURCE-LINKED INTELLIGENCE

Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Current large language models (LLMs) increasingly benefit from external tool integration, especially for tasks requiring reliable computation and verification. Motivated by this, we study calculator tool calling for improving mathematical reasoning on the Countdown task. We first analyze reasoning failures and find that calculation errors account for a substantial portion of incorrect responses. We then construct supervised fine-tuning datasets to teach the model useful tool-use patterns and how to interpret returned outputs. Building on this tool-formatted policy, we apply several on-policy r

Read original source ↗ Open in workspace

recordType

paper

region

Global