# In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks

arXiv: https://arxiv.org/abs/2604.27891 · HTML: https://mlsanity.com/paper/2604.27891/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models](https://mlsanity.com/paper/2403.12881/) (2024)
- [ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditions](https://mlsanity.com/paper/2601.06112/) (2026)
- [When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail](https://mlsanity.com/paper/2601.04748/) (2026)
- [Large Language Models can accomplish Business Process Management Tasks](https://mlsanity.com/paper/2307.09923/) (2023)
- [WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models](https://mlsanity.com/paper/2411.05451/) (2024)
- [An Empirical Study of Agent Developer Practices in AI Agent Frameworks](https://mlsanity.com/paper/2512.01939/) (2025)
- [Procedural Knowledge Improves Agentic LLM Workflows](https://mlsanity.com/paper/2511.07568/) (2025)
- [Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models](https://mlsanity.com/paper/2404.14772/) (2024)

## Built on by (most cited first, 2 of 2)

- [Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost](https://mlsanity.com/paper/2605.22502/) (2026)
- [StateM: Reaching 95.3% Raw Accuracy, or a 15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling](https://mlsanity.com/paper/2608.15089/) (2026)

## Abstract (arXiv)

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.