# QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL

arXiv: https://arxiv.org/abs/2510.00967 · HTML: https://mlsanity.com/paper/2510.00967/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 60 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 19 of 19)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Ising formulations of many NP problems](https://mlsanity.com/paper/1302.5843/) (2013)
- [Community detection in networks: A user guide](https://mlsanity.com/paper/1608.00163/) (2016)
- [VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use](https://mlsanity.com/paper/2509.01055/) (2025)
- [Challenges and Opportunities in Quantum Optimization](https://mlsanity.com/paper/2312.02279/) (2023)
- [Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Models](https://mlsanity.com/paper/2406.14712/) (2024)
- [Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and Optimization](https://mlsanity.com/paper/2504.11109/) (2025)
- [Meta-Designing Quantum Experiments with Language Models](https://mlsanity.com/paper/2406.02470/) (2024)
- [Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction](https://mlsanity.com/paper/2504.14557/) (2025)
- [QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming](https://mlsanity.com/paper/2508.20134/) (2025)
- [A Practical Quantum Instruction Set Architecture](https://mlsanity.com/paper/1608.03355/) (2016)
- [KetGPT - Dataset Augmentation of Quantum Circuits using Transformers](https://mlsanity.com/paper/2402.13352/) (2024)
- [QAOA-GPT: Efficient Generation of Adaptive and Regular Quantum Approximate Optimization Algorithm Circuits](https://mlsanity.com/paper/2504.16350/) (2025)
- [Graph isomorphism and adiabatic quantum computing](https://mlsanity.com/paper/1304.5773/) (2013)
- [Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant](https://mlsanity.com/paper/2508.20907/) (2025)
- [LLM-Guided Ans"atze Design for Quantum Circuit Born Machines in Financial Generative Modeling](https://mlsanity.com/paper/2509.08385/) (2025)

## Built on by (most cited first, 11 of 11)

- [Towards autonomous quantum physics research using LLM agents with access to intelligent tools](https://mlsanity.com/paper/2511.11752/) (2025)
- [QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation](https://mlsanity.com/paper/2604.08570/) (2026)
- [Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluation](https://mlsanity.com/paper/2605.27210/) (2026)
- [Aligning Quantum Operators with Large Language Models](https://mlsanity.com/paper/2606.13811/) (2026)
- [When Close Enough Is Not Enough: Autoregressive Drift in Quantum Circuit Synthesis](https://mlsanity.com/paper/2607.12780/) (2026)
- [EARL: Efficient Agentic Reinforcement Learning Systems for Large Language Models](https://mlsanity.com/paper/2510.05943/) (2025)
- [Generative AI for Quantum Circuits and Quantum Code: A Technical Review and Taxonomy](https://mlsanity.com/paper/2603.16216/) (2026)
- [QASM-Eval: A Dataset to Train and Evaluate LLMs on OpenQASM-3 Beyond Quantum Circuits](https://mlsanity.com/paper/2605.30358/) (2026)
- [Fine-Tuning Large Language Models for Quantum Reasoning](https://mlsanity.com/paper/2606.21974/) (2026)
- [Leveraging LLM-Based Agentic Systems to Generate Quantum Applications for Test Optimization](https://mlsanity.com/paper/2607.00939/) (2026)
- [AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits](https://mlsanity.com/paper/2609.33192/) (2026)

## Abstract (arXiv)

Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the circuits. (ii) LLMs often generate low-quality or incorrect quantum circuits due to the lack of quantum domain-specific knowledge. We propose QUASAR, an agentic reinforcement learning (RL) framework for quantum circuits generation and optimization based on tool-augmented LLMs. To align the LLM with quantum-specific knowledge and improve the generated quantum circuits, QUASAR designs (i) a quantum circuit verification approach with external quantum simulators and (ii) a sophisticated hierarchical reward mechanism in RL training. Extensive evaluation shows improvements in both syntax and semantic performance of the generated quantum circuits. When augmenting a 4B LLM, QUASAR has achieved the validity of 99.31% in Pass@1 and 100% in Pass@10, outperforming industrial LLMs of GPT-4o, GPT-5 and DeepSeek-V3 and several supervised-fine-tuning (SFT)-only and RL-only baselines.