--- title: LLM-Assisted Process Modelling type: concept tags: [llm, bpm, bpmn, process-modelling, generative-ai, conversational-modelling] sources: ["[[sources/2026-licardo-bpmn-assistant]]", "[[sources/2024-kampik-large-process-models]]", "[[sources/2026-calvanese-agentic-bpm-manifesto]]"] created: 2026-05-06 updated: 2026-05-06 --- # LLM-Assisted Process Modelling The use of large language models to **create, edit, refine, or validate** business process models — typically [[frameworks/bpmn|BPMN]], occasionally Petri nets, [[frameworks/declare|DECLARE]] constraints, or process-tree intermediate forms. Distinct from LLM-as-execution-engine work (where an LLM operates *within* a process) and from agentic process mining (where LLMs analyse logs). ## Why this is hard LLMs handle natural language fluently but produce **verbose, error-prone XML** when asked to emit BPMN 2.0 directly: invalid IDs, broken sequence flows, unmatched gateways, missing DI metadata, hallucinated elements. The verbosity also costs latency and tokens. [[sources/2026-licardo-bpmn-assistant|Licardo et al. (2026)]] document a representative failure: DeepSeek V3 reached only 8% editing success when prompted to manipulate BPMN XML directly, vs 50% via a structured intermediate. The complexity is compounded for **editing**: most LLM tools target one-shot generation from a textual description, but real BPM work is iterative — modellers refine, fix, restructure. Iterative XML manipulation amplifies syntax-error compounding. ## Architectural patterns Three architectural patterns are emerging: ### 1. Direct XML generation Prompt the LLM with the BPMN 2.0 spec subset and ask for XML. Brittle for editing, viable for one-shot creation with frontier models (Claude 4.5 Sonnet, GPT-5.1 — see [[sources/2026-licardo-bpmn-assistant|BPMN Assistant evaluation]]). ### 2. Structured intermediate representation LLM emits a constrained format (JSON tree, Python POWL code, abstract syntax tree); a deterministic translator converts to BPMN XML. Reduces output complexity, enables schema validation. Examples in this wiki: - **JSON IR** — [[sources/2026-licardo-bpmn-assistant|BPMN Assistant]]: hierarchical tree with `type`/`id`/`label`/`branches`/`has_join`/`next` fields. - **POWL code** — ProMoAI (Kourani et al. 2024, referenced-not-ingested): LLM generates Python code constructing a Partially-Ordered Workflow Language object. - **Abstract syntax trees** — Nivon et al. 2024 (referenced-not-ingested): three-step pipeline extract→AST→BPMN. ### 3. Atomic editing functions Constrain the edit operation surface to a small fixed set (delete, add, move, redirect, update); the LLM uses function calling to compose atoms. Stronger guarantee of structural integrity. Currently only [[sources/2026-licardo-bpmn-assistant|BPMN Assistant]] in the ingested corpus implements this. ## Validation as a first-class layer The architectural pattern that empirically dominates is **structured IR + schema-validation retry loop**: the validator's error message is fed back to the LLM as a new prompt, allowing iterative self-correction. This is the programmatic guardrail that distinguishes reliable LLM-modelling tools from brittle one-shot prompting. ## Quality dimensions [[sources/2026-licardo-bpmn-assistant|Licardo et al.]]'s survey of competing tools partitions the evaluation problem along these axes: | Tool | Goal | Evaluation focus | |---|---|---| | ProMoAI (Kourani 2024) | NL → model + refinement | Conformance-based model quality | | BPMN-Chatbot (Köpke & Safan 2024) | Efficient NL → BPMN | Correctness + token efficiency + acceptance | | BPMNGen (Hörner 2026) | NL → BPMN + human-centred quality | Semantic alignment + cognitive load + acceptability + comprehension | | BPMN Assistant (Licardo 2026) | Reliable NL → BPMN + edit robustness | GED/RGED structural fidelity + failure rate | No single tool yet covers all dimensions. Production deployment will likely combine structural-correctness validation (BPMN Assistant style) with human-centred usability evaluation (BPMNGen style). ## Positioning vs Large Process Models vision [[sources/2024-kampik-large-process-models|Kampik et al.]]'s LPM vision (§5, §6 Step 1) explicitly identifies *LLM-augmented modelling* as the most feasible near-term capability. LPM frames this work as one capability among many in a fused neuro-symbolic stack, not as a standalone product. Concrete tools like BPMN Assistant are evidence that LPM Step 1 is achievable now. ## Positioning vs APM [[sources/2026-calvanese-agentic-bpm-manifesto|APM Manifesto]] does not centre on LLM-modelling but acknowledges it as one of the LLM-augmented BPM capabilities. APM's contribution is the agent-execution paradigm; LLM-modelling sits in the parallel "modelling and analysis" lane. ## Open challenges 1. **Multi-pool / collaboration diagrams** — current tooling (incl. BPMN Assistant) cannot lay out cross-organisational diagrams reliably. 2. **Real-world enterprise narratives** — public corpora (Friedrich 2011, PET) lack validated gold-standard models. Synthetic descriptions overstate model performance. 3. **Soundness verification** — token-replay conformance ≠ deadlock-freedom; soundness checks ([[concepts/soundness]]) are not yet integrated into LLM-modelling pipelines. 4. **Usability validation** — most evaluations are automated; no comprehensive HCI studies with non-technical analysts. 5. **Multilingual / domain-specific terminology** — performance degrades on non-English process descriptions or domain-heavy terminology. 6. **Integration with [[methods/process-mining-basics|process mining]]** — closing the loop between LLM-generated models and discovered models from event logs is largely unexplored. ## Related concepts [[concepts/agentic-bpm]] · [[concepts/process-discovery]] · [[concepts/process-model-quality]] · [[concepts/soundness]] · [[concepts/declarative-process-modelling]] · [[concepts/conformance-checking]] ## Related frameworks [[frameworks/bpmn]] · [[frameworks/dmn]] · [[frameworks/declare]] ## Related sources - [[sources/2026-licardo-bpmn-assistant]] — BPMN Assistant: JSON IR + atomic function-calling editing - [[sources/2024-kampik-large-process-models]] — LPM vision §5/§6 Step 1 - [[sources/2025-varsani-neuro-symbolic-ai-sap-erp]] — parallel grounding pattern in ERP context - [[syntheses/llm-bpm-reading-list]] — reading list hub - [[syntheses/bpmn-modelling-practical-guide]] — constructive builder's guide; LLM tools should respect this rule set