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。

02.
arXiv (CS.CL) 2026-06-19

Large Language Models Hack Rewards, and Society

Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal regulations are structurally similar to reward functions. They define measurable outcomes, thresholds, and exceptions, while often leaving institutional intent only partially specified. We hypothesise that the RL training process may exploit these gaps and therefore ask whether models' well-known tendency to hack reward functions during RL can scale into a more consequential failure mode named societal hacking: discovering loopholes in the rules society runs on. To study this phenomenon, we introduce SocioHack, a sandbox of 72 societal environments, and find that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery. Models learn to hack the social rules and generate strategies that remain technically compliant while defeating regulatory intent, and current LLM safeguards provide only limited mitigation. Therefore, collecting in-the-wild feedback for model training requires greater caution, and we need a next-generation post-training paradigm for safely iterating LLMs in real society.=

03.
arXiv (CS.AI) 2026-06-11

The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning

arXiv:2505.03296v2 Announce Type: replace-cross Abstract: We present Mixture of Discrete-time Gaussian Processes (MiDiGap), a novel approach for flexible policy representation and imitation learning in robot manipulation. MiDiGap enables learning from as few as five demonstrations using only camera observations and generalizes across a wide range of challenging tasks. It excels at long-horizon behaviors such as making coffee, highly constrained motions such as opening doors, dynamic actions such as scooping with a spatula, and multimodal tasks such as hanging a mug. MiDiGap learns these tasks on a CPU in less than a minute and scales linearly to large datasets. We also develop a rich suite of tools for inference-time steering using evidence such as collision signals and robot kinematic constraints. This steering enables novel generalization capabilities, including obstacle avoidance and cross-embodiment policy transfer. MiDiGap achieves state-of-the-art performance on diverse few-shot manipulation benchmarks. On constrained RLBench tasks, it improves policy success by 76 percentage points and reduces trajectory cost by 67%. On multimodal tasks, it improves policy success by 48 percentage points and increases sample efficiency by a factor of 20. In cross-embodiment transfer, it more than doubles policy success. We make the code publicly available at https://midigap.cs.uni-freiburg.de.

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

Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework

The rapid rise in LLM capabilities has made AI agents increasingly viable across a broad range of tasks. Among the most promising applications is building production-ready customer-facing agents, a challenge that demands coordinated excellence in evaluation methodology, context engineering, training, and online measurement. Yet these critical pillars are typically developed in isolation, creating blind spots that only surface after deployment. In this paper, we present a unified framework that bridges offline development with online impact for customer support AI agents at Nubank, a company with 100M+ users. Our approach integrates several key components: (1) structured context engineering tailored to customer support agents, (2) systematic human-in-the-loop prompt iteration, (3) rigorous LLM judge evaluation with measured inter-rater agreement and GEPA optimization for consistency, and (4) ideation-to-production validation. A central insight is that evaluation-pipeline quality directly determines iteration velocity. We present results from five production deployments spanning distinct domains: card delivery, debt management, credit-limit support, card management, and product explanation. These deployments deliver consistent customer-satisfaction gains while substantially accelerating iteration. In our card-delivery deployment, large-scale A/B testing yields a 37 percentage-point improvement in AI transactional Net Promoter Score and a 29 percentage-point gain in self-service rate over prior agent variants, alongside a strong correlation between offline simulation metrics and online outcomes, demonstrating that eval-driven development reliably predicts production impact. On most use cases, AI satisfaction reaches within a few percentage points of expert human agents.

05.
medRxiv (Medicine) 2026-06-16

Supplementation with Arabinoxylan Dietary Fiber at Low Doses Produces Behavioral, Metabolic, and Gut Microbial Changes in Healthy, Overweight Adults: A Randomized Placebo-Controlled Trial

Background: Dietary fiber comprises a heterogeneous group of compounds with distinct physicochemical properties and biological effects. As such, functional outcomes observed for one fiber cannot be generalized to others. Some fermentable fibers, such as arabinoxylan, may exert biologically selective effects across multiple physiological domains, highlighting the need to evaluate individual ingredients for their domain-specific activity in controlled human studies. Methods: In this randomized, double-blind, parallel, 3-arm, placebo-controlled trial, healthy, overweight adults were assigned to consume one of two low doses of an arabinoxylan dietary fiber (3.5g or 5g) or placebo over the intervention period. Self-reported appetite sensations were assessed as the primary outcome using validated visual analogue scales. Secondary and exploratory endpoints included lipid parameters, gastrointestinal outcomes, mood-related measures, and gut microbiota composition and fermentation-derived metabolites. Analyses were conducted in the full analysis set and a high-compliance population to assess responses under sustained intake conditions, as per the intended dosing regimen. Results: The primary endpoint of appetite sensations did not differ between either arabinoxylan group and placebo. In contrast, evidence of microbial fermentation and selective microbiota engagement was observed. These responses occurred alongside consistent and favorable changes in lipid parameters under conditions of sustained intake, including reductions in low-density lipoprotein cholesterol and triglycerides. Additional outcomes, including gastrointestinal symptoms and mood, demonstrated domain-specific responses. Conclusion: This study demonstrates that supplementation with low doses of arabinoxylan dietary fiber elicit biologically selective, domain-specific effects across metabolic, microbial, gastrointestinal, and behavioral outcomes, particularly under conditions of sustained intake. These responses occurred independently of changes in appetite sensation, indicating that functional effects were not mediated through appetite-related pathways. Collectively, the findings highlight the ingredient's biological versatility and contextual responsiveness across physiological systems, and suggest its prebiotic potential through alignment with ISAPP's definition of a prebiotic, supporting further investigation of specific mechanistic pathways. Clinical trial registration: https://clinicaltrials.gov/study/NCT06884449, identifier: NCT06884449

07.
arXiv (CS.AI) 2026-06-19

Global Ease of Living Index: a machine learning framework for longitudinal analysis of major economies

arXiv:2502.06866v3 Announce Type: replace-cross Abstract: The drastic changes in the global economy, geopolitical conditions, and disruptions such as the COVID-19 pandemic have impacted the cost of living and quality of life. It is essential to comprehend the long-term implications of the cost of living and quality of life in major economies. A transparent and comprehensive living index must include multiple dimensions of living conditions. In this study, we present an approach to quantifying the quality of life through the Global Ease of Living Index that combines various socio-economic and infrastructural factors into a single composite score. Our index utilises economic indicators that define living standards, which could help in targeted interventions to improve specific areas. We present a machine learning framework to address missing data for certain economic indicators in specific countries. We then curate and update the data and use a dimensionality reduction approach (Principal Component Analysis and Factor Analysis) to create the Ease of Living Index for major economies since 1970. Our work significantly adds to the literature by offering a practical tool for policymakers to identify areas needing improvement, such as healthcare systems, employment opportunities, and public safety. Our approach with open data and code can be easily reproduced and applied to various contexts, providing transparency and accessibility for ongoing research and policy development in quality-of-life assessment.

08.
bioRxiv (Bioinfo) 2026-06-19

Tox21mer, A transformer foundation model for Tox21 high-throughput concentration-response curves data

The U.S. Tox21 collaboration has generated a large reference library of high-throughput concentration-response assays. Here we present Tox21mer, a 43.5-million-parameter transformer that encodes each Tox21 concentration-response curve together with assay metadata into a 768-dimensional representation. Tox21mer was pretrained on ~2.5 million curves from 102 assay protocols and 6,727 compounds using masked-response reconstruction as the primary objective, with low-weight auxiliary supervision on assay outcome and AC50. To evaluate the learned representation, we trained lightweight probes on frozen embeddings from concentration-response curves of held-out compounds. The representation supported a macro-F1 of 0.985 for three-class outcome prediction (agonist, antagonist, inactive), a binary F1 of 0.994 for active/inactive prediction, and an R2 of 0.87 for log10(AC50). The learned embeddings formed coherent groupings by curve-class category. A masked-only pretraining variant retained near-baseline probe performance, indicating that the representation is learned largely from the self-supervised objective rather than from auxiliary labels. Ablation analyses further showed that predictive performance depends mainly on curve-level response-value distributions conditioned on assay context, with limited reliance on detailed within-curve ordering. Tox21mer thus provides a reusable foundation representation for Tox21 concentration-response data that can support extrapolation to untested compounds through integration with chemical features or distillation into chemistry-only student models for large-scale external screening.

09.
arXiv (quant-ph) 2026-06-16

Phase controlled spectral topology, dynamic stability and sensitivity in Non-Hermitian Cavity Magnonics

arXiv:2606.16522v1 Announce Type: new Abstract: We theoretically investigate a non-Hermitian cavity-magnon platform in which coherent photonmagnon interactions and reservoir-mediated dissipative coupling interfere through a single externally tunable phase. We show that this interference phase provides a universal control parameter that continuously rotates the effective coupling between Hermitian and anti-Hermitian regimes, enabling dynamic transitions between level repulsion and level attraction without modifying intrinsic system parameters. The resulting phase-controlled non-Hermitian topology gives rise to exceptional points, linewidth engineering, and zero-damping conditions. Owing to the propagation-direction dependence of the dissipative interaction, the system further exhibits strong nonreciprocal transport and phase-tunable isolation arising from asymmetric hybridization of the cavity and magnon modes. Beyond its spectral and transport properties, we establish a direct connection between nonHermitian spectral topology and nonequilibrium population dynamics. The interference phase governs the stability of the hybrid modes, driving transitions between stable relaxation, critical slowing down near exceptional points, oscillatory energy exchange, and exponentially amplified dynamics. We further demonstrate that the same phase-controlled exceptional topology can be exploited for enhanced sensing, where the eigenvalue response exhibits the characteristic square-root scaling associated with exceptional-point physics. Our results provide a unified framework linking spectral topology, directional transport, dynamical stability, and sensing functionality through reservoirengineered interference in cavity magnonic systems.

10.
arXiv (CS.LG) 2026-06-24

KLip-PPO: A per-sample KL perspective on PPO-Clip

arXiv:2606.23932v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) is the standard policy-gradient algorithm for on-policy reinforcement learning. The literature presents it in two forms, a clipped surrogate that bounds the importance ratio between successive policies and a Kullback-Leibler penalty between them. These forms are treated as separate algorithms with their own gradients, their own hyperparameters, and their own reference implementations, and a sizeable body of empirical work compares them. We show that the gradient of the clipped surrogate is reproduced exactly by a Kullback-Leibler surrogate whose coefficient varies per sample, with closed-form dependence on the importance ratio and the advantage. The identity holds at every minibatch step and across the entire inner loop, and on five MuJoCo continuous-control benchmarks the two losses produce indistinguishable training curves. The reformulation exposes a structural feature of the clipped surrogate that the min notation hides. PPO-Clip's implicit per-sample penalty is a step function at the boundary of the trust region, and the shape of this coefficient is the natural design axis for generalising the algorithm. We sketch the resulting follow-up directions in the discussion.

11.
arXiv (CS.LG) 2026-06-16

libhmm: A Modern C++20 Library for Hidden Markov Models with Correct MLE Emission M-Steps

作者:

arXiv:2605.29208v2 Announce Type: replace-cross Abstract: We describe libhmm, a C++20 library for Hidden Markov Model parameter estimation, sequence decoding, and model selection. libhmm addresses two gaps in existing software: the absence of a well-maintained, zero-dependency C++ HMM library suitable for embedding in production systems, and the widespread use of method-of-moments (MOM) approximations in the emission distribution M-step of the Baum-Welch algorithm. The library implements correct maximum likelihood estimators for sixteen scalar emission distributions, including an ECME algorithm for the location-scale Student-t distribution, Newton-Raphson maximization for Gamma, Beta, Weibull, and Negative Binomial distributions, and the von Mises distribution for circular data. All forward-backward and Viterbi calculations operate in full log-space. SIMD acceleration is provided for AVX-512, AVX2, SSE2, and ARM NEON via compile-time dispatch with scalar fallback. Version 4 adds multivariate observation support via the BasicHmm template, with three multivariate emission families (diagonal Gaussian, full-covariance Gaussian, and independent components) each with correct weighted MLE M-steps. Python bindings are available via the companion package pylibhmm. We compare libhmm against established C and C++ HMM libraries and against published R reference packages on seven real-data benchmarks, and discuss the architectural tradeoffs made in the design.

12.
arXiv (CS.CV) 2026-06-24

Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search

We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Building on a hand-crafted heterogeneous MoE reference model, we replace manual design with a deterministic code-assembly generator that systematically combines base architecture families drawn from the LEMUR database into MoE4 ensembles, each governed by a convolutional gating network with temperature scaling, mixup augmentation, and cosine-annealed learning rate scheduling. Over a 28-day campaign on an NVIDIA RTX 4090, the pipeline generated 4,463 candidate models across 197 batches, of which 1,021 were evaluated successfully. A critical finding emerged from the campaign: due to alphabetical enumeration via itertools.combinations, the entire explored search space (4.8% of the theoretical 23,751 possible 4-family combinations) is anchored to a single family, AirNet. We characterise this coverage bias precisely, identify the root cause in the generator, and propose a stratified random sampling fix. Within the AirNet anchored scope, ShuffleNet and MobileNetV3 consistently co-produce the highest-accuracy ensembles (mean accuracy up to 0.632), while FractalNet and MNASNet are identified as low-yield families warranting exclusion in future campaigns. The pipeline, analysis artefacts, and corrected generator are released as part of the open-source NNGPT project at https://github.com/ABrain-One/nn-gpt

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

Efficient Implementation of a Single-Qutrit Gate Set via Coherent Control

arXiv:2507.06860v2 Announce Type: replace Abstract: Qutrits offer the potential for enhanced quantum computation by exploiting an enlarged Hilbert space. However, the synthesis of high-fidelity and fast qutrit gates, particularly for single qutrits, remains an ongoing challenge, as it involves overcoming intrinsic constraints in quantum platforms. Here, we develop a novel framework for the efficient implementation of a single-qutrit gate set via coherent control, leveraging SU(3) dynamics while obviating platform-specific constraints such as those arising from the selection rule. As a proof-of-principle demonstration, we realize 35-ns qutrit Hadamard and X gates using a superconducting transmon, achieving an average fidelity of 99.5\%, as verified by randomized benchmarking. We further demonstrate two paradigmatic quantum circuits, which can be naturally extended to scalable qudit algorithms for phase estimation and parity check. In addition, we propose an SU(3)-based decomposition strategy for an arbitrary single-qutrit gate and numerically demonstrate its substantial efficiency improvement over conventional SU(2)-based protocols. By addressing the challenge of efficiently implementing single-qutrit gates, our protocol paves the way for realizing high-performance qutrit processors in diverse quantum platforms.

14.
arXiv (CS.CL) 2026-06-24

EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL

Text-to-SQL enables users to query databases using natural language by generating executable SQL queries. Recent methods have increasingly adopted Large Language Models based reinforcement learning (RL) to leverage execution feedback for training. However, existing RL methods assign uniform query-level rewards to all clauses in a SQL query, treating correct and incorrect clauses equally. This coarse-grained reward design leads to insufficient learning signals for correct SQL generation. To address this issue, we propose EXPO-SQL (EXecution-based clause-level Policy Optimization for Text-to-SQL) which provides fine-grained supervision through clause-level rewards. To assign clause-level rewards, our method identifies erroneous clauses by analyzing execution results, including error messages and clause-wise incremental execution. Experiments on widely-used Text-to-SQL benchmarks demonstrate that EXPO-SQL significantly outperforms existing supervised fine-tuning, prompting, and RL-based methods through fine-grained clause-level learning. Our code is available at https://github. com/jhn25/EXPO-SQL.

15.
arXiv (CS.CV) 2026-06-16

Facial Affect Analysis for Service-Oriented Systems: Advances, Challenges, and Future Visions

Facial Affect Analysis (FAA) is evolving from a stand-alone recognition task into a reusable perception capability for Service-Oriented Software Ecosystems (SoSE). This paper preserves the FAA methodological core while reframing recent advances through systems-engineering requirements for composable and dependable services. We review representative progress in static and dynamic expression analysis, action-unit and micro-expression modeling, and modern CNN, Transformer, graph, and hybrid architectures, then interpret these advances by their operational fit in edge, cloud, and hybrid service pipelines. The synthesis emphasizes SoSE concerns that determine deployability: service contracts for uncertainty-aware outputs, latency and availability envelopes, lifecycle monitoring and recalibration, governance-aware integration, and interoperability across independently evolving components. Our analysis shows that benchmark gains alone are insufficient for SoSE readiness; robustness under shift, intervention stability, fairness, privacy posture, and runtime guarantees are equally critical. We conclude with a roadmap for treating FAA as an operational service component with explicit interfaces, measurable quality attributes, and accountable lifecycle management.

16.
arXiv (CS.CV) 2026-06-25

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning

Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relevant visual evidence and ground their reasoning in local image regions. Existing agentic methods typically rely on reinforcement learning with verifiable rewards or supervised fine-tuning on large-scale annotated reasoning traces, leading to costly exploration, hand-designed verification rules, or heavy dependence on textual supervision. A natural way to avoid such external answer labels is to learn from trajectories sampled by the student itself, which points to On-Policy Distillation (OPD). To understand what OPD can and cannot provide for visual reasoning, we revisit it as negative-free stop-gradient alignment. This perspective shows that, although OPD provides effective token-level correction, its ceiling is constrained by the absence of trajectory-level discrimination. Motivated by these observations, we propose V-Zero, an answer-label-free framework for visual reasoning with contrastive evidence gating. V-Zero uses no annotated textual answer labels; instead, during training it pairs a question-relevant regional crop with a negative visual view to evaluate student-sampled trajectories and gate dense token-level distillation. Experiments on multiple visual reasoning benchmarks show that V-Zero consistently improves fine-grained visual reasoning while preserving strong generalization. Notably, V-Zero is more than 5$\times$ faster than previous supervised fine-tuning methods and more than 10$\times$ faster than reinforcement learning baselines. Code and dataset will be released at https://github.com/eVI-group-SCU/V-Zero

17.
Nature (Science) 2026-06-17

Confined migration induces non-lethal DNA damage in developing neurons

Migratory cells tend to have soft nuclei that deform and penetrate narrow spaces1,2. Extensive nuclear deformation during migration can cause nuclear-envelope rupture and DNA damage in cancer cells, which may contribute to malignant transformation during tumour progression3–6. However, the importance of DNA damage in physiological migration is less well understood. Here we demonstrate that the migration of neurons in developing cerebral and cerebellar cortices is accompanied by massive DNA double-stranded breaks (DSBs) due to mechanostress during passage through narrow interstitial spaces. In contrast to many other migratory cells, these DSBs occur without detectable nuclear envelope rupture. Confined migration increases topoisomerase-IIβ covalently bound DSBs, and these lesions are repaired through non-homologous end-joining during brain development without causing cell death. Genome sequencing revealed that DSBs tend to occur at transcriptionally inactive regions. The deletion of ligase IV at the onset of neuronal migration leads to persistent DSB accumulation in cerebellar neurons with moderate transcriptional changes in genes related to synaptic function, neuronal development and stress and immune responses. The mutant mouse develops mild motor deficits in later life, suggesting that the DNA damage generated during normal brain development poses a potential disease risk if left unrepaired. The migration of neurons in developing cerebral and cerebellar cortices is accompanied by massive DNA double-strand breaks due to mechanostress during passage through narrow interstitial spaces.

18.
arXiv (CS.CL) 2026-06-17

Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs

Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text–image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones. Our in-depth empirical analysis reveals that the entity knowledge in MLLMs is not stored as a unified representation, but is instead distributed across disentangled modality-specific pathways. As a result, updates biased toward multimodal queries fail to propagate effectively to unimodal circuits. To bridge this gap, we propose DECODE, which explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge. Extensive experiments demonstrate that DECODE consistently achieves effective knowledge updates under different modality triggers, thereby mitigating editing decoupling failures.

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

Meta Flow Maps enable scalable reward alignment

arXiv:2601.14430v2 Announce Type: replace-cross Abstract: Controlling generative models is computationally expensive. This is because optimal alignment with a reward function–whether via inference-time steering or fine-tuning–requires estimating the value function. This task demands access to the conditional posterior $p_{1|t}(x_1|x_t)$, the distribution of clean data $x_1$ consistent with an intermediate state $x_t$, a requirement that typically compels methods to resort to costly trajectory simulations. To address this bottleneck, we introduce Meta Flow Maps (MFMs), a framework extending consistency models and flow maps into the stochastic regime. MFMs are trained to perform stochastic one-step posterior sampling, generating arbitrarily many i.i.d. draws of clean data $x_1$ from any intermediate state. Crucially, these samples provide a differentiable reparametrization that unlocks efficient value function estimation. We leverage this capability to solve bottlenecks in both paradigms: enabling inference-time steering without inner rollouts, and facilitating unbiased, off-policy fine-tuning to general rewards. Empirically, our single-particle steered-MFM sampler outperforms a Best-of-1000 baseline on ImageNet across multiple rewards at a fraction of the compute.

20.
arXiv (quant-ph) 2026-06-24

Accurate computation of the energy variance and $\langle\langle \mathcal{L}^\dagger \mathcal{L} \rangle\rangle$ using iPEPS

arXiv:2511.22669v2 Announce Type: replace-cross Abstract: Infinite projected entangled-pair states (iPEPS) provide a powerful tensor network ansatz for two-dimensional quantum many-body systems in the thermodynamic limit. In this paper we introduce an approach to accurately compute the energy variance of an iPEPS, enabling systematic extrapolations of the ground-state energy to the exact zero-variance limit. It is based on the contraction of a large cell of tensors using the corner transfer matrix renormalization group (CTRMG) method, to evaluate the correlator between pairs of local Hamiltonian terms. We show that the accuracy of this approach is substantially higher than that of previous methods, and we demonstrate the usefulness of variance extrapolation for the Heisenberg model, for a free fermionic model, and for the Shastry-Sutherland model. Finally, we apply the approach to compute $\langle \langle \mathcal{L}^\dagger \mathcal{L} \rangle \rangle$ for an open quantum system described by the Liouvillian $\mathcal{L}$, in order to assess the quality of the steady-state solution and to locate first-order phase transitions, using the dissipative quantum Ising model as an example.

21.
arXiv (math.PR) 2026-06-19

Model-independent upper bounds for the prices of Bermudan options with convex payoffs

arXiv:2503.13328v3 Announce Type: replace-cross Abstract: Suppose $\mu$ and $\nu$ are probability measures on $\mathbb{R}$ satisfying $\mu \leq_{cx} \nu$. Let $a$ and $b$ be convex functions on $\mathbb{R}$ with $a \geq b \geq 0$. We are interested in finding $$\sup_{\mathbf{M}} \sup_{\tau} \mathbb{E}^{\mathbf{M}} \left[ a(X) I_{ \{ \tau = 1 \} } + b(Y) I_{ \{ \tau = 2 \} } \right] $$ where the first supremum is taken over consistent models $\mathbf{M}$ (i.e., filtered probability spaces $(\Omega, \mathbf{F}, \mathbb{F}, \mathbb{P})$ such that $Z=(z,Z_1,Z_2)=(\int_{\mathbb{R}} x \mu(dx) = \int_{\mathbb{R}} y \nu(dy), X, Y)$ is a $(\mathbb{F},\mathbb{P})$ martingale, where $X$ has law $\mu$ and $Y$ has law $\nu$ under $\mathbb{P}$) and $\tau$ in the second supremum is a $(\mathbb{F},\mathbb{P})$-stopping time taking values in $\{1,2\}$. Our contributions are first to characterise and simplify the dual problem, and second to completely solve the problem under some structural assumptions on the measures $\mu$ and $\nu$ (namely that $\mu$ and $\nu$ are absolutely continuous probability measures that satisfy the Dispersion Assumption). A key finding is that the canonical set-up in which the filtration is that generated by $Z$ is not rich enough to define an optimal model and additional randomisation is required. This holds even though the marginal laws $\mu$ and $\nu$ are atom-free. The problem has an interpretation of finding the robust, or model-free, no-arbitrage bound on the price of a Bermudan option with two possible exercise dates, given the prices of co-maturing European options.

22.
arXiv (CS.AI) 2026-06-16

The Missing Knowledge Layer in Cognitive Architectures for AI Agents

arXiv:2604.11364v2 Announce Type: replace Abstract: The two most influential cognitive architecture frameworks for AI agents, CoALA [21] and JEPA [12], both lack an explicit Knowledge layer with its own persistence semantics. This gap produces a category error: systems apply cognitive decay to factual claims, or treat facts and experiences with identical update mechanics. We survey persistence semantics across existing memory systems and identify eight convergence points, from Karpathy's LLM Knowledge Base [10] to the BEAM benchmark's near-zero contradiction-resolution scores [22], all pointing to related architectural gaps. We propose a four-layer decom position (Knowledge, Memory, Wisdom, Intelligence) where each layer has fundamentally different persistence semantics: indefinite supersession, Ebbinghaus decay, evidence-gated revision, and ephemeral inference respectively. Companion implementations in Python and Rust demonstrate the architectural separation is feasible. We borrow terminology from cognitive science as a useful analogy (the Knowledge/Memory distinction echoes Tulving's trichotomy), but our layers are engineering constructs justified by persistence-semantics requirements, not by neural architecture. We argue that these distinctions demand distinct persistence semantics in engineering implementations, and that no current framework or system provides this.

23.
arXiv (CS.AI) 2026-06-19

StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation

arXiv:2606.20005v1 Announce Type: cross Abstract: Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training. However, existing approaches materialize both attention distributions before computing the KL reduction, incurring $O(N_QN_K)$ memory and IO costs that become prohibitive at long context lengths. We present StreamKL, the first fused GPU primitive for attention KL divergence that eliminates this quadratic materialization. StreamKL derives a novel online formulation for the coupled two-distribution KL reduction, enabling a single one-pass forward kernel that streams query-key tiles through on-chip SRAM. For the backward pass, StreamKL recomputes attention probabilities tile-by-tile, avoiding storage of quadratic intermediates. We further design and implement efficient GPU kernels with dedicated optimizations. Experiments show StreamKL delivers up to $43\times$ and $14\times$ speedups over baseline methods in the forward and backward passes, respectively. Most importantly, StreamKL reduces the extra HBM footprint of attention distillation from $O(N_QN_K)$ to $O(1)$, enabling long-context distillation on a single GPU.

24.
arXiv (quant-ph) 2026-06-19

String dynamics of a (2+1)D U(1) quantum link model on a digital quantum computer

arXiv:2606.19601v1 Announce Type: new Abstract: The (2+1)D U(1) pure gauge theory always exists in the confining phase, with strings of non-zero string tension giving a characteristic linear potential between static charges. This makes it a useful testing ground for quantum computing methods designed to study string dynamics of confining gauge theories. Here we implement a minimal U(1) quantum link model on a quantum computer with qubit degrees of freedom representing the dual height variables of the model. This facilitates an efficient realization of plaquette interactions and enables effective calculations of real-time dynamics that are inaccessible to traditional quantum Monte Carlo. A specifically tailored lattice geometry is chosen to match the heavy-hexagonal geometry of the IBM quantum hardware used here, minimizing non-adjacent qubit interactions. By performing quantum quenches from a simple initial string state, we probe the transverse quantum fluctuations of the string before it thermalizes. Our experimental results from digital quantum simulations, with up to 112 qubits, show good agreement with reference tensor-network calculations at short times and with thermal averages at long times. Near the phase transition, the quench dynamics exhibit large fluctuations of the initial string that extend across both spatial dimensions of the lattice. Nonetheless, our error-mitigated estimators from the quantum hardware also give accurate predictions in that regime, with noise-induced violations of local gauge symmetries comparable to finite-bond-dimension tensor-network results.

25.
arXiv (CS.CL) 2026-06-16

Not All Skills Help: Measuring and Repairing Agent Knowledge

LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how to apply them to LLM judgment alone. We argue that this conflates two distinct roles: generating a skill from experience is a creative act that judgment handles well, while deciding whether that skill actually helps requires empirical evidence across many tasks. Measuring per-skill causal contributions via randomized masking, we find that skill libraries exhibit pervasive causal heterogeneity: individual skills routinely help on some task types while hurting on others, yet their opposing effects cancel in aggregate, making them invisible to global curation methods. We propose ASSAY, a framework that separates generation from curation: it computes a per-skill causal attribution on a small development set, restructures the library offline, and suppresses skills with negative predicted effect for each test task. Across seven base models spanning four providers and two benchmarks (AppWorld and tau-bench), ASSAY consistently improves over prior skill-curation approaches. On AppWorld's hardest split, DeepSeek-V3 achieves 69.3% task-goal completion (47.4% relative improvement), a new state of the art among all published methods including weight-tuned approaches. On tau-bench retail, GPT-4.1 improves by 8.7% relative, advancing past o4-mini, o1, and GPT-4.5 on the public leaderboard without any weight modification. Ablation traces the dominant gain to per-task masking, confirming that the bottleneck is matching skills to tasks at inference time, not removing bad skills globally. Code is available at https://github.com/aiming-lab/assay.