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

2026-02-12

AI Summary

This work addresses the challenges of deploying large language models to execute multi-step tasks under strict monetary budget constraints, where the vast state-action space, high exploration costs, and high outcome variance hinder effective decision-making. To tackle these issues, the authors propose the INTENT framework, which introduces an intention-driven hierarchical planning mechanism. During inference, INTENT employs an intention-aware hierarchical world model to anticipate future tool invocation trajectories and integrates risk-calibrated cost estimation to guide online decision-making. Evaluated on the StableToolBench benchmark, the approach strictly adheres to budget limits while significantly improving task success rates and demonstrates robustness under varying tool pricing and budget adjustments.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

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.

Problem

• budget-constrained
• tool-augmented agents
• costly tool use
• monetary budget
• sequential decision making

Innovation

• budget-constrained agents
• intention-based planning
• tool-augmented LLMs
• hierarchical world model
• cost-aware decision making