# Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution

arXiv: https://arxiv.org/abs/2607.14456 · HTML: https://mlsanity.com/paper/2607.14456/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 52 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 22 of 22)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [Why Does the Effective Context Length of LLMs Fall Short?](https://mlsanity.com/paper/2410.18745/) (2024)
- [Flow: Modularized Agentic Workflow Automation](https://mlsanity.com/paper/2501.07834/) (2025)
- [FlowMind: Automatic Workflow Generation with LLMs](https://mlsanity.com/paper/2404.13050/) (2024)
- [ProAgent: From Robotic Process Automation to Agentic Process Automation](https://mlsanity.com/paper/2311.10751/) (2023)
- [PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks](https://mlsanity.com/paper/2407.13244/) (2024)
- [SmartFlow: Robotic Process Automation using LLMs](https://mlsanity.com/paper/2405.12842/) (2024)
- [PromptDebt: A Comprehensive Study of Technical Debt Across LLM Projects](https://mlsanity.com/paper/2509.20497/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have accelerated the adoption of software development agents, now widely available as Integrated Development Environment (IDE) extensions and standalone applications. While these agents are typically general-purpose, it remains unclear whether specialist agents justify their additional development effort. We investigate this question in the context of business process automation, focusing on the transformation of Business Process Model and Notation (BPMN) diagrams into executable agentic workflows. Since BPMN specifies explicit control-flow semantics, we focus on deterministic workflows in which a fixed process model and inputs uniquely determine the executed path. We introduce a specialist workflow for this task and compare it against generalist agents such as Roo and Cline. Our results show that the specialist solution produces agents that outperform generalist baselines by approximately 9-20 percentage points in tool-use exactness, 2-4x in penalty-adjusted latency, and 3x fewer tool-call errors, while reducing generation token cost by over 95% and eliminating repair iterations. We also find that generalist agents generate code inconsistently in both functionality and quality, limiting their suitability for industrial settings where reliability and maintainability are essential.