预算约束下的智能大语言模型：基于意图规划的昂贵工具使用策略

Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use

February 12, 2026

作者: Hanbing Liu, Chunhao Tian, Nan An, Ziyuan Wang, Pinyan Lu, Changyuan Yu, Qi Qi

cs.AI

摘要

我们研究预算受限的工具增强智能体，该场景要求大语言模型在严格货币预算下通过调用外部工具解决多步骤任务。我们将此设定形式化为上下文空间中的序列决策问题，其中工具执行具有价格随机性，由于状态-动作空间庞大、结果方差高且探索成本惊人，直接规划变得难以处理。针对这些挑战，我们提出INTENT——一种推理时规划框架，该框架利用意图感知的分层世界模型来预测未来工具使用情况与风险校准成本，并在线指导决策。在成本增强型StableToolBench测试中，INTENT在严格保证硬预算可行性的同时，显著提升了任务成功率，且在工具价格波动、预算变化等动态市场条件下仍保持稳健性。

English

We study budget-constrained tool-augmented agents, where a large language model must solve multi-step tasks by invoking external tools under a strict monetary budget. We formalize this setting as sequential decision making in context space with priced and stochastic tool executions, making direct planning intractable due to massive state-action spaces, high variance of outcomes and prohibitive exploration cost. To address these challenges, we propose INTENT, an inference-time planning framework that leverages an intention-aware hierarchical world model to anticipate future tool usage, risk-calibrated cost, and guide decisions online. Across cost-augmented StableToolBench, INTENT strictly enforces hard budget feasibility while substantially improving task success over baselines, and remains robust under dynamic market shifts such as tool price changes and varying budgets.