# Neurosymbolic Repair for Low-Code Formula Languages

arXiv: https://arxiv.org/abs/2207.11765 · HTML: https://mlsanity.com/paper/2207.11765/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 76 references that are in the map.
- First posted on arXiv 24 Jul 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Semi-supervised Sequence Learning](https://mlsanity.com/paper/1511.01432/) (2015)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)
- [RobustFill: Neural Program Learning under Noisy I/O](https://mlsanity.com/paper/1703.07469/) (2017)
- [Graph-based, Self-Supervised Program Repair from Diagnostic Feedback](https://mlsanity.com/paper/2005.10636/) (2020)
- [Learning to Infer Graphics Programs from Hand-Drawn Images](https://mlsanity.com/paper/1707.09627/) (2017)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [Getafix: Learning to Fix Bugs Automatically](https://mlsanity.com/paper/1902.06111/) (2019)
- [Neural Program Repair by Jointly Learning to Localize and Repair](https://mlsanity.com/paper/1904.01720/) (2019)
- [Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples](https://mlsanity.com/paper/1804.01186/) (2018)
- [Learning to Complete Code with Sketches](https://mlsanity.com/paper/2106.10158/) (2021)
- [Learning Syntactic Program Transformations from Examples](https://mlsanity.com/paper/1608.09000/) (2016)
- [Multi-modal Program Inference: a Marriage of Pre-trainedLanguage Models and Component-based Synthesis](https://mlsanity.com/paper/2109.02445/) (2021)
- [Don't Panic! Better, Fewer, Syntax Errors for LR Parsers](https://mlsanity.com/paper/1804.07133/) (2018)
- [Learning the Relation between Code Features and Code Transforms with Structured Prediction](https://mlsanity.com/paper/1907.09282/) (2019)
- [An error correcting parser for context free grammars that takes less than cubic time](https://mlsanity.com/paper/1406.3405/) (2014)

## Built on by (most cited first, 12 of 12)

- [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://mlsanity.com/paper/2208.11640/) (2022)
- [A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification](https://mlsanity.com/paper/2305.14752/) (2023)
- [Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models](https://mlsanity.com/paper/2302.04662/) (2023)
- [Fully Autonomous Programming with Large Language Models](https://mlsanity.com/paper/2304.10423/) (2023)
- [FLAME: A small language model for spreadsheet formulas](https://mlsanity.com/paper/2301.13779/) (2023)
- [Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback](https://mlsanity.com/paper/2507.18755/) (2025)
- [Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models](https://mlsanity.com/paper/2503.07693/) (2025)
- [Diffusion is a code repair operator and generator](https://mlsanity.com/paper/2508.11110/) (2025)
- [Agent-Driven Automatic Software Improvement](https://mlsanity.com/paper/2406.16739/) (2024)
- [Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments](https://mlsanity.com/paper/2404.01754/) (2024)
- [Benchmark Dataset Generation and Evaluation for Excel Formula Repair with LLMs](https://mlsanity.com/paper/2508.11715/) (2025)
- [LIFT: Last-Mile Fine-Tuning for Table Explicitation](https://mlsanity.com/paper/2605.13424/) (2026)

## Abstract (arXiv)

Most users of low-code platforms, such as Excel and PowerApps, write programs in domain-specific formula languages to carry out nontrivial tasks. Often users can write most of the program they want, but introduce small mistakes that yield broken formulas. These mistakes, which can be both syntactic and semantic, are hard for low-code users to identify and fix, even though they can be resolved with just a few edits. We formalize the problem of producing such edits as the last-mile repair problem. To address this problem, we developed LaMirage, a LAst-MIle RepAir-engine GEnerator that combines symbolic and neural techniques to perform last-mile repair in low-code formula languages. LaMirage takes a grammar and a set of domain-specific constraints/rules, which jointly approximate the target language, and uses these to generate a repair engine that can fix formulas in that language. To tackle the challenges of localizing the errors and ranking the candidate repairs, LaMirage leverages neural techniques, whereas it relies on symbolic methods to generate candidate repairs. This combination allows LaMirage to find repairs that satisfy the provided grammar and constraints, and then pick the most natural repair. We compare LaMirage to state-of-the-art neural and symbolic approaches on 400 real Excel and PowerFx formulas, where LaMirage outperforms all baselines. We release these benchmarks to encourage subsequent work in low-code domains.