Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents

• URL: http://arxiv.org/abs/2603.17150v1
• Date: Tue, 17 Mar 2026 21:28:59 GMT
• Title: Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents
• Abstract summary: Agentic AI systems can now generate code with remarkable fluency.<n>But a fundamental question remains: emphdoes the generated code actually do what the user intended?
• Score: 7.228124845671868
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic AI systems can now generate code with remarkable fluency, but a fundamental question remains: \emph{does the generated code actually do what the user intended?} The gap between informal natural language requirements and precise program behavior -- the \emph{intent gap} -- has always plagued software engineering, but AI-generated code amplifies it to an unprecedented scale. This article argues that \textbf{intent formalization} -- the translation of informal user intent into a set of checkable formal specifications -- is the key challenge that will determine whether AI makes software more reliable or merely more abundant. Intent formalization offers a tradeoff spectrum suitable to the reliability needs of different contexts: from lightweight tests that disambiguate likely misinterpretations, through full functional specifications for formal verification, to domain-specific languages from which correct code is synthesized automatically. The central bottleneck is \emph{validating specifications}: since there is no oracle for specification correctness other than the user, we need semi-automated metrics that can assess specification quality with or without code, through lightweight user interaction and proxy artifacts such as tests. We survey early research that demonstrates the \emph{potential} of this approach: interactive test-driven formalization that improves program correctness, AI-generated postconditions that catch real-world bugs missed by prior methods, and end-to-end verified pipelines that produce provably correct code from informal specifications. We outline the open research challenges -- scaling beyond benchmarks, achieving compositionality over changes, metrics for validating specifications, handling rich logics, designing human-AI specification interactions -- that define a research agenda spanning AI, programming languages, formal methods, and human-computer interaction.

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)
• SkillForge: Compositional Skill Synthesis with Verification-in-the-Loop for Generating Formally Verified Dafny Programs [10.916179875278326]
  We introduce SKILLFORGE, a framework that decomposes formal code synthesis into a library of atomic, reusable skills.<n>A verification-driven harness orchestrates these skills.<n>On a curated benchmark of natural language to Dafny specification pairs, SKILLFORGE substantially outperforms both state-of-the-art agentic approaches.
  arXiv  Detail & Related papers  (2026-08-30T15:15:00Z)
• ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation [54.788849448970154]
  We introduce ClarifyCodeBench, a novel interactive benchmark for evaluating Large Language Models' capability in resolving requirement ambiguity.<n>We conduct a systematic evaluation of six state-of-the-art LLMs using ClarifyCodeBench.<n>Our empirical results yield three critical insights: 1) Capability Decoupling: Strong code generation performance does not inherently translate to effective requirement clarification; 2) The Reasoning Paradox: While increased computational thinking enhances code correctness, it yields marginal gains in identifying ambiguities.
  arXiv  Detail & Related papers  (2026-07-01T09:58:59Z)
• VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents [57.240036084348354]
  We introduce VASO, a framework for verification-guided self-evolution of robot skill contracts.<n>VASO verifies logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications.<n>On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples.
  arXiv  Detail & Related papers  (2026-06-03T20:02:35Z)
• Enhancing Formal Software Specification with Artificial Intelligence [1.4217721366366873]
  Formal software specification is known to enable early error detection and explicit invariants.<n>It has seen limited industrial adoption due to its high notation overhead and the expertise required to use traditional formal languages.<n>Recent advances in artificial intelligence make it possible to retain many of the benefits of formal specification while substantially reducing these costs.
  arXiv  Detail & Related papers  (2026-01-11T13:53:22Z)
• Autoformalizer with Tool Feedback [52.334957386319864]
  Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements.<n>Existing formalizer still struggles to consistently generate valid statements that meet syntactic validity and semantic consistency.<n>We propose the Autoformalizer with Tool Feedback (ATF), a novel approach that incorporates syntactic and consistency information as tools into the formalization process.
  arXiv  Detail & Related papers  (2025-10-08T10:25:12Z)
• Position: Intelligent Coding Systems Should Write Programs with Justifications [9.304020701255093]
  We argue that these systems should not only generate code but also produce clear, consistent justifications that bridge model reasoning and user understanding.<n>We advocate exploring neuro-symbolic approaches for justification generation, where symbolic constraints guide behavior during training and program semantics are enriched through neural representations.
  arXiv  Detail & Related papers  (2025-08-08T05:04:47Z)
• Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny [78.1575956773948]
  Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification processes are neither reliable nor scalable.<n>A promising yet largely uncharted alternative is formal language-based reasoning.<n>Grounding LLMs in rigorous formal systems where generative models operate in formal language spaces (e.g., Dafny) enables the automatic and mathematically provable verification of their reasoning processes and outcomes.
  arXiv  Detail & Related papers  (2025-07-22T08:13:01Z)
• Leveraging LLMs for Formal Software Requirements -- Challenges and Prospects [0.0]
  VERIFAI1 aims to investigate automated and semi-automated approaches to bridge this gap.<n>This position paper presents a preliminary synthesis of relevant literature to identify recurring challenges and prospective research directions.
  arXiv  Detail & Related papers  (2025-07-18T19:15:50Z)
• Evaluating LLM-driven User-Intent Formalization for Verification-Aware Languages [6.0608817611709735]
  We propose a metric for evaluating the quality of specifications for verification-aware languages. We show that our metric agrees closely on a human-labeled dataset of Dafny specifications for the popular MBPP code-generation benchmark. We also outline formal verification challenges that need to be addressed to apply the technique more widely.
  arXiv  Detail & Related papers  (2024-06-14T06:52:08Z)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)
• Interactive Code Generation via Test-Driven User-Intent Formalization [60.90035204567797]
  Large language models (LLMs) produce code from informal natural language (NL) intent. It is hard to define a notion of correctness since natural language can be ambiguous and lacks a formal semantics. We describe a language-agnostic abstract algorithm and a concrete implementation TiCoder.
  arXiv  Detail & Related papers  (2022-08-11T17:41:08Z)

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.