# FlowAgent: Achieving Compliance and Flexibility for Workflow Agents

arXiv: https://arxiv.org/abs/2502.14345 · HTML: https://mlsanity.com/paper/2502.14345/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 2 of its 33 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

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

## Builds on (most cited first, 2 of 2)

- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases](https://mlsanity.com/paper/2308.11761/) (2023)

## Built on by (most cited first, 19 of 19)

- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [Get Experience from Practice: LLM Agents with Record & Replay](https://mlsanity.com/paper/2505.17716/) (2025)
- [Position: The Real Barrier to LLM Agent Usability is Agentic ROI](https://mlsanity.com/paper/2505.17767/) (2025)
- [CangLing-KnowFlow: A Unified Knowledge-and-Flow-fused Agent for Comprehensive Remote Sensing Applications](https://mlsanity.com/paper/2512.15231/) (2025)
- [Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning](https://mlsanity.com/paper/2602.01983/) (2026)
- [MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning](https://mlsanity.com/paper/2512.23412/) (2025)
- [Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents](https://mlsanity.com/paper/2607.11346/) (2026)
- [Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation](https://mlsanity.com/paper/2602.13574/) (2026)
- [Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language](https://mlsanity.com/paper/2604.19667/) (2026)
- [PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents](https://mlsanity.com/paper/2608.19861/) (2026)
- [Evaluating the Search Agent in a Parallel World](https://mlsanity.com/paper/2603.04751/) (2026)
- [Tools as Continuous Flow for Evolving Agentic Reasoning](https://mlsanity.com/paper/2605.07339/) (2026)
- [COVENANT: Natural-Language Workflow Compilation for Aligned Agent Execution](https://mlsanity.com/paper/2607.25400/) (2026)
- [Vibe AIGC: A New Paradigm for Content Generation via Agentic Orchestration](https://mlsanity.com/paper/2602.04575/) (2026)
- [DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue](https://mlsanity.com/paper/2606.17904/) (2026)
- [Specifying AI-SDLC Processes: A Protocol Language for Human-Agent Boundaries](https://mlsanity.com/paper/2606.20615/) (2026)
- [Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution](https://mlsanity.com/paper/2608.21341/) (2026)
- [How Strongly Should Task State Influence an LLM Agent?](https://mlsanity.com/paper/2609.25686/) (2026)
- [Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection](https://mlsanity.com/paper/2610.18881/) (2026)

## Abstract (arXiv)

The integration of workflows with large language models (LLMs) enables LLM-based agents to execute predefined procedures, enhancing automation in real-world applications. Traditional rule-based methods tend to limit the inherent flexibility of LLMs, as their predefined execution paths restrict the models' action space, particularly when the unexpected, out-of-workflow (OOW) queries are encountered. Conversely, prompt-based methods allow LLMs to fully control the flow, which can lead to diminished enforcement of procedural compliance. To address these challenges, we introduce FlowAgent, a novel agent framework designed to maintain both compliance and flexibility. We propose the Procedure Description Language (PDL), which combines the adaptability of natural language with the precision of code to formulate workflows. Building on PDL, we develop a comprehensive framework that empowers LLMs to manage OOW queries effectively, while keeping the execution path under the supervision of a set of controllers. Additionally, we present a new evaluation methodology to rigorously assess an LLM agent's ability to handle OOW scenarios, going beyond routine flow compliance tested in existing benchmarks. Experiments on three datasets demonstrate that FlowAgent not only adheres to workflows but also effectively manages OOW queries, highlighting its dual strengths in compliance and flexibility. The code is available at https://github.com/Lightblues/FlowAgent.