# Grounded Normative Rule Generation with Structured Search

arXiv: https://arxiv.org/abs/2608.22229 · HTML: https://mlsanity.com/paper/2608.22229/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [DART: Open-Domain Structured Data Record to Text Generation](https://mlsanity.com/paper/2007.02871/) (2020)
- [Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models](https://mlsanity.com/paper/2408.02442/) (2024)
- [A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering](https://mlsanity.com/paper/2005.05257/) (2020)
- [Emergence of Social Norms in Generative Agent Societies: Principles and Architecture](https://mlsanity.com/paper/2403.08251/) (2024)
- [Learning to Generate Structured Output with Schema Reinforcement Learning](https://mlsanity.com/paper/2502.18878/) (2025)
- [RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios](https://mlsanity.com/paper/2412.08972/) (2024)
- [AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making](https://mlsanity.com/paper/2411.03865/) (2024)
- [SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning](https://mlsanity.com/paper/2506.05425/) (2025)
- [Enhancing LLM-Based Social Bot via an Adversarial Learning Framework](https://mlsanity.com/paper/2508.17711/) (2025)
- [Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games](https://mlsanity.com/paper/2410.07863/) (2024)
- [Social World Model-Augmented Mechanism Design Policy Learning](https://mlsanity.com/paper/2510.19270/) (2025)
- [InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding](https://mlsanity.com/paper/2509.16534/) (2025)

## Abstract (arXiv)

Normative rules like institutional charters and workplace policies must be both human-readable and operationally verifiable against actual environment records. However, current language generation and structured-output benchmarks primarily reward surface fluency or schema compliance, leaving operational grounding weakly tested. This creates a critical vulnerability where standard language models generate plausible-sounding policies that fail during enforcement because they rely on unavailable data logs or misaligned scopes. To address this challenge, we formalize the problem as Grounded Normative Rule Synthesis (GNRS) and introduce GNRS-Search, a framework that utilizes Markov Chain Monte Carlo (MCMC) sampling to optimize a discrete, five-slot And-Or Graph (AOG). By explicitly decoupling intermediate operational structure from final prose generation, this method isolates executable feasibility from writing style and allows rule failures to be localized prior to surface realization. We evaluate our approach on GNRS-Bench, a benchmark spanning 116 controlled goals across eight scene families, and RealCharter-Bench, which evaluates transfer to 53 real-derived policy tasks with hidden source clauses. GNRS-Search raises average rubric quality from 68.8% to 81.0% and ranks first under a disclosed executable composite metric, while systematic slot interventions confirm that performance gains stem from robust operational logic rather than rhetorical tuning. Ultimately, by transforming automated rule drafting into an inspectable search problem, this work provides a foundational paradigm for deploying verifiable and compliance-ready personal agents within regulated environments.