---
title: "Agentic Business Process Management: A Research Manifesto"
type: source
tags: [apm, bpm, agentic-ai, multi-agent-systems, manifesto]
authors: [Calvanese Diego; Casciani Angelo; De Giacomo Giuseppe; Dumas Marlon; Fournier Fabiana; Kampik Timotheus; La Malfa Emanuele; Limonad Lior; Marrella Andrea; Metzger Andreas; Montali Marco; Amyot Daniel; Fettke Peter; Polyvyanyy Artem; Rinderle-Ma Stefanie; Sardiña Sebastian; Tax Niek; Weber Barbara]
year: 2026
venue: "arXiv:2603.18916v1 [cs.AI]"
kind: paper
raw_path: "raw/Agentic_Business_Process_Management_A_Research_Man.pdf"
created: 2026-04-13
updated: 2026-04-13
key_claims:
  - APM extends BPM to govern autonomous agents as first-class functional entities.
  - Autonomy is enabled — not eliminated — through a framing mechanism that enforces process awareness.
  - Four core agent capabilities are required in APM systems, in order of precedence — framed autonomy, explainability, conversational actionability, self-modification.
  - Frames are normative (deontic constraints); classical BPMN/DECLARE specifications are operational and therefore distinct from APM frames.
  - Self-modification distinguishes short-term adaptation (instance-specific) from long-term evolution (shared across executions).
  - APM positions itself as successor to the Process Mining Manifesto (2012) and complement to AI-Augmented BPMS (2023).
  - LLMs alone are insufficient for intelligent BPM; symbolic frames remain essential.
---

# Agentic Business Process Management: A Research Manifesto

Manifesto paper authored by 18 researchers from the BPM, multi-agent systems, and AI communities, derived from **Dagstuhl Seminar #25192 "AUTOBIZ"** and the **PMAI'25 workshop at ECAI 2025**. It articulates the conceptual foundations of *Agentic Business Process Management* (APM) — an extension of [[concepts/agentic-bpm|BPM for governing autonomous agents]].

## Summary

The manifesto argues that classical BPM/RPA systems assume predefined workflows executed by passive software components, but the emergence of LLM-based agents demands a new paradigm where **software and human agents act as primary functional entities** that perceive, reason, and act within explicit *process frames*. This shift is characterised not by eliminating control but by **[[concepts/framed-autonomy|framing it]]**: agents retain autonomy yet remain aligned with organisational goals through normative constraints.

The paper introduces a two-level conceptual architecture:

- **Macro level (APM System):** the socio-technical environment hosting interoperating agents, tools, and protocols (MCP, ACP, RDF, KQML), where a **framing mechanism** imposes process-awareness and goal-alignment on agents.
- **Micro level (APM Agent):** individual agents running a **[[concepts/perceive-reason-act|Perceive–Reason–Act]]** loop with three conceptual modules (perception, reasoning, action), drawing on foundational ontologies ([[frameworks/dolce-gfo|DOLCE, GFO]]), agent-oriented modelling ([[frameworks/tropos-i-star|i*, Tropos]]), and classical AI constructs ([[frameworks/bdi-agents|BDI]], [[frameworks/fipa|FIPA]]).

Four capabilities are required of an APM agent, ordered intentionally:

1. **[[concepts/framed-autonomy|Framing]]** — internalising normative frames so the agent is process-aware and guard-railed.
2. **[[concepts/explainability-apm|Explainability]]** — articulating the rationale behind decisions; a prerequisite for trust, debugging, and regulatory compliance (GDPR, EU AI Act).
3. **[[concepts/conversational-actionability|Conversational Actionability]]** — interacting with humans and other agents via natural language or formal protocols, and mapping conversations to four enactment roles (Query / Recommend / Create / Execute).
4. **[[concepts/self-modification|Self-Modification]]** — adapting (short-term, instance-specific) and evolving (long-term, model-level) based on experience.

A research agenda enumerates **19 named challenges** across these capabilities (F1–F4, X1–X5, A1–A5, M1–M5) plus **5 cross-cutting challenges** (C1–C5): legacy onboarding via agent-centric process mining, security and prompt-injection risk, benchmark contamination, liability under the EU AI Act, and engineering methods.

## Framing distinctions introduced
- **Normative frame** vs **operational frame.** Normative frames specify deontic requirements (obligations, permissions, prohibitions); operational frames (BPMN, DECLARE) specify *how* to act. APM treats the normative as first-class.
- **Autonomy** ≠ **automation.** Automation executes predefined tasks exactly; autonomy perceives, reasons, and chooses within a frame.
- **Adaptation** (ephemeral, instance-level) vs **evolution** (persistent, model-level) — see [[concepts/self-modification]].
- **Centralised** vs **distributed** intelligence — affects where frames are placed (on process vs on individual decision-makers).

## Positioning
- Successor-in-spirit to the [[sources/2012-vanderaalst-process-mining-manifesto|Process Mining Manifesto (2012)]].
- Makes agent-centricity explicit where the [[sources/2023-dumas-ai-augmented-bpms|AI-Augmented BPMS manifesto (2023)]] left it implicit.
- Complements [[sources/2024-kampik-large-process-models|Large Process Models (2024)]] while asserting LLMs alone are insufficient.
- Parallels the four-level analytics pyramid of [[sources/2023-chapela-campa-augmented-process-execution|Chapela-Campa & Dumas (2023)]].

## Connections

**Concepts:** [[concepts/agentic-bpm]], [[concepts/framed-autonomy]], [[concepts/process-awareness]], [[concepts/explainability-apm]], [[concepts/conversational-actionability]], [[concepts/self-modification]], [[concepts/perceive-reason-act]]

**Authors (entities):** [[entities/diego-calvanese]], [[entities/angelo-casciani]], [[entities/giuseppe-de-giacomo]], [[entities/marlon-dumas]], [[entities/fabiana-fournier]], [[entities/timotheus-kampik]], [[entities/emanuele-la-malfa]], [[entities/lior-limonad]], [[entities/andrea-marrella]], [[entities/andreas-metzger]], [[entities/marco-montali]], [[entities/daniel-amyot]], [[entities/peter-fettke]], [[entities/artem-polyvyanyy]], [[entities/stefanie-rinderle-ma]], [[entities/sebastian-sardina]], [[entities/niek-tax]], [[entities/barbara-weber]]

**Frameworks/methods:** [[frameworks/bdi-agents]], [[frameworks/fipa]], [[frameworks/tropos-i-star]], [[methods/agent-oriented-process-mining]]

**Related sources (stubs):** [[sources/2023-dumas-ai-augmented-bpms]], [[sources/2012-vanderaalst-process-mining-manifesto]], [[sources/2024-kampik-large-process-models]], [[sources/2023-chapela-campa-augmented-process-execution]]

## Open questions raised by the source
- How to operationalise frames on real-world symbolic data (F3)
- How to design incentive mechanisms that make frame-compliance intrinsically valuable to agents (F4)
- How to balance autonomy / delegation / control at the KPI level (A4–A5)
- Benchmark contamination risk (C3) — a methodological warning relevant to any future PPM evaluation work.