Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

External Quantum Reservoir Guidance for Complex AI-Assistant Tasks

Maksym Husarov

Published Sep 10, 2026• 0 citations
Publisher

Abstract

External Quantum Reservoir Assist is designed to help an AI assistant identify the core of a difficult request and organize a useful response by adding dynamically generated guidance through a REST or MCP integration. This study evaluates final answers from an archived experiment using one response pair from each of 50 synthetic scenario families. Thirty-nine pairs formed the primary complex decision-support group, while eleven provided routine, constraint-challenge, and technical-explanation controls. Within the primary group, reservoir-assisted answers were preferred in 17 cases, baseline answers in 8, with 13 ties and 1 unclear case. The tie-adjusted preference rate was 61.8% (95% family-bootstrap interval: 48.7–73.7%). The clearest descriptive gains were observed in actionability and validation guidance, while major-error flags occurred equally often in both conditions. Assistance increased total token usage by 32.9% and median paired estimated end-to-end time by 7.51 seconds. The results provide directional evidence that external reservoir guidance can improve practical decision support for selected complex AI-assistant tasks, while also demonstrating substantial uncertainty and operational overhead. The study does not establish general response superiority, reduced factual-error rates, or a quantum-specific advantage. The accompanying minimized dataset and executable analysis reproduce the reported statistics and figures without additional model calls.

DOI
10.5281/zenodo.22687314

Related papers

Quantum Reservoir-Assisted Context Orchestration for Large Language Models: A 500-Prompt Paired Evaluation

Maksym Husarov

Large language models increasingly operate within systems that provide retrieved knowledge, policies, tool descriptions, workflow state, and other contextual signals. This work investigates Quantum Reservoir Assist, a pre-generation context-orchestration layer that uses a CUDA-Q-based quantum reservoir process to rank candidate contextual signals and construct dynamic decision-support guidance for an otherwise unchanged downstream language model. We evaluate the complete pipeline using a paired benchmark of 500 production-like prompts across ten categories, including architecture and system design, troubleshooting, multi-constraint reasoning, incident response, agent tool planning, security and reliability, and technical explanation. Both experimental paths use the same downstream LLM and generation settings. Across the benchmark, Quantum Reservoir Assist produced a mean absolute increase of approximately 0.172 in the system’s internal answer-readiness/accuracy proxy. The strongest mean proxy improvements occurred in troubleshooting, ambiguous or underspecified requests, conflicting constraints, security and reliability, and multi-constraint tasks. Reservoir assistance also introduced measurable operational overhead, including increased downstream token usage and substantial preprocessing latency under the CUDA-Q simulation configuration used in this experiment. The results demonstrate systematic effects of quantum-reservoir-assisted pre-generation context orchestration, but do not establish ground-truth answer-accuracy improvement or quantum computational advantage. The study therefore motivates controlled ablations against static guidance and classical context-ranking methods.

•Aug 26, 2026•0 citations

Quantum Reservoirs as External Decision Layers for LLMs: Evidence from RAG and Agentic Systems

Maksym Husarov

I evaluated whether a quantum AI reservoir can improve the decisions produced by retrieval-augmented generation (RAG) and tool-using Agentic workflows. Two complementary experiments used the same five workflow variants: RAG, RAG + QR, Agentic, Agentic + QR, and LLM + QR. Each experiment contained 201 main tasks and three repeats, yielding 6,030 answers overall. The first experiment used synthetic planning scenarios; the second used numerical quantities extracted from quantum-domain books and technical papers. In the designated first repeat, QR increased complete structured success from 75.1% to 90.5% for synthetic RAG and from 27.4% to 52.2% for synthetic Agentic. On real-source tasks, the corresponding rates increased from 46.8% to 57.7% and from 34.3% to 55.7%. Both paired improvements were positive in every repeat of both experiments. LLM + QR achieved 94.0% on synthetic tasks and 54.7% on real-source tasks in the first repeat, exceeding both unassisted baselines in each experiment. The results support the integrated reservoir-guidance module as a useful addition to the evaluated decision workflows and motivate a simpler single-call architecture when all required evidence is available. The study evaluates a simulator-backed quantum/classical module; it does not establish quantum computational advantage or isolate the quantum component from its classical guidance components.

•Sep 20, 2026•0 citations

Beyond QAOA: A Review of AI and Quantum Computing for Adaptive Combinatorial Optimization

Hoong Chuin Lau

Near-term quantum approaches to combinatorial optimization are limited by qubit counts, circuit fidelity, sampling cost, and the difficulty of encoding constraints, while machine learning is increasingly used to configure and control quantum optimization workflows. We call such workflows adaptive: decisions conventionally fixed in advance, from formulation and penalties to shot budgets, backends, and whether to invoke a quantum processor at all, are made by learned policies that respond to the instance, the progress of the solve, or the hardware. This review examines three paradigms, AI for quantum optimization, quantum for AI-driven optimization, and AI-quantum co-optimization, and organizes the literature by the decision being learned rather than by application. A structured search identified a 119-paper corpus, of which 67 papers form an evidence core coded in detail. The evidence is considerably stronger for AI-assisted quantum optimization than for the reverse direction: learning already reduces quantum evaluations, improves initialization, supports decomposition and penalty control, and mitigates noise, whereas evidence that quantum computation improves learned optimizers remains largely confined to small-scale simulation. Experimental controls are thin: of 52 studies in the three paradigms, 22 include no classical baseline, the quantum contribution is fully isolated in 10 of 24 where an ablation applies, and the median largest experiment uses 16 qubits. We introduce an M0-M5 evidence hierarchy, from simulation to practical quantum advantage, and find no broadly convincing result at the highest level. We argue that scaling is increasingly a systems problem: the question is not only whether a problem fits on a quantum processor, but how classical and quantum resources should be allocated across the optimization process.

quant-pharXiv:2610.11759•Oct 9, 2026•1 citation

Quantum AI Reservoirs with Optional Graph Context across LLM, RAG and Agentic Workflows

Maksym Husarov

This study evaluates an external simulator-backed quantum/classical guidance component with optional graph context across direct LLM advice, retrieval-augmented generation (RAG), and tool-using Agentic workflows. Three conditions are compared: Baseline, QR only, and QR + graph. The RAG and Agentic evaluation comprises 17 tasks, three conditions, and three repeats per workflow, producing 306 answers. A deterministic evaluator measures complete success through structured decision correctness, quotation validity, decisive-source coverage, and, for Agentic workflows, consistency with a simulated commit. Complete RAG success was 88.2% for Baseline, 92.2% for QR only, and 98.0% for QR + graph. Complete Agentic success was 62.7%, 54.9%, and 86.3%, respectively. Relative to QR only, graph context increased success by 5.9 percentage points in RAG and 31.4 points in Agentic. The combined configuration exceeded Agentic Baseline in all three repeats. Task-conditional bootstrap intervals support a clearer benefit in Agentic; the RAG intervals include zero. A separate single-request advisory comparison produced weighted LLM-review scores of 87.5, 95.0, and 95.0 out of 100. These exploratory scores are reported separately and are not accuracy percentages. The release includes the article and two public JSON supplements containing anonymized trial outcomes, summaries, evaluation settings, and advisory score vectors. Proprietary implementation, prompts, source passages, and model response texts are withheld. The findings concern the integrated guidance and evidence-acquisition system on the evaluated tasks. They do not establish quantum computational advantage, isolate the quantum component as the cause of improvement, or demonstrate general superiority. The main evaluation is a follow-up run on previously inspected tasks, not an unseen holdout.

•Oct 3, 2026•0 citations

Quantum AI-Scientist: A Framework for Quantum Application Discovery in Biomedicine

Min Yang, Sha Cao, Fei Li +1 more

Despite rapid advances in quantum algorithms and hardware, translating these developments into concrete, verifiable real-world applications remains a major challenge. Here, we present Quantum AI-Scientist, a retrieval-augmented, multi-agent framework for discovering potential applications of quantum computing in biomedicine. Unlike conventional AI-scientist systems designed to solve predefined tasks, Quantum AI-Scientist identifies computational problems within a biomedical research domain that may benefit from quantum primitives. Four coordinated agents retrieve and analyze literature data to characterize the capabilities of quantum primitives, identify structurally compatible biomedical problems, translate candidate applications into falsifiable evaluation plans, and synthesize the resulting evidence to rank candidates and recommend further development strategies. The framework maintains a traceable evidence chain of literature-derived evidence, computational formulations, experimental results, and final recommendations. It also explicitly distinguishes structural compatibility from practical executability, empirical improvement, and quantum advantage. Across eight biomedical benchmarks, the staged workflow increased the macro-F1 score for formulation recovery from 82.6% to 88.1% compared with an equal-evidence, single-call baseline, while reducing token consumption at the cost of increased API latency. Case studies involving spatial probe selection and cell lineage inference demonstrate how proposed applications can be translated into executable evaluations of technical feasibility, preliminary empirical improvement, and quantum advantage. Collectively, these results establish a systematic and auditable framework for proposing, testing, and prioritizing biomedical applications of quantum computing.

Proceedings of the AAAI Symposium Series•Nov 6, 2026•0 citations

Policy-Guided AI Assistance for Hybrid Quantum Computing

Taylor Miss

AI-assisted quantum programming requires a clear separation between generating candidate solutions and authorizing their execution. This paper presents a conceptual framework that assigns proposal generation to an AI assistant, validation and orchestration to a classical controller, and measurement execution to a quantum backend. A structured quantum-job contract links circuit artifacts, observables, shot allocations, backend selection, and provenance to explicit admission checks. The framework adapts responsibility-allocation and runtime-control principles from enterprise AI architectures while distinguishing software compliance from scientific correctness. An analytically solvable single-qubit variational example illustrates expectation-value estimation, finite-shot uncertainty, and resource-aware measurement allocation. The analysis shows why an authorized execution must still be assessed for measurement consistency, statistical uncertainty, and physical bias. A proposed evaluation protocol addresses accuracy, policy enforcement, reproducibility, operational cost, and researcher workload. The contribution is an architectural design and analytical illustration rather than an experimentally validated system; no measured reliability improvement or quantum advantage is claimed.

•Sep 11, 2026•0 citations
External Quantum Reservoir Assist is designed to help an AI assistant identify the core of a difficult request and organize a useful response by adding dynamically generated guidance through a REST or MCP integration. This study evaluates final answers from an archived experiment using one response pair from each of 50 synthetic scenario families. Thirty-nine pairs formed the primary complex decision-support group, while eleven provided routine, constraint-challenge, and technical-explanation controls. Within the primary group, reservoir-assisted answers were preferred in 17 cases, baseline answers in 8, with 13 ties and 1 unclear case. The tie-adjusted preference rate was 61.8% (95% family-bootstrap interval: 48.7–73.7%). The clearest descriptive gains were observed in actionability and validation guidance, while major-error flags occurred equally often in both conditions. Assistance increased total token usage by 32.9% and median paired estimated end-to-end time by 7.51 seconds. The results provide directional evidence that external reservoir guidance can improve practical decision support for selected complex AI-assistant tasks, while also demonstrating substantial uncertainty and operational overhead. The study does not establish general response superiority, reduced factual-error rates, or a quantum-specific advantage. The accompanying minimized dataset and executable analysis reproduce the reported statistics and figures without additional model calls.
Large language models increasingly operate within systems that provide retrieved knowledge, policies, tool descriptions, workflow state, and other contextual signals. This work investigates Quantum Reservoir Assist, a pre-generation context-orchestration layer that uses a CUDA-Q-based quantum reservoir process to rank candidate contextual signals and construct dynamic decision-support guidance for an otherwise unchanged downstream language model. We evaluate the complete pipeline using a paired benchmark of 500 production-like prompts across ten categories, including architecture and system design, troubleshooting, multi-constraint reasoning, incident response, agent tool planning, security and reliability, and technical explanation. Both experimental paths use the same downstream LLM and generation settings. Across the benchmark, Quantum Reservoir Assist produced a mean absolute increase of approximately 0.172 in the system’s internal answer-readiness/accuracy proxy. The strongest mean proxy improvements occurred in troubleshooting, ambiguous or underspecified requests, conflicting constraints, security and reliability, and multi-constraint tasks. Reservoir assistance also introduced measurable operational overhead, including increased downstream token usage and substantial preprocessing latency under the CUDA-Q simulation configuration used in this experiment. The results demonstrate systematic effects of quantum-reservoir-assisted pre-generation context orchestration, but do not establish ground-truth answer-accuracy improvement or quantum computational advantage. The study therefore motivates controlled ablations against static guidance and classical context-ranking methods.
I evaluated whether a quantum AI reservoir can improve the decisions produced by retrieval-augmented generation (RAG) and tool-using Agentic workflows. Two complementary experiments used the same five workflow variants: RAG, RAG + QR, Agentic, Agentic + QR, and LLM + QR. Each experiment contained 201 main tasks and three repeats, yielding 6,030 answers overall. The first experiment used synthetic planning scenarios; the second used numerical quantities extracted from quantum-domain books and technical papers. In the designated first repeat, QR increased complete structured success from 75.1% to 90.5% for synthetic RAG and from 27.4% to 52.2% for synthetic Agentic. On real-source tasks, the corresponding rates increased from 46.8% to 57.7% and from 34.3% to 55.7%. Both paired improvements were positive in every repeat of both experiments. LLM + QR achieved 94.0% on synthetic tasks and 54.7% on real-source tasks in the first repeat, exceeding both unassisted baselines in each experiment. The results support the integrated reservoir-guidance module as a useful addition to the evaluated decision workflows and motivate a simpler single-call architecture when all required evidence is available. The study evaluates a simulator-backed quantum/classical module; it does not establish quantum computational advantage or isolate the quantum component from its classical guidance components.
Near-term quantum approaches to combinatorial optimization are limited by qubit counts, circuit fidelity, sampling cost, and the difficulty of encoding constraints, while machine learning is increasingly used to configure and control quantum optimization workflows. We call such workflows adaptive: decisions conventionally fixed in advance, from formulation and penalties to shot budgets, backends, and whether to invoke a quantum processor at all, are made by learned policies that respond to the instance, the progress of the solve, or the hardware. This review examines three paradigms, AI for quantum optimization, quantum for AI-driven optimization, and AI-quantum co-optimization, and organizes the literature by the decision being learned rather than by application. A structured search identified a 119-paper corpus, of which 67 papers form an evidence core coded in detail. The evidence is considerably stronger for AI-assisted quantum optimization than for the reverse direction: learning already reduces quantum evaluations, improves initialization, supports decomposition and penalty control, and mitigates noise, whereas evidence that quantum computation improves learned optimizers remains largely confined to small-scale simulation. Experimental controls are thin: of 52 studies in the three paradigms, 22 include no classical baseline, the quantum contribution is fully isolated in 10 of 24 where an ablation applies, and the median largest experiment uses 16 qubits. We introduce an M0-M5 evidence hierarchy, from simulation to practical quantum advantage, and find no broadly convincing result at the highest level. We argue that scaling is increasingly a systems problem: the question is not only whether a problem fits on a quantum processor, but how classical and quantum resources should be allocated across the optimization process.
This study evaluates an external simulator-backed quantum/classical guidance component with optional graph context across direct LLM advice, retrieval-augmented generation (RAG), and tool-using Agentic workflows. Three conditions are compared: Baseline, QR only, and QR + graph. The RAG and Agentic evaluation comprises 17 tasks, three conditions, and three repeats per workflow, producing 306 answers. A deterministic evaluator measures complete success through structured decision correctness, quotation validity, decisive-source coverage, and, for Agentic workflows, consistency with a simulated commit. Complete RAG success was 88.2% for Baseline, 92.2% for QR only, and 98.0% for QR + graph. Complete Agentic success was 62.7%, 54.9%, and 86.3%, respectively. Relative to QR only, graph context increased success by 5.9 percentage points in RAG and 31.4 points in Agentic. The combined configuration exceeded Agentic Baseline in all three repeats. Task-conditional bootstrap intervals support a clearer benefit in Agentic; the RAG intervals include zero. A separate single-request advisory comparison produced weighted LLM-review scores of 87.5, 95.0, and 95.0 out of 100. These exploratory scores are reported separately and are not accuracy percentages. The release includes the article and two public JSON supplements containing anonymized trial outcomes, summaries, evaluation settings, and advisory score vectors. Proprietary implementation, prompts, source passages, and model response texts are withheld. The findings concern the integrated guidance and evidence-acquisition system on the evaluated tasks. They do not establish quantum computational advantage, isolate the quantum component as the cause of improvement, or demonstrate general superiority. The main evaluation is a follow-up run on previously inspected tasks, not an unseen holdout.
Despite rapid advances in quantum algorithms and hardware, translating these developments into concrete, verifiable real-world applications remains a major challenge. Here, we present Quantum AI-Scientist, a retrieval-augmented, multi-agent framework for discovering potential applications of quantum computing in biomedicine. Unlike conventional AI-scientist systems designed to solve predefined tasks, Quantum AI-Scientist identifies computational problems within a biomedical research domain that may benefit from quantum primitives. Four coordinated agents retrieve and analyze literature data to characterize the capabilities of quantum primitives, identify structurally compatible biomedical problems, translate candidate applications into falsifiable evaluation plans, and synthesize the resulting evidence to rank candidates and recommend further development strategies. The framework maintains a traceable evidence chain of literature-derived evidence, computational formulations, experimental results, and final recommendations. It also explicitly distinguishes structural compatibility from practical executability, empirical improvement, and quantum advantage. Across eight biomedical benchmarks, the staged workflow increased the macro-F1 score for formulation recovery from 82.6% to 88.1% compared with an equal-evidence, single-call baseline, while reducing token consumption at the cost of increased API latency. Case studies involving spatial probe selection and cell lineage inference demonstrate how proposed applications can be translated into executable evaluations of technical feasibility, preliminary empirical improvement, and quantum advantage. Collectively, these results establish a systematic and auditable framework for proposing, testing, and prioritizing biomedical applications of quantum computing.
AI-assisted quantum programming requires a clear separation between generating candidate solutions and authorizing their execution. This paper presents a conceptual framework that assigns proposal generation to an AI assistant, validation and orchestration to a classical controller, and measurement execution to a quantum backend. A structured quantum-job contract links circuit artifacts, observables, shot allocations, backend selection, and provenance to explicit admission checks. The framework adapts responsibility-allocation and runtime-control principles from enterprise AI architectures while distinguishing software compliance from scientific correctness. An analytically solvable single-qubit variational example illustrates expectation-value estimation, finite-shot uncertainty, and resource-aware measurement allocation. The analysis shows why an authorized execution must still be assessed for measurement consistency, statistical uncertainty, and physical bias. A proposed evaluation protocol addresses accuracy, policy enforcement, reproducibility, operational cost, and researcher workload. The contribution is an architectural design and analytical illustration rather than an experimentally validated system; no measured reliability improvement or quantum advantage is claimed.