Utility-Guided Agent Orchestration for Efficient LLM Tool Use

2026-03-20

AI Summary

This work addresses the trade-off between response quality and execution cost in large language model (LLM) agents when using external tools, a challenge often exacerbated by existing approaches that are either overly rigid or prone to redundant calls and high latency. The authors propose a utility-guided explicit orchestration framework that models agent behavior as a multi-action decision problem, dynamically selecting among responding, retrieving, invoking tools, verifying outcomes, and halting execution. This framework explicitly balances utility, cost, uncertainty, and redundancy, eschewing implicit control via prompt engineering in favor of a lightweight redundancy suppression mechanism and a utility-driven dynamic scheduling algorithm. Experimental results demonstrate that the proposed approach effectively governs the cost–performance trade-off, significantly improving agent behavior across diverse baselines and strategy variants, thereby validating the efficacy of utility-aware design in controllable agent orchestration.

Technology Category

• Multiagent Systems: Mechanism Design
• Planning, Routing, and Scheduling: Planning with Language Models
• 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

Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task performance at the expense of excessive tool calls, longer trajectories, higher token consumption, and increased latency. In this paper, we study agent orchestration as an explicit decision problem rather than leaving it entirely to prompt-level behavior. We propose a utility-guided orchestration policy that selects among actions such as respond, retrieve, tool call, verify, and stop by balancing estimated gain, step cost, uncertainty, and redundancy. Our goal is not to claim universally best task performance, but to provide a controllable and analyzable policy framework for studying quality-cost trade-offs in tool-using LLM agents. Experiments across direct answering, threshold control, fixed workflows, ReAct, and several policy variants show that explicit orchestration signals substantially affect agent behavior. Additional analyses on cost definitions, workflow fairness, and redundancy control further demonstrate that lightweight utility design can provide a defensible and practical mechanism for agent control.

Problem

• LLM tool use
• quality-cost trade-off
• agent orchestration
• execution cost
• tool call efficiency

Innovation

• utility-guided orchestration
• LLM agent
• tool use
• cost-quality trade-off
• decision policy