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

Interaction-enabled topological pumping of Rydberg electrons

arXiv:2606.15126v1 Announce Type: cross Abstract: Topological pumping is a paradigmatic realization of quantized transport in band systems, yet its fate in strongly correlated regimes, especially with long-range interactions, remains largely unexplored. Here we report the experimental observation of interaction-enabled topological pumping of correlated Rydberg electrons in a synthetic lattice. We show that dipolar exchange interactions induce a controllable shift of the underlying topological singularity in parameter space, such that a fixed pumping trajectory can be driven through successive topological transitions by tuning the interaction strength alone. This leads to the emergence and breakdown of quantized transport. The observations are consistent with an effective Rice-Mele description with interaction-renormalized onsite potentials and are supported by characterizing the adiabaticity and robustness to control trajectory imperfections. Our results establish a platform for exploring interaction-controlled topological transport beyond perturbative regimes and open a route toward engineering correlated topological matter in synthetic quantum systems.

02.
arXiv (CS.CV) 2026-06-17

GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments

Training embodied agents in the real world requires skilled operators and expensive hardware. Simulation environments offer a compelling alternative by enabling large-scale, cost-effective data augmentation. Consequently, rapidly constructing high-fidelity simulation scenes with a minimal sim-to-real gap has become a critical objective in robot learning. While reconstruction-based methods provide superior visual quality, current workflows are hindered by inefficient data acquisition and subpar foreground object extraction. We thus propose GASE, a highly automated system for simulation scene construction. GASE leverages multi-view video streams from panoramic camera arrays to enable rapid environment scanning. To ensure high-quality asset generation, our pipeline introduces a camera-pose-based strategy that robustly extracts objects across frames in the 2D domain, followed by high-fidelity scene inpainting. Foreground objects and the static background are then reconstructed independently and seamlessly imported into physics simulators for policy training. Extensive experiments demonstrate that GASE outperforms existing 3D Gaussian-based methods in segmentation accuracy by over 10\% while achieving state-of-the-art inpainting quality. Furthermore, real-robot deployments across manipulation and navigation tasks maintains a performance gap of less than 10\% compared to policies trained purely on real-world data. These results confirm that GASE provides an efficient and highly effective solution for bridging the sim-to-real gap. Code will be released.

03.
arXiv (quant-ph) 2026-06-17

Active Quantum Reservoir Engineering: Using a Qubit to Manipulate its Environment

arXiv:2505.16898v4 Announce Type: replace Abstract: Quantum reservoir engineering leverages dissipative processes to achieve desired behavior, with applications ranging from entanglement generation to quantum error correction. Therein, a structured environment acts as an entropy sink for the system and no time-dependent control over the system is required. We develop a theoretical framework for active reservoir engineering, where time-dependent control over a quantum system is used to manipulate its environment. In this case, the system may act as an entropy sink for the environment. Our framwork captures the dynamical interplay between system and environment, and provides an intuitive picture of how finite-size effects and system-environment correlations allow for manipulating the environment by repeated initialization of the quantum system. We illustrate our results with two examples: a superconducting qubit coupled to an environment of two-level systems and a semiconducting quantum dot coupled to nuclear spins. In both scenarios, we find qualitative agreement with previous experimental results, illustrating how active control can unlock new functionalities in open quantum systems.

04.
arXiv (CS.CV) 2026-06-19

Scaling Self-Play for End-to-End Driving

End-to-end autonomous driving models are typically trained on offline human-demonstration datasets that provide limited state coverage and often no closed-loop feedback, making them prone to compounding errors when deployed in closed-loop and brittle to long-tail agent interactions. To overcome these limitations, we propose an alternative strategy for training end-to-end driving models: large-scale self-play directly from pixels in simulation. While prior self-play approaches have shown promising transfer to real-world driving, they typically assume vectorized Bird's-Eye-View (BEV) observations that are incompatible with end-to-end policies operating directly on sensor observations. To this end, we introduce Gigapixel, a high-throughput batched driving simulator with perspective rendering, enabling scalable self-play directly from pixel observations. Rather than targeting compute-costly photorealistic sensor simulation, Gigapixel renders a simplified bounding-box world that preserves essential scene structure while achieving throughput at 50k agent steps per second. Since direct pixel-space self-play RL is prohibitively sample-inefficient at end-to-end model scale, we propose self-play DAgger training: we train pixel-based policies in self-play via on-policy distillation from a privileged RL teacher. To bridge the sim-to-real gap, we subsequently transfer the self-play trained policies to real-world sensor data through lightweight perception adaptation. Policies trained in Gigapixel and adapted to real-world sensor data achieve competitive performance on the HUGSIM and NAVSIM-v2 benchmarks without human trajectory supervision. Moreover, scaling self-play training yields proportional gains in policy performance, establishing self-play as a practical and scalable strategy for training end-to-end models.

05.
arXiv (CS.CV) 2026-06-11

Understanding Cross-Sensor Feature Variations for Generalizable 3D Perception

Radar-camera BEV perception often suffers from degraded performance when evaluated across datasets, as changes in driving scenes, sensor configurations, and environmental conditions can alter both the input observations and the internal fused representations. This work studies this issue from the perspective of source-domain variation modeling, aiming to improve the robustness of BEV-based 3D detectors without relying on target-domain samples. We introduce a framework that characterizes visual scene variations in the frequency domain and uses them to synthesize diverse source-domain views. By comparing the resulting fused BEV representations, the framework further captures how image-level variations influence multi-modal BEV features. These variation patterns are then used to regularize the detector, encouraging the learned fusion space to remain stable under latent scene changes. The proposed method is applied only during training and leaves the inference pipeline unchanged. Experiments on cross-dataset radar-camera 3D detection between View-of-Delft and TJ4DRadSet demonstrate consistent improvements over multiple BEV fusion backbones, and the gains remain effective when a small amount of target-domain data is available.

06.
bioRxiv (Bioinfo) 2026-06-10

Promera: a unified model for biomolecular structure prediction, filtering, and design

Generative models have become staple tools for modeling and designing biomolecular structures. However, although these tools have improved in structural prediction accuracy, their ability to filter designed binders—an essential use case—remains insufficient; whereas design methods have focused more on unconstrained binder generation rather than capabilities enabled by controllable design. We introduce Promera, a unified generative model that combines all-atom structure prediction with improved filtering and controllable design. We find that Promera's confidence metrics are more accurate for filtering binders from non-binders for both miniproteins and nanobodies, while its co-folding performance surpasses popular open-source models (OpenFold3-p2, Boltz-2) on therapeutically relevant categories. As a design model, Promera generates binders by predicting masked protein sequences with optional epitope, paratope, and template constraints. Remarkably, our nanobody designs match the in silico success rates from backprop-based techniques (mBER) when evaluated under co-folding confidence filters. We further provide two in silico demonstrations of the the versatile capabilities of our design method: epitope targeting of the Andes hantavirus glycoprotein with VHHs and active state stabilization of the beta-2 andrenergic GPCR. We conclude by proposing a scaling law for co-folding models, suggesting a path for further performance improvement.

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

ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models

arXiv:2606.19919v1 Announce Type: new Abstract: Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost. Existing efficiency-oriented methods attempt to shorten or mix reasoning strategies, yet often degrade reasoning capability. We identify the root cause as sequence-level coupling between efficiency incentives and correctness optimization, which implicitly penalizes long but correct reasoning trajectories. To address this issue, we propose Adaptive Dual-Process Thinking (ADaPT), a token-level dual-process framework that explicitly decouples efficiency and correctness signals during training. ADaPT introduces a mode-selection token to control fast and slow reasoning, applying efficiency-related rewards exclusively to this token to avoid penalizing correct long reasoning while encouraging efficiency when appropriate. Moreover, ADaPT enables precise and continuous control over the efficiency-performance trade-off at inference time: by adjusting the generation probability of the mode-selection token, a single trained model can smoothly move along the efficiency-performance Pareto frontier. Extensive experiments demonstrate that ADaPT significantly reduces inference cost while maintaining strong reasoning performance across multiple benchmarks.

08.
arXiv (CS.CL) 2026-06-16

Neuron Level Analysis of Large Language Model in Legal Domain Reasoning

We presented a neuron-level analysis of legal-domain reasoning in LLMs, comparing it with other applied domain tasks across seven open-weight models. Using neuron attribution scores to rank and suppress influential neurons, we confirmed that suppressing the identified neurons collapses accuracy on the target task, whereas suppressing the same number of random neurons does not. We further found a small subset of neurons influential across all seven tasks; once these are removed, suppressing the remaining neurons degrades only the task they were identified from, revealing genuinely task-specific neurons in every model studied. Within the legal domain, the three benchmarks exhibit relatively high neuron overlap and tend to be affected jointly, suggesting of legal components neurons that span jurisdictions. The distribution of identified neurons in our experiments suggests that the hypothesis that influential neurons are concentrated in middle MLP layers may depend on the input format and content, rather than being a universal phenomenon.

09.
arXiv (CS.CV) 2026-06-16

SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration

Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence. Despite recent progress in joint layout-and-mesh generation, existing methods often rely on holistic or weakly decomposed pipelines that entangle many factors at once and demand extensive scene-level supervision, limiting their generalization to complex real-world environments. We propose a multi-agent orchestration framework that decomposes single-image 3D scene generation into three structured stages: scene initialization, environment construction, and multi-agent refinement. The initialization stage extracts image-derived object masks, builds object-level 3D representations, and predicts an initial spatial layout to form a coarse 3D scene. The environment-construction stage then leverages this initialization together with point-map geometry to build an environmental scaffold of supporting surfaces, room boundaries, materials, and illumination. Finally, in the refinement stage, a planner agent identifies structural and visual inconsistencies, applies simple corrections directly, and dispatches specialist agents for complex localized revisions that are reintegrated into the global scene. To provide reliable structural initialization while reducing reliance on scene-level annotations, we further introduce a geometry-aware layout predictor supervised by sparse geometric priors derived from point maps. Unlike fully supervised layout generators, the predictor can be trained from segmentation-level data and generalizes robustly to diverse real-world scenes. Extensive experiments on benchmark datasets show that our method consistently outperforms prior approaches in geometric accuracy, spatial consistency, and perceptual realism.

10.
arXiv (CS.AI) 2026-06-17

Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference

arXiv:2606.17165v1 Announce Type: cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in the hope of experimenting faster and at lower cost. We study when a treatment effect estimated on LLM outcomes recovers the effect that would have been measured on the human population of interest. Distributional equivalence between LLM and human outcomes would make any standard estimator valid but is unrealistic. We therefore develop a statistical framework that adapts surrogate endpoint theory to LLMs. The framework shows that calibrating LLM outcomes to human outcomes identifies the average treatment effect under surrogacy and comparability conditions that are jointly weaker than distributional equivalence. When these conditions fail, the effect of interest is only partially identified, and we provide diagnostics that can falsify surrogacy on historical experiments together with a bound on the worst-case bias from limited overlap. We further show that the stochasticity inherent to LLMs introduces both bias and variance, but using an average of multiple draws as the surrogate mitigates both. We illustrate the methods and theory in simulations and an application to A/B tests on Upworthy headlines. A central takeaway from our work is that the validity of LLM outcomes as surrogates can only be falsified for past treatments and never verified for new ones, so human experiments remain indispensable for novel interventions. We discuss the role of LLM choice, prompting, and temperature as design variables, and how to size human experiments for validation.

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

From Uniform to Learned Graph Priors: Diffusion for Structure Discovery

arXiv:2606.11831v1 Announce Type: cross Abstract: Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges. However, these methods typically rely on oversimplified, factorized graph priors. Such priors, typically nearing uniform distributions, treat edges as independent entities. This systemic misalignment does not match the real-world systems and yields diffuse and indecisive edge posteriors limiting the reliability of structural discovery. To address this, we propose Diff-prior, a diffusion-parameterized adaptive prior used to calibrate latent graph distribution rather than generate graphs. Our core insight is to reframe prior integration as a learnable denoising-style calibration that organizes scattered, uncertain edge posteriors into a more reliable overall structure which can be trained by the diffusion model. Diff-prior learns an adaptive structure prior that performs structured calibration on the edge posteriors during inference, guiding it towards a distribution closer to the underlying structure. The diff-prior operates before structural sampling and acts as a denoising calibrator directly on the encoder edge distribution, which provides a generic training paradigm over structured variables. Experiments on standard benchmarks validated our framework, and the results indicate that Diff-prior improves the performance of structure inference and generates more decisive edge posteriors across multiple NRI-family architectures. The code is available on https://github.com/Hardy158118/Diffprior.

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

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First, a dense predictive loss uses a masking-based objective in which both visible and masked tokens contribute to the training signal, encouraging explicit spatial and temporal grounding. Second, deep self-supervision applies the self-supervised objective hierarchically across multiple intermediate encoder layers to improve representation quality. Third, multi-modal tokenizers enable unified training across images and videos. Finally, the model benefits from effective scaling in both model capacity and training data. Together, these design choices produce representations that are spatially structured, semantically coherent, and temporally consistent. Empirically, V-JEPA 2.1 achieves state-of-the-art performance on several challenging benchmarks, including 7.71 mAP on Ego4D for short-term object-interaction anticipation and 40.8 Recall@5 on EPIC-KITCHENS for high-level action anticipation, as well as a 20-point improvement in real-robot grasping success rate over V-JEPA-2 AC. The model also demonstrates strong performance in robotic navigation (5.687 ATE on TartanDrive), depth estimation (0.307 RMSE on NYUv2 with a linear probe), and global recognition (77.7 on Something-Something-V2). These results show that V-JEPA 2.1 significantly advances the state of the art in dense visual understanding and world modeling.

13.
arXiv (quant-ph) 2026-06-17

Fabless Quantum Chip Design and Commercial Production

arXiv:2606.17956v1 Announce Type: new Abstract: This paper proposes a fabless quantum-chip design and production architecture for superconducting quantum computing, centered on the SPICE-Q multiphysics simulation framework. The proposed ecosystem connects process-certified quantum PDKs, parameterized device cells, traceable model cards, SPICE-Q physical modeling languages, unified Q-EDA flows, foundry sign-off rules, cryogenic test feedback, and reusable quantum IP. In this model, design firms do not merely outsource fabrication; they prepare verified tape-outs under standardized process constraints and calibrated physical models. Its economic value lies in reducing repetitive device debugging, process exploration, and low-level layout effort, while its feasibility depends on PDK maturity, foundry yield, cryogenic test throughput, model-prediction accuracy, data-feedback mechanisms, and IP licensing boundaries. We argue that superconducting quantum chips can move from the current largely vertically integrated development model toward a fabless-foundry ecosystem only when hardware design is supported by standardized, verifiable, and reusable software and process interfaces. The required pillars are certified PDKs, PCell-based parameterized design, SPICE-Q cross-physics simulation, end-to-end Q-EDA automation, and a tradable quantum-IP market. By adapting lessons from the classical semiconductor industry to quantum hardware, this framework defines a path toward scalable, manufacturable, and commercially reusable superconducting quantum-chip design.

14.
medRxiv (Medicine) 2026-06-17

Clinical Study Protocol of the 'Biomarkers of Severity of COVID-19 Patients' (BIOMARCOVID) Project

Introduction The coronavirus disease 2019 (COVID-19) pandemic has challenged health care systems worldwide, in certain areas exceeding hospital capacities and human resources. This has underscored the importance of having better tools to predict the outcome of potentially severe respiratory infections such as SARS-CoV-2. Predicting COVID-19 severity may allow physicians to better manage ICU beds and increase the chances of patient survival through appropriate management. During the toughest months of the pandemic, most physicians tried to identify patients that might develop severe forms based primarily on clinical features on admission (e.g., BMI, age). In this context, significant research has focused on identifying comorbidities, clinical manifestations, and routine blood biomarkers to predict disease severity. However, despite the demonstrated value of untargeted metabolomics in assessing severity, limited data exist on its use for identifying novel metabolite biomarkers that could improve both the sensitivity and specificity of outcome prediction. Our goal is to identify metabolite biomarkers that could enhance the predictive accuracy of standard medical biology data and clinical parameters. Methods and analysis This is a retrospective, observational, monocentric cohort study conducted at the Centre Hospitalier Universitaire Grenoble Alpes (CHUGA). The maximum number of eligible patients admitted for PCR-confirmed COVID-19 between March and December 2020 will be included. Severity outcome is defined using the WHO 10-category ordinal scale (mild: categories 4-5; severe: >5). Blood samples were collected within 48 hours of admission and analyzed for 62 routine blood tests and untargeted multiplatform LC-MS/MS metabolomics across four national platforms. Statistical analysis will include logistic regression with variable selection for the primary aim, and multi-block chemometric integration of clinical, biological, and metabolomics data as a secondary aim. Ethics and dissemination A study steering committee has been formed to ensure the accuracy of the collected data by thoroughly reviewing it prior to the data lock. All aspects of the study comply with ethical standards, including approval by the CHUGA institutional review board and adherence to CNIL Reference Methodology MR004 for the protection of participants' rights, privacy, and confidentiality. This study is registered on the French Health Data Hub (number F20210218154851). Results will be disseminated through peer-reviewed publications, presentations at national and international scientific and clinical conferences, and reports shared with key healthcare system stakeholders.

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

Akasha 2: Hamiltonian State Space Duality and Visual-Language Joint Embedding Predictive Architectur

作者:

We present Akasha 2, a state-of-the-art multimodal architecture that integrates Hamiltonian State Space Duality (H-SSD) with Visual-Language Joint Embedding Predictive Architecture (VL-JEPA). The system leverages the Mamba-3 Selective State Space Model (SSM) augmented by a Sparse Mixture of Hamiltonian Experts (SMoE-HE) that enforces latent physical conservation laws through symplectic integration. For visual synthesis, we introduce Hamiltonian Flow Matching (HFM) and persistent 3D Gaussian Splatting (3DGS), enabling ultra-low latency (

16.
medRxiv (Medicine) 2026-06-11

A global cross-sectional survey of health professionals' interest-confidence gaps in value-based health care implementation: a learning needs assessment

Abstract Objectives Value-Based Health Care (VBHC) increasingly guides health system redesign internationally. Despite the increasing availability of VBHC education, gaps remain between health professionals' conceptual understanding of VBHC and their confidence to implement it in practice. This study assessed perceived learning needs and preferences of healthcare professionals across foundational topics essential to VBHC implementation. Design Cross-sectional online survey study Setting and participants The survey was distributed to the global VBHC community and yielded 518 responses. Most respondents were based in the UK and Ireland (51%) and 65% had more than 10 years of experience in the health sector. Participants represented a variety of professional backgrounds, including clinicians (34%), operational or executive managers and leaders (22%), and life sciences or procurement professionals (13%). Primary and secondary outcome measures Primary outcome measures included self-reported interest and confidence across 15 VBHC domains and the magnitude of the gap between them. Secondary outcomes included perceived implementation challenges and preferred VBHC learning approaches, including prior engagement with VBHC-related learning. Results Respondents identified substantial VBHC implementation challenges, including implementing outcome measurement (62.4%), conflicting priorities (57.7%), and resistance to change (56.8%). Interest in all VBHC domains was high (median >= 80/10), while confidence to implement remained substantially lower across most domains (median

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

Power Battery Detection

Power batteries are essential components in electric vehicles, where internal structural defects can pose serious safety risks. We conduct a comprehensive study on a new task, power battery detection (PBD), which aims to localize the dense endpoints of cathode and anode plates from industrial X-ray images for quality inspection. Manual inspection is inefficient and error-prone, while traditional vision algorithms struggle with densely packed plates, low contrast, scale variation, and imaging artifacts. To address this issue and drive more attention into this meaningful task, we present PBD5K, the first large-scale benchmark for this task, consisting of 5,000 X-ray images from nine battery types with fine-grained annotations and eight types of real-world visual interference. To support scalable and consistent labeling, we develop an intelligent annotation pipeline that combines image filtering, model-assisted pre-labeling, cross-verification, and layered quality evaluation. We formulate PBD as a point-level segmentation problem and propose MDCNeXt, a model designed to extract and integrate multi-dimensional structure clues including point, line, and count information from the plate itself. To improve discrimination between plates and suppress visual interference, MDCNeXt incorporates two state space modules. The first is a prompt-filtered module that learns contrastive relationships guided by task-specific prompts. The second is a density-aware reordering module that refines segmentation in regions with high plate density. In addition, we propose a distance-adaptive mask generation strategy to provide robust supervision under varying spatial distributions of anode and cathode positions. The source code and datasets will be publicly available at \href{https://github.com/Xiaoqi-Zhao-DLUT/X-ray-PBD}{PBD5K}.

18.
arXiv (CS.CV) 2026-06-16

FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty

Vision-language models (VLMs) are playing an increasingly important role across multiple domains. In many applications, such as robotics, it is crucial to quantify the uncertainty in the output of these models. } We develop FUSE, a probabilistic framework for capturing two complementary sources of uncertainty in vision-language modeling: (i) aleatoric embedding-level uncertainty derived from input data vision-language ambiguity, and (ii) epistemic model-level uncertainty estimated from the semantic response diversity of VLMs. Our approach formulates a Bayesian fusion mechanism that analytically combines these uncertainty sources to produce a scalar measure of uncertainty. This measure can be used to reliably predict the model's output correctness for downstream applications. We demonstrate that our method outperforms baselines and achieves SOTA uncertainty calibration.

19.
arXiv (quant-ph) 2026-06-17

Impact of Network Constraints on Fault-Tolerant Distributed Quantum Computing

arXiv:2606.17495v1 Announce Type: new Abstract: As we move towards scalable and modular quantum computing, quantum data centres become imperative. Existing analyses typically treat network constraints in isolation or through simplified models, leaving the interplay between error correction operations and communication resources underexplored. In this work, we present an end-to-end simulation framework that jointly models surface-code operations, internal QPU connectivity, and realistic network constraints including finite entanglement generation rates, limited communication qubits, and bandwidth contention, producing execution latency, from which logical error rate estimates are obtained. The framework is modular by design, allowing individual components such as routing heuristics, scheduling policies, and network topologies to be independently replaced. Numerical evaluation reveals distinct operating regimes in which the optimal resource allocation and code distance selection shift depending on the network characteristics. These results point to tradeoffs in the design of distributed quantum computing architectures that are not visible when computation and communication are modeled separately.

20.
Science (Express) 2026-05-07

TranscriptFormer: A generative cell atlas across 1.5 billion years of evolution | Science

作者: 未知作者

Single-cell transcriptomics is revolutionizing our understanding of cellular diversity, yet comparing transcriptional programs across the tree of life remains challenging. We developed TranscriptFormer, a family of generative foundation models trained on up to 112 million cells spanning 1.53 billion years of evolution across 12 species. We demonstrate state-of-the-art performance on cell type classification, even for species separated over 685 million years of evolution, and zero-shot disease state identification in human cells. Developmental trajectories, phylogenetic relationships and cellular hierarchies emerge naturally in TranscriptFormer’s representations without any explicit training on these annotations. This work establishes a powerful framework for quantitative single-cell analysis and comparative cellular biology, thus demonstrating that universal principles of cellular organization can be learned and predicted across the tree of life.

21.
arXiv (CS.AI) 2026-06-19

Which Pairs to Compare for LLM Post-Training?

arXiv:2606.19607v1 Announce Type: new Abstract: Preference-based post-training has become a central paradigm for aligning language models. A common data-collection strategy is to generate a small set of completions for each prompt and label the resulting comparison pairs. However, human preference labels are often much more expensive than generating additional completions, suggesting a different use of the same labeling budget: generate a larger pool of completions, but label only the most informative comparison pairs. This paper studies which pairs should be compared in preference-based post-training. We formulate comparison curation as a sampling-design problem and evaluate designs by the quality of the final policy under the preference-based post-training objective. We instantiate this framework for Direct Preference Optimization (DPO), analyzing how the choice of labeled pairs propagates through DPO training to downstream policy performance. Our main results provide matching upper and lower bounds on the post-training optimality gap of the DPO-trained policy. The bounds show that comparison selection affects downstream performance through a single design-dependent information matrix, which links label allocation to parameter estimation error and policy suboptimality. This yields an explicit optimization criterion for budgeted comparison curation and motivates practical sampling designs for selecting informative pairs from large generated completion pools. Experiments on synthetic settings and language-model post-training benchmarks show that the proposed designs consistently improve sample efficiency over common comparison-selection heuristics.

22.
arXiv (CS.AI) 2026-06-15

A Multi-Agent AI System for Automated High School Transcript Processing: Collaborative Document Analysis at Scale

arXiv:2606.13916v1 Announce Type: new Abstract: Each year, college admissions offices face an overwhelming challenge: processing millions of high school transcripts, each with unique formats, grading systems, and layouts. This manual process creates operational bottlenecks that delay admissions decisions and consume valuable resources. We present a transformative solution through a multi-agent AI system where specialized agents collaborate to automatically process diverse transcript formats through intelligent coordination and communication. Our multi-agent architecture consists of three specialized agents-a Pattern Recognition Agent for format-specific parsing, a Semantic Analysis Agent for natural language understanding, and a Vision Intelligence Agent for multimodal document analysis-coordinated by an Orchestration Agent that manages agent communication and result reconciliation. Our key innovation lies in agent-based quality control using GPA extraction as a coordination signal, ensuring reliable agent collaboration and preventing critical information loss. When evaluated on 40 real world transcripts from high schools across 13 U.S. states, our agent system successfully processed every document, achieving 96.7% accuracy compared to expert manual review while maintaining practical processing speeds of 45 seconds per transcript. This work demonstrates how multi-agent coordination can solve complex document processing challenges, offering institutions a scalable, collaborative AI solution that preserves accuracy while dramatically reducing processing time.

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

A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation

Existing approaches to post-train models for long-context tasks face complementary limitations: (i) supervised fine-tuning (SFT) provides stable supervision but suffers from exposure bias; (ii) reinforcement learning methods such as Group Relative Policy Optimization (GRPO) train on model-generated trajectories but struggle with long-horizon credit assignment and sparse rewards; and (iii) on-policy distillation (OPD) provides dense token-level guidance but does not directly optimize task rewards. We study these complementary strategies for long-context alignment and derive a recipe that combines GRPO with OPD-style teacher guidance: the student learns from its own rollouts using outcome-level rewards, while a stronger teacher provides dense token-level regularization in place of the standard reference policy. This is especially useful when process-level supervision is difficult to obtain. To support this study, we introduce LongBlocks, a synthetic multilingual dataset spanning multi-hop reasoning, contextual grounding, and long-form generation. Through controlled ablations, we isolate the roles of cold-start initialization, teacher anchoring, and data mixing, showing that our recipe yields a more stable and effective path to long-context reasoning than GRPO or OPD while preserving short-context capabilities.

24.
arXiv (CS.CL) 2026-06-15

Rethinking the Trust Region in LLM Reinforcement Learning

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio clipping mechanism in PPO is structurally ill-suited for the large vocabularies inherent to LLMs. PPO constrains policy updates based on the probability ratio of sampled tokens, which serves as a noisy single-sample Monte Carlo estimate of the true policy divergence. This creates a sub-optimal learning dynamic: updates to low-probability tokens are aggressively over-penalized, while potentially catastrophic shifts in high-probability tokens are under-constrained, leading to training inefficiency and instability. To address this, we propose Divergence Proximal Policy Optimization (DPPO), which substitutes heuristic clipping with a more principled constraint based on a direct estimate of policy divergence (e.g., Total Variation or KL). To avoid huge memory footprint, we introduce the efficient Binary and Top-K approximations to capture the essential divergence with negligible overhead. Extensive empirical evaluations demonstrate that DPPO achieves superior training stability and efficiency compared to existing methods, offering a more robust foundation for RL-based LLM fine-tuning. Our code is available at https://github.com/sail-sg/Stable-RL.

25.
arXiv (CS.AI) 2026-06-19

Co-policy: Responsive Human-Robot Co-Creation for Musical Performances

arXiv:2606.19914v1 Announce Type: cross Abstract: Art has long stood as a pivotal expression of human creativity. Embodied artificial intelligence offers a route for generative models to participate in that creativity through physical action rather than disembodied digital content. In robotic music co-creation, it is challenging to connect semantic musical understanding with real-time and physically executable performance. We present Co-policy, a framework for human-robot musical co-creation that separates semantic intent grounding, constrained musical variation, and visuomotor execution. To ground musical semantics, Co-policy uses pre-inference semantic anchors and a fine-tuned Qwen-vl planner (F-Qwen) to transform speech, live musical seeds, and visual observations into structured co-creation plans. To support low-latency execution, Co-policy introduces a Gaussian-Mixture Visuomotor Policy (GMP), implemented as a conditional mixture-density policy that maps target notes and visual context to multimodal robot actions in a single forward pass. Unlike robotic playback systems that merely reproduce user-specified notes, Co-policy generates complementary musical responses under both musical and physical constraints. Real-robot chime experiments, ablations, and expert evaluation show improved intent alignment, execution accuracy, and response frequency over diffusion-policy and ablated baselines, supporting physically grounded action generation as a key requirement for embodied human-AI co-creation.