Abstract:Modern AI systems increasingly rely on workflows composed of multiple interacting agents, some powered by large language models (LLMs) and others by conventional computational modules. This paper analyzes the fundamental tradeoffs between latency, reliability, and cost in LLM-enabled agentic workflows. We introduce performance models for both LLM and non-LLM agents that capture the relationship between computational effort and output quality, incorporating the impact of reasoning and output tokens for LLM agents using a parametric exponential reliability function. Then, we study the design of sequential workflows under latency and cost constraints. Main results include a water-filling token allocation policy and characterizations of optimal workflow reliability in terms of shadow prices.
| Subjects: | Artificial Intelligence (cs.AI); Software Engineering (cs.SE) |
| Cite as: | arXiv:2605.23929 [cs.AI] |
| (or arXiv:2605.23929v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.23929 arXiv-issued DOI via DataCite |
From: Ya-Ting Yang [view email]
[v1]
Tue, 21 Apr 2026 23:09:16 UTC (646 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。