Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use
This addresses a practical problem for developers of AI agents that use paid APIs, though it appears incremental as it builds on existing tool-augmented agent frameworks.
The paper tackles the problem of budget-constrained tool-augmented agents where large language models must solve multi-step tasks using costly external tools under strict monetary limits, proposing INTENT to enforce budget feasibility while improving task success rates.
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.