Guardado en:
Detalles Bibliográficos
Autores principales: Dennis, Simon, Diamond, Michael, Patil, Rivaan, Shabahang, Kevin, Guo, Hao
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.27891
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909016085495808
author Dennis, Simon
Diamond, Michael
Patil, Rivaan
Shabahang, Kevin
Guo, Hao
author_facet Dennis, Simon
Diamond, Michael
Patil, Rivaan
Shabahang, Kevin
Guo, Hao
contents Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking state and injecting routing instructions at every turn. We present a controlled comparison showing that for procedural tasks, this architecture is dominated by a simpler alternative: putting the entire procedure in the system prompt and letting the model self-orchestrate. Across three domains -- travel booking (14 nodes), Zoom technical support (14 nodes), and insurance claims processing (55 nodes) -- we evaluate 200 conversations per condition using LLM-as-judge scoring on five quality criteria. The in-context approach scores 4.53--5.00 on a 5-point scale while a LangGraph orchestrator using the same model scores 4.17--4.84. The orchestrated system fails on 24% of travel, 9% of Zoom, and 17% of insurance conversations, compared to 11.5%, 0.5%, and 5% for the in-context baseline. While external orchestration may have been necessary for earlier models, advances in frontier model capabilities have made it unnecessary for multi-turn conversations following a defined procedure.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27891
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks
Dennis, Simon
Diamond, Michael
Patil, Rivaan
Shabahang, Kevin
Guo, Hao
Artificial Intelligence
Machine Learning
Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking state and injecting routing instructions at every turn. We present a controlled comparison showing that for procedural tasks, this architecture is dominated by a simpler alternative: putting the entire procedure in the system prompt and letting the model self-orchestrate. Across three domains -- travel booking (14 nodes), Zoom technical support (14 nodes), and insurance claims processing (55 nodes) -- we evaluate 200 conversations per condition using LLM-as-judge scoring on five quality criteria. The in-context approach scores 4.53--5.00 on a 5-point scale while a LangGraph orchestrator using the same model scores 4.17--4.84. The orchestrated system fails on 24% of travel, 9% of Zoom, and 17% of insurance conversations, compared to 11.5%, 0.5%, and 5% for the in-context baseline. While external orchestration may have been necessary for earlier models, advances in frontier model capabilities have made it unnecessary for multi-turn conversations following a defined procedure.
title In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.27891