# XML Prompting as Grammar-Constrained Interaction: Fixed-Point Semantics, Convergence Guarantees, and Human-AI Protocols

arXiv: https://arxiv.org/abs/2509.08182 · HTML: https://mlsanity.com/paper/2509.08182/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 57 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [Flexible and Efficient Grammar-Constrained Decoding](https://mlsanity.com/paper/2502.05111/) (2025)
- [Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding](https://mlsanity.com/paper/2310.07075/) (2023)
- [Structure Inducing Pre-Training](https://mlsanity.com/paper/2103.10334/) (2021)
- [Constrained Decoding with Speculative Lookaheads](https://mlsanity.com/paper/2412.10418/) (2024)
- [Fixed-Point Theorems and the Ethics of Radical Transparency: A Logic-First Treatment](https://mlsanity.com/paper/2509.06055/) (2025)

## Built on by (most cited first, 4 of 4)

- [ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation](https://mlsanity.com/paper/2603.25770/) (2026)
- [AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection](https://mlsanity.com/paper/2603.04921/) (2026)
- [PromptPack: Scaling LLM Annotation Agents for Online Recommendation](https://mlsanity.com/paper/2607.20528/) (2026)
- [Attention is Case-Sensitive](https://mlsanity.com/paper/2608.03711/) (2026)

## Abstract (arXiv)

Structured prompting with XML tags has emerged as an effective way to steer large language models (LLMs) toward parseable, schema-adherent outputs in real-world systems. We develop a logic-first treatment of XML prompting that unifies (i) grammar-constrained decoding, (ii) fixed-point semantics over lattices of hierarchical prompts, and (iii) convergent human-AI interaction loops. We formalize a complete lattice of XML trees under a refinement order and prove that monotone prompt-to-prompt operators admit least fixed points (Knaster-Tarski) that characterize steady-state protocols; under a task-aware contraction metric on trees, we further prove Banach-style convergence of iterative guidance. We instantiate these results with context-free grammars (CFGs) for XML schemas and show how constrained decoding guarantees well-formedness while preserving task performance. A set of multi-layer human-AI interaction recipes demonstrates practical deployment patterns, including multi-pass "plan → verify → revise" routines and agentic tool use. We provide mathematically complete proofs and tie our framework to recent advances in grammar-aligned decoding, chain-of-verification, and programmatic prompting.