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 (math.PR) 2026-06-16

BBP Phase Transition for a Doubly Sparse Deformed Model

arXiv:2603.04832v3 Announce Type: replace Abstract: We prove the equivalent of the Baik, Ben Arous, Péché (2004) phenomenon for a novel, doubly sparse model where both the Wigner noise matrix and signal vector(s) are sparse. Specifically, we consider a deformed sub-Gaussian sparse Wigner ensemble with a fixed number of sub-Gaussian spike vectors of the same-order sparsity added. We show that spike vectors with signals greater than one are correlated with the top eigenvectors of the deformed ensemble and that each spike vector of signal greater than one induces an outlier eigenvalue. Notably, our results hold in the supercritical sparsity regime for the Wigner matrix ($q \gg \frac{\log n}{n}$) and for any sparse spike vector with an unbounded number of entries ($np\to \infty$). No further relationship between the sparsities of the noise matrix ($q$) and spike vectors ($p$) is necessary. This generalizes the work of Benaych-Georges and Nadakuditi (2010) and Péché (2005).

03.
bioRxiv (Bioinfo) 2026-06-16

Physics-Driven Zero-Shot Reconstruction of Isotropic 3D Fluorescence Microscopy under Undersampled Acquisition

Three-dimensional (3D) imaging represents the development of next generation of fluorescence microscopy. However, routine axial down-sampling makes isotropic resolution unrealistic. Here, we propose DeepUI, a physical zero-shot framework designed to achieve isotropic 3D fluorescence images from a low axial sampling rate. DeepUI fully leverages the intrinsic characteristics of 3D images through physics-guided degradation, which incorporates spatial-frequency joint learning to generate a scaled optical transfer function, combined with noise degradation and an up-sampling branch. Typically requiring just 5 minutes for training and 0.5 minutes for high-throughput and fast prediction, we demonstrate the superior performance of DeepUI to get isotropic results, and the exclusivity to axial down-sampling conditions, even in more challenging conditions, including defocused background, noise, and resolution blur.

04.
arXiv (quant-ph) 2026-06-12

Proper and improper mixed states serve as different prior beliefs for quantum state retrodiction

arXiv:2502.10030v2 Announce Type: replace Abstract: A mixed quantum state can be taken as capturing an unspecified form of ignorance; or as describing the lack of knowledge about the true pure state of the system ("proper mixture"); or as arising from entanglement with another system that has been disregarded ("improper mixture"). These different views yield identical density matrices and therefore identical predictions for future measurements. But when used as prior beliefs for inferring the past state from later observations ("retrodiction"), they lead to different updated beliefs. This is a purely quantum feature of Bayesian agency. Based on this observation, we establish a framework for retrodicting on any quantum belief and we prove a necessary and sufficient condition for the equivalence of beliefs. We also illustrate how these differences have operational consequences in quantum state recovery.

05.
arXiv (CS.LG) 2026-06-17

A Convex Quasilinearization Method for Solving Nonlinear PDEs with Physics-Informed Neural Networks

arXiv:2606.18175v1 Announce Type: cross Abstract: We present a numerical method for the forward solution of nonlinear partial differential equations (PDEs) in which Bellman-Kalaba quasilinearization reduces the nonlinear problem to a sequence of linear subproblems, each discretized by collocation onto a trial space that is linear in its parameters and solved by a single direct linear least-squares QR factorization. The trial space, which we term Linear-in-Learnables (LiL), comprises representations whose trainable parameters enter linearly, including random-feature extreme learning machines, spectral polynomial bases, and trigonometric expansions, each implemented as a physics-informed neural network. The method thus replaces the nonconvex gradient-based training that limits standard PINNs with a convex per-step solve. We establish local Newton-Kantorovich convergence of the outer iteration to a residual-limited neighborhood under an explicit smallness condition, with the limiting accuracy governed by the best-approximation residual of the trial space rather than by an optimization tolerance. The method, denoted LiL-Q, is assessed on seven benchmarks spanning scalar nonlinear PDEs (Bratu, viscous Burgers, Buckley-Leverett), coupled systems (plane-strain elasticity and the incompressible Navier-Stokes equations in two and three spatial dimensions), and steady-state Darcy flow with heterogeneous permeability. Across these problems, LiL-Q converges in single-digit outer iterations in most cases, even at the coarsest basis sizes and independent of the parameter count. When the exact solution lies in the span of the trial space, the method recovers it to machine precision in a single solve. On the Navier-Stokes benchmarks, it matches or exceeds published PINN solvers with up to two orders of magnitude fewer trainable parameters, without gradient-based optimization.

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

Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing

arXiv:2606.12816v1 Announce Type: cross Abstract: Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors. Routes that appear efficient by standard overhead metrics can still lose fidelity when they pass through poorly calibrated couplers. We study a calibration-aware graph reinforcement-learning router that uses same-day IBM Heron r2 calibration data to choose hardware-edge SWAPs. We train the policy with proximal policy optimization and evaluate it with exact simulated fidelity across nine Munich Quantum Toolkit (MQT) Bench circuits and three calibration snapshots. Across these evaluations, pooled mean exact fidelity is $0.727$, compared with $0.440$ for SABRE-best20 and $0.481$ for target-aware SABRE. Fidelity gains come with higher routed two-qubit counts and are concentrated in the 5q and 8q circuit families; under the fixed tree action graph, all 10q families favor SABRE-best20. Overall, our results show that calibration-aware learned routing can improve fidelity beyond gate-count-driven compilation.

07.
Nature Biotechnology 2026-06-22

Affordable centimeter-scale 3D microscopy with submicrometer resolution

作者: 未知作者

Submicrometer-resolution three-dimensional (3D) imaging of large samples has been constrained by the short working distance, high cost and inflexible design of immersion objectives. We developed hybrid solid–liquid optics (HySIL) — a refractive framework with index-matched components — for submicrometer-resolution 3D imaging of centimeter-scale samples in various immersion media using inexpensive air objectives.

08.
medRxiv (Medicine) 2026-06-24

Pembrolizumab, Temozolomide and HSPPC-96 Vaccine in Newly Diagnosed Glioblastoma Post-Chemoradiation: Results from a Multi-institutional, Phase 2, Randomized, Placebo-Controlled Trial

Background: GBM is one of the most common and most aggressive brain tumors in adults, and upfront standard of care treatment has limited efficacy. Immune checkpoint inhibitor strategies have significantly improved outcomes in various solid tumors but have not proven effective in GBM, suggesting other strategies may be needed to realize their full potential. Methods: GBM patients were treated with upfront standard of care chemoradiation with temozolomide and pembrolizumab, followed by adjuvant temozolomide and pembrolizumab for six nine-week cycles. Depending on production of sufficient vaccine, patients were randomized into HSPPC-96 vaccine or placebo group (q4 weeks) while those with failed vaccine production continued on study unblinded as an ancillary group. The primary objective was overall survival at one year, and secondary endpoints were progression-free survival at six months, overall and progression-free survival, radiographic response, and tolerability by patient-reported outcomes and adverse event documentation. Results: 90 patients were screened, 32 were treated (8 vaccine, 9 placebo, 15 ancillary), and 26 were evaluable for radiographic responses prior to accrual termination. The study did not meet its primary endpoint of overall survival at one year (65.5% in vaccine group, 75% in placebo). Progression-free endpoints were mildly improved in the vaccine group but were not significant, and response rates were not significantly different. The regimen was well-tolerated and safe. Conclusions: Though limited by early discontinuation, these findings do not support the combination of pembrolizumab and HSPPC-96 vaccine with standard of care therapy. Trials Registration: ClinicalTrials.gov identifier: NCT03018288

09.
arXiv (CS.LG) 2026-06-25

Sample complexity of unbalanced entropic OT

arXiv:2606.24987v1 Announce Type: cross Abstract: Optimal transport (OT) has become a central language for comparing probability measures, but exact balanced OT is often both too rigid for data with missing, created, or destroyed mass and subject to unfavorable high-dimensional sample complexity. Entropic regularization and unbalanced relaxations address these limitations in complementary ways. Entropy smooths the geometry, improves statistical behavior, and enables fast Sinkhorn-type algorithms, while unbalanced marginal penalties replace hard conservation constraints by divergence terms adapted to noisy empirical data. This paper studies the sample complexity of entropic unbalanced OT at the level of the optimal coupling, rather than only the scalar transport value. We develop a translation-invariant dual formulation, prove compactness and strong convexity properties for the intrinsic dual variables, and convert these geometric estimates into high-probability finite-sample bounds for empirical couplings. The results clarify why regularization is a practical necessity in machine learning applications: it softens the curse of dimensionality, reduces the number of samples needed for stable transport estimation, and keeps the resulting estimators compatible with scalable Sinkhorn-type solvers.

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

Diffuse AI Control on Fuzzy Tasks

arXiv:2606.08892v2 Announce Type: replace Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment. Diffuse AI Control is a subfield of AI safety concerned with mitigating risks from AI sabotage distributed over long deployment horizons (diffuse threats). These risks are particularly pernicious on fuzzy tasks, i.e. tasks which are hard to grade or require intuition. To understand diffuse threats on fuzzy tasks, we introduce a framework that considers AI control as an adversarial game between a blue team and a red team. The blue team uses a weak trusted model to construct a weak score against which they would train a strong, potentially subversive model to remove the subversion propensity if it were present. The red team then tries to find model behaviors that are rated highly by the weak score, and thus might not be trained out, but actually correspond to poor performance. We test our framework on the task of writing experimental proposals for research questions from recent ML papers. We use a language model with access to the original paper as a proxy "ground-truth" scorer. Our red team discovers subversive behaviors using multi-objective evolutionary prompt optimization. We show that Opus~4.6 can write proposals that are worse according to the ground truth proxy than those of GPT-OSS-20B, while the weak scorer rates them as highly as the best proposals from Opus 4.6. We then propose an adversarial optimization algorithm for the blue team that discovers more robust prompts for the weak model. This algorithm produces a blue team prompt that our red team optimization fails to exploit.

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

Iterative Visual Thinking: Teaching Vision-Language Models Spatial Self-Correction through Visual Feedback

Vision-language models (VLMs) achieve strong singleshot spatial grounding, yet lack any mechanism to observe and correct their own predictions. We find that naively prompting a VLM to iterate over rendered visualizations of its predictions causes catastrophic failure: Acc@0.5 on referring expression comprehension collapses from 79.6% to 48.7% (a 31 percentage point drop), revealing a fundamental gap between grounding capability and self-correction ability. We propose Iterative Visual Thinking (IVT), a closed-loop framework in which the model predicts a bounding box, observes the prediction rendered on the image, and iteratively refines through visual feedback. A two-phase training recipe closes the self-correction gap: first, we exploit the base model's own predictions as realistic errors and prompt a teacher VLM to generate corrective reasoning traces, yielding supervised data without human annotation; second, we apply Group Relative Policy Optimization (GRPO) with a simple IoU reward to stabilize multi-step refinement. On a mixed benchmark spanning RefCOCOg, Ref-Adv, and Ref-L4 (505 test samples), SFT warm-up with IVT surpasses the single-shot base model on every metric: Acc@0.5 rises to 82.0% (+2.4pp), Acc@0.7 to 74.1% (+3.2pp), and Acc@0.9 to 48.3% (+2.8pp). GRPO further reduces per-step IoU degradation by 5x, stabilizing the refinement trajectory. All training uses only 2,400 samples on a single GPU, demonstrating that spatial self-correction is a learnable capability that can be instilled at modest scale.

13.
arXiv (CS.LG) 2026-06-11

PCS-UQ: Uncertainty Quantification via the Predictability-Computability-Stability Framework

arXiv:2505.08784v2 Announce Type: replace-cross Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety. In this paper we introduce PCS-UQ, a framework based on the Predictability, Computability, and Stability (PCS) principles for veridical data science. Starting with a candidate set of models or algorithms, PCS-UQ integrates a rigorous prediction-check to screen out unsuitable models in the set and utilizes bootstrap samples, in order to capture both inter-sample variability and algorithmic instability for the prediction-checked algorithms. We then introduce a novel multiplicative calibration scheme to enhance local adaptivity, which basically corresponds to a new score in conformal prediction. Moreover, we produce a compilation of 17 real-world regression datasets with manually-constructed subgroups. On this benchmark, PCS-UQ maintains the target coverage while outperforming or matching conformal methods equipped with oracle-selected algorithms in interval width. PCS-UQ achieves consistent subgroup coverage, outperforming these oracle-selected conformal methods. Notably, PCS-UQ stands out in achieving both competitive interval widths and consistent subgroup coverage.Across 6 classification datasets, PCS-UQ reduces prediction set sizes by 20\%. To scale the framework for deep learning, we propose computationally efficient variants that bypass expensive retraining. On three computer vision benchmarks, these variants reduce prediction set sizes by 20\% over conformal baselines. Finally, we provide theoretical proof that a modified PCS-UQ algorithm preserves valid coverage under exchangeability as a form of split conformal inference.

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

Weakly Supervised Segmentation as Semantic-Based Regularization

Weakly supervised semantic segmentation (WSSS) trains dense pixel-level segmentation models from partial or coarse annotations such as bounding boxes, scribbles, or image-level tags. While recent work leverages foundation models such as the Segment Anything Model (SAM) to generate pseudo-labels, these approaches typically depend on heuristic prompt choices and offer limited ways to incorporate prior knowledge or heterogeneous labels. We address this gap by taking a neurosymbolic perspective: integrating differentiable fuzzy logic with deep segmentation models. Weak annotations and domain-specific priors are unified as continuous logical constraints that fine-tune SAM under weak supervision. The refined foundation model then produces improved pseudo-labels, from which we train a second-stage prompt-free segmentation model. Experiments on Pascal VOC 2012 and the REFUGE2 optic disc/cup segmentation dataset show that our logic-guided fine-tuning yields higher-quality pseudo-labels, leading to state-of-the-art segmentation accuracy that often exceeds densely supervised baselines.

15.
arXiv (CS.CV) 2026-06-25

CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks

Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures composed of unimodal encoders, such as DINO and BERT, remains a significant challenge. ParameterEfficient Fine-Tuning (PEFT) methods like LowRank Adaptation (LoRA) enable lightweight adaptation, yet they operate in isolation within each modality, limiting their ability in capturing cross-modal interactions. In this paper, we take a step in bridging this gap with Cross-Modal LowRank Adaptation (CoLA), a novel PEFT framework that extends LoRA by introducing a dedicated inter-modal adaptation pathway alongside the standard intra-modal one. This dual-path design enables CoLA to adapt unimodal foundation models to multimodal tasks effectively, without interference between modality-specific and crossmodal learning. We evaluate CoLA across a range of vision-language (RefCOCO, RefCOCO+, RefCOCOg) and audio-visual (AVE, AVS) benchmarks, where it consistently outperforms LORA, achieving a relative gain of around 3% and 2%, respectively, while maintaining parameter efficiency. Notably, CoLA enables the first multitask PEFT framework for visual grounding, bridging a key gap in efficient multimodal adaptation. Code is available at https://github.com/peterwisu/CoLA

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

BitNet Text Embeddings

LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage. BITEMBED converts pretrained LLM backbones into BitNet-style embedding encoders with ternary weights, quantized activations, and lightweight normalization refinement. The converted model is adapted to representation learning through continual contrastive pre-training, followed by supervised contrastive fine-tuning with both similarity-distribution distillation and attention-relation distillation from a full-precision teacher. Beyond quantizing the backbone, BITEMBED further trains output embeddings to support multiple storage precisions meeting different storage needs in various scenarios. Experiments on MMTEB (eng, v2) with Qwen3-0.6B and Gemma3-270M show that BITEMBED is largely comparable to full precision teacher embedders. Moreover, BITEMBED flexibly obtains text embeddings of various precisions, achieving a trade-off between performance and storage cost.

17.
arXiv (CS.CL) 2026-06-15

A Computational Audit of Demographic Association Encoding in ClinicalBERT Language Predictions

Transformer-based clinical language models are increasingly integrated into high-stakes clinical decision support pipelines, yet the computational mechanisms through which demographic associations encoded in medical documentation propagate into model probability distributions remain empirically underspecified. We present a systematic computational audit of representational bias in ClinicalBERT (Alsentzer et al., 2019), a BERT-based model pretrained on MIMIC-III discharge summaries, employing two complementary probing methodologies: Log Probability Bias Analysis (LPBA), which quantifies demographic descriptor-induced shifts in masked token probability distributions across behavioral and evaluative semantic categories, and Masked Language Model-based analysis (MLM), which probes internal representational structure for demographic agency attribution encoding across 98 real clinical sentence templates and eight intersectional race-gender combinations. Corpus frequency analysis operationalizes the distinction between statistical disparity and bias amplification by benchmarking model outputs against empirical term frequencies in the MIMIC-III training corpus. Of 32 statistically significant findings, 65.6% contradict observed corpus distributions, rising to 80% for Black patients and 87.5% for agency attribution under MLM probing, providing direct empirical evidence that representational bias in ClinicalBERT operates predominantly through model-internal amplification rather than training data inheritance. Keywords: natural language processing, clinical documentation, algorithmic auditing, representational bias, health equity 1

18.
medRxiv (Medicine) 2026-06-22

Agentic Artificial Intelligence for Hospital Readmission Review: A Single-Center Blinded Evaluation and Exploratory Qualitative Analysis

Background: Manual review of 30-day hospital readmissions can identify actionable quality and safety problems, but it is labor-intensive. We developed and evaluated an agentic AI workflow for evidence-grounded readmission review. Materials and methods: We studied adult patients with unplanned 30-day readmission after discharge from a medicine hospitalist service at a single academic health system. An AI agent using a large language model queried a database containing notes, encounters, procedures, laboratory results, and other clinical data, and completed the same structured readmission-review rubric used by physicians. In the primary comparative evaluation, 20 randomly selected readmissions from 2025 were each reviewed by two physicians and the AI system. Blinded physician evaluators rated review quality. After rubric refinement, the AI workflow was applied to 100 recent readmissions in an exploratory expanded-cohort analysis of recurring improvement opportunities. Results: In the primary comparative evaluation, the AI classified 9/20 readmissions (45%) as preventable, compared with 19/40 physician reviews (47.5%). Blinded overall quality ratings were similar for AI and physician reviews (4.35 vs. 4.20 on a 1-5 scale; mean difference 0.15, 95% CI -0.20 to 0.48; p=0.49), as were factuality/support and usefulness/actionability ratings. No AI hallucinations were identified during factuality review. Agreement on preventability and primary readmission category was low for both AI-human and human-human comparisons. The AI system cost $0.23 per chart; physician reviewers took a median of 15 minutes, corresponding to an estimated $42.43 per chart. In the exploratory expanded-cohort analysis, AI-assisted review identified recurring vulnerabilities in post-discharge follow-up plans, incomplete inpatient workups, medication-safety transitions, and indwelling-device transitions. Conclusions: Agentic AI produced readmission reviews with similar blinded quality ratings to physician reviews in this small single-center primary comparative evaluation and supported identification of recurring quality-improvement themes in the exploratory expanded-cohort analysis. Preventability judgments remained variable among both AI and physicians, underscoring the need for human oversight and prospective evaluation before operational use.

19.
arXiv (math.PR) 2026-06-18

Law of the Iterated Logarithm for $p$-Walks on $\mathbb{Z}$

作者:

arXiv:2606.19131v1 Announce Type: new Abstract: The $p$-rotor walk on $\mathbb{Z}$ is a self-interacting walk that interpolates between the simple random walk and the deterministic rotor walk. While the weak convergence of this model to a perturbed Brownian motion is known, its almost sure asymptotic boundaries have not been characterized. In this paper, we establish the exact Law of the Iterated Logarithm (LIL) for the $p$-rotor walk. Utilizing the decomposition of the walk into a martingale perturbed by its running extrema, we obtain first a functional Law of the Iterated Logarithm for the linearly interpolated paths of the $p$-walk. We then obtain the classical LIL constants by solving a calculus of variations problem over the perturbed Strassen set.

20.
Nature Medicine 2026-06-08

Effects of SGLT2 inhibition on incident heart failure in carriers of cardiomyopathy-associated genetic variants

Although the beneficial effects of sodium–glucose cotransporter 2 (SGLT2) inhibition in heart failure (HF) have been well established, it is unknown whether SGLT2 inhibition confers benefit in carriers of rare variants in cardiomyopathy-associated genes. Here we evaluated whole-exome sequencing data from the randomized DECLARE-TIMI 58 trial, in which adults with type 2 diabetes and increased cardiovascular risk were randomized to dapagliflozin or placebo treatment. Pathogenic or likely pathogenic variants (P/LP) in high-confidence cardiomyopathy genes were identified, and treatment effects on hospitalization for HF (HHF) were compared between carriers of such variants and noncarriers. Among 12,685 patients for whom sequence data were obtained, 121 carried a cardiomyopathy variant (76 dilated cardiomyopathy, 25 hypertrophic cardiomyopathy and 25 arrhythmogenic cardiomyopathy). Over a median follow-up of 4.2 years, dapagliflozin lowered the risk of HHF more strongly in carriers (hazard ratio 0.18, 95% confidence interval 0.04–0.86) than in noncarriers (hazard ratio 0.70, 95% confidence interval 0.57–0.86; P interaction 0.03). Absolute risk reduction was 13.0% in carriers and 1.0% in noncarriers (P interaction 0.03). Most carriers (82%) had no prior HF, and in carriers without prior HF, treatment with dapagliflozin reduced the absolute risk of HHF by 12.8%, compared with a reduction of 0.6% in noncarriers (P interaction 0.01). The findings from this cohort of older and high-risk patients raise the possibility that SGLT2 inhibitor treatment should be started early to prevent HF in individuals who carry P/LP cardiomyopathy variants. These results need to be confirmed in a prospective, dedicated trial of preventive HF treatments in carriers of P/LP cardiomyopathy-associated variants. In a whole-exome sequencing analysis, the beneficial effects of the SGLT2 inhibitor dapagliflozin in reducing the risk of future heart failure hospitalization in individuals with type 2 diabetes were markedly greater in individuals who carried a cardiomyopathy-associated genetic variant compared with noncarriers, suggesting a personalized preventative therapy based on genetic information.

21.
arXiv (CS.LG) 2026-06-17

MiniFool – Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks

arXiv:2511.01352v2 Announce Type: replace Abstract: In this paper, we present a new algorithm, MiniFool, that implements physics-inspired adversarial attacks for testing neural network-based classification tasks in particle and astroparticle physics. While we initially developed the algorithm for the search for astrophysical tau neutrinos with the IceCube Neutrino Observatory, we apply it to further data from other science domains, thus demonstrating its general applicability. Here, we apply the algorithm to the well-known MNIST data set and furthermore, to Open Data data from the CMS experiment at the Large Hadron Collider. The algorithm is based on minimizing a cost function that combines a $\chi^2$ based test-statistic with the deviation from the desired target score. The test statistic quantifies the probability of the perturbations applied to the data based on the experimental uncertainties. For our studied use cases, we find that the likelihood of a flipped classification differs for both the initially correctly and incorrectly classified events. When testing changes of the classifications as a function of an attack parameter that scales the experimental uncertainties, the robustness of the network decision can be quantified. Furthermore, this allows testing the robustness of the classification of unlabeled experimental data.

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

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

arXiv:2602.00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time. Existing infinite-horizon methods, which often rely on discounted contraction, do not naturally account for this fixed-horizon structure. We introduce a modified Q-function: rather than targeting the full-horizon, we learn a K-step lookahead Q-function that truncates planning to the next K steps. To further improve sample efficiency, we introduce a thresholding mechanism: actions are selected only when their estimated K-step lookahead value exceeds a time-varying threshold. We provide an efficient tabular learning algorithm for this novel objective, proving it achieves fast finite-sample convergence: it achieves minimax optimal constant regret for $K=1$ and $\mathcal{O}(\max((K-1),C_{K-1})\sqrt{SAT\log(T)})$ regret for any $K \geq 2$. We numerically evaluate the performance of our algorithm under the objective of maximizing reward. Our implementation adaptively increases K over time, balancing lookahead depth against estimation variance. Empirical results demonstrate superior cumulative rewards over state-of-the-art tabular RL methods across synthetic MDPs and RL environments: JumpRiverswim, FrozenLake and AnyTrading. Code is provided on \href{https://github.com/jamie01713/K-Step-Lookahead}{github}.

23.
arXiv (CS.AI) 2026-06-18

A Link between Shock-wave Theory and Symmetry-reduced Stochastic Gradient Descent for Artificial Neural Networks

arXiv:2606.18303v1 Announce Type: cross Abstract: We develop a mathematically explicit link between shock-wave theory and the symmetry-quotiented learning dynamics of stochastic gradient descent, drawing on differential geometry, Lie group theory, and fluid mechanics. Specifically, after quotienting parameter symmetries and applying local-entropy coarse-graining, the effective dynamics satisfy a viscous Hamilton–Jacobi equation on the quotient manifold. Moreover, under the assumption that the raw parameter dynamics can be summarized by a gradient field on the quotiented space, the gradient of the coarse-grained loss function obeys a Burgers-type equation, and shock formation can be established rigorously. We apply our theory to multilayer perceptrons, convolutional neural networks, Transformers, and mean-field networks, and show that they obey the Hamilton–Jacobi or Burgers-type equations. We conjecture that this framework also yields practical diagnostics for deep learning. In architectures such as Transformers, raw parameter norms are often distorted by symmetry redundancy and may therefore be misleading, whereas symmetry-corrected quotient observables provide a principled basis for monitoring, forecasting, and controlling training-phase transitions.

24.
arXiv (CS.AI) 2026-06-19

Playful Agentic Robot Learning

arXiv:2606.19419v1 Announce Type: cross Abstract: Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive. We introduce RATs, Robotics Agent Teams designed for play-time skill acquisition. During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library. At test time, the agent reuses relevant skills from this frozen library to help solve new tasks. Experiments in LIBERO-PRO and MolmoSpaces show that play-learned skills improve held-out downstream tasks over no-play and random-play baselines, with 20.6 and 17.0 percentage-point gains over CaP-Agent0 on LIBERO-PRO and MolmoSpaces, respectively. Moreover, the learned skills can be plugged into other inference-time Code-as-Policy agents by simply retrieving them into the context, improving RoboSuite and real-world transfer by 8.9 and 8.8 points, respectively, without finetuning the underlying model.

25.
arXiv (CS.AI) 2026-06-15

Regulating the Machine Contributor: Governance and Policy Alignment in Open Source

arXiv:2606.14594v1 Announce Type: cross Abstract: AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision. Open-source software, however, evolves through a process designed for humans: contributor agreements, codes of conduct, and review norms all assume a legally accountable person who can attest to provenance and answer reviewer questions. Autonomous and semi-autonomous AI contributors strain those assumptions, and the 2025-2026 record of agent-driven incidents, AI-generated nuisance volume, and platform-level shutdowns shows that the gap is operationally consequential. Several open-source organisations have responded with contribution policies, but the result is fragmented, and its alignment with emerging AI governance frameworks (EU AI Act, NIST AI RMF with the UC Berkeley Agentic AI Profile, ISO/IEC 42001 and 23894) is unmapped at the contribution level. We compare policies across six organisations (SymPy, LLVM, matplotlib, OpenInfra, the Apache Software Foundation, and the Linux Foundation) using Most-Similar Systems Design with indicator-based coding and process tracing for SymPy and LLVM. From this we derive a six-dimensional taxonomy (disclosure, responsibility, human oversight, licensing, enforcement, maintainer workload), an ordinal Policy Maturity Score, and a mapping of documented agent incidents onto the dimensions each policy fails to govern. Aligning the dimensions with the regulatory frameworks above identifies overlapping gaps neither side currently closes, and we close by sketching the shape of a harmonised tiered framework and the empirical evaluation needed to calibrate it.