# AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits

arXiv: https://arxiv.org/abs/2609.33192 · HTML: https://mlsanity.com/paper/2609.33192/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [S*: Test Time Scaling for Code Generation](https://mlsanity.com/paper/2502.14382/) (2025)
- [Execution-Based Evaluation for Open-Domain Code Generation](https://mlsanity.com/paper/2212.10481/) (2022)
- [Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening](https://mlsanity.com/paper/2506.02355/) (2025)
- [DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models](https://mlsanity.com/paper/2410.07331/) (2024)
- [CodeJudge: Evaluating Code Generation with Large Language Models](https://mlsanity.com/paper/2410.02184/) (2024)
- [CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation](https://mlsanity.com/paper/2311.08588/) (2023)
- [Quantum circuit synthesis with diffusion models](https://mlsanity.com/paper/2311.02041/) (2023)
- [EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking](https://mlsanity.com/paper/2502.12466/) (2025)
- [Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and Optimization](https://mlsanity.com/paper/2504.11109/) (2025)
- [QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm Design](https://mlsanity.com/paper/2410.07961/) (2024)
- [Meta-Designing Quantum Experiments with Language Models](https://mlsanity.com/paper/2406.02470/) (2024)
- [QuanBench: Benchmarking Quantum Code Generation with Large Language Models](https://mlsanity.com/paper/2510.16779/) (2025)
- [QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL](https://mlsanity.com/paper/2510.00967/) (2025)
- [QCoder Benchmark: Bridging Language Generation and Quantum Hardware through Simulator-Based Feedback](https://mlsanity.com/paper/2510.26101/) (2025)
- [Quantum Circuit Generation via test-time learning with large language models](https://mlsanity.com/paper/2602.03466/) (2026)
- [Aligning Quantum Operators with Large Language Models](https://mlsanity.com/paper/2606.13811/) (2026)

## Abstract (arXiv)

Scientific code generation can produce executable programs that fail to compute the intended scientific object. We study this problem in language-model synthesis of Clifford circuits, which prepare the stabilizer states used in quantum error correction and admit exact classical verification. In our target-conditioned framework, each target is given as compact signed stabilizer generators, and an exact verifier checks the generated OpenQASM circuits. We supervise models with Aaronson-Gottesman chain-of-thought (AG-CoT) traces checked by the verifier, and continue training on model generations that the verifier accepts. Across two independently trained model families (3B and 7B), AG-CoT supervision multiplies greedy-decode state-equivalence accuracy by four to six times over circuit-only baselines, and verifier-filtered continuation training adds a further consistent gain atop both. A complementary 32B study shows that supervised models achieve near-perfect syntax and Clifford validity while the strongest direct model reaches 6.14% state equivalence per target, rising to over 10% under verifier-guided selection with multiple candidates. These results show that algorithmic trace supervision gives a large, statistically significant gain in both model families and that verifier-filtered continuation adds a further repeated gain. The persistent gap between Clifford validity and state equivalence confirms that exact verification is necessary: a circuit can be syntactically and physically valid yet prepare the wrong quantum state.