QuantumMind: Constraint-Grounded Agentic Reasoning for Speedup Analysis in Quantum Computing
Yijing Zuo, Zhe Fu, Zihan Nie, Zhihui Zhu, Haohan Wang
cs.AI, cs.MA
Submitted: 2026-08-07
Updated: 2026-08-11
License: http://creativecommons.org/licenses/by/4.0/
The gist: Identifying a meaningful quantum speedup requires more than matching a classical problem to a familiar quantum primitive: the claim must preserve the task, respect access and output models, expose
Terminology
Abstract
Identifying a meaningful quantum speedup requires more than matching a classical problem to a familiar quantum primitive: the claim must preserve the task, respect access and output models, expose required promises, and remain within a defensible complexity scope. We present QuantumMind, an auditable agentic workflow for generating and conservatively screening quantum-acceleration hypotheses. A fixed sequence of typed, role-specialized actions formalizes the public task, analyzes structure and classical bottlenecks, matches a source-linked registry of quantum primitives and barriers, and constructs a scoped candidate scheme. A deterministic ten-check validator assigns the authoritative verdict; completed states are compiled into a Quantum Acceleration Evidence Graph and passed through a downward-only research screen that cannot strengthen the decision. We evaluate QuantumMind against seven task-adapted prompting and agentic controls on 582 identical open-discovery tasks. Under the frozen Open-Discovery Score (ODS), QuantumMind obtains 53.1 mean ODS, exceeding the strongest baseline by 17.3 points (48.2% relative), and wins 355 of 582 paired tasks against that baseline. It passes the graph audit on 99.8% of tasks, compared with 43.6% for the strongest baseline, and ranks first in all seven task families. The results indicate that typed state transitions and deterministic evidence control contribute beyond fluent generation alone.
Sources
- Quantum Amplitude Amplification and Estimation
- Agents for self-driving laboratories applied to quantum computing
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- A Quantum Algorithm for Finding the Minimum
- QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming
- QuanBench: Benchmarking Quantum Code Generation with Large Language Models
- Automated Hypothesis Validation with Agentic Sequential Falsifications
- AI Agents That Matter
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Quantum walk speedup of backtracking algorithms
- CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
- PaperBench: Evaluating AI's Ability to Replicate AI Research
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers
- Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems