---
title: "Toward Self-Modifying Autonomous Business Process Systems"
type: source
tags: [abps, agentic-bpm, self-modification, adaptation, evolution, mape-k, autonomy-levels]
authors: [Elyasaf, Achiya; Metzger, Andreas; Sardina, Sebastian; Senderovich, Arik; Serral Asensio, Estefania; Tax, Niek]
year: 2025
venue: "PMAI'25: 4th International Workshop on Process Management in the AI Era, co-located with ECAI 2025, Bologna"
kind: paper
raw_path: "raw/ABPS/Self-modifying autonomous business process systems.pdf"
sources: []
key_claims:
  - "Autonomous Business Process Systems (ABPSs) are systems that operate with minimal human intervention while modifying their own structure and behavior over time."
  - "Self-modification has two principal types: adaptation (short-term, instance-specific, no model change) vs evolution (long-term, model-level, affects future instances)."
  - "Adaptation maps naturally onto the MAPE-K self-adaptation loop (Monitor–Analyze–Plan–Execute over a shared Knowledge base)."
  - "Five dimensions classify ABPS modifications: D1 adaptation vs evolution; D2 task/flow/process granularity; D3 reactive vs proactive; D4 human-driven vs autonomous; D5 planned vs emergent."
  - "Proposes a three-level autonomy roadmap inspired by SAE J3016: Level 1 Process Assistance, Level 2 Partial Autonomy, Level 3 Contextual Autonomy. Level 3 corresponds to agentic BPM."
  - "Most current BPM systems sit at Level 1–2; ABPSs must reach Level 3, which requires self-modifying capabilities: concept-drift detection, adaptation/evolution decision, strategy selection, generalization, and explainable communication."
  - "Three core research challenges: (1) governance, oversight, and human interaction (learning-to-defer, XAI, multi-objective optimization); (2) continual learning and adaptation management (feedback loops, bounded knowledge representations); (3) modeling and measuring aleatoric vs epistemic uncertainty."
  - "Running example: automated warehouse where robot rerouting (adaptation) and a preventive maintenance rule after 900 operations (evolution) illustrate the spectrum."
  - "Derived from AutoBiz Dagstuhl seminar 25192."
created: 2026-04-15
updated: 2026-04-15
---

# Toward Self-Modifying Autonomous Business Process Systems

## Summary
Elyasaf et al. present the conceptual groundwork for **self-modifying Autonomous Business Process Systems (ABPSs)** — systems that change their own structure/behavior with minimal human intervention. The paper is explicitly positioned as output from the AutoBiz Dagstuhl Seminar 25192 working group on self-modification, complementary to the group outputs on framed autonomy, conversational actionability, and explainability.

The authors adopt the **adaptation vs evolution** distinction: adaptation is short-term and instance-specific (rerouting one order around a malfunctioning robot), evolution is long-term and model-level (introducing a preventive maintenance rule after patterns emerge over thousands of picks). They ground adaptation in the software-engineering **MAPE-K** self-adaptation loop (Monitor, Analyze, Plan, Execute, over a Knowledge base) and evolution in software-evolution literature.

They organize the problem space across **five dimensions**: (D1) adaptation vs evolution; (D2) task / control-flow / process granularity; (D3) reactive vs proactive (where proactive draws on [[concepts/predictive-process-monitoring|predictive]] and prescriptive monitoring); (D4) human-driven vs autonomous; (D5) planned vs emergent (bottom-up learning).

A key contribution is the **autonomy-level roadmap** adapted from SAE J3016: Level 0 No Automation, Level 1 Process Assistance (recommendations, anomaly flags), Level 2 Partial Autonomy (bounded automation), Level 3 Contextual Autonomy (autonomous orchestration with human fallback only in edge cases). Level 3 aligns with agentic BPM. Table 1 cross-multiplies levels by modification object (task/flow/process) to sketch capability requirements per cell.

Section 5 elaborates three core research challenges: **Governance, Oversight, and Human Interaction** (learning-to-defer, XAI-based justification, multi-objective optimization over performance/cost/compliance/satisfaction, LLM-as-a-judge for quality assurance); **Continual Learning and Adaptation Management** (closed-loop recording of adaptation effectiveness, safe generalization, bounded knowledge representations for long-running processes); and **Modeling and Measuring Uncertainty** (separating aleatoric randomness from epistemic lack-of-knowledge, Bayesian/fuzzy representations, explainable uncertainty communication).

## Connections
- Deepens [[concepts/self-modification]] with the 5D classification and autonomy-level roadmap; the adaptation/evolution distinction matches the APM manifesto ([[sources/2026-calvanese-agentic-bpm-manifesto]]).
- New concept: [[concepts/abps-autonomy-levels]] (SAE-inspired three-level roadmap).
- New concept: [[concepts/mape-k-loop]] (self-adaptation canonical loop) — cross-refs software engineering.
- New concept: [[concepts/aleatoric-vs-epistemic-uncertainty]].
- New entities: [[entities/achiya-elyasaf]], [[entities/estefania-serral-asensio]].
- Existing entities updated: [[entities/andreas-metzger]], [[entities/sebastian-sardina]], [[entities/arik-senderovich]], [[entities/niek-tax]].
- Relates to [[concepts/predictive-process-monitoring]] and prescriptive monitoring (Metzger et al.; Bozorgi/Dumas/La Rosa/Polyvyanyy 2023).
- Complements [[concepts/framed-autonomy]] and [[concepts/explainability-apm]] as sibling AutoBiz outputs.
- Complements [[sources/2025-fournier-agentic-ai-process-observability]] — observability is an input to the MAPE-K Monitor/Analyze phases.