Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs
For system designers of LLM-based multi-agent workflows, this provides a theoretical framework and optimization policy to balance latency, reliability, and cost.
This paper analyzes the tradeoffs between latency, reliability, and cost in LLM-enabled agentic workflows, introducing performance models and a water-filling token allocation policy to optimize sequential workflows under constraints.
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.