Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs

• URL: http://arxiv.org/abs/2605.23929v1
• Date: Tue, 21 Apr 2026 23:09:16 GMT
• Title: Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs
• Abstract summary: This paper analyzes the fundamental tradeoffs between latency, reliability, and cost in LLM-enabled agentic.<n>We introduce performance models for both LLM and non-LLM agents that capture the relationship between computational effort and output quality.<n>Main results include a water-filling token allocation policy and characterizations of optimal workflow reliability in terms of shadow prices.
• Score: 22.661656301757663
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution [47.70578021328887]
  Large language model (LLM)-based multi-agent systems often exhibit complex failure modes.<n>We introduce AFANet, a lightweight graph-based framework that models interaction trajectories through step-level semantic signals and agent-level relationships.<n>Our results suggest that effective agent failure attribution does not require heavy reasoning and a lightweight, structured approach can achieve strong performance.
  arXiv  Detail & Related papers  (2026-08-19T06:16:09Z)
• Optimizing Service Operations via LLM-Powered Multi-Agent Simulation [1.2997358113120427]
  We introduce an LLM-powered multi-agent simulation framework for optimizing service operations.<n>We pose the problem as optimization with decision-dependent uncertainty.<n>We develop an on-trajectory learning algorithm that, on a single simulation run, simultaneously constructs zeroth-order gradient estimates and updates design parameters to optimize steady-state performance.
  arXiv  Detail & Related papers  (2026-04-06T03:14:33Z)
• On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins [0.0]
  We present three critical design principles for integrating resilience and oversight into Digital Twins.<n>A key contribution is detailed characterization of LLM-induced errors across model descriptions of varying detail and complexity.
  arXiv  Detail & Related papers  (2026-03-26T20:38:03Z)
• Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs [62.17306142810532]
  We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters.<n>Chime traces the best latency, reducing end-to-end latency by 1.2--2.4$times$ and improving task performance by 8.0-9.5 percentage points on average over competitive baselines.
  arXiv  Detail & Related papers  (2026-03-23T17:01:42Z)
• LLM for Large-Scale Optimization Model Auto-Formulation: A Lightweight Few-Shot Learning Approach [10.44190976207354]
  LEAN-LLM-OPT is a workflow framework for large-scale OPTimization auto-formulation.<n>It decomposes the modeling task into structured sub-tasks and offloads mechanical data-handling operations to auxiliary tools.<n>It achieves strong performance on large-scale optimization modeling tasks and is competitive with state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-01-14T17:09:57Z)
• Network and Systems Performance Characterization of MCP-Enabled LLM Agents [2.952262068394116]
  Model Context Protocol (MCP) has recently gained increased attention within the AI community for providing a standardized way for large language models (LLMs) to interact with external tools and services.<n>This paper presents a measurement-based analysis of MCP-enabled interactions with LLMs, revealing trade-offs between capability, performance, and cost.
  arXiv  Detail & Related papers  (2025-10-20T05:13:47Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)
• FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning [70.38817963253034]
  This paper first discusses these challenges of federated fine-tuning LLMs, and introduces our package FS-LLM as a main contribution. We provide comprehensive federated parameter-efficient fine-tuning algorithm implementations and versatile programming interfaces for future extension in FL scenarios. We conduct extensive experiments to validate the effectiveness of FS-LLM and benchmark advanced LLMs with state-of-the-art parameter-efficient fine-tuning algorithms in FL settings.
  arXiv  Detail & Related papers  (2023-09-01T09:40:36Z)
• AgentBench: Evaluating LLMs as Agents [99.12825098528212]
  Large Language Model (LLM) as agents has been widely acknowledged recently.<n>We present AgentBench, a benchmark that consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
  arXiv  Detail & Related papers  (2023-08-07T16:08:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.