Grounded Normative Rule Generation with Structured Search

2026-08-23

AI Summary

为解决规范性规则生成中的操作可行性问题，提出GNRS-Search框架，利用MCMC采样优化And-Or图，提高规则的可执行性和合规性。

Abstract

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.

Problem

• normative rules
• operational grounding
• language generation
• executable feasibility
• policy enforcement

Innovation

• Grounded Normative Rule Synthesis (GNRS)
• Markov Chain Monte Carlo (MCMC) sampling
• And-Or Graph (AOG)
• executable feasibility