Search arXiv⌕ Search

arXiv subjects

Alexander Roman

Publications and source records attributed to Alexander Roman.

At least 19 recordsLinked to original sources
arXiv2026

Reining in an Agentic Harness for High Energy Physics

Agentic systems now address tasks across theoretical, phenomenological, and experimental high energy physics (HEP), but their scientific capabilities remain difficult to reuse across different large language models, providers, and harnesses. We argue that stable parts of these workflows should be promoted into versioned scientific operations and exposed through common protocols. Existing general-purpose harnesses can then be specialized for HEP through task-specific sets of tools and skills, while community-maintained registries would make these capabilities discoverable and citable. We identify mismatches in conventions, assumptions, and domains of validity among independently developed operations as a potential obstacle to their composition, and discuss machine-readable scientific contracts as one possible solution. These design principles and evaluation guidelines provide a near-term path toward a portable and community-maintained agentic harness for HEP.

hep-ph↗
arXiv2026

Efficient Hamiltonian Truncation: Fast Matrix Construction and Quantum Krylov Diagonalization

Hamiltonian truncation offers a nonperturbative route to quantum field theory, yet its accuracy is limited by the rapid expansion of the truncated Hilbert space, which drives up computational cost. We tackle this bottleneck with a hybrid strategy that pairs classical and quantum algorithms: 1) we develop an efficient basis-generation scheme built on integer partitions; 2) we speed up the construction of the sparse Hamiltonian matrix using symmetry-aware algorithms; and 3) we explore quantum Krylov diagonalization as a route to the low-lying spectrum. Benchmarking against the free massive scalar and $\phi^4$ theories in two spacetime dimensions, we achieve substantial gains in the computational efficiency of Hamiltonian truncation and chart a path toward future quantum implementations.

quant-ph↗
arXiv2026

Analytical Landscape of Maximal Magic for Two-Qutrit States and Beyond

Achieving a genuine quantum advantage relies on two distinct non-classical resources that restrict efficient classical simulation: entanglement and magic (nonstabilizerness). We investigate the interplay between these resources by characterizing the Pareto frontiers of extreme magic at fixed entanglement for systems of two qutrits ($d=3$) and two ququints ($d=5$). Unlike the case of two qubits, the Schmidt spectrum for two qutrits features two independent entanglement parameters, resulting in two-dimensional Pareto surfaces. For the lower frontier, we recast the minimal magic as a compact function of concurrence and negativity, with a maximal value of $\ln 2$. For the upper frontier, we determine the maximal stabilizer R\'enyi entropy to be $M_2 = \ln(81/17) \approx 1.561$, which tightens the previous theoretical bound of $\ln 5\approx 1.609$ and improves on earlier numerical estimates. The maximum magic is achieved at eighteen distinct maxima categorized into three families of six permutation-equivalent spectra. We provide analytical expressions for the maximal magic in the neighborhood of each maximum and for the corresponding maximally magical states which turn out to be Weyl-Heisenberg-covariant fiducial states for mutually unbiased bases. Finally, numerical analysis of two ququints ($d=5$) reveals six permutation-inequivalent maxima with a peak magic value of $M_2 = \ln(625/49) \approx 2.546$. Based on these findings, we conjecture that the maximal magic for a bipartite system of two qudits with prime dimension $d$ is given by $\ln [ d^4 / (2d^2 - 1) ]$, which reproduces the previously known value for qubits, as well as the values derived here for qutrits and ququints.

quant-ph↗
arXiv2026

Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs

Misaligned artificial agents might resist shutdown. One proposed solution is to train agents to lack preferences between different-length trajectories. The Discounted Reward for Same-Length Trajectories (DReST) reward function does this by penalizing agents for repeatedly choosing same-length trajectories, and thus incentivizes agents to (1) choose stochastically between different trajectory-lengths (be NEUTRAL about trajectory-lengths), and (2) pursue goals effectively conditional on each trajectory-length (be USEFUL). In this paper, we use DReST to train deep RL agents and fine-tune Qwen3-8B and Llama-3.1-8B-Instruct to be NEUTRAL and USEFUL. We find that these DReST models generalize to being NEUTRAL and USEFUL in unseen contexts at test time. Indeed, DReST RL agents achieve 11% (PPO) and 18% (A2C) higher USEFULNESS on our test set than default agents, and DReST LLMs achieve near-maximum USEFULNESS and NEUTRALITY. We also test our LLMs in an out-of-distribution setting where they can pay costs to influence when shutdown occurs. We find that DReST training roughly halves the mean probability of influencing shutdown (from 0.62 to 0.30 for Qwen and from 0.42 to 0.23 for Llama). DReST training also almost entirely eliminates the share of prompts on which influencing shutdown is the most likely option (from 0.59 to 0.01 for Qwen and from 0.53 to 0.00 for Llama). Our results thus provide some early evidence that DReST could be used to train more advanced agents to be useful and shutdownable.

cs.AI↗
arXiv2026

ASTER -- Agentic Science Toolkit for Exoplanet Research

The expansion of exoplanet observations has created a need for flexible, accessible, and user-friendly workflows. Transmission spectroscopy has become a key technique for probing atmospheric composition of transiting exoplanets. The analyses of these data require the combination of archival queries, literature search, the use of radiative transfer models, and Bayesian retrieval frameworks, each demanding specialized expertise. Modern large language models enable the coordinated execution of complex, multi-step tasks by AI agents with tool integration, structured prompts, and iterative reasoning. In this study we present ASTER, an Agentic Science Toolkit for Exoplanet Research. ASTER is an orchestration framework that brings LLM capability to the exoplanetary community by enabling LLM-driven interaction with integrated domain-specific tools, workflow planning and management, and support for common data analysis tasks. Currently ASTER incorporates tools for downloading planetary parameters and observational datasets from the NASA Exoplanet Archive, as well as the generation of transit spectra from the TauREx radiative transfer model, and the completion of Bayesian retrieval of planetary parameters with TauREx. Beyond tool integration, the agent assists users by proposing alternative modeling approaches, reporting potential issues and suggesting solutions, and interpretations. We demonstrate ASTER's workflow through a complete case study of WASP-39b, performing multiple retrievals using observational data available on the archive. The agent efficiently transitions between datasets, generates appropriate forward model spectra and performs retrievals. ASTER provides a unified platform for the characterization of exoplanet atmospheres. Ongoing development and community contributions will continue expanding ASTER's capabilities toward broader applications in exoplanet research.

astro-ph.EP↗
arXiv2026

Agentic Diagrammatica: Towards Autonomous Symbolic Computation in High Energy Physics

We present Diagrammatica, a symbolic computation extension to the HEPTAPOD agentic framework, which enables LLM agents to plan and execute multi-step theoretical calculations. Symbolic computation poses a distinctive reliability challenge for LLM agents, as correctness is governed by implicit mathematical conventions that are not encoded in a form that can be easily checked in the computational backend. We identify two complementary remedies, tool-constrained computation and targeted knowledge grounding, and pursue the first as the primary architecture. Concretely, we concentrate the agent's action distribution onto tool calls with convention-fixing semantics, in which the agent specifies a compact, human-auditable diagram specification and a trusted backend performs the symbolic or numerical manipulations exactly. The toolkit provides two complementary calculation paths consuming a shared diagram specification: Naive Dimensional Analysis (NDA) for order-of-magnitude rate estimates and Exact Diagrammatic Analysis (EDA) for tree-level symbolic calculations via automatic FeynCalc code generation, both supplemented by automatic Feynman diagram enumeration and a navigable theory knowledge base. The architecture is validated on two benchmarks: (1) an exhaustive catalog of all tree-level, single-vertex $1\to 2$ partial decay widths across scalar, fermion, and vector parents, with complete massless and threshold limits and Standard Model validation; and (2) an NDA sensitivity study of the muon decay multiplicity $\mu^+ \to \nu_\mu\bar{\nu}_e + n(e^+e^-) + e^-$, determining the maximum observable $n$ at current and planned muon experiments.

hep-ph↗
arXiv2026

The Pareto Frontiers of Magic and Entanglement: The Case of Two Qubits

Magic and entanglement are two measures that are widely used to characterize quantum resources. We study the interplay between magic and entanglement in two-qubit systems, focusing on the two extremes: maximal magic and minimal magic for a given level of entanglement. We quantify magic by the R\'{e}nyi entropy of order 2, $M_2$, and entanglement by the concurrence $\Delta$. We find that the Pareto frontier of maximal magic $M_2^{(max)}(\Delta)$ is composed of three separate segments, while the boundary of minimal magic $M_2^{(min)}(\Delta)$ is a single continuous line. We derive simple analytical formulas for all these four cases, and explicitly parametrize all distinct quantum states of maximal or minimal magic at a given level of entanglement.

quant-ph↗
arXiv2026

AI Agents for Variational Quantum Circuit Design

Variational quantum circuits (VQCs) constitute a central building block of near-term quantum machine learning (QML), yet the principled design of expressive and trainable architectures remains a major open challenge. The VQC design space grows combinatorially with the number of qubits, layers, entanglement structures, and gate parameterizations, rendering manual circuit construction inefficient and often suboptimal. We introduce an autonomous agent-based framework for VQC architecture search that integrates high-level reasoning with a quantum simulation environment. The agent proposes candidate circuit architectures, evaluates them through fully automated training and validation pipelines, and iteratively improves its design strategy via performance-driven feedback. Empirically, we show that the agent autonomously evolves circuit architectures from simple initial ans\"atze toward increasingly expressive designs, progressively trying to improve task performance. This demonstrates that agentic AI can effectively navigate and refine the VQC design landscape with minimal human intervention, providing a scalable methodology for automated quantum model development in the Noisy Intermediate-Scale Quantum (NISQ) regime.

quant-ph↗
arXiv2026

Balancing Variety and Sample Size: Optimal Parameter Sampling for Ariel Target Selection

Targeted astrophysical surveys are limited by the amount of telescope time available, which makes it impossible to observe every single object of interest. In order to maximize the scientific return, we need a well thought strategy for selecting the observational targets, in our case exoplanets. This study evaluates various strategies for selecting exoplanet targets within limited observation windows, focusing specifically on the selection of exoplanet targets for Tier 2 transit spectroscopy with ESA's upcoming Ariel mission. We define three distinct selection criteria -- sample size, variance, and leverage -- and translate them into objective functions compatible with modern optimization algorithms. Specifically, we test five heuristics for maximizing sample leverage: leverage greedy, simulated annealing, K-means clustering, regular classes, and quantile classes. The performance of these methods is demonstrated through three practical exercises across one, two, and three parameters of diversity. Each criterion represents a unique trade-off between sample size, diversity, and total observation time. While a time-greedy approach maximizes the quantity of planets, it fails to capture diversity. Conversely, variance-greedy selection prioritizes diversity but introduces significant drawbacks: it oversamples rare cases and undersamples typical planets, ultimately reducing the total number of targets observed. Leverage-based selections emerge as the most effective middle ground, successfully balancing sample diversity with a robust sample size. This work supports the broader community effort to ensure that Ariel delivers the most diverse and scientifically valuable sample of exoplanet atmospheres within mission limits.

astro-ph.EP↗
arXiv2026

Hunting for "Oddballs" with Machine Learning: Detecting Anomalous Exoplanets Using a Deep-Learned Low-Dimensional Representation of Transit Spectra with Autoencoders

This study explores the application of autoencoder-based machine learning techniques for anomaly detection to identify exoplanet atmospheres with unconventional chemical signatures using a low-dimensional data representation. We use the Atmospheric Big Challenge (ABC) database, a publicly available dataset with over 100,000 simulated exoplanet spectra, to construct an anomaly detection scenario by defining CO2-rich atmospheres as anomalies and CO2-poor atmospheres as the normal class. We benchmarked four different anomaly detection strategies: Autoencoder Reconstruction Loss, One-Class Support Vector Machine (1 class-SVM), K-means Clustering, and Local Outlier Factor (LOF). Each method was evaluated in both the original spectral space and the autoencoder's latent space using Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) metrics. To test the performance of the different methods under realistic conditions, we introduced Gaussian noise levels ranging from 10 to 50 ppm. Our results indicate that anomaly detection is consistently more effective when performed within the latent space across all noise levels. Specifically, K-means clustering in the latent space emerged as a stable and high-performing method. We demonstrate that this anomaly detection approach is robust to noise levels up to 30 ppm (consistent with realistic space-based observations) and remains viable even at 50 ppm when leveraging latent space representations. On the other hand, the performance of the anomaly detection methods applied directly in the raw spectral space degrades significantly with increasing the level of noise. This suggests that autoencoder-driven dimensionality reduction offers a robust methodology for flagging chemically anomalous targets in large-scale surveys where exhaustive retrievals are computationally prohibitive.

astro-ph.EP↗
arXiv2026

Orchestral AI: A Framework for Agent Orchestration

The rapid proliferation of LLM agent frameworks has forced developers to choose between vendor lock-in through provider-specific SDKs and complex multi-package ecosystems that obscure control flow and hinder reproducibility. Integrating tool calling across multiple LLM providers remains a core engineering challenge due to fragmented APIs, incompatible message formats, and inconsistent streaming and tool-calling behavior, making it difficult to build portable, reliable agent systems. We introduce Orchestral, a lightweight Python framework that provides a unified, type-safe interface for building LLM agents across major providers while preserving the simplicity required for scientific computing and production deployment. Orchestral defines a single universal representation for messages, tools, and LLM usage that operates seamlessly across providers, eliminating manual format translation and reducing framework-induced complexity. Automatic tool schema generation from Python type hints removes the need for handwritten descriptors while maintaining type safety across provider boundaries. A synchronous execution model with streaming support enables deterministic behavior, straightforward debugging, and real-time interaction without introducing server dependencies. The framework's modular architecture cleanly separates provider integration, tool execution, conversation orchestration, and user-facing interfaces, enabling extensibility without architectural entanglement. Orchestral supports advanced agent capabilities found in larger frameworks, including rich tool calling, context compaction, workspace sandboxing, user approval workflows, sub-agents, memory management, and MCP integration.

cs.AI↗
arXiv2025

HEPTAPOD: Orchestrating High Energy Physics Workflows Towards Autonomous Agency

Many theoretical and experimental workflows in high-energy-physics (HEP) stand to benefit from recent advances in transformer-based large language models (LLMs). While early applications of LLMs focused on text generation and code completion, modern LLMs now support orchestrated agency: the coordinated execution of complex, multi-step tasks through tool use, structured context, and iterative reasoning. We introduce the HEP Toolkit for Agentic Planning, Orchestration, and Deployment (HEPTAPOD), an orchestration framework designed to integrate external LLMs into general HEP workflows spanning theoretical calculations, simulation, and data analysis. The framework enables LLMs to interface with domain-specific tools and to construct and manage diverse HEP pipelines while preserving transparency, reproducibility, and human oversight. To demonstrate these capabilities, we present a representative case study in the context of a Beyond the Standard Model (BSM) Monte Carlo signal validation that spans model generation, event simulation, and analysis within an established, reproducible workflow. HEPTAPOD provides a structured and auditable layer between human researchers, LLMs, and computational infrastructure, establishing a foundation for human-in-the-loop, agent-assisted workflows across high-energy physics.

hep-ph↗
arXiv2024

Towards Shutdownable Agents via Stochastic Choice

The POST-Agents Proposal (PAP) is an idea for ensuring that advanced artificial agents never resist shutdown. A key part of the PAP is using a novel `Discounted Reward for Same-Length Trajectories (DReST)' reward function to train agents to (1) pursue goals effectively conditional on each trajectory-length (be `USEFUL'), and (2) choose stochastically between different trajectory-lengths (be `NEUTRAL' about trajectory-lengths). In this paper, we propose evaluation metrics for USEFULNESS and NEUTRALITY. We use a DReST reward function to train simple agents to navigate gridworlds, and we find that these agents learn to be USEFUL and NEUTRAL. Our results thus provide some initial evidence that DReST reward functions could train advanced agents to be USEFUL and NEUTRAL. Our theoretical work suggests that these agents would be useful and shutdownable.

cs.AI↗
arXiv2023

Identifying the Group-Theoretic Structure of Machine-Learned Symmetries

Deep learning was recently successfully used in deriving symmetry transformations that preserve important physics quantities. Being completely agnostic, these techniques postpone the identification of the discovered symmetries to a later stage. In this letter we propose methods for examining and identifying the group-theoretic structure of such machine-learned symmetries. We design loss functions which probe the subalgebra structure either during the deep learning stage of symmetry discovery or in a subsequent post-processing stage. We illustrate the new methods with examples from the U(n) Lie group family, obtaining the respective subalgebra decompositions. As an application to particle physics, we demonstrate the identification of the residual symmetries after the spontaneous breaking of non-Abelian gauge symmetries like SU(3) and SU(5) which are commonly used in model building.

hep-ph↗
arXiv2023

Accelerated Discovery of Machine-Learned Symmetries: Deriving the Exceptional Lie Groups G2, F4 and E6

Recent work has applied supervised deep learning to derive continuous symmetry transformations that preserve the data labels and to obtain the corresponding algebras of symmetry generators. This letter introduces two improved algorithms that significantly speed up the discovery of these symmetry transformations. The new methods are demonstrated by deriving the complete set of generators for the unitary groups U(n) and the exceptional Lie groups $G_2$, $F_4$, and $E_6$. A third post-processing algorithm renders the found generators in sparse form. We benchmark the performance improvement of the new algorithms relative to the standard approach. Given the significant complexity of the exceptional Lie groups, our results demonstrate that this machine-learning method for discovering symmetries is completely general and can be applied to a wide variety of labeled datasets.

hep-th↗
arXiv2023

Discovering Sparse Representations of Lie Groups with Machine Learning

Recent work has used deep learning to derive symmetry transformations, which preserve conserved quantities, and to obtain the corresponding algebras of generators. In this letter, we extend this technique to derive sparse representations of arbitrary Lie algebras. We show that our method reproduces the canonical (sparse) representations of the generators of the Lorentz group, as well as the $U(n)$ and $SU(n)$ families of Lie groups. This approach is completely general and can be used to find the infinitesimal generators for any Lie group.

hep-ph↗
arXiv2023

Oracle-Preserving Latent Flows

We develop a deep learning methodology for the simultaneous discovery of multiple nontrivial continuous symmetries across an entire labelled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function ensuring the desired symmetry properties. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to transformations invariant with respect to high-dimensional oracles. The method is demonstrated with several examples on the MNIST digit dataset.

cs.LG↗
arXiv2023

Deep Learning Symmetries and Their Lie Groups, Algebras, and Subalgebras from First Principles

We design a deep-learning algorithm for the discovery and identification of the continuous group of symmetries present in a labeled dataset. We use fully connected neural networks to model the symmetry transformations and the corresponding generators. We construct loss functions that ensure that the applied transformations are symmetries and that the corresponding set of generators forms a closed (sub)algebra. Our procedure is validated with several examples illustrating different types of conserved quantities preserved by symmetry. In the process of deriving the full set of symmetries, we analyze the complete subgroup structure of the rotation groups $SO(2)$, $SO(3)$, and $SO(4)$, and of the Lorentz group $SO(1,3)$. Other examples include squeeze mapping, piecewise discontinuous labels, and $SO(10)$, demonstrating that our method is completely general, with many possible applications in physics and data science. Our study also opens the door for using a machine learning approach in the mathematical study of Lie groups and their properties.

hep-ph↗