Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 63%MathFoundationRL/Book-Mathematical-Foundation-of-Reinforcement-Learning →
“Fuzzy title match (0.76): “Learning to Use Tools: Reinforcement Learning for Tool-Integ” ≈ “MathFoundationRL/Book-Mathematical-Foundation-of-Reinforceme””
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Minghui Xu →
“Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning”
- LinkedLinked via arxiv author · 85%Jiazi Wang →
“Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning”
- FuzzySimilar title/name (fuzzy) · 84%amitness/learning →
“Fuzzy title match (0.92): “Learning to Use Tools: Reinforcement Learning for Tool-Integ” ≈ “amitness/learning””