Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (quant-ph) 2026-06-16

The Inverse Born Rule Equivalence. On the Informational Limits of Real-Valued Amplitude Encodings and the Measurement of Quantum Advantage in Data Embeddings

arXiv:2602.21350v2 Announce Type: replace Abstract: When does quantum data encoding provide genuine quantum advantage, and when does it merely rephrase a classically solvable problem? We prove an Equivalence Theorem demonstrating that any encoding mapping classical data to real-valued amplitudes, $\vert\psi_c\rangle = \sum_i c_i \vert i\rangle$ with $c_i \in \mathbb{R}$ and $\sum_i c_i^2 = 1$, composed with a data-independent parameterised unitary and computational-basis measurement, yields exactly the class of classical quadratic forms. We identify the geometric mechanism driving this collapse: the restriction to $\mathbb{R}$ forces a vanishing Berry connection, removing the complex phases required for data-dependent quantum interference. To operationalize this boundary, we introduce encoding diagnostics – phase complexity $C[\Phi]$ and mode-wise von Neumann mutual information $I[\Phi]$ – and link them to the information-geometric excess $\Delta g$. We show that for all real-valued encodings, $\Delta g = 0$ identically. We term the misidentification of such models as evidence of quantum computational power the Inverse Born Rule Fallacy. Supported by numerical experiments, our results establish that complex-phase structure is a strictly necessary condition for data-driven (Type~B) quantum advantage.

02.
arXiv (quant-ph) 2026-06-17

Impulse Decoding of Quantum LDPC Codes: Equivalence of Degeneracy and Code-Shortening

arXiv:2606.18240v1 Announce Type: new Abstract: Quantum error correction is essential for building scalable quantum computers. Within the stabilizer formalism, the Calderbank-Shor-Steane framework constructs quantum codes from pairs of classical linear codes. A distinctive feature in this setting is degeneracy, where multiple equivalent error estimates exist-a phenomenon that has no classical counterpart, and the lack of a meaningful classical coding-theoretic interpretation of which has remained a gap in the literature. In this paper, we demonstrate that degeneracy is closely related to the classical operation of shortening of a linear block code. Interestingly, the shortening here takes place at the decoder rather than at the encoder. Leveraging this insight, we present a parallel decoding scheme for quantum low-density parity-check codes, which we term impulse decoding, that significantly outperforms belief propagation with ordered statistics decoding, as well as several other existing techniques, under both code-capacity and circuit-level noise, with significantly lesser complexity. We then present another algorithm based on decoding of residual errors, which when combined with impulse decoding achieves further performance improvement under circuit-level noise.

03.
arXiv (quant-ph) 2026-06-16

No Universal Purification in Quantum Mechanics

arXiv:2509.21111v2 Announce Type: replace Abstract: Many central tasks in fundamental physics and quantum information processing are possible only insofar as mixed quantum states can be made purer. In this work, we prove that the linearity and positivity of quantum mechanics impose general restrictions on quantum purification, unveiling a new fundamental principle of quantum information processing. We first establish that no quantum operation can transform a finite number of copies of an unknown quantum state or channel into an exactly pure output that depends non-trivially on the input, thereby ruling out an important form of universal purification in both static and dynamical settings. Building on this, we show that, upon relaxing the requirement of exact purity, one can establish quantitative sample-complexity lower bounds for approximate purification that hold for arbitrary physically allowed strategies, whose scaling matches the performance of purification-related tasks across several different areas of quantum information processing. Moreover, this lower bound leads to a generalized standard quantum limit for learning arbitrary functions of a quantum state, greatly extending earlier results based on quantum Fisher information and revealing a deep connection between purification and quantum learning. Extending this principle to other important settings, we establish, for the first time, an exponential sample-complexity lower bound for approximate pure dilation state preparation and a no-go theorem for approximate bosonic Gaussian state purification with passive Gaussian operations, establishing much more stringent limitations under practical operational constraints.

04.
arXiv (CS.CL) 2026-06-16

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models

This technical report introduces VibeThinker-3B, a compact dense model with 3B parameters developed to investigate how far verifiable reasoning can be pushed within a strictly small-model regime. Building upon the Spectrum-to-Signal post-training paradigm, we systematically enhance the model through an optimized pipeline that includes curriculum-based supervised fine-tuning, multi-domain reinforcement learning, and offline self-distillation. Experimental evaluations demonstrate that VibeThinker-3B achieves frontier-level performance on highly demanding verifiable tasks. Specifically, it attains a score of 94.3 on AIME26 (improving to 97.1 with claim-level test-time scaling), an 80.2 Pass@1 on LiveCodeBench v6, and exhibits strong out-of-distribution generalization with a 96.1\% acceptance rate on recent unseen LeetCode contests. This effectively places it in the performance band of first-tier reasoning systems, matching or exceeding flagship models that are orders of magnitude larger, such as DeepSeek V3.2, GLM-5, and Gemini 3 Pro. Furthermore, a score of 93.4 on IFEval confirms that this extreme reasoning enhancement does not compromise strict instruction controllability. Extending our previous 1.5B work, these findings motivate the Parametric Compression-Coverage Hypothesis, which views verifiable reasoning as compressible into compact reasoning cores, while open-domain knowledge and general-purpose competence require broad parameter coverage over facts, concepts, and long-tail scenarios. This perspective suggests that compact models are not merely deployment-efficient substitutes, but a complementary path toward frontier-level performance in parameter-dense capability regimes.

05.
arXiv (CS.AI) 2026-06-15

Large-scale semantic mapping of learner agency and autonomy reveals what measurement and generative AI research overlook

arXiv:2606.10881v2 Announce Type: replace Abstract: Learner agency and autonomy are foundational to personal development, yet a pervasive "jingle-jangle" fallacy (i.e. identical terms denoting different constructs, distinct terms denoting identical ones) has substantially hindered cumulative knowledge. Treating meaning as a phenomenon constituted through use in linguistic practice, we extracted 8,954 definitions and 2,700 scale items from over 14,000 publications, to investigate how researchers actually used learner agency and autonomy with a semantic analysis pipeline. The definitional landscape of two constructs resolves into three dimensions: regulation and control of learning (task), intrinsic motivation and internal decision-making (person), and social-relational action (sociocultural), thereby empirically quantifying the jingle-jangle fallacy. Existing scales, however, systematically underrepresent the sociocultural dimension. Critically, current generative AI research in education concentrates on learning regulation and control, narrowing the behavioral repertoire that AI-mediated learning environments are designed to cultivate. Beyond conceptual clarification, this work carries direct implications for conceptualization, measurement, and practice towards supporting the multidimensional learner agency and autonomy.

06.
arXiv (CS.CL) 2026-06-15

Pragmatic Inference for Moral Reasoning Acquisition: Generalization via Metapragmatic Links

While moral reasoning has emerged as a promising research direction for large language models (LLMs), achieving robust generalization remains a critical challenge. This challenge arises from the gap between what is said and what is morally implied. In this paper, we build on metapragmatic links and Moral Foundations Theory to close this gap. Specifically, we develop a pragmatic inference approach that enables LLMs, given a moral situation, to acquire the metapragmatic links between moral reasoning objectives and the social variables that influence them. We adapt this approach to three different moral reasoning tasks to demonstrate its adaptability and generalizability. Experimental results show that our approach significantly enhances LLMs' generalization in moral reasoning, paving the way for future research to leverage pragmatic inference across a wide range of moral reasoning tasks.

07.
arXiv (CS.CL) 2026-06-12

GENIE: A Fine-Grained Measure for Novelty

Large Language Models have consistently demonstrated a lack of creativity and diversity across tasks. Prior work has focused on addressing whether models are capable of generating creative outputs. Here, we aim to consider novelty and investigate what makes model-generated content novel or not novel in a task-specific manner. We propose a fine-grained evaluation metric GENIE to measure the novelty of responses along task-specific features with respect to a population of responses. We show that unlike GENIE, holistic metrics struggle to capture the high-dimensionality of novelty and do not provide insight on which properties they target. Finally, we use GENIE to measure the effectiveness of mitigation methods that address creativity to better understand where these methods can improve novelty.

08.
arXiv (CS.CL) 2026-06-11

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning

Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation. Zeroth-order (ZO) optimization avoids this overhead by estimating gradients through forward passes alone, yet it typically converges slowly because random Gaussian perturbations yield high-variance gradient estimates in high-dimensional parameter spaces. In this paper, we propose a plug-and-play framework that turns random perturbations into more effective descent directions. The key idea is to draw a small pool of candidate perturbations, evaluate their loss values, and then select or combine those that are best aligned with the optimization objective. We develop two instantiations of this idea: MeZO-GV, which forms a guiding vector from the contrast between low-loss and high-loss perturbation groups, and MeZO-Greedy, which keeps the single best perturbation within a fixed evaluation budget. We theoretically show that both strategies yield a larger per-step reduction in the objective than standard ZO estimation, leading to improved convergence rates. Experiments on LLMs of different scales and architectures confirm that the proposed methods integrate naturally with existing ZO optimizers and consistently improve convergence speed and task accuracy. On OPT-13B, our approach outperforms all ZO baselines across 11 benchmarks and exceeds gradient-based methods on 9 of them, while retaining the memory efficiency of forward-only optimization.

09.
arXiv (math.PR) 2026-06-11

On the spatio-temporal increments of nonlinear parabolic SPDEs and the open KPZ equation

arXiv:2508.05032v3 Announce Type: replace Abstract: We study spatio-temporal increments of the solutions to nonlinear parabolic SPDEs on a bounded interval with Dirichlet, Neumann, or Robin boundary conditions. We identify the exact local and uniform spatio-temporal moduli of continuity for the sample functions of the solutions. These moduli of continuity results imply the existence of random points in space-time at which spatio-temporal oscillations are exceptionally large. We also establish small-ball probability estimates and Chung-type laws of the iterated logarithm for spatio-temporal increments. Our method yields extension of some of these results to the open KPZ equation on the unit interval with inhomogeneous Neumann boundary conditions. Our key ingredients include new strong local non-determinism results for linear stochastic heat equation under various types of boundary conditions, and detailed estimates for the errors in linearization of spatio-temporal increments of the solution to the nonlinear equation.

10.
arXiv (quant-ph) 2026-06-11

Fisher geometry reshapes the effect of incompatibility in multiparameter quantum estimation

arXiv:2606.11343v1 Announce Type: new Abstract: Multiparameter quantum estimation faces two fundamental obstacles: sloppiness, i.e., anisotropy of the quantum Fisher information matrix (QFIM) that renders some parameter directions insensitive, and incompatibility, the non-commutativity of optimal measurements for different parameters. The trade-off bound $C_T$ captures their joint impact on precision, but it has remained unclear how the distribution of incompatibility across parameter planes affects its overall cost. Here we separate the total amount of incompatibility from its location. We introduce a dimensionless quantity $G_n^{(F)}$ that measures the alignment between the incompatibility distribution and the eigenvalues of the QFIM, and show how the Frobenius scale of the incompatibility contribution factorizes. We obtain a bound and prove the incompatibility cost lies between this bound and a rank-dependent multiple thereof. We also prove that at fixed sloppiness, or equivalently fixed Fisher volume, concentrating incompatibility into a single parameter plane reduces the optimized trade-off cost because the Fisher geometry can then be reshaped to allocate more Fisher area to that plane. A qutrit $SU(2)$ encoding numerically confirms that states with larger incompatibility strength can nevertheless incur a smaller cost if the matching factor $G$ is sufficiently small. Our results establish that the distribution of incompatibility relative to the Fisher eigenbasis is a central diagnostic for multiparameter estimation, beyond the total incompatibility strength.

11.
arXiv (quant-ph) 2026-06-19

Anomalous magneto-optical response at $\mathrm{RuO_2 / WSe_2}$ van der Waals interface

arXiv:2606.20262v1 Announce Type: cross Abstract: Ruthenium dioxide ($\mathrm{RuO_2}$) has been proposed as an altermagnetic candidate, although its magnetic ground state remains controversial. Here, we probe weak interfacial magnetic states at the surface of (001)-oriented $\mathrm{RuO_2}$ films using the magnetic proximity effect (MPE) in a van der Waals heterostructure consisting of monolayer tungsten diselenide ($\mathrm{WSe_2}$) atop $\mathrm{RuO_2}$. Temperature-dependent magneto-optical spectroscopy reveals an anomalous excitonic energy shift and a deviation from conventional Varshni behavior below 55 K that are absent in an encapsulated $\mathrm{WSe_2}$ control sample. The anomalous shift reverses sign upon field cooling with opposite magnetic field polarity, indicating a magnetic origin. Polarization-resolved measurements further show a nearly field-independent and fluctuating valley splitting in $\mathrm{WSe_2 / RuO_2}$ in strong contrast to the conventional linear Zeeman splitting observed in the control bare $\mathrm{WSe_2}$ sample. These results suggest that the valley states are governed predominantly by interfacial exchange fields associated with weak surface magnetic states in $\mathrm{RuO_2}$, which do not produce a conventional linear Zeeman response within the applied magnetic field range. Importantly, this approach enables direct optical probing of emergent surface magnetism without introducing an additional ferromagnetic layer, positioning MPE-based optical probing as a tool for investigating weak surface magnetism and offering new possibilities for studying magnetic materials with controversial magnetic states.

13.
arXiv (quant-ph) 2026-06-16

Suppressing Intrinsic Spin-Phonon Errors in Trapped-Ion Quantum Simulation

arXiv:2606.15518v1 Announce Type: new Abstract: Trapped-ion quantum simulators realize programmable spin models through phonon-mediated interactions. For Hamiltonians with noncommuting terms, however, the same phonon bus generates intrinsic spin-phonon errors that strongly distort the target dynamics. Because these errors are governed by the full time history of the spin-dependent phonon motion, they survive standard loop-closing control and limit simulation accuracy. Using a sequence of frame transformations, we isolate the residual error dynamics and show that this intrinsic error can be strongly suppressed while preserving programmable Ising couplings. Full spin-boson simulations of multi-ion chains demonstrate orders-of-magnitude lower error than both constant-drive and conventional loop-closing protocols. These results remove a central precision barrier in trapped-ion analog quantum simulation and enable accurate programmable simulation of noncommuting many-body Hamiltonians and dynamical protocols.

14.
arXiv (CS.AI) 2026-06-11

Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

arXiv:2606.11409v1 Announce Type: cross Abstract: Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly. In practice, the computational expense of different attack strategies can vary by orders of magnitude. Consequently, ASR at a fixed budget can obscure the true effort required to jailbreak a model, thereby making it hard to determine whether an attack's cost justifies its payoff to the attacker. We propose a compute-aware evaluation framework based on computational pressure, measured in cumulative floating-point operations (FLOPs), as a proxy for adversarial effort. We introduce risk-compute curves, which map compute budgets to attack risk, and derive two metrics that summarize the average pressure required for a given attack to succeed. Across ten models spanning three families and four different stages in language model training and alignment, evaluated with three attack strategies (gradient-based, iterative refinement, and template-based) on two jailbreak robustness benchmarks, we find: (1) alignment training has non-monotonic effects on compute-space robustness; (2) scaling model size reduces gradient-based attack effectiveness but has limited impact on cheaper template-based attacks; (3) gradient-based attacks optimized on a surrogate model can transfer to a separate target model, providing a way to reduce attacker costs; (4) compute cost varies by up to ${\approx}5{\times}$ across harm categories within a single model; and (5) safety-aligned RL increases aggregate cost while leaving some categories disproportionately accessible. We release our framework to enable compute-aware risk assessment and evaluation.

15.
arXiv (math.PR) 2026-06-16

Sharp One-Dimensional Sub-Gaussian Comparison in Convex Order

作者:

arXiv:2604.26819v2 Announce Type: replace Abstract: We prove that any random variable $X$ whose moment generating function is point-wise upper bounded by that of $ G \sim \mathcal{N}(0,1) $ must be dominated by $ G/\mathbb{E}[|G|] $ in convex order, meaning $ \mathbb{E}[f(X)] \le \mathbb{E}[f(G/\mathbb{E}[|G|])] $ for all convex $f$. This is sharp as witnessed by $ X \sim \mathrm{Unif}(\{-1,1\}) $ and $ f(x) = |x| $.

16.
arXiv (CS.LG) 2026-06-16

Machine Learning-Driven Chemical Reactor Network Modeling of the Sandia-D Flame

arXiv:2606.14729v1 Announce Type: cross Abstract: Turbulent combustion simulations are crucial for many scientific and engineering systems. However, the high cost to fully resolve the complex multiscale and multiphysics behavior makes direct simulation typically infeasible. The equivalent reactor network (ERN) approach attempts to improve computational efficiency by replacing a multidimensional turbulent simulation with a series of much cheaper 0-D and 1-D chemical reactors, providing a surrogate model that retains detailed chemistry at the cost of simplified flow physics. However, their development remains a challenge, often requiring either expert analysis, or automated approaches that sacrifice accuracy. In this work, we develop an automated machine-learning-assisted framework for constructing ERNs of the Sandia-D turbulent methane/air flame. Principal component analysis is first used to reduce high-dimensional thermochemical computational fluid dynamics (CFD) data to a low-dimensional latent space, where k-means clustering identifies physically interpretable flame regions used to initialize a reactor-network graph. This initialization is then refined using finite-difference gradient descent wrapped around non-differentiable Cantera reactor simulations. Across 30 RANS simulations spanning a range of pilot temperatures and inlet methane compositions, the optimized 7-reactor ERN achieves a maximum-temperature $R^2$ score of 0.7945 while preserving a $\sim6000\times$ speedup over the CFD solver. Outlet CO prediction remains more challenging, with a final $R^2$ score of $-0.4183$, but improves substantially from the unoptimized clustering initialization. These results show that unsupervised thermochemical feature extraction can provide effective physics-informed initializations for ERN construction, while gradient-based refinement can significantly improve predictive accuracy without manual reactor-network design.

17.
arXiv (CS.LG) 2026-06-16

PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates

arXiv:2606.16602v1 Announce Type: new Abstract: Neural operator models trained on simulation data often lose accuracy when applied to experimental measurements due to the sim-to-real gap. Standard fine-tuning with limited real data can reduce this gap, but it may also damage the core physics-relevant representations learned during pretraining. Although knowledge-preserving adaptation has been widely investigated in vision or language tasks, it remains unclear whether these methods are suitable for neural operators whose architectures and protected knowledge are fundamentally different. Neural operators need to preserve core-scale physical structures rather than semantic or visual features. We propose PhysGuard, a physics-preserving framework for accurate sim-to-real adaptation of neural operators. Specifically, PhysGuard uses the empirical Fisher Information Matrix computed on simulation data to identify physics-critical parameter directions, then restricts fine-tuning updates to directions that do not interfere with them. A layer-wise Gram-matrix formulation makes this efficient for models with millions of parameters, while an adaptive threshold automatically determines the protected subspace size. A spectral probe experiment shows that the dominant Fisher directions are strongly associated with low-frequency output structures. Experiments on benchmark across four neural operator architectures and different physical systems show that PhysGuard performs strongly on most evaluation metrics compared to baselines. The benefits are most evident under severe domain shift, where it reduces low-frequency error by up to 32\% compared to standard fine-tuning while maintaining adaptability. Our code is available at https://github.com/ZhouChaunge/PhysGuard.

18.
Nature (Science) 2026-06-10

Building user-driven climate adaptation products

Climate adaptation products have traditionally been developed using a supply-driven model reliant on available climate information, leading to usability gaps1–4. To better meet user needs, the climate services field has recognized a need to shift towards a demand-driven model emphasizing co-production, that is, user-driven, scientifically informed products created through shared knowledge practices1–5. However, co-production can be challenging, especially for researchers unfamiliar with the approach or for digital and software-based products with complex user needs2,5–8. User-centred design, from the human–computer interaction field, offers a process that could complement co-production approaches to product development, yet its potential remains underexplored2. Here we show how user-centred design can be integrated into, and strengthen, co-production approaches for building user-driven climate adaptation products. Through a systematic review of the co-production and user-centred design literature, we identify key processes, mechanisms and best practices for both approaches. Our findings offer practical guidance for researchers and propose an integrated approach for developing climate adaptation products that are useful, usable and used. A systematic review and analysis shows how user-centred design can be integrated into, and strengthen, co-production approaches for building user-driven climate adaptation products.

19.
arXiv (CS.LG) 2026-06-12

Disparate Impact in Synthetic Data Generation

arXiv:2606.13105v1 Announce Type: new Abstract: We revisit the fairness notion of disparate impact for synthetic data generation (SDG), that assesses whether the utility of generated records is the same across sensitive groups. Our approach departs from existing work on fair SDG, that address the problem of correcting for undue biases in the observed distribution, hence redefining SDG as learning a distribution that is not that of the real data. By contrast, non-disparate impact is notably achieved when the synthetic and real distributions are the same. We expose reasons why SDG may fail to reach that solution and discuss why approximation and estimation errors occur and can be disparate across groups. We notably look into the expressive power of SDG methods relative to distribution complexity, sampling errors due to group proportions, and estimation errors induced by differential privacy mechanisms. We illustrate cases of disparate impact on both artificial and real-world data, focusing on SDG methods that rely on probabilistic graphical models. We also introduce a strategy of learning group-wise SDG models and illustrate how it can improve both the overall utility and its parity in many settings.

20.
arXiv (CS.CV) 2026-06-11

Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks

While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations. Pixel-wise attacks frequently introduce unnatural, high-frequency visual artifacts, while latent-space frameworks are confined by the limited search space of low-dimensional manifolds and inherent reconstruction flaws. To resolve these limitations, we propose Latent Geometric Chords (LGC) for Query-Efficient Decision-Based Adversarial Attacks alongside a variant, LGC-H. At its core, LGC navigates decision boundaries by executing a curvature-aware geometric search within a compressed semantic manifold. To guarantee high visual fidelity and circumvent dimensionality bottlenecks, we introduce a Residual-based Adversarial Generation (RAG) mechanism. RAG isolates semantic perturbations as geometric chords and superimposes them directly onto the original source image. RAG substantially resolves baseline reconstruction flaws and effectively doubles the permissible search space dimensions. Experimental results demonstrate that LGC achieves robust cross-dataset transferability and substantially outperforms state-of-the-art baselines. Notably, our method, LGC, minimizes perturbation magnitudes while achieving state-of-the-art visual fidelity–with a Structural Similarity Index Measure (SSIM) exceeding 0.99 and a Learned Perceptual Image Patch Similarity (LPIPS) below 0.01 at 5000 queries–and sustaining high attack success rates under stringent perceptual constraints, successfully compromising adversarially trained robust models. The source code is available at: https://github.com/eihmuekhine/Latent-Geometric-Chords.

21.
arXiv (CS.LG) 2026-06-16

Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance

arXiv:2606.15531v1 Announce Type: new Abstract: Fine-tuning aligned language models on benign tasks (e.g. math tutoring) systematically breaks safety guardrails, even when training data contains no harmful content. While mechanistic approaches have shed light on where alignment resides in model weights, they do not by provide a general formal framework for deriving guarantees about when fine-tuning degrades it – leaving the field without principled tools for predicting or preventing alignment collapse. We develop a local geometric framework through geometric analysis of parameter-space trajectories and apply it to understand the fragility of alignment in fine-tuning. While first-order analysis suggests orthogonal updates are safe, we prove this is illusory: the curvature of the fine-tuning loss induces second-order acceleration that can induce second-order drift into alignment-sensitive regions. We formalize a construct of our framework as the Alignment Instability Condition (AIC), three geometric properties that, when present, are sufficient to guarantee degradation. Our main result proves quartic onset of alignment degradation along gradient-flow trajectories, determined by how sharply alignment depends on specific parameters and how strongly tasks couple to these parameters. These findings yield formal sufficient conditions under which static first-order protection can fail under gradient descent. We further empirically validate the framework's foundations, showing that the Fisher Information Matrix provides a proxy for the degree of safety degradation across diverse fine-tuning.

22.
arXiv (CS.AI) 2026-06-17

Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement Learning

arXiv:2606.18111v1 Announce Type: cross Abstract: Fairness is an important aspect of decision-making in multi-objective reinforcement learning (MORL), where policies must ensure both optimality and equity across multiple, potentially conflicting objectives. While single-policy MORL methods can learn fair policies for fixed user preferences using welfare functions such as the generalized Gini welfare function (GGF), they fail to provide the diverse set of policies necessary for dynamic or unknown user preferences. To address this limitation, we formalize the fair optimization problem in multi-policy MORL, where the goal is to learn a set of Pareto-optimal policies that ensure fairness across all possible user preferences. Our key technical contributions are threefold: (1) We show that for concave, piecewise-linear welfare functions (e.g., GGF), fair policies remain in the convex coverage set (CCS), which is an approximated Pareto front for linear scalarization. (2) We demonstrate that non-stationary policies, augmented with accrued reward histories, and stochastic policies improve fairness by dynamically adapting to historical inequities. (3) We propose three novel algorithms, which include integrating GGF with multi-policy multi-objective Q-Learning (MOQL), state-augmented multi-policy MOQL for learning non-statoinary policies, and its novel extension for learning stochastic policies. We evaluate our algorithms across various domains and compare our methods against the state-of-the-art MORL baselines. The empirical results show that our methods learn a set of fair policies that accommodate different user preferences.

23.
arXiv (CS.AI) 2026-06-17

Online LLM Selection via Constrained Bandits with Time-Varying Demand

arXiv:2606.17489v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in edge-cloud inference systems to handle diverse user tasks with heterogeneous accuracy, latency, and cost profiles. Selecting the appropriate LLM for each incoming task is critical for ensuring service quality and efficient resource utilization. However, model heterogeneity, stochastic and unknown performance characteristics, and time-varying task demands make static selection strategies inadequate. Real-world deployments often impose hard resource budgets such as monetary expenditure limits, along with soft service-level requirements such as latency guarantees. These constraints introduce additional challenges for online decision-making. We formulate this problem as a constrained stochastic bandit learning task, where the learner sequentially selects models under both packing-type (hard) and covering-type (soft) constraints, while adapting to time-varying task demand. The learner operates without access to the underlying reward, cost, or latency distributions and must rely on partial feedback. We develop a novel online learning algorithm that leverages confidence-bound estimates and demand predictions to balance reward maximization with long-term constraint satisfaction. We provide theoretical guarantees showing sublinear regret and sublinear covering constraint violations compared to an offline benchmark with full information. Experimental results on synthetic workloads demonstrate the effectiveness and robustness of our approach in dynamic, resource-constrained environments.

24.
arXiv (CS.AI) 2026-06-16

Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment

arXiv:2606.14948v1 Announce Type: cross Abstract: LLMs have substantially improved software engineering yet real-world development requires architectural understanding. Such understanding is prohibitively expensive to label manually and impossible to verify through tests alone. We propose an agentic judging pipeline using a strong LLM as a scalable proxy for expert architectural evaluation, comprising two judges: the Architecture Complexity Judge (ACJ), which estimates codebase-specific architectural understanding a task demands, and the Architecture Quality Judge (AQJ), which evaluates patch conformance to repository-specific architectural conventions via source-grounded rubrics. Fine-tuning Qwen3-8B/14B/32B on 3,360 curated instances achieves resolved rates of up to 27.2% on SWE-bench Verified - up to 540% over the base model and 256% over unfiltered fine-tuning. Meanwhile, the trained models achieve strong cross-language generalization and consistent improvements in architectural patch quality.

25.
arXiv (quant-ph) 2026-06-16

Benchmarking Quantum Computers via Protocols, Comparing IBM's Heron vs IBM's Eagle

arXiv:2603.04377v3 Announce Type: replace Abstract: As quantum computing hardware rapidly advances, objectively evaluating the capabilities and error rates of new processors remains a critical challenge for the field. A clear and realistic understanding of current quantum performance is essential for guiding research priorities and driving meaningful progress. In this work, we apply and extend a protocol-based benchmarking methodology (Meirom, Mor, Weinstein Arxiv 2505.12441) that utilizes well-defined \underline{quantumness} thresholds. By evaluating performance at protocol level rather than the gate level, this approach provides a transparent and intuitive assessment of whether specific quantum processors, or isolated sub-chips within them, can demonstrate a practical quantum advantage. To illustrate the utility of this method, we compare two generations of IBM quantum computers: the older Eagle architecture and the newer Heron architecture. Our findings reveal the genuine operational strengths and limitations of these devices, demonstrating substantial performance improvements in the newer Heron generation. This work was made possible by IBM Quantum policies that enable independent and objective assessment of its quantum computers and sub-chips. We strongly encourage other companies to emulate the independent qubit availability and the fair pricing that allow researchers to perform such assessments.