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.
@article{arxiv.2602.11541,
title = {Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use},
author = {Hanbing Liu and Chunhao Tian and Nan An and Ziyuan Wang and Pinyan Lu and Changyuan Yu and Qi Qi},
journal= {arXiv preprint arXiv:2602.11541},
year = {2026}
}