Skip to content

From Reading Code to Reading Spec: A Verified Layer for LLM-Driven Codebase Maintenance

Sep 2026 · 0 citations · 21 references
Computer Science

TL;DR

The Provable Representation Of Original Functionality (PROOF) is introduced, which manages codebases indirectly via structured specifications via structured specifications to enable full-lifecycle codebase management strictly through these specifications.

Abstract

The rapid growth of LLM-generated code increases software complexity and the maintenance burden on engineers. While LLMs offer a potential automated alternative, this structural complexity hinders their ability to manage codebases directly. We introduce the Provable Representation Of Original Functionality (PROOF), which manages codebases indirectly via structured specifications. To enable full-lifecycle codebase management strictly through these specifications, PROOF abstracts codebase topology into a hierarchical natural-language representation. To establish absolute trust, the system proves semantic equivalence by reconstructing source code exclusively from this specification. This verified foundation drives maintenance requests, executing code modifications while synchronously updating itself to prevent semantic drift. Experiments on real-world repositories confirm the effectiveness of these specifications.

View source

Similar papers

Book Open access Oct 2026

From Code to Low-Code: An LLM-Driven Pipeline for Lifting Code Clones into Reusable Abstractions

Low-Code Development Platforms (LCDPs) promise substantial efficiency gains by allowing citizen developers to create applications from reusable building blocks instead of manually writing code. Realizing these benefits, however, depends on having such abstractions in the first place. Therefore, a curated library of reu...

Raphael Zefferer, Bernhard Schenkenfelder, Stefan Wagner · 1 citation

From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents

Can coding agents restore software that no longer runs while preserving its underlying methods, and reconstruct industrial software engines from open specifications? Here we introduce ReviveBench, a benchmark with two task families evaluated by hidden verifiers calibrated against native execution environments, establis...

Tian-Yu Liu, Ding-Yuan Dai, Yu-Fan Du et al. · 0 citations
Book Aug 2026

Can Formal Specifications Be Synthesized from Tests Alone?

This approach uses LLMs to infer candidate specifications solely from test code and dynamic execution traces: the LLM observes only the program interface, selected inputs, and corresponding outputs or state changes, while the implementation internals remain hidden.

Tian-Hai Liu, Maximilian Müller, Tobias Hey et al. · 0 citations

E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch

E2E-SWE is introduced, a benchmark for evaluating whether coding agents can build complete, functional software repositories end to end and finds substantial variation in end-to-end repository generation ability, providing strong model differentiation while leaving considerable headroom for future progress.

Hantian Ding, Chloe Bi, Jia-Cheng Zhu et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.