Beyond Text Editing: Algebraic Manipulation of Source Code

• URL: http://arxiv.org/abs/2607.18742v1
• Date: Tue, 21 Jul 2026 06:05:17 GMT
• Title: Beyond Text Editing: Algebraic Manipulation of Source Code
• Abstract summary: Source code is almost universally edited as plain text.<n>The mismatch between the syntactic and semantic requirements of valid and correct code, and the unconstrained text editing process introduces friction.<n>We propose the novel alternative approach of source code algebra, where the code is modified by applying to it a sequence of logical algebraic operations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Source code is almost universally edited as plain text. However, the mismatch between the syntactic and semantic requirements of valid and correct code, and the unconstrained text editing process trying to produce it, introduces friction that degrades the programming task. It is also increasingly costly in the era of LLM-based coding agents, which must materialize their high-level plan of intended changes as low-level text edits dispersed throughout the codebase, often requiring them to re-read large portions of code. We propose the novel alternative approach of source code algebra, where the codebase is modified by applying to it a sequence of logical algebraic operations. Each operation makes the full set of changes necessary for a single semantic change, analogous to mathematical equation rewriting. We sketch initial properties of such operations - including composition, nullipotency, and commutativity - that distinguish this approach from text editing, and make it well-suited as a substrate for agentic code editing. A feasibility probe with our proof-of-concept implementation (SCAS) suggests that LLM agents can use source code algebra to complete a non-local, cross-file code change with both higher success rates and one to two orders of magnitude fewer tokens, relative to text-based baselines. While preliminary, this is consistent with the hypothesis that having LLMs emit algebraic operations, rather than rewritten code, is a promising direction for code editing - and motivates broader future research into source code algebra, such as comprehensive operator libraries, formal properties, and human-facing tooling.

Related papers

• SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging [49.898541267264115]
  Maintenance is increasingly challenging due to outdated technologies, sparse documentation, and developer retirement.<n>Traditional rule-based transcompilers yield outputs that are difficult to read and maintain.<n>We propose SEDCoT, a novel-to-C translation framework.
  arXiv  Detail & Related papers  (2026-07-05T03:07:10Z)
• What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code [72.9921566968371]
  We revisit the claim that code improves reasoning through controlled pretraining experiments on a 10T-token corpus with fine-grained domain separation.<n>Code substantially improves programming ability but does not act as a general reasoning enhancer.<n>Cross-domain structured reasoning traces, such as code-text and math-text mixtures, are better explained.
  arXiv  Detail & Related papers  (2026-05-19T12:37:01Z)
• TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar [8.34539885321864]
  We show that semantically identical code snippets can be tokenized differently depending on superficial factors such as whitespace or identifier naming.<n>We introduce TokDrift, a framework that applies semantic-preserving rewrite rules to create code variants differing only in tokenization.<n>Our findings identify misaligned tokenization as a hidden obstacle to reliable code understanding and generation.
  arXiv  Detail & Related papers  (2025-10-16T17:59:45Z)
• Exploring Direct Instruction and Summary-Mediated Prompting in LLM-Assisted Code Modification [10.964060011243234]
  This paper presents a study of using large language models (LLMs) in modifying existing code.<n>"prompting" serves as the primary interface for developers to communicate intents to LLMs.<n>This study investigates two prompting strategies for LLM-assisted code modification.
  arXiv  Detail & Related papers  (2025-08-02T23:52:49Z)
• CodeRAG: Supportive Code Retrieval on Bigraph for Real-World Code Generation [69.684886175768]
  Large language models (LLMs) have shown promising performance in automated code generation.<n>In this paper, we propose CodeRAG, a retrieval-augmented code generation framework.<n> Experiments show that CodeRAG achieves significant improvements compared to no RAG scenarios.
  arXiv  Detail & Related papers  (2025-04-14T09:51:23Z)
• CodeCipher: Learning to Obfuscate Source Code Against LLMs [5.872773591957006]
  We propose CodeCipher, a novel method that perturbs privacy from code while preserving the original response from LLMs. CodeCipher transforms the LLM's embedding matrix so that each row corresponds to a different word in the original matrix, forming a token-to-token confusion mapping for obfuscating source code. Results show that our model successfully confuses the privacy in source code while preserving the original LLM's performance.
  arXiv  Detail & Related papers  (2024-10-08T08:28:54Z)
• Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting [78.48355455324688]
  We propose a novel zero-shot synthetic code detector based on the similarity between the original code and its LLM-rewritten variants.<n>Our results demonstrate a significant improvement over existing SOTA synthetic content detectors.
  arXiv  Detail & Related papers  (2024-05-25T08:57:28Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• InstructCoder: Instruction Tuning Large Language Models for Code Editing [26.160498475809266]
  We explore the use of Large Language Models (LLMs) to edit code based on user instructions. InstructCoder is the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing. Our findings reveal that open-source LLMs fine-tuned on InstructCoder can significantly enhance the accuracy of code edits.
  arXiv  Detail & Related papers  (2023-10-31T10:15:35Z)
• Guess & Sketch: Language Model Guided Transpilation [59.02147255276078]
  Learned transpilation offers an alternative to manual re-writing and engineering efforts. Probabilistic neural language models (LMs) produce plausible outputs for every input, but do so at the cost of guaranteed correctness. Guess & Sketch extracts alignment and confidence information from features of the LM then passes it to a symbolic solver to resolve semantic equivalence.
  arXiv  Detail & Related papers  (2023-09-25T15:42:18Z)
• GrACE: Generation using Associated Code Edits [23.643567386291988]
  We endowing pre-trained large language models (LLMs) of code with the knowledge of prior, relevant edits. The generative capability of the LLMs helps address the diversity in code changes and conditioning code generation on prior edits. We evaluate two well-known LLMs, Codex and CodeT5, in zero-shot and fine-tuning settings respectively.
  arXiv  Detail & Related papers  (2023-05-23T14:55:44Z)
• Composable Text Controls in Latent Space with ODEs [97.12426987887021]
  This paper proposes a new efficient approach for composable text operations in the compact latent space of text. By connecting pretrained LMs to the latent space through efficient adaption, we then decode the sampled vectors into desired text sequences. Experiments show that composing those operators within our approach manages to generate or edit high-quality text.
  arXiv  Detail & Related papers  (2022-08-01T06:51:45Z)

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.