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.
Science (Express) 2026-06-11

Laser phase plate improves structure determination of small proteins by cryo-EM | Science

作者: 未知作者

Phase plates can in principle overcome the poor image contrast in electron cryo–microscopy (cryo-EM) and the resulting limits on the structural reconstruction of small proteins. However, previous designs have been unstable and compromised the high-resolution signal. They have thus been unable to surpass results achieved by standard cryo-EM. Here, we show that the laser phase plate (LPP), installed in a custom, modern Titan Krios microscope, enhances the resolution in single-particle reconstruction of small proteins by improving specimen-motion correction, recovery of information from the early frames, as well as particle visualization, 3D classification, and alignment. These advances use standard defocus ranges and reconstruction procedures, but open the door to LPP-tailored protocols offering further improvements by leveraging the LPP demonstrated here.

02.
arXiv (CS.AI) 2026-06-15

Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization

arXiv:2606.13949v1 Announce Type: new Abstract: Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the current task, which can leak sensitive but unnecessary context such as authentication codes, private notifications, and background application states. We propose MINIM, a trusted local broker that performs privacy-aware minimization on the client side before any observation leaves the device. Grounded in Contextual Integrity (CI), MINIM learns a dual-score representation for each UI element by predicting an inherent sensitivity score (s) and a task-conditioned necessity score (n). These scores drive a ternary disclosure policy that keeps essential elements, abstracts sensitive attributes when needed, and removes task-irrelevant content. We optimize a CI-aware objective that penalizes necessity errors more strongly on high-risk content, enabling aggressive pruning while preserving task-critical information. Experiments on real-world UI observations derived from WebArena show that MINIM substantially reduces task-irrelevant sensitive leakage while preserving task-critical semantic context and the interactive affordances required for reliable agent actions.

03.
arXiv (CS.AI) 2026-06-16

Understanding Diversity Collapse in RLVR via the Lens of Overtraining

arXiv:2606.15455v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a key approach for enhancing the reasoning abilities of large language models. However, RLVR often suffers from diversity collapse: Pass@$1$ improves while high-$k$ Pass@$k$ degrades, which is viewed as a narrowing of the model's reasoning boundary. We formalize this diversity collapse through the lens of overtraining: once a problem's contribution to the reference metric has effectively saturated, further updates no longer expand what the model can solve but still concentrate probability mass on the trajectories favored by on-policy sampling. Under a standard setup with few rollouts per problem, even a single observed success places a problem in a nearly saturated regime for high-$k$ Pass@$k$, so most updates in standard RLVR are overtraining from the boundary perspective. This perspective also suggests a reading of whether RLVR can expand the model's reasoning abilities beyond the base model: since RLVR is structurally biased against high-$k$ Pass@$k$, its aggregate decline does not by itself mean that no new reasoning gains occurred. Interventionally, restricting updates to problems with zero observed success lifts Pass@$256$ above the base model on difficult benchmarks; observationally, a non-trivial fraction of initially unsolvable problems become solvable during standard RLVR training. Building on these findings, we propose Bayesian Boundary Gating (BBG), which redirects optimization away from overtraining by estimating each problem's marginal contribution to the reasoning boundary. Across multiple reasoning benchmarks, BBG improves average Pass@$k$ across a wide range of $k$.

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

Multi-Granular Attention-Driven Reinforcement Learning Framework for Web Intelligent Enhancement Systems

arXiv:2606.19690v1 Announce Type: new Abstract: From the past few years, web intelligent enhancement systems increasingly rely on heterogeneous and dynamic web data to deliver personalized, context-aware services. However, traditional machine learning, deep learning, and reinforcement learning models often struggle with semantic understanding, adaptability, and scalability in continuously evolving web environments. In this research, a Multi-Granular Attention-based Reinforcement Web Intelligent Enhancement System (MGAR-WIES) is proposed to address the challenges by integrating semantic graph modeling, attention mechanisms, and adaptive reinforcement learning. Initially, heterogeneous web data comprising structured, semi-structured and unstructured sources are collected and preprocessed for generating unified feature representations. These representations are transformed into a dynamic semantic graph, where entities and their relationships are modeled by using graph embeddings enhanced by attention mechanisms for capturing both local relevance and global contextual dependencies. Subsequently, an adaptive multi-agent reinforcement learning strategy leverages the attention-aware semantic states to optimize personalized web actions like content recommendation, navigation optimization, and service adaptation. Finally, the continuous online feedback is further integrated to update graph representations and learning policies in real time by ensuring sustained adaptability and performance. The proposed MGAR-WIES acheived better results in terms of accuracy (80%) when compared with existing approaches.

05.
arXiv (CS.CV) 2026-06-12

ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection

Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging due to rare and heterogeneous anomalies and the scarcity of labelled data. This scarcity makes unsupervised approaches predominant, yet existing methods often rely on reconstruction or forecasting, which struggle with complex data, or on embedding-based approaches that require domain-specific anomaly synthesis and fixed distance metrics. We propose ASTER, a framework that generates pseudo-anomalies directly in the latent space, avoiding handcrafted anomaly injections and the need for domain expertise. A latent-space decoder produces tailored pseudo-anomalies to train a Transformer-based anomaly classifier, while a pre-trained LLM enriches the temporal and contextual representations of this space. Experiments on three benchmark datasets show that ASTER achieves state-of-the-art performance and sets a new standard for LLM-based TSAD.

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

R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?

In this work, we aim to develop effective data synthesis techniques that autonomously synthesize multimodal training data for enhancing MLLMs in solving complex real-world tasks. To this end, we propose Collective Adversarial Data Synthesis (CADS), a novel and general approach to synthesize high-quality, diverse and challenging multimodal data for MLLMs. The core idea of CADS is to leverage collective intelligence to ensure high-quality and diverse generation, while exploring adversarial learning to synthesize challenging samples for effectively driving model improvement. Specifically, CADS operates with two cyclic phases, i.e., Collective Adversarial Data Generation (CAD-Generate) and Collective Adversarial Data Judgment (CAD-Judge). CAD-Generate leverages collective knowledge to jointly generate new and diverse multimodal data, while CAD-Judge collaboratively assesses the quality of synthesized data. In addition, CADS introduces an Adversarial Context Optimization mechanism to optimize the generation context to encourage challenging and high-value data generation. With CADS, we construct MMSynthetic-20K and train our model R1-SyntheticVL, which demonstrates superior performance on various benchmarks.

07.
arXiv (math.PR) 2026-06-11

Exact Fourier dimensions of dyadic Mandelbrot cascades on curves of nonvanishing curvature under minimal integrability

arXiv:2606.11758v1 Announce Type: new Abstract: We prove an exact Fourier-dimension formula for scalar dyadic Mandelbrot cascades pushed forward to fixed C^2 Jordan curves with nonvanishing curvature. Let W be in the minimal Kahane-Peyriere regime, let the scalar dyadic cascade live on T = R/Z, and let gamma map T to R^2 be a fixed C^2 Jordan curve with nonvanishing curvature, parametrized at constant speed. For the push-forward measure mu_gamma, we prove that, almost surely on non-extinction, its Fourier dimension is A_loc(W), the usual local exponent obtained by optimizing over q>1 from the moment expression involving E[W^q]. The upper bound follows from the scalar circle local-dimension theorem, bi-Lipschitz transfer to the fixed curve, and a deterministic curved-support obstruction for Fourier dimension. The lower bound follows from a fixed-curve finite-r annular theorem, which gives summable annular Fourier decay under a single finite moment witness. The main analytic input is a deterministic phase-geometry package for fixed nondegenerate C^2 curves: stationary tubes, derivative bands, and phase-bin coefficient estimates replacing the explicit trigonometric structure available on the unit circle.

08.
arXiv (CS.CV) 2026-06-18

Do as I Do: Dexterous Manipulation Data from Everyday Human Videos

How can we scalably generate data for robotic manipulation, especially on human-like platforms such as dexterous multi-fingered hands? Learning from human videos has recently emerged as a likely answer to this question. However, difficulties in estimating hand-object interaction and crossing the human-to-robot embodiment gap have hindered the adoption of abundant monocular RGB-only human videos as the primary source of robot manipulation data. In this work, we present DO AS I DO, an algorithm to reconstruct and retarget monocular RGB human videos to multi-fingered dexterous robotic hands. DO AS I DO reconstructs hand-object interactions from various egocentric and exocentric in-the-wild video sources. The algorithm then retargets these hand-object interaction estimates into a sequence of actions executable in the real world, yielding robot-complete manipulation data from disparate human videos. Overall, DO AS I DO outperforms previous state of the art in estimating hand-object interactions and extracting dexterous manipulation trajectories from RGB videos, as we show in experiments on datasets with ground truths and on a dataset of video clips collected online. Our experiments enable us to propose an efficacy playbook for practitioners collecting human data for manipulation.

09.
arXiv (CS.AI) 2026-06-15

Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance

arXiv:2606.14000v1 Announce Type: new Abstract: Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance. We address both limitations by applying a coding agent to formalize Numerical Methods for Ordinary Differential Equations, a textbook in numerical analysis that is largely absent from mathlib, stressing the agent's capacity to develop new theory from scratch. We further introduce a systematic, reproducible three-dimensional framework for evaluating the quality of agent-produced formalizations beyond compilation: semantic correctness, Mathlib reuse, and cross-file reuse via LLM-as-judge methods. Applying this framework to our own formalization and to the released outputs of RepoProver and M2F, we uncover recurring unfaithful formalization patterns, including incomplete multi-part statements, added weakening hypotheses, and parameter restrictions, that kernel acceptance entirely obscures. Our results suggest that compilation-based metrics substantially overstate formalization quality, and we provide a reproducible audit methodology to support more rigorous evaluation of future autoformalization systems.

10.
arXiv (CS.LG) 2026-06-19

Towards Graph-Based Deep Learning for Map Generalization: Insights from Building Footprints Simplification and Aggregation

arXiv:2606.19956v1 Announce Type: new Abstract: Map generalization remains one of the fundamental tasks in cartography, especially for the simplification and aggregation of complex building footprints. This study presents the first exploratory application of graph-based deep learning to both tasks, reformulating simplification as node movement prediction and aggregation as link prediction within a unified graph learning framework. We evaluate representative graph neural network architectures (GCN, GAT, and GraphSAGE) on multi-scale building datasets, showing that GraphSAGE demonstrates relative strengths in link prediction accuracy, while also revealing persistent challenges in precise node movement prediction. Beyond quantitative performance, the results highlight that aggregation poses greater complexity and challenges than simplification, underscoring the difficulty of capturing higher-level spatial relationships in map generalization with current deep learning approaches. Although limitations such as data imbalance and the need for post-processing remain, the study provides valuable insights and methodological directions for advancing automated map generalization with deep learning approaches.

11.
arXiv (CS.CL) 2026-06-12

Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs

Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token-generation rates. To unlock this potential, we present Spiffy, a speculative decoding algorithm to accelerate dLLM inference while provably preserving the model's output distribution. This work addresses the unique challenges involved in applying ideas from speculative decoding of AR-LLMs to dLLMs. Spiffy performs auto-speculation to eliminate the overheads of an independent draft model, structuring draft states in the form of a novel directed draft graph to take advantage of the bidirectional, blockwise nature of dLLM generation. These draft graphs are calibrated offline to maximize acceptance rates and are dynamically pruned during inference for improved computational efficiency. We present a detailed formulation of Spiffy and demonstrate its ability to accelerate LLaDA, Dream, and SDAR models in combination with KV caching and threshold-based dynamic unmasking leading to up to $8.6\times$ reduction in model inferences and $6.3\times$ acceleration in token rate.

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

Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training

arXiv:2601.17654v2 Announce Type: replace Abstract: The computing demand of AI is growing at an unprecedented rate, but energy supply is not keeping pace. As a result, energy has become an expensive and contended resource that requires explicit management and optimization. Although recent works have made significant progress in large model training optimization, they focus on optimizing either dynamic or static energy consumption. We find that fine-grained kernel scheduling and frequency scaling jointly and interdependently impact both dynamic and static energy consumption. Based on this finding, we design Kareus, a training system that pushes the time-energy tradeoff frontier by optimizing both aspects. Kareus decomposes the intractable joint optimization problem into local, partition-based subproblems. It then uses a multi-pass multi-objective optimization algorithm to find execution schedules that push the time-energy tradeoff frontier. Compared to the state of the art, Kareus reduces training energy by up to 28.3% at the same training time, or reduces training time by up to 27.5% at the same energy consumption.

13.
arXiv (quant-ph) 2026-06-19

Effective Faraday interaction between light and Helium-3 nuclear spins in a multi-pass cell

arXiv:2606.20328v1 Announce Type: new Abstract: Helium-3 nuclear spins form an exceptionally stable quantum system with extremely long coherence time, offering exciting opportunities for quantum technologies. In particular, nuclear spin-squeezed states promise enhanced precision for sensing tasks and tests of new physics. A central challenge for all these applications is the realization of a controllable light-nuclear spin interface. Here we experimentally demonstrate such an interface by exploiting metastability-exchange collisions in a low-pressure helium-3 gas cell at room temperature. A radio-frequency discharge produces a small population of metastable atoms that both enables efficient optical pumping and mediates an effective Faraday interaction between the collective nuclear spin and an optical probe. We quantitatively characterize the strength of this interaction as a function of the nuclear polarization, applied magnetic field, and probe-beam parameters. Moreover, we show that using a multi-pass cell enhances this interaction by effectively increasing the optical depth. Extrapolating to a tenfold increase of the probe power used in the present experiment, we project a measurement-induced squeezing rate of 0.52 s$^{-1}$. Our results provide a practical pathway for optical access to helium-3 nuclear spins and open prospects for generating long-lived, macroscopic nuclear spin-squeezed states for quantum metrology.

14.
arXiv (CS.LG) 2026-06-18

Shrinkage priors for Bayesian Substitute Confounders

arXiv:2606.18535v1 Announce Type: cross Abstract: Multi-cause observational studies contain information about unmeasured confounding through the dependence structure among causes. However, literal imputation of the unobserved confounder is often more complex than learning a lower-dimensional substitute score that preserves the shared assignment variation needed for stable causal adjustment. The deconfounder (Wang and Blei, 2019) and related substitute confounder methods exploit this idea, but flexible assignment models can fit the joint distribution of the causes while producing scores that over-encode the treatment vector, collapse overlap, or capture single-cause variation. We develop a Bayesian factor assignment framework for learning sparse substitute confounders that retain coarse multi-cause dependence with shrinkage priors. The theory is stated at the level of posterior concentration, factor score contraction, and overlap-preserving assignment geometry and therefore does not rely on a particular shrinkage prior. Under these conditions, the proposed regression-adjusted estimators are consistent for mean potential outcomes when the corresponding latent variable identification assumptions hold. Shrinkage priors provide a natural tool for latent structural learning: they favour low-dimensional factors supported by multiple causes, discourage effectively single-cause factors, and induce an ordering of the latent factors through progressive shrinkage. Synthetic experiments illustrate the roles of signal strength, outcome validity, and geometry-aware regularization. In an Alzheimer's Disease Neuroimaging Initiative (ADNI) baseline analysis, sparse substitute scores recover much of the adjustment obtained by directly conditioning on invasive cerebrospinal-fluid biomarkers, while collapse diagnostics identify when fitted factors reduce to individual observed measurements.

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

Mechanisms of Introspective Awareness

arXiv:2603.21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept – a phenomenon termed "introspective awareness." We investigate the mechanisms underlying this capability in open-weights models. First, we find that it is behaviorally robust: models detect injected steering vectors at moderate rates with 0% false positives across diverse prompts and dialogue formats. Notably, this capability emerges specifically from post-training; we show that preference optimization algorithms like DPO can elicit it, but standard supervised finetuning does not. We provide evidence that detection cannot be explained by simple linear association between certain steering vectors and directions promoting affirmative responses. We trace the detection mechanism to a two-stage circuit in which "evidence carrier" features in early post-injection layers detect perturbations monotonically along diverse directions, suppressing downstream "gate" features that implement a default negative response. This circuit is absent in base models and robust to refusal ablation. Identification of injected concepts relies on largely distinct later-layer mechanisms that only weakly overlap with those involved in detection. Finally, we show that introspective capability is substantially underelicited: ablating refusal directions improves detection by +53%, and a trained bias vector improves it by +75% on held-out concepts, both without meaningfully increasing false positives. Our results suggest that this introspective awareness of injected concepts is robust and mechanistically nontrivial, and could be substantially amplified in future models. Code: https://github.com/safety-research/introspection-mechanisms.

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

BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart

arXiv:2511.19162v3 Announce Type: replace-cross Abstract: Bioart brings living material into artistic practice, where a single work can be at once an aesthetic object, a scientific instrument, and an ethical provocation. Traditional categories sort such works along one axis at a time, which flattens the very hybridity that defines the field and leaves curators no way to compare works across many dimensions together. I introduce BioArtlas, a computational atlas that represents each bioartwork along many curated dimensions at once and organizes the field by conceptual similarity rather than by medium or chronology. My method embeds the keywords of all 81 works on each of thirteen interpretive axes, groups related concepts into a shared codebook that tames inconsistent terminology, and then searches systematically for a clustering that is both statistically clean and interpretable. Among the methods that place every work on the map, agglomerative clustering separates the field far more cleanly than the usual k-means baseline (silhouette 0.664 versus 0.483), whereas density-based methods reach higher scores only by discarding most of the corpus as noise. By separating rigorous analysis from public storytelling, BioArtlas turns the tangled complexity of bioart into a navigable landscape, openly available as an interactive interface (https://www.bioartlas.com) and dataset (https://github.com/joonhyungbae/BioArtlas).

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

SP-GCRL: Influence Maximization on Incomplete Social Graphs

arXiv:2605.12513v2 Announce Type: replace-cross Abstract: Influence maximization (IM) in real platforms is challenged by incomplete, noisy social graphs and non-stationary diffusion dynamics. We propose SP-GCRL, a social-propagation-aware graph contrastive reinforcement learning framework that learns end-to-end seed selection under partial observability.We first introduce a social-propagation-aware nonlinear diffusion function to model reinforcement/diminishing effects and probability drift under repeated exposure; we then construct dual structural views and perform contrastive learning to obtain node representations robust to missing edges and weak ties, while replacing expensive strategy metrics with a GAT-based regression surrogate to improve efficiency and scalability; finally, we use DDQN to learn an end-to-end seed selection policy on top of these representations. Experiments on multiple real-world networks show that SP-GCRL achieves significant gains over heuristic and learning-based baselines across budgets and topologies, while maintaining strong large-scale scalability.

19.
arXiv (CS.LG) 2026-06-11

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

arXiv:2605.03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient algorithm for finetuning GCPs that maintains off-policy critic networks to maximize data reuse and propagate policy gradients through the full generative process of the policy via a modified PPO objective, using critics as the terminal reward. OGPO achieves state-of-the-art performance on manipulation tasks spanning multi-task settings, high-precision insertion, and dexterous control. To our knowledge, it is also the only method that can fine-tune poorly-initialized behavior cloning policies to near full task-success with no expert data in the online replay buffer, and does so with few task-specific hyperparameter tuning. Through extensive empirical investigations, we demonstrate that OGPO drastically outperforms methods alternatives on policy steering and learning residual corrections, and identify the key mechanisms behind its performance. We further introduce practical stabilization tricks, including success-buffer regularization, two-sided conservative advantages, and Q-variance reduction, to mitigate critic over-exploitation across state- and pixel-based settings. Beyond proposing OGPO, we conduct a systematic empirical study of GCP finetuning, identifying the stabilizing mechanisms and failure modes that govern successful off-policy full-policy improvement.

20.
medRxiv (Medicine) 2026-06-16

Care Delivery Gap framework: a proof-of-concept patient-reported measure of guideline-referenced care-process omissions in sickle cell disease

Abstract Background:Sickle cell disease (SCD) is concentrated in sub-Saharan Africa, where delivery of guideline-referenced care remains challenging. Current evaluation approaches rely largely on access indicators and clinical outcomes, which do not directly measure care delivery. We developed the Care Delivery Gap (CDG) framework, a patient-reported approach for identifying care-process omissions, and conducted a proof-of-concept study to assess feasibility and explore variation across income strata. Methods: We conducted a cross-sectional framework-development study involving a proof-of-concept sample of 52 individuals with SCD or caregivers recruited through clinics and moderated SCD communities across Africa, North America, and Europe between June 2025 and March 2026. The CDG framework assessed patient-reported omissions in specialist involvement, follow-up continuity, cardiovascular screening, and biochemical surveillance. Analyses were descriptive. Results: Substantial multi-domain care-process omissions were identified despite high reported healthcare engagement. Across geographic income strata, cardiovascular screening was reported by 4/35 (11%) LMIC versus 16/17 (94%) HIC participants, and regular follow-up within the preceding 12 months by 14/35 (40%) versus 16/17 (94%), respectively. High CDG scores, representing 1 omissions across three or four domains, occurred in 20/35 (57%) LMIC compared with 1/17 (6%) HIC participants. Similar disparities were observed across specialist review and vitamin B12 surveillance domains. Conclusion: A structured patient-reported framework identified multi-domain omissions in guideline-referenced SCD care, including among individuals reporting healthcare access. The divergence between access indicators and reported care delivery suggests that service contact alone may not reflect care quality. The framework provides a feasible foundation for future process-level quality measurement in high-burden settings.

21.
Nature Biotechnology 2026-06-05

Structural motif search across the protein universe with Folddisco

作者:

Detecting similar protein structural motifs in large structure collections is computationally expensive. We developed Folddisco, a fast structural motif search tool that uses an index of position-independent geometric features, including side-chain orientation, combined with a rarity-based scoring system. Folddisco is 20-fold faster in querying and fourfold more storage-efficient than existing methods while improving accuracy. Folddisco is freely available online ( https://folddisco.foldseek.com ), along with a webserver ( https://search.foldseek.com/folddisco ). Folddisco enables protein structural motif search in million scale databases.

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

The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation

LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized. We study repeated identical evaluations on 29 tasks spanning 10 categories using two OpenAI judge models (GPT-4o-mini and GPT-4.1-mini), with 50 pairwise trials and 50 pointwise trials per question, supplemented by temperature and prompt-sensitivity ablations. Across judges, pairwise preferences flip on average 13.6% of the time, with 28% of questions exceeding a 20% flip rate and one question reaching 56%. GPT-4o-mini also exhibits a significant first-position bias (72% A-majority, p = 0.024). At the same time, mean pointwise score gaps are small (0.19–0.36 on a 10-point scale) and not statistically significant in aggregate, producing a pairwise–pointwise gap: judges frequently choose a winner even when their own scalar scores provide little evidence of a meaningful quality difference. Beyond within-judge instability, cross-judge agreement is only 76% ($\kappa = 0.51$), semantically equivalent prompt templates change majority outcomes in 25% of tested cases, and deterministic decoding reduces but does not eliminate inconsistency. A reliability curve analysis shows that, in our dataset, 11 repeated trials are needed for a majority vote to recover the 50-trial reference verdict with 95% probability on average, rising to 15 for high-variance questions. These findings suggest that single-trial LLM judging is often too noisy for high-stakes evaluation, and that multi-trial aggregation, position randomization, and explicit uncertainty reporting should be standard practice. Because both judges are from a single provider, cross-provider replication remains an important next step.

23.
arXiv (CS.CL) 2026-06-15

Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling

Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space. Existing methods face notable limitations: GRPO samples exclusively from the root, saturating high-probability trajectories while leaving deep, error-prone states under-explored. Tree-based methods blindly disperse budgets across trivial or unrecoverable states, causing sampling dilution that fails to uncover rare correct suffixes and destabilizes local baselines. To address this, we propose Deep Dense Exploration (DDE), a strategy that focuses exploration on $pivots$-deep, recoverable states within unsuccessful trajectories. We instantiate DDE with DEEP-GRPO, which introduces three key innovations: (1) a lightweight data-driven utility function that automatically balances recoverability and depth bias to identify pivot states; (2) local dense resampling at each pivot to increase the probability of discovering correct subsequent trajectories; and (3) a dual-stream optimization objective that decouples global policy learning from local corrective updates. Experiments on mathematical reasoning benchmarks demonstrate that our method consistently outperforms GRPO, tree-based methods, and other strong baselines. Code is available at https://github.com/AgentCombo/DEEP-GRPO

24.
arXiv (quant-ph) 2026-06-16

Sub-Poissonian Statistics and Quantum Non-Gaussianity from High-Harmonic Generation

arXiv:2602.10882v4 Announce Type: replace Abstract: Quantum technologies are powered by platforms to generate complex non-classical states of matter or light to realize applications. We investigate the non-classical properties of high-harmonic generation in semiconductors, an emerging photonic platform. Measuring the click statistics of three double-digit orders, we evaluate witness operators to certify the non-classicality of the generated states. We show that higher-order harmonics driven by a coherent laser are squeezed and entangled. The properties of the emission are well retrieved with an entangled Gaussian state model, obtained by numerical state optimization to multiple observables. Additionally, we perform inter-order heralded measurements to engineer the quantum state of the emission. The heralded states have distinct properties, showing sub-Poissonian photon statistics. Further, we witness the generation of a quantum non-Gaussian state, a resource highly relevant for quantum information. With this, we establish high-harmonic generation as a platform for generating quantum optical resources.

25.
arXiv (CS.CL) 2026-06-17

Rethinking Groups in Critic-Free RLVR

Reinforcement learning (RL) has become a central paradigm for post-training large language models. Existing critic-free RL methods typically generate a group of rollouts for the same question to estimate value baselines for advantage computation. However, this design suffers from data inefficiency, group synchronization barriers, and inflexibility with structured rollouts. In this work, we revisit the role of the ``group'' and show that its underlying function is not merely to estimate baselines but to prevent false penalties on negative samples. Building on this insight, we propose negative token filtering, a simple and effective strategy that enables stable single-rollout training. We apply it to two batch-level advantage methods, achieving comparable performance on reasoning tasks and stronger performance on agentic tasks relative to group-based RL techniques.