Governed Metaprogramming for Intelligent Systems: Reclassifying Eval as a Governed Effect

• URL: http://arxiv.org/abs/2605.05248v2
• Date: Mon, 11 May 2026 09:24:46 GMT
• Title: Governed Metaprogramming for Intelligent Systems: Reclassifying Eval as a Governed Effect
• Abstract summary: We present governed metaprogramming, a language design where programrepresentations are first-class values.<n>We prove three properties: purity of form manipulation, the no-bypass theorem, and boundary preservation.<n>The central contribution is reclassifying eval from a language primitive into a governed effect.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: AI systems increasingly synthesize executable structure at runtime: LLMs generate programs, agents construct workflows,self-improving systems modify their own behavior. In classical homoiconic and staged languages, the transition from coderepresentation to execution is unrestricted. eval is a language primitive, not a governed operation. We argue that ingovernedintelligent systems, this transition is an authority amplification: it converts symbolic structure into executableauthority andmust be mediated like any other effect. We present governed metaprogramming, a language design where programrepresentations(machine forms) are first-class values, form manipulation is pure computation, and materialization (the transition fromform toexecutable machine) is a governed effect subject to structural inspection. The governance system analyzes the proposedprogram'scapability requirements, policy compliance, and resource estimates before permitting execution. We formalize twojudgments: pureform evaluation (which emits no directives) and governed materialization (which emits exactly one governed directive). Weprovethree properties: purity of form manipulation, the no-bypass theorem, and boundary preservation. We implement the designinMashinTalk, a DSL for AI workflows compiling to BEAM bytecode, and report on integration with 454 existingmachine-checked Rocqtheorems. The central contribution is reclassifying eval from a language primitive into a governed effect.

Related papers

• The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis [50.473217152006875]
  MIMIC is a framework that leverages executable code as a rigorous medium for reasoning data synthesis.<n>MIMIC transforms algorithms into verifiable reasoning trajectories through narrative fusion, code-guided test synthesis, and dynamic code instrumentation.<n>Our method significantly elevates accuracy across general reasoning, complex mathematical benchmarks, and fine-grained deterministic tasks.
  arXiv  Detail & Related papers  (2026-09-13T17:04:16Z)
• Is Code Better Than Language for Algorithmic Reasoning [58.86873062890482]
  We show that for tool-augmented language models, comparing natural-language reasoning with code-execution pipelines is difficult because the comparison changes both the intermediate representation and the execution mechanism.<n>We separate these factors with an intermediate intervention: the model expresses its reasoning as executable code, and the language model simulates that code in context to produce an answer.<n>We observe that the intermediate intervention is not meaningfully different from natural-language reasoning (+0.15pp)
  arXiv  Detail & Related papers  (2026-06-14T04:17:21Z)
• Syntax-driven Incremental Program Verification of Matching Logic Properties [36.861969535480526]
  We present an approach to the incremental verification of programs written in KernelC.<n>The approach is based on a syntactic-semantic framework that enables analyzing code chunks in isolation.<n>Results show that our approach does not penalize the efficiency of formal verification and can outperform program re-verification after changes.
  arXiv  Detail & Related papers  (2026-06-07T20:32:37Z)
• REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry [0.0]
  Large Language Models (LLMs) enable new forms of agentic automation.<n>We present REGAL, a registry-driven architecture for deterministic grounding of agentic AI systems in enterprise telemetry.
  arXiv  Detail & Related papers  (2026-03-03T14:13:39Z)
• The Auton Agentic AI Framework [5.410458076724158]
  The field of Artificial Intelligence is undergoing a transition from Generative AI to Agentic AI.<n>This transition exposes a fundamental architectural mismatch: Large Language Models (LLMs) produce unstructured outputs, whereas the backend infrastructure they must control requires deterministic, schema-conformant inputs.<n>The present paper describes the Auton Agentic AI Framework, a principled architecture for the creation, creation, and governance of autonomous agent.
  arXiv  Detail & Related papers  (2026-02-27T06:42:08Z)
• Monadic Context Engineering [59.95390010097654]
  This paper introduces Monadic Context Engineering (MCE) to provide a formal foundation for agent design.<n>We demonstrate how Monads enable robust composition, how Applicatives provide a principled structure for parallel execution, and crucially, how Monad Transformers allow for the systematic composition of these capabilities.<n>This layered approach enables developers to construct complex, resilient, and efficient AI agents from simple, independently verifiable components.
  arXiv  Detail & Related papers  (2025-12-27T01:52:06Z)
• The Meta-Prompting Protocol: Orchestrating LLMs via Adversarial Feedback Loops [0.6345523830122167]
  Meta-Prompt Protocol formalizes the orchestration of Large Language Models as a programmable, self-optimizing system.<n>Treating natural language instructions as differentiable variables within a semantic graph and utilizing textual critiques as gradients, this architecture mitigates hallucination and prevents model collapse.
  arXiv  Detail & Related papers  (2025-12-17T03:32:21Z)
• Behavior Trees vs Executable Ontologies: a Comparative Analysis of Robot Control Paradigms [51.56484100374058]
  We compare two approaches to modeling robotic behavior: imperative Behavior Trees (BTs) and declarative Executable Ontologies (EO)<n>BTs structure behavior hierarchically using control-flow, whereas EO represents the domain as a temporal, event-based semantic graph driven by dataflow rules.
  arXiv  Detail & Related papers  (2025-11-19T09:38:01Z)
• Prompt Decorators: A Declarative and Composable Syntax for Reasoning, Formatting, and Control in LLMs [0.0]
  This paper introduces Prompt Decorators, a declarative, composable syntax that governs behavior through compact control tokens.<n>Each decorator modifies a behavioral dimension, such as verbose reasoning style, structure, or tone, without changing task content.<n>It defines a unified syntax, scoping model, and deterministic processing pipeline enabling predictable and auditable behavior composition.
  arXiv  Detail & Related papers  (2025-10-21T17:35:49Z)
• WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding [58.1177179119881]
  We introduce wgrammar, a lightweight decoding engine that integrates domain-aware simplification, constraint decomposition, and mask caching.<n> wgrammar achieves up to 250x speedup over existing systems.
  arXiv  Detail & Related papers  (2025-07-22T17:13:47Z)
• Training Neural Networks as Recognizers of Formal Languages [87.06906286950438]
  We train and evaluate neural networks directly as binary classifiers of strings.<n>We provide results on a variety of languages across the Chomsky hierarchy for three neural architectures.<n>Our contributions will facilitate theoretically sound empirical testing of language recognition claims in future work.
  arXiv  Detail & Related papers  (2024-11-11T16:33:25Z)
• Pre-Trained Language Models for Interactive Decision-Making [72.77825666035203]
  We describe a framework for imitation learning in which goals and observations are represented as a sequence of embeddings. We demonstrate that this framework enables effective generalization across different environments. For test tasks involving novel goals or novel scenes, initializing policies with language models improves task completion rates by 43.6%.
  arXiv  Detail & Related papers  (2022-02-03T18:55:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.