1
DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
DeepTool通过过程监督强化学习实现工具集成推理中的交错深思，提升LLM在策略规划与自纠正上的表现。
arXiv:2605.29568v1 Announce Type: new Abstract: Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However,…