CS Paper Radar

Daily listing

2026-11-17 · cs.CE

8 papers first submitted this day (UTC) in cs.CE — Computational Engineering, Finance, and Science. arXiv announces a day's submissions the next evening, so the newest day fills up over ~24 h.

Score = weighted mean ofCitations 20%Upvotes 10%Code stars 10%Venue 15%Code/data 10%Novelty 15%Momentum 15%Substance 5%how it works

AI & Machine Learning 1

Action-outcome coupling: a pre-investment feasibility audit for offline reinforcement learning in supply chain operations

cs.LG cs.CEecon.EMstat.AP ·2026-11-17 ·Tung Dang, The Hung Phung, Son Lam Nguyen, Tu Nguyen
theory
Abstract · 40 pages

Prescriptive analytics initiatives in logistics, such as offline reinforcement learning and next-best-action systems, are often funded before anyone verifies that the available historical logs can support an improved decision policy. We formalise this pre-investment feasibility question via action-outcome coupling: a total-effect variance index measuring how much expected outcomes change with the logged action. Coupling provides an algorithm-independent upper bound on any policy's achievable value, expressed in monetary units per decision for both single-step and discounted sequential objectives. We also analyse the asymptotic false-licensing risk of an invalid workflow: fitting a value model and evaluating the model's greedy policy on the same data. The false-licence rate is driven mainly by the number of state cells over which selection is performed, rising from the nominal test level with one cell to near certainty with a few dozen, while overlap has a smaller effect. We then propose an audit that assigns logs to four tiers of decision support, separately for fixed and contextual policies, and returns an explicit stopping rationale. On a randomised e-commerce log, the audit endorses a fixed recommendation policy, certifying gains equal to 30 per cent of the theoretical ceiling; the remaining gap reflects bound looseness under an 80-action design. Two public logistics logs fail at different checkpoints: one because the target is an accounting identity of the action, and another because, with 27 clusters, estimated coupling stays below the design's detectability threshold even though a conservative offline learner certifies an improvement in 29 of 30 seeds.

0.21

People & Society 7

What Do LLMs Use to Judge Synthesis Recipes? An Experimental Analysis on 240 Solid-State Syntheses

cs.CE cond-mat.mtrl-sci ·2026-11-17 ·Derek van Tilborg, Laura-Bianca Pasca, Harry Sevi, Kyle Reeves, Thomas Loux +4 more
publishedbenchmark
Abstract · 23 pages, 13 figures, NeurIPS Ai4Mat

Inorganic materials discovery is increasingly limited by synthesis rather than by material design. Large language models (LLMs) are being adopted to propose synthesis conditions with little experimental evidence of their capabilities and biases. Here, we carry out an experimental synthesis benchmark of 240 experiments across eight known and unknown inorganic oxides and subsequently evaluate an LLM as a zero-shot ranker over fixed banks of solid-state synthesis recipes. For each pair of recipes for the same oxide target, `GPT-5.6-Sol` selects the recipe expected to yield higher target-phase purity. We aggregate these pairwise preferences using a regularized Bradley-Terry model to obtain a ranked list of synthesis recipes for a given target material. By comparison with the actual purity, obtained through X-ray diffraction, we measure `GPT-5.6-Sol`'s performance as a zero-shot ranker (0.72 pairwise accuracy). By selective removal of the information exposed to the model during this ranking, we conclude that ranking is driven predominantly by thermal features, with reaction chemistry modulating the effect. Ranking accuracy tracks the purity-temperature correlation by target (Spearman ρ= 0.91\), \(p = 0.002\), and on the six thermally-driven targets withholding all chemical identity hardly impacts performance (0.68) compared to withholding temperature (0.56). Ranking performance was higher on known than unknown targets, but the group-level difference was not statistically conclusive. The methodological choices highlight the need for more experimentally validated synthesis benchmarks and position LLMs as a thermally informed prior.

0.57

ReBoT-MiCS: Reliability-Aware Bounding Time for Enhancing Timing Behavior of Embedded Mixed-Criticality Systems

cs.CE cs.SE ·2026-11-17 ·Mohammad Abbasinia, Behnaz Ranjbar, Akash Kumar
Abstract

In Mixed-Criticality (MC) systems, considering multiple Worst-Case Execution Times (WCETs) for the same task, corresponding to different system operation modes, presents a fundamental challenge in MC system design. Identifying suitable WCETs for lower (LO) criticality system operational modes is inherently difficult. Tight low WCET values may trigger frequent mode switches that degrade Quality-of-Service (QoS) by dropping/degrading the lower-criticality tasks and reducing their functionality. However, more conservative values reduce resource efficiency. Moreover, low WCET selection affects exposure assumptions under the adopted transient-fault model, which is used in reliability-aware scheduling analysis. Although some studies have considered low WCET determination to make a reasonable trade-off between processor utilization, mode switching probability and QoS, reliability constraints are typically addressed separately through fault-tolerance mechanisms. This separation overlooks the opportunity to use execution-time bounds as part of design-time reasoning about exposure-related reliability constraints. In this regard, we propose a reliability-aware analytical scheme, named ReBoT-MiCS, to determine low WCETs at design time, jointly balancing utilization, QoS, mode switches, and probabilistic reliability constraints of each task criticality level under a transient-fault exposure model. Experiments conducted with various synthetic and embedded benchmarks demonstrate the efficacy of the proposed scheme, in which utilization can be improved by up to 27.6% and 11.67% on average, while bounding the mode switching probability by up to 5.48%, and satisfying the specified reliability constraints

0.33

Nonlinearity-preserving quantum simulation of flows in the early fault-tolerant regime

cs.CE quant-phnlin.CD ·2026-11-17 ·Hansol Noh, Unam Oh, Sangkyu Baek, Doyeol, Ahn
Abstract

Ensemble prediction of nonlinear dynamics propagates a probability density whose linear transport equation retains the nonlinear drift, but grid-dependent circuit costs leave end-to-end feasibility in early fault-tolerant quantum computing unresolved. We couple polynomial reduced-order models fitted by sparse identification of nonlinear dynamics to Walsh-synthesized Koopman-von Neumann (KvN) transport and surface-code resource estimation. At fixed model dimension and drift degree, per-step transport rotation counts scale polylogarithmically with cells per reduced coordinate. Balancing model accuracy against circuit costs makes reduced-model polynomial degree a design variable for early fault-tolerant quantum simulation. For a cylinder wake approaching saturation, preparation, propagation and sampling to 1% relative root-mean-square field error against the radial model are estimated to take 1.62 h on about 560,000 physical qubits. Estimated three-coordinate wake runtimes span hours to weeks below one million qubits. IBM hardware experiments demonstrate nonlinear radial KvN transport for this wake, using reference circuits to mitigate noise.

0.33

Coordinating integration of multidisciplinary design analysis and optimisation codes with design structure matrices

cs.CE physics.comp-phcs.SE ·2026-11-17 ·W. J. Rutten, L. F. P. Etman, F. Warmer
Abstract · 18 pages, 5 figures, 9 tables. Submitted to Fusion Engineering and Design

The integrated analysis and optimisation codes used to design nuclear fusion reactors need to become increasingly large scale, multidisciplinary and complex to computationally verify design requirements more thoroughly and earlier in the design process. Though the manner in which the integrated models are coupled can have significant implications for computational efficiency, the structure of couplings typically remains hidden in the implementation of a design framework. As this problem is not unique to fusion, we frame integrated design problems as applications of the broader field of Multidisciplinary Design Analysis and Optimisation (MDAO). Originally developed for complex system design problems in e.g. aerospace, the MDAO field uses (extended) Design Structure Matrices (DSMs) to display the architecture of integrated analysis and optimisation codes. The aim of this work is to introduce these DSM methods and demonstrate how they can be used to improve the transparency and efficiency of design codes in fusion. As a proof of concept, DSM methods are applied to two case studies: stellarator optimisation with SIMSOPT and the PROCESS systems code. With these cases, we illustrate how a DSM can help identify structural assumptions in the code, and how architectural insight can be used to improve computational efficiency. In particular, we demonstrate the computational impact by modifying the PROCESS solver architecture based on the feedback loops revealed in an automatically generated DSM, yielding a significant reduction in model evaluations. Such architectural changes are considered especially impactful for future design frameworks that combine higher fidelity models with large numbers of inexpensive models.

0.31

Efficient Robust Optimization via an Adaptive Mono-Level Gaussian Process Surrogate

cs.CE ·2026-11-17 ·Julius Schultz, Mustafa Essou, Ulrich Römer
benchmark
Abstract

Optimization under uncertainty seeks designs that perform robustly despite varying operating conditions or uncertain model parameters. However, identifying such designs typically requires solving an optimization problem with a nested uncertainty analysis, resulting in a high computational burden. Surrogate models can alleviate this burden and enable optimization under uncertainty even with computationally expensive simulation models. This paper proposes a novel surrogate-based approach that reduces the number of costly model evaluations required for robust optimization. The approach adopts a mono-level strategy, in which a single Gaussian process surrogate is constructed and adaptively refined for both optimization and uncertainty analysis. Refinement in the design space is guided by a sampling-based uncertainty indicator that propagates the surrogate's epistemic uncertainty to the robustness measure. Efficient uncertainty estimation is crucial for the scalability of the algorithm and achieved through pathwise sampling combined with a weight-space representation of the Gaussian process. The proposed approach is evaluated on several analytical benchmark models and requires fewer model evaluations than a state-of-the-art bi-level surrogate approach while achieving comparable solution accuracy. Once trained, the mono-level surrogate can be reused to optimize different robustness measures at reduced cost. Moreover, the approach is successfully applied to a structural optimization problem with constraints and design variable uncertainty.

0.28

Embedding or bridging? AI4Science teams differ more in knowledge recombination than in problem novelty

cs.CE cs.DL ·2026-11-17 ·Yun Fu, Jielan Ding
Abstract · 21 pages, 8 figures, 43 references

AI for Science (AI4Science) is reshaping scientific research, yet how the organization of AI-related and domain-scientific work relates to different dimensions of research performance remains poorly understood. We analyze 489,409 AI4Science articles published between 1990 and 2025, identifying seven affiliation-based organizational configurations comprising three forms of embedding and four forms of cross-unit bridging. Focusing on 2006-2025, we examine two dimensions of research performance: knowledge creation, characterized by scientific problem novelty and knowledge-recombination breadth, and research impact, assessed through journal placement and citation impact. We find that organizational configurations differ only modestly in problem novelty but substantially in knowledge-recombination breadth. Cross-unit bridging is consistently associated with broader knowledge recombination, particularly in AI-oriented bridging, without a corresponding advantage in problem novelty. However, greater recombination breadth does not necessarily align with stronger research impact. Science-oriented and Multi-orientation bridging exhibit the most consistent positive associations with JCI Q1 journal placement and citation impact, although neither shows a statistically significant adjusted advantage in publication in the Elite-4 journals (Nature, Science, Cell, and PNAS). These research-impact differences remain largely intact after accounting for problem novelty and recombination breadth. Our findings reveal that organizational configurations are associated with distinct patterns of knowledge creation and research impact, rather than a single hierarchy of research performance. The results highlight the importance of considering organizational arrangements in relation to specific scientific objectives, rather than assuming that any one configuration is universally superior.

0.24

Residual-Guided Multi-Step Conditional Generation for Fast Airfoil Flow Field Prediction

cs.CE ·2026-11-17 ·Weishao Tang, Mingcheng Lei, Yufei Zhang
Abstract

Deep-learning surrogate models for aerodynamic flow prediction are efficient within the training distribution, but their accuracy often degrades sharply in out-of-distribution (OOD) scenarios. To improve OOD robustness for airfoil flow-field inference, this study proposes a residual-guided sequential inference framework to correct the unreliable local flow field. The framework consists of three Transformer-based components: a Flow Initializer for direct flow prediction, a Residual-based Corrector for high-residual regions, and a Shock-based Corrector for shock regions. The framework is evaluated on an engineering-oriented OOD test set built from CFD-based aerodynamic optimization trajectory. The proposed framework reduces the L1 error, CL error, and CD error by 30%, 59%, and 41%, respectively, relative to the usual single step Geo-to-Flow prediction. The additional iterative inference cost is only 0.25s per sample. These results demonstrate that the proposed framework provides an effective route for improving OOD robustness in airfoil surrogate modeling.

0.18