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 (CS.AI) 2026-06-16

RecourseBench: A Modular Framework for Reproducible Algorithmic Recourse Evaluation

arXiv:2606.16113v1 Announce Type: new Abstract: Algorithmic recourse methods provide counterfactual explanations that inform individuals of the actions required to overturn an unfavorable model decision. Despite rapid methodological progress, principled comparison remains elusive; existing frameworks are often difficult to extend and lack both interoperability and systematic verification that integrated methods faithfully reproduce their originally reported results. We introduce RecourseBench, a unified evaluation framework built around three commitments namely, modularity, reproducibility, and interactivity. The framework decomposes the pipeline into five fully decoupled layers – Data, Preprocessing, Model, Recourse Method, and Evaluation – governed by abstract interfaces and a dynamic registry. To address the reproducibility gap in prior benchmarks, we introduce a four-tier classification system in which every integrated method is validated by an automated test suite against its originally reported results. We further provide an interactive web interface for flexible, configuration-driven comparison across methods, datasets, and model architectures. Our framework currently integrates 28 state-of-the-art recourse methods and, to our knowledge, constitutes the first recourse benchmark to explicitly enforce method-level reproducibility through automated, quantitative testing.

02.
arXiv (CS.AI) 2026-06-16

Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations

arXiv:2606.14817v1 Announce Type: cross Abstract: This work presents the design, implementation, and evaluation of a system for generating personalized reading content using Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG). The proposed architecture consists of four modules: Input, RAG, Generation, and Judging and enables users to specify both a question and a target reading content complexity. RAG is employed to retrieve relevant information from the Internet, enriching and grounding the content produced by three modern LLMs: Meta LLaMA 4 Scout, LLaMA 3.1 8B Instant, and Google Gemma2 9B. Reading materials are generated using three prompting strategies (Chain-of-Thought, zero-shot, and few-shot), and the LLM-as-a-Judge module automatically evaluates answer quality and alignment with the desired readability level. Experimental results show that RAG consistently improves system performance across all models and prompting techniques, increasing relevance and particularly groundedness by up to 26-35 percentage points. Overall, the findings demonstrate that the RAG-augmented architecture effectively produces reading content tailored to user queries and desired textual complexity.

04.
Nature (Science) 2026-06-15

Nanocrystal-tailored recombination for all-perovskite tandem solar modules

作者:

The commercialization of all-perovskite tandem solar modules is hindered by the reliance on the conventional gold-based tunnel recombination junction (TRJ)1,2. Specifically, this TRJ introduces substantial near-infrared parasitic absorption3 and suffers from interfacial instability4, limiting both photocurrent generation and operational durability. Here, we develop a solution-processed interconnecting layer based on surface-engineered indium oxide (In2O3) nanocrystals featuring high optical transparency, wherein controlled nanocrystal morphology and tailored ligand chemistry enable smooth interfacial contact and favorable energy level alignment. Critically, we introduce a phosphonic acid additive into the lead–tin (Pb–Sn) perovskite precursor, which synergistically improves the electronic contact with the In2O3 recombination layer, thereby enhancing hole extraction. In addition, the additive regulates perovskite crystallization to mitigate residual strain during film formation, ensuring high-quality large-area deposits. This coordinated interfacial and crystallization engineering strategy simultaneously enhances carrier recombination efficiency at the interconnection layer, improves carrier extraction, and promotes large-area film uniformity in all-perovskite tandems. As a result, a 65-cm2 all-perovskite tandem solar module achieves a certified power conversion efficiency of 26.2%5, with an open-circuit voltage of 2.182 V, a fill factor of 77.4%, and a short-circuit current density of 15.6 mA cm-2 in terms of averaged subcell performance, measured by Japan Electrical Safety and Environment Technology Laboratories (JET). This marks a significant advance toward scalable perovskite tandem photovoltaics.

05.
medRxiv (Medicine) 2026-06-24

Co-development of anxiety and depression in UK and Brazil youth; a cross-country comparison

Importance Anxiety and depression frequently co occur and show developmentally patterned co-development from childhood to adolescence. Adult psychiatric outcomes vary according to the timing, sequencing, and persistence of early symptoms, yet it remains unclear whether patterns of co development are comparable across high income and low and middle income country contexts. Objective Examine joint developmental trajectories of anxiety and depression from childhood to adolescence and their associations with anxiety and depression diagnoses in young adulthood. Design, Setting and Participants Population based prospective cohort studies in the UK (Avon Longitudinal Study of Parents and Children [ALSPAC], N=9,586) and Brazil (Pelotas 2004 Birth Cohort, N=3,815). Main Outcomes and Measures Trajectories were derived using parallel process latent growth models and latent class growth analyses of anxiety and depression using the Development and Well Being Assessment at early childhood (6-7 years), middle childhood (10-11 years), and adolescence (13-15 years). Diagnoses of anxiety and depression at 18 years were assessed via the Clinical Interview Schedule (ALSPAC) and the Mini International Neuropsychiatric Interview (Pelotas). Results Prevalence of anxiety and depression from early childhood to adolescence was similar across cohorts. Co-development was stronger in ALSPAC, with modest increases in both conditions, whereas in Pelotas, anxiety increased rapidly while depression showed little average change. In both cohorts, four trajectory classes were identified: stable-low (ALSPAC, 41%; Pelotas, 54%), increasing (31%; 28%), decreasing (23%; 15%), and persistent-high anxiety/increasing depression (5%; 3%). Compared with the stable-low class, youth in the increasing and persistent-high classes had elevated odds of depression (ALSPAC: OR=2.0 [95% CI, 1.4-2.8] and 4.2 [2.6-6.7]; Pelotas: 2.2 [1.5-3.3] and 2.9 [1.4-6.0]) and anxiety in young adulthood (ALSPAC: 1.6 [1.2-2.2] and 4.8 [3.2-7.0]; Pelotas: 1.7 [1.2-2.6] and 2.9 [1.5-5.8]). No increased risk was observed in the decreasing class. Conclusions and Relevance Patterns of anxiety and depression co development were comparable across the UK and Brazil, suggesting shared developmental pathways. However, more rapid increases in anxiety among Brazilian youth may reflect context specific risk factors. Persistence or emergence beyond early childhood was critical for identifying later diagnostic risk in both settings, highlighting the importance of early monitoring and intervention.

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

Mean-Field Parallel Decoding for Discrete Diffusion Language Models

arXiv:2606.15805v1 Announce Type: new Abstract: Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding. However, selecting tokens independently by marginal confidence limits effective parallelism: tokens that appear reliable in isolation can form incompatible configurations when several positions are updated at once. We introduce a training-free decoding framework that coordinates these parallel updates. At each forward pass, the method assigns a commit score to each masked position and refines these scores using pairwise interactions derived from the model's predictive distributions. A variational relaxation yields a simple fixed-point update that suppresses conflicting simultaneous commitments within a single forward pass. This mechanism allows the decoder to commit more tokens in parallel while maintaining competitive generation quality. The method is lightweight, requires no auxiliary model or retraining, and drops into existing diffusion decoding pipelines without modification. Experiments on reasoning and code-generation benchmarks show consistent improvements in the quality-latency trade-off.

07.
arXiv (CS.AI) 2026-06-18

DRIFT: Refining Instruction Data via On-Policy Data Attribution

arXiv:2606.18307v1 Announce Type: cross Abstract: Optimizing the training data distribution for Supervised Fine-Tuning (SFT) dictates the capability of Large Language Models (LLMs). While existing data curation methods excel at accelerating training under constrained budgets, they are less suited to elevating the capability upper bound. The challenge here is no longer to identify a smaller subset that preserves performance, but to refine the data distribution toward instances most capable of improving the final model. To address this problem, we explore instance-level data attribution using Influence Functions (IF). We identify that standard IF formulations struggle in this setting due to two structural limitations: a proximity gap caused by off-policy validation targets, and a severe bias towards gradient norm. We propose DRIFT (Data Refinement via On-Policy Influence Functions for Supervised Fine-Tuning). Instead of relying on external reference data, DRIFT utilizes the model's on-policy rollouts as validation targets, which empirically minimizes the parameter proximity gap and better aligns with the local neighborhood assumption of IF. It further applies signed weighting based on trajectory correctness and debiases influence scores against the gradient hacking issue, allowing a small set of validation queries to act as reliable anchors for attributing the full dataset. Experiments on 7B-parameter instruction and reasoning models show that DRIFT consistently raises the performance ceiling on both, outperforming existing data curation baselines.

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

Physically Constrained Ensemble Gaussian Process Modelling for Expensive Quantum Systems with Heteroskedastic Noise

arXiv:2606.11240v1 Announce Type: cross Abstract: Accurate modeling of quantum many-body systems often requires computationally expensive simulations such as Density Matrix Renormalization Group (DMRG) or Quantum Monte Carlo (QMC) calculations. These methods, while precise, impose significant time and resource constraints, limiting their use in exhaustive parameter exploration. Moreover, these expensive simulations can contain variable errors over the large unknown parameter space, which needs to be quantified and propagated. Thus, predictive modelling is required to estimate the functional space accurately over scarcely sampled data with heteroskedastic noise, while preserving the physical relevance of the estimation. Therefore, we present a Physically Constrained Ensemble Gaussian Process (pc-EGP) framework designed to efficiently model complex and noisy quantum systems under physical consistency constraints. The proposed method first enforces physical constraints as a user controlled weighted penalty to the data-driven loss function of the Gaussian Process (GP) surrogates. Then an ensemble of such GP models is trained with variable noisy simulations via numerical quadrature method where these multiple GP(s) at different nodes is integrated as a quadrature weighted average. We first demonstrate the framework on synthetically generated data before applying to quantum systems. In the first case study, we leverage DMRG simulations of the Bose-Hubbard Model to predict the critical interaction parameter Uc governing the superfluid-to-Mott-insulator transition. In the second case study, we demonstrate our method on QMC simulations, of a quantum liquid confined inside a nanoporous silicate with the goal of optimizing a chemical environment to realize a one-dimensional superfluid. Compared to conventional GP, pc-EGP achieves a better balance of accuracy and physically meaningful predictions.

09.
arXiv (quant-ph) 2026-06-24

Optimization of Secret Key Rate for BB84 under Collective Rotation Noise

arXiv:2605.21140v3 Announce Type: replace Abstract: Practical quantum key distribution (QKD) systems operate under noise, but security of most protocols have been analyzed under ideal noiseless scenarios. In this work, we investigated security performance of BB84 protocol under effect of collective rotation noise. Using theoretical quantum information frameworks, we analyzed key security parameters including quantum bit error rate (QBER), mutual information and secret key rate (SKR). Security of protocol is studied under various eavesdropping scenarios based on intercept and resend attacks. Our results show that collective rotation noise has a significant impact on the information shared between the two parties. Particularly, we extended prior treatments by suggesting a noise engineering strategy where we identified a non-zero noise range where information accessed by Eve is minimized while corresponding SKR degradation remains relatively small. This analysis provide insights into robustness of BB84 protocol under realistic noisy channels and may contribute towards development of more resilient QKD systems.

10.
arXiv (quant-ph) 2026-06-24

On the localization transition from MAA to AA models

arXiv:2606.24720v1 Announce Type: cross Abstract: Despite their potential similarity between the mosaic Aubry-André (MAA) and AA models, the MAA model allows mobility edges (MEs), whereas the AA model does not. Here we develop a new double quasiperiodic MAA (DMAA) model consisting of one primitive MAA with nonzero even-site potentials and the other modified one with both nonzero odd-site potentials and a tunable amplitude factor, to reveal how localization transitions evolve from MAA to AA models. Interplays and competitions among the extended, critical and localized states arising from superpositions of double quasi-periodic MAA potentials enable new twice and multiple localization-delocalization transitions besides the original single localization transition. Our numerical calculations on inverse participation ratio, normalized participation ratio, fractal dimension and real-space wavefunction distribution confirm such localization features. The continuum model simulations on the experimental polariton modes also yield consistent results and hence validate their experimental feasibility. The constructed DMAA model provides a new framework for studying the localization transition processes between two analogous quasiperiodic models and broadens the understanding of Anderson localization.

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

Schattor: Schatten-family methods for deep learning optimization

arXiv:2606.15702v1 Announce Type: cross Abstract: Modern deep learning optimization features heterogeneous parameter structures, noisy gradients, and highly nonconvex landscapes, posing significant challenges for both algorithm design and theoretical analysis. Motivated by the limitations of SGD and the success of adaptive optimizers, we propose {\it Schattor}, a family of adaptive first-order methods based on Schatten norms. Schattor unifies SGD and the recently proposed matrix-variate adaptive optimizer Muon within a single Schatten-norm-based framework. We establish dimension-free stationarity guarantees for methods in the Schattor family for stochastic matrix optimization problems via a novel matrix martingale moment bound. We also develop multi-block extensions that adaptively balance block-wise optimization progress and prove dimension-free stationarity guarantees in this more general setting.

12.
arXiv (CS.LG) 2026-06-16

GPT-Based Fast Simulation of CLAS12 Detector Hits via Conditional Autoregressive Generation

arXiv:2606.16035v1 Announce Type: cross Abstract: Modern particles physics experiments have demonstrated an increasing need for fast, high-fidelity detector simulation as detector components have improved and subsequent computational requirements approach the limits of available resources. Recently, deep generative models have emerged as a promising alternative to traditional Monte-Carlo methods, with recent works drawing inspiration from large language models (LLMs) and self-supervised next-token prediction methods. In this work, we present an application of a GPT-style autoregressive transformer as a fast surrogate model for the calorimeter inside the CLAS12 experiment at the Thomas Jefferson National Accelerator Facility. The model is conditioned on incident momentum and generates realistic detector hits autoregressively across all nine calorimeter layers as sequences of strip, ADC, and TDC tokens. We demonstrate that the model faithfully reproduces hit multiplicity, spatial distributions, energy deposits, and the energy-momentum response of the electromagnetic calorimeter. The generator achieves inference rates exceeding 700 events per second on a single GPU, providing a substantial speedup over traditional Geant4-based simulations while maintaining physics fidelity essential for high-luminosity experimental programs.

13.
arXiv (CS.CV) 2026-06-24

Trimming the Long-Tail of Visual World Modeling Evaluation

Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irregular interactions remains underrepresented. Although recent visual world models, including image and video generation models, achieve impressive realism on existing benchmarks, they primarily focus on simulating common physical interactions. This raises a central question: Do current visual world models internalize and generalize physical principles? In this work, we introduce Tailor-Bench, a benchmark that challenges world models to simulate irregular physical interactions. To enable systematic evaluation, we design three scenario modes that progressively challenge model reasoning: Regular scenarios reflect common tool-task pairs, Unconventional scenarios replace conventional tools with attribute-compatible substitutes to test affordance generalization, and Impossible scenarios introduce attribute-violating tools to probe constraint awareness. Additionally, we design two complementary settings under a unified evaluation protocol: predictive generation requires inferring outcomes without guidance, while descriptive generation specifies the target outcome for faithful realization. Our experimental results reveal a clear long-tail gap in physical world modeling: performance degrades from Regular to Unconventional and Impossible scenarios, indicating limited generalization beyond common interactions. Failure analysis further shows that models rely on superficial visual patterns: image models fail to realize correct state changes, while video models further suffer from temporal inconsistencies.

14.
Nature (Science) 2026-06-17

Optical metasurfaces for general vision processing on the edge

作者:

Large-scale artificial intelligence (AI) models achieve notable performance in computer vision but require substantial computational resources, limiting their deployment on edge devices1,2. Optical neural networks (ONNs) promise reduced latency and energy consumption by making use of the inherent parallelism of light3. However, present ONNs struggle to scale and are confined to simple tasks, owing to the challenges of replicating exact algebraic operations of digital models using physical (analogue) systems. This work introduces a new paradigm that directly embeds core computer vision principles, including similarity-based recognition, attention-guided perception and detail–context fusion, into a large-scale optical metasurface. By unifying optical physics with these computer vision fundamentals, we develop a photonic–electronic engine that overcomes scalability and generality barriers, enabling high-accuracy, general-purpose computer vision at the edge. The resulting system combines a 41-million-parameter optical metasurface front end with a co-designed, ultraefficient 87,000-parameter digital back end, outperforming many digital models with tens of millions of parameters across object detection, segmentation, 3D reconstruction and video understanding. We build a deployable prototype and demonstrate real-time edge visual processing in natural scenes. This work represents a path towards practical optical computing for general vision tasks in complex natural environments, enabling a new paradigm for low-energy, low-latency, real-time on-device vision intelligence. By embedding core computer vision principles into a large-scale optical metasurface, an efficient vision processing system using far fewer parameters is demonstrated to outperform many digital models and enables deployment on edge devices.

15.
arXiv (CS.AI) 2026-06-11

Signed Compression Progress on a Sealed Audit is Goodhart-Resistant

arXiv:2606.11417v1 Announce Type: cross Abstract: Compression progress is a long-standing proposal for intrinsic motivation: reward an agent when its world model becomes better at predicting or compressing experience. The folk claim is that this reward is "credible" because it is paid only for learning. We make this precise and prove it. If intrinsic reward is the signed decrease of a fixed sealed-audit loss, r_t = E(theta_{t-1}) - E(theta_t), then cumulative reward telescopes exactly to endpoint audit improvement, so no policy can push reward up indefinitely while true audit performance stagnates or degrades. For finite audit panels the same result holds with a sharp false-positive budget: cumulative empirical reward is at most true audit improvement plus 2 Delta_n(F, delta), the uniform audit deviation of the model class. This is horizon-free: adaptivity over time costs nothing once the sealed panel uniformly controls the class. The theorem also identifies the failure modes: the guarantee disappears if progress is clipped, scored on the agent's own stream, exposed to a high-capacity model on a reusable panel, or applied to a neural class that makes Delta_n vacuous. We give a Lean 4 mechanization of the structural core (telescoping, the finite-audit bound, finite Gibbs, and the entropy floor) and an experiment suite on ARC-TGI grid-transformation generators with adaptive holdout attacks. Experiments confirm the theory: finite-audit deviation scales as n^{-0.527}; signed progress resists clip-farming, stream leakage, and noisy-TV curiosity; naive reusable audits are exploitable by black-box scalar feedback, while standard release defenses keep the attack below the 2 Delta_n threshold. Signed compression progress on a sealed audit is an accounting signal of genuine improvement.

16.
medRxiv (Medicine) 2026-06-24

Repetitive Transcranial Magnetic Stimulation over Primary Somatosensory Cortex for Upper Limb Function in Stroke: An Exploratory Randomized Controlled Trial

Background: Stroke often causes Upper Limb (UL) functional impairments. The Primary Somatosensory Cortex (S1) plays an important role in motor learning. Repetitive Transcranial Magnetic Stimulation (rTMS) over S1 could enhance UL recovery. We aimed to explore its preliminary effects on UL motor activity and function post-stroke. Methods: An exploratory parallel-group randomized controlled trial in people with chronic stroke (>3 months) and moderate hemiparesis was conducted. Participants received 20 sessions of active or sham 5Hz rTMS over affected S1, with Robot-Assisted Therapy and Task-Oriented Training, 5 days/week for 4 weeks. The primary endpoint was UL motor activity (Action Research Arm Test, ARAT). Secondary measures were the UL Fugl-Meyer Assessment (UL-FMA) and sensory outcomes. Results: The baseline-adjusted mean difference (MD) in ARAT was 4.05 points [0.78, 7.33], favoring active stimulation. Secondary measures did not favor active stimulation (UL-FMA: MD = 2.62 [-1.51, 6.76]; sensory outcomes showed no between-group differences). Conclusion: High-frequency rTMS over S1 may enhance UL motor activity (ARAT), but no evidence for motor impairment (UL-FMA) or sensory domains was found. Compensation rather than restoration may underlie this improvement. Stimulation targets should match the intended recovery domain, although larger trials are needed to confirm these preliminary findings.

17.
PLOS Medicine 2026-05-15

Spatial transcriptomic-metabolic features of tumor foci and tumor capsule in microvascular invasion with hepatocellular carcinoma: A spatial multi-omics study

作者:

by Zhi-Hui Luo, Na Wang, Jingwei Zhao, Fei Long, Si Wu, Wei Zhong, Wei-Ming Chen, Bicheng Wang, Kun Wang, Yufeng Yuan, Jingjiao Zhou, Chunhui Yuan, Fubing Wang Background Microvascular invasion (MVI) is closely related to the recurrence and metastasis of hepatocellular carcinoma (HCC), but the underlying cellular mechanism remains largely elusive. This study aims to elucidate the regional cellular discrepancy between MVI-positive (MVI+) and MVI-negative (MVI−) HCC by integrating Spatial transcriptomics (ST) and spatial metabolomics (SM). Methods and findings ST and SM were performed on six tissue samples from four patients (including 2 MVI+, 2 MVI−, and 2 paratumor tissues), with the integration of 79 public single-cell RNA sequencing datasets of HCC. Patient identity was used as a covariate in the linear equation for regional differentially expressed gene analysis with the ST data. Clinical validation was conducted through multiplex immunofluorescence staining in 79 patients, together with external validation in the cancer genome atlas (TCGA)-liver hepatocellular carcinoma (LIHC) cohort (n = 299) and an independent microarray dataset (n = 62). For cell-type-specific metabolic profiling, spatial transcriptomic-metabolic registration was performed. The functional roles of key metabolites were further validated in vitro using inflammatory cancer-associated fibroblasts (iCAFs) derived from hepatic stellate cells (HSCs) and primary CAFs through co-culture models and various functional assays assessing cell proliferation, migration, and invasion. In the tumor lesion, a malignant STMN1+HMGN2+GPC3+ cell subtype enriched in MVI+ HCC was identified, which exhibited enhanced proliferative activity and was associated with poor prognosis. This finding was further confirmed in a local cohort of 79 patients, where multiplex immunofluorescence staining for the three genes (STMN1, HMGN2, and GPC3) showed significantly higher expression in the MVI+ group than in the MVI− group (p = 0.046). Integrated SM analysis further revealed that this cell population underwent metabolic reprogramming characterized by suppressed glycerolipid metabolism. In the tumor capsule, iCAFs-related genes were downregulated in MVI+ cases, and iCAFs were located distally from the tumor boundary. Spatial metabolite mapping showed a strong correlation between taurine and iCAFs, and functional assays demonstrated that taurine promotes HCC proliferation and migration by suppressing iCAF activity. One limitation of this study is the small sample size of spatial omics data, which hinders a more complete molecular functional analysis of the STMN1+HMGN2+GPC3+ cell subtype and iCAFs in MVI+ HCC. Larger-scale ST cohorts are required to further validate and expand the findings of this study. Conclusions This integrative spatial atlas proposes a hypothesis that there exists a highly proliferative and metabolically reprogrammed malignant cell subtype in the tumor lesion of MVI+ HCC, and that taurine in the tumor capsule modulates iCAF activity to influence tumor progression. The exploratory results provide mechanistic insights into MVI-related HCC progression and offer potential avenues for targeted therapeutic intervention of MVI+ HCC.

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

Multiple cyclicity and Wavelet Decomposition with Channel Correlation for Long-term Time Series Forecasting

arXiv:2606.17996v1 Announce Type: cross Abstract: Cyclicity and trend are important components of time series data and many studies based on cyclicity and trend have achieved good results in long-term time series forecasting. However, we believe that current work neglects the influence of real-world inter-channel correlations in time series data which leads to suboptimal predictions. Furthermore, these models rely on complex designs to capture diverse information so that resulting in low computational efficiency. To address this challenge, we propose McWC, a long-term time series forecasting model that separately models the cyclicity, trend, and inter-channel correlations. Specifically, McWC first decouples cyclical information from data using a multi-layer cyclicity construction module. Then, it extracts inter-channel correlations using multi-layer perceptron. Next, it models and fuses the multi-layer high-frequency and low-frequency information from data using a multi-level wavelet decomposition module. Finally, it aggregates the results of different components to obtain the output. Simultaneously, we decouple intra-channel autocorrelations by calculating a loss function in the frequency domain. Experiments on six real-world datasets demonstrate that McWC achieves state-of-the-art performance, exhibiting excellent computational efficiency and historical information extraction capabilities.

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

RACL: Reasoning-Agent Control Layers for Continuous Metaheuristic Learning

arXiv:2606.20142v1 Announce Type: new Abstract: This paper introduces RACL, a Reasoning-Agent Control Layer for metaheuristics. RACL places a reasoning agent above an existing optimizer. The agent does not replace the optimizer and does not modify business constraints. Instead, it controls the optimizer's internal search behavior by observing operational memory, reasoning over past behavior, formulating bounded hypotheses, testing interventions, evaluating outcomes, applying guardrails, consolidating useful policies and explaining its decisions. The experiment uses vehicle routing as a testbed, but the contribution is not a new routing solver, a particular ALNS configuration or a specific set of routing rules. The contribution is the RACL method: a way for a reasoning agent to discover, validate, consolidate and explain algorithmic control rules for a metaheuristic. In the current experimental setting, RACL improves or ties the Operational Memory Policy in 21 of 21 feasible cases and improves or ties a non-reasoning Stagnation-Triggered Policy in 18 of 21 feasible cases, with an average RACL vs STP cost delta of -0.641%. In the Sevilla-9/10 runtime sample, RACL improves average cost by -8.337% versus Fixed and -1.605% versus STP without showing material computational overhead. During the proof-of-concept, Codex was used as an in-the-loop reasoning agent observing executions, interpreting logs and proposing live bounded interventions. The policy proxy was later used only to make quantitative evaluation reproducible.

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

TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions

We introduce TRON, a rendering framework that combines 3D Gaussian ray tracing with neural rendering to enable realistic and controllable rendering of real-world 3D scenes under novel lighting, dynamic object motion, object insertion, and material editing. Prior approaches that rely solely on physically based rendering (PBR) of Gaussian representations struggle to achieve realistic relighting due to imperfections in reconstructed geometry, material estimates, and light transport estimation. At the same time, neural rendering methods often lack an explicit scene representation, limiting their ability to support interactive editing with fine-grained manipulation. TRON bridges these two paradigms. We use intrinsic decomposition priors from a learned inverse rendering model to regularize the material properties of a Gaussian field, and repurpose a ray tracer to provide radiometric guidance rather than final pixels. By treating this output as a structured 3D scaffold, we empower a lightweight neural renderer to bridge the domain gap between shading-model constrained estimates and photorealistic output. Our key insight is that the combination of explicit 3D knowledge with robust material priors provides speed and controllability, while neural rendering enables the synthesis of photorealistic images. To support real-world scenarios, we train our neural renderer with a multi-stage strategy consisting of large-scale pretraining and targeted fine-tuning on a newly constructed dataset of 2.1M rendered synthetic and real-world frames from 3D reconstructions. TRON outperforms Gaussian-based relighting methods in realism, and prior neural renderers in editability and speed. To the best of our knowledge, TRON is the first method to enable practical interactive applications in captured 3D environments, offering realistic appearance under dynamic geometric, lighting and material conditions.

21.
arXiv (CS.AI) 2026-06-18

Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training

arXiv:2606.19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs. Existing works explore two directions to reduce cost: seed exploration improves training convergence by selecting high-contrast samples, yet adds compute to the critical path; spot GPUs offer 69–77\% lower cost, yet sit idle during training because DiT rollouts finish nearly simultaneously, which prevents LLM-style pipelining of rollout with training. Spot preemptions further break Sequence Parallelism (SP) groups, fragmenting GPU topology. We present Spotlight, the first system that harvests spot GPUs for DiT RL post-training. Spotlight rests on two key insights we devise: (1)~we show that exploration can tolerate stale model weights because exploration that uses the model weights from the previous iteration preserves the relative ranking of random seeds, allowing exploration to run on idle spot GPUs during training. (2)~SP reconfiguration can reuse on-node state, reducing group recovery from minutes to sub-second launches. Built on these insights, Spotlight introduces three techniques: a bandit-based exploration planner that maximizes reward variance within the training time budget, elastic sequence parallelism that reconfigures SP groups on the fly via persistent schedulers and intra-node weight copying, and a preemption-aware pull-based request scheduler that balances load and commits in-flight state upon preemption. We implement Spotlight on the open-source RL platform ROLL and evaluate it on Qwen-Image post-training. Spotlight reaches the same target validation score $4\times$ faster than baselines, reducing total cost by $1.4$-$6.4\times$ while achieving superior image quality on DeepSeek-OCR and Geneval datasets with resolution $512\times512$ and $1280\times1280$.

22.
arXiv (CS.AI) 2026-06-12

MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling

arXiv:2606.12935v1 Announce Type: new Abstract: Parallel test-time scaling samples many reasoning traces and majority-votes their answers, improving LLM accuracy but requiring traces to run to completion, incurring substantial computational overhead. We observe that probing partial traces at intermediate checkpoints can extract current answers without disrupting generation, revealing an evolving aggregate vote. Based on this observation, we introduce MARS, a margin-adversarial stopping rule that estimates which active traces are likely to change their answers and stops once the leader remains safe under a conservative bound on future vote movement. The rule separates two sources of uncertainty. It learns the trace-level switch probabilities that determine how much of the current margin is likely to be retained, while handling the harder question of where switching traces land through an adversarial bound calibrated from warmup traces. With true switch probabilities, MARS guarantees with high probability that the early-stopped answer matches the full-budget vote. In practice, a five-feature logistic model closely matches oracle switching behavior. Across three reasoning models and three competition-math benchmarks, MARS saves 25-47% of self-consistency tokens and 14-29% on top of DeepConf Online, a strong confidence-weighted baseline that already filters and truncates weak traces, while matching the accuracy of the corresponding full-budget baselines.

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

Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL

arXiv:2605.05481v2 Announce Type: replace Abstract: We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy. That distribution over states is unknown and cannot be sampled for the purposes of training the value function. Conservative updates solve this problem, but at the cost of shrinking the policy update. This paper explores an alternative solution, Approximate Next Policy Sampling (ANPS), which addresses the problem by modifying the training distribution rather than constraining the policy update. ANPS is satisfied if the distribution of the training data approximates that of the next policy. To demonstrate the feasibility and efficacy of ANPS, we introduce Stable Value Approximate Policy Iteration (SV-API). SV-API modifies the standard approximate policy iteration loop to hold the target policy fixed while an iteratively updated behavioral policy gathers relevant experience. It only commits to a new policy once a convergence criterion has been met. If certain stability criteria are met, the update is guaranteed to be safe; otherwise, it remains no less safe than standard approximate policy iteration. Applying SV-API to PPO yields Stable Value PPO (SV-PPO), which matches or improves performance on high-dimensional discrete (Atari) and continuous control benchmarks while executing substantially larger target policy updates. These results demonstrate the viability of ANPS as a new solution to this classic challenge in RL.

24.
arXiv (CS.CV) 2026-06-25

Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher

Chest X-ray visual question answering (CXR VQA) requires models not only to predict correct answers, but also to produce reliable medical reasoning. However, existing reinforcement-learning-based training typically relies on answer-level rewards, which are often too coarse to improve chain-of-thought (CoT) quality and can become ineffective when group-level advantages collapse to zero. We propose Teach-to-Reason (T2R), a framework that introduces comparison-based supervision into CoT optimization through a self-improving Teacher and a competition-guided Reasoner. As the Teacher is iteratively strengthened via self-competition, the Reasoner is optimized against progressively stronger Teacher-generated references. We further introduce a case-wise reward design that preserves the original reward-induced positive/negative partition when it is informative, and restores supervision from competition scores when the original reward signal degenerates. Experiments on multiple CXR open-ended VQA benchmarks show that T2R consistently outperforms strong baselines, indicating that comparison-based supervision, when integrated in a controlled and principled manner, provides a more effective training signal for reasoning optimization.

25.
medRxiv (Medicine) 2026-06-12

Estimating the effectiveness of syndromic screening at airports for Bundibugyo ebolavirus disease

We used a stochastic simulation model to estimate the effectiveness of combined exit and entry airport screening for Bundibugyo ebolavirus disease (BVD), using natural-history parameters from a Bayesian re-analysis of the 2012 Isiro outbreak. For a 12-hour international flight from DRC or Uganda at 86% screening sensitivity, we estimate 65% of infected travellers would arrive undetected (95% CrI: 38 - 76%). The main driver of this outcome is the relative duration of the the incubation period (approximately 7.7 days) and the onset-to-severe-disease interval (approximately 4 days): most infected travellers board before symptom onset and are undetectable by any syndromic screen, whilst those who are symptomatic progress rapidly to illness severe enough to preclude travel. This is compounded during active epidemic growth, when recently exposed (and therefore pre-symptomatic) cases are overrepresented among travellers. Syndromic airport screening offers limited protection against BVD spread via air travel, and should be complemented by outbreak control at source and strengthened clinical surveillance in receiving countries with high travel connectivity to affected areas.