Progra: Progress-Aware Reinforcement Learning for Multi-Turn Function Calling

Real-world tasks with Large Language Models (LLMs) require multi-turn, multi-step conversations, often involving complex function calls and multiple user interactions. Existing methods either decompose multi-turn trajectories into independent single samples, neglecting task-level structure, or rely on end-to-end reinforcement learning (RL) without explicit progress modeling. To overcome these limitations, we propose P ROGRA , a framework that explicitly incorporates progress awareness into LLM training for multi-turn function calling. P ROGRA combines a Progress Awareness Generation pipeline to construct training data linking conversation summaries with future plans, and Progress Awareness-Guided RL to condition decisions on this awareness, reducing redundancy and aligning local actions with global task completion. Experiments on two public benchmarks show that P ROGRA substantially outperforms prior meth-ods for robust, efficient multi-turn function calling. Our code is available at https://github. com/FatCatCHC/Progra .