Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation

2026-08-25

AI Summary

本文提出一种成本-效用对齐框架，通过成本分析、效用归因等五阶段方法解决LLM代理执行任务时资源消耗与任务贡献不匹配的问题。

Abstract

LLM agents execute tasks through multi-step trajectories that accumulate cost in tokens, latency, monetary fees, and environmental risk while producing utility only at the aggregate task level. Prior surveys address inference optimization, agent capabilities, or evaluation in isolation, leaving practitioners without principled tools to determine whether a trajectory's resource expenditure is justified by its task contribution. We address this gap by developing a trajectory-centric cost-utility alignment framework that treats resource consumption and task contribution as dual ledgers over the same execution, organized around five analytical stages: cost profiling, utility attribution, misalignment diagnosis, targeted adaptation, and evaluation. Utility attribution is central to this structure: rather than relying on aggregate outcomes, it organizes contribution methods by evidential strength, from process proxies and information dependency to counterfactual replay, supplying the causal evidence that grounds diagnosis and guides adaptation. Using this framework, we analyze recent agent systems, attribution methods, and evaluation protocols covering efficiency, reliability, and economic value, as well as five forms of misalignment spanning cognitive and context use, external interaction, recovery-loop control, resource-capability allocation, and multi-agent coordination, together with their targeted adaptations. The result is a closed analytical loop connecting the cost side of agent execution to its utility side, providing a structured basis for resource-aware agent design and deployment.

Problem

• Cost-Utility Alignment
• LLM Agents
• Resource Expenditure
• Task Contribution
• Trajectory Analysis

Innovation

• cost-utility alignment
• trajectory-centric framework
• utility attribution
• misalignment diagnosis
• targeted adaptation