# SPARC: Scenario Planning and Reasoning for Automated C Unit Test Generation

arXiv: https://arxiv.org/abs/2602.16671 · HTML: https://mlsanity.com/paper/2602.16671/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 17 of 17)

- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023)
- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation](https://mlsanity.com/paper/2305.04207/) (2023)
- [Automated Unit Test Improvement using Large Language Models at Meta](https://mlsanity.com/paper/2402.09171/) (2024)
- [TestART: Improving LLM-based Unit Testing via Co-evolution of Automated Generation and Repair Iteration](https://mlsanity.com/paper/2408.03095/) (2024)
- [LLM Test Generation via Iterative Hybrid Program Analysis](https://mlsanity.com/paper/2503.13580/) (2025)
- [Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation](https://mlsanity.com/paper/2501.10200/) (2025)
- [ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.02330/) (2025)
- [Translating Large-Scale C Repositories to Idiomatic Rust](https://mlsanity.com/paper/2511.20617/) (2025)
- [REACCEPT: Automated Co-evolution of Production and Test Code Based on Dynamic Validation and Large Language Models](https://mlsanity.com/paper/2411.11033/) (2024)
- [CITYWALK: Enhancing LLM-Based C++ Unit Test Generation via Project-Dependency Awareness and Language-Specific Knowledge](https://mlsanity.com/paper/2501.16155/) (2025)
- [Knowledge Matters: Injecting Project and Testing Knowledge into LLM-based Unit Test Generation](https://mlsanity.com/paper/2511.14224/) (2025)
- [Mull it over: mutation testing based on LLVM](https://mlsanity.com/paper/1908.01540/) (2019)
- [Large Language Models for Unit Test Generation: Achievements, Challenges, and Opportunities](https://mlsanity.com/paper/2511.21382/) (2025)
- [Automated Test Suite Enhancement Using Large Language Models with Few-shot Prompting](https://mlsanity.com/paper/2602.12256/) (2026)
- [ATLAS: Multi-View Code Representation Tool for C and C++ Source Programs](https://mlsanity.com/paper/2512.12507/) (2025)

## Abstract (arXiv)

Automated unit test generation for C remains a formidable challenge due to the semantic gap between high-level program intent and the rigid syntactic constraints of pointer arithmetic and manual memory management. While Large Language Models (LLMs) exhibit strong generative capabilities, direct intent-to-code synthesis frequently suffers from the leap-to-code failure mode, where models prematurely emit code without grounding in program structure, constraints, and semantics. This will result in non-compilable tests, hallucinated function signatures, low branch coverage, and semantically irrelevant assertions that cannot properly capture bugs. We introduce SPARC, a neuro-symbolic, scenario-based framework that bridges this gap through four stages: (1) Control Flow Graph (CFG) analysis, (2) an Operation Map that grounds LLM reasoning in validated utility helpers, (3) Path-targeted test synthesis, and (4) an iterative, self-correction validation loop using compiler and runtime feedback. We evaluate SPARC on 59 real-world and algorithmic subjects, where it outperforms the vanilla prompt generation baseline by 31.36% in line coverage, 26.01% in branch coverage, and 20.78% in mutation score, matching or exceeding the symbolic execution tool KLEE on complex subjects. SPARC retains 94.3% of tests through iterative repair and produces code with significantly higher developer-rated readability and maintainability. By aligning LLM reasoning with program structure, SPARC provides a scalable path for industrial-grade testing of legacy C codebases.