Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents

ArXi:2602.02050v3 Announce Type: replace Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing latency and degrading inference performance, making managing tool-use behavior challenging. In this work, we conduct entropy-based pilot experiments and observe a strong positive correlation between entropy reduction and high-quality tool calls.