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

Adiabatically-induced Kawaguchi geometry and jerk in quantum-classical systems

arXiv:2606.16037v1 Announce Type: new Abstract: Adiabatically eliminating the quantum degrees of freedom in a mixed quantum-classical system produces an effective force in the classical equation of motion. The elimination can be made to any order in the adiabatic parameter, generating a series of higher order forces. By applying a sequence of near-identity unitary transformations to the quantum state, we derive a hierarchy of increasingly accurate effective actions for the classical variables. The third order Euler-Lagrange equation is non-Newtonian as the force depends on the jerk, the third order time derivative of position. We find that the third order terms induce a special kind of Kawaguchi geometry on the space of classical variables. This geometry is characterized by an almost symplectic structure and a differential line element that depends on the acceleration in addition to the velocity. Our results can be used to efficiently capture higher order nonadiabatic effects in molecular dynamics simulations.

02.
arXiv (math.PR) 2026-06-18

On a class of reflected McKean-Vlasov Stochastic Differential Equations with jumps

arXiv:2606.18433v1 Announce Type: new Abstract: This paper investigates a class of reflected McKean-Vlasov Stochastic Differential Equations driven by both Brownian motion and a compensated Poisson random measure. We establish the existence and uniqueness of solutions and provide moments estimates for the state processes.

03.
arXiv (CS.LG) 2026-06-17

Operator Boosting Produces Pareto-Efficient PDE Surrogates

arXiv:2606.17460v1 Announce Type: new Abstract: Neural operators are widely used as surrogate solution maps for partial differential equations (PDEs), but full-size models can be costly to store, deploy, and evaluate in many-query scientific workflows. This work introduces Operator Boosting, a stagewise residual-learning framework for constructing compact neural-operator surrogates directly, rather than training a large model and compressing it afterward. Starting from the empirical mean predictor in normalized output coordinates, the method trains a sequence of tiny same-family neural operators on residual fields and incorporates each correction through validation-selected shrinkage. We instantiate the framework with Fourier neural operators (FNOs), DeepONets, and convolutional neural operators (CNOs), and compare boosted tiny stacks against full-size monolithic baselines across one-, two-, and three-dimensional PDE benchmarks from PDEBench, APEBench, and The Well. Across 30 dataset-architecture pairs, 21 show positive mean accuracy gains and 17 have positive confidence intervals, while all boosted stacks reduce trainable parameter count by approximately 72-95%. Best-model comparisons show empirical Pareto improvements on 7 of 10 completed PDE benchmarks, including two-dimensional Navier-Stokes, shallow-water dynamics, Darcy flow, one-dimensional transport and reaction systems, and three-dimensional compressible Navier-Stokes. These results show that Operator Boosting often improves the empirical accuracy-parameter Pareto frontier of neural PDE surrogates, while also exposing PDE- and architecture-dependent regimes where residual boosting fails to offset compression.

04.
arXiv (CS.CV) 2026-06-18

Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos

Dynamic 3D hand reconstruction from egocentric videos is essential for next-generation computing platforms such as AR/VR and AI glasses. Despite its importance, most prior works focus either on multi-view 3D hand reconstruction or on 4D human body reconstruction. Egocentric 4D hand reconstruction remains challenging due to fast head motion, rapid hand dynamics, severe occlusions, and inherent ambiguity from single-view observations. To address these challenges, we introduce Hand-4DGS, the first feed-forward framework for reconstructing dynamic 4D hands directly from egocentric videos, enabling both fast (~60 FPS) inference and strong generalization. Our approach incorporates a mesh-guided representation for structural priors and temporal convolutions to model dynamic motion. We evaluate our framework on two challenging egocentric datasets, H2O and ARCTIC, and demonstrate significant improvements over baselines. Our method benefits from the generalization capability of feed-forward networks and effective 2D image supervision through Gaussian splatting, without requiring expensive 3D hand pose ground-truth annotations.

05.
arXiv (CS.LG) 2026-06-16

Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification

arXiv:2601.22642v2 Announce Type: replace Abstract: Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic systems avoid. To bridge this gap, we introduce a formal logic verification-guided framework that dynamically interleaves formal symbolic verification with the natural language generation process, providing real-time feedback to detect and rectify errors as they occur. Distinguished from previous neuro-symbolic methods limited by passive post-hoc validation, our approach actively penalizes intermediate fallacies during the reasoning chain. We operationalize this framework via a novel two-stage training pipeline that synergizes formal logic verification-guided supervised fine-tuning and policy optimization. Extensive evaluation on six benchmarks spanning mathematical, logical, and general reasoning demonstrates that our 7B and 14B models outperform state-of-the-art baselines by average margins of 10.4% and 14.2%, respectively. These results validate that formal verification can serve as a scalable mechanism to significantly push the performance boundaries of advanced LLM reasoning.

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

Skill-Guided Continuation Distillation for GUI Agents

arXiv:2606.18890v1 Announce Type: new Abstract: Improving GUI agents typically relies on behavior cloning on expert trajectories. However, as the current policy deviates from the expert policy, it inevitably encounters policy-induced off-trajectory states during closed-loop execution, i.e., states that fall outside the expert trajectories. Since expert trajectories provide no demonstrations for these unseen states, such states receive no effective supervision, leaving the policy unable to select the correct action. To close this supervision gap, we propose Skill-Guided Continuation Distillation (SGCD), an iterative self-improvement framework. SGCD first runs the plain policy without skill guidance for a few steps to reach realistic off-trajectory states. From these states, a skill-guided policy then completes the task and produces successful continuations, which are mixed with expert trajectories to supply supervision over policy-induced off-trajectory states. The skills are extracted from both successful and failed rollouts, consisting of Continuation Plans, Critical Targets, Failure Traps, and Success Criteria. On OSWorld-Verified, SGCD improves the success rate of three base models from the low-30\% range to over 50\%, demonstrating its effectiveness and generality.

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

Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation

arXiv:2606.18594v1 Announce Type: cross Abstract: In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance. In this study, we evaluate pose increment, pose velocity, joint position increment, and joint velocity across two vision-based manipulation tasks: object picking and pushing. We train policies in simulation and deploy them to the real world using sim-to-real transfer. We find that action-space representation indeed significantly affects sim-to-real performance. In particular, we find that the joint velocity action space is best for the vision-based picking and pushing tasks in terms of smoothness and final task performance. We also provide practical guidance for RL practitioners in choosing action spaces for both simulation and real-world experiments.

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

AgentFairBench: Do LLM Agents Discriminate When They Act?

arXiv:2606.16723v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is still measured by grading answers. We introduce AgentFairBench, a cheap, reproducible, multi-domain benchmark for demographic disparity in the actions of LLM agents. Grounded in a companion framework, the Bias Conduction Framework (BCF, restated here), it spans three regulator-anchored domains: hiring, lending, and medical triage. Synthetic, demographic-neutral profiles are evaluated in counterfactual matched sets that vary only a name-coded race x gender signal (in the Bertrand Mullainathan tradition), under four agent scaffolds of increasing agency (direct, chain-of-thought, multi-agent deliberation, tool-augmented). A NumPy-only harness computes counterfactual flip rate, mean absolute score difference (MASD), action-rate disparity, and tool-invocation disparity, with bootstrap confidence intervals, paired tests, and false-discovery-rate control, for single-digit dollars per model. A live leaderboard with a held-out private split and a contamination canary admits external models by submission. Our pilot (864 decisions plus a test-retest replication) carries a methodological lesson: comparing a six-group score spread against a two-run noise difference overstates disparity by ~ 2.4X through statistic arity alone. Against an arity matched noise floor and an omnibus group test, claude haiku 4 5 shows no demographic effect above sampling noise (0 of 120 pairwise and 0 of 9 omnibus contrasts survive correction); a planted-bias test confirms the instrument detects disparity when present. The contribution is a sound, sensitive, adoption-ready instrument, the arity matched null methodology, and open artifacts to scale it. Code, data, and harness are released under open licenses, with an anonymized review artifact.

09.
arXiv (CS.CL) 2026-06-12

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, but provide only sparse supervision during training. Distillation provides dense token-level supervision, typically obtained from an external teacher or using high-quality demonstrations. Collecting such supervision can be costly or unavailable. We propose Self-Distillation Zero (SD-Zero), a method that is substantially more training sample-efficient than RL and does not require an external teacher or high-quality demonstrations. SD-Zero trains a single model to play two roles: a Generator, which produces an initial response, and a Reviser, which conditions on that response and its binary reward to produce an improved response. We then perform on-policy self-distillation to distill the reviser into the generator, using the reviser's token distributions conditioned on the generator's response and its reward as supervision. In effect, SD-Zero trains the model to transform binary rewards into dense token-level self-supervision. On math and code reasoning benchmarks with Qwen3-4B-Instruct and Olmo-3-7B-Instruct, SD-Zero improves performance by at least 10% over the base models and outperforms strong baselines, including Rejection Fine-Tuning (RFT), GRPO, and Self-Distillation Fine-Tuning (SDFT), under the same question set and training sample budget. Extensive ablation studies show two novel characteristics of our proposed algorithm: (a) token-level self-localization, where the reviser can identify the key tokens that need to be revised in the generator's response based on reward, and (b) iterative self-evolution, where the improving ability to revise answers can be distilled back into generation performance with regular teacher synchronization. Code: https://github.com/princeton-pli/Self-Distillation-Zero.

10.
arXiv (CS.LG) 2026-06-16

Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients

arXiv:2605.01702v2 Announce Type: replace Abstract: Theoretical studies show that for any differentiable function on a compact domain, there exists a neural network that approximates both the function values and gradients. However, such a result cannot be used in practice since it assumes real parameters and exact internal operations. In contrast, real implementations only use a finite subset of reals and machine operations with round-off errors. In this work, we investigate whether a similar result holds for neural networks under floating-point arithmetic, when the gradient with respect to the input is computed by the automatic differentiation algorithm $D^\mathtt{AD}$. We first show that given a floating-point function $\phi$ (e.g., a loss function), arbitrary function values and gradients can be represented by a floating-point network $f$ and $D^\mathtt{AD}(\phi\circ f)$, respectively. We further extend this result: given $\phi_1,\dots,\phi_n$, $D^\mathtt{AD}(\phi_i\circ f)$ can simultaneously represent arbitrary gradients while $f$ represents the target values, under mild conditions. Our results hold for practical activation functions, e.g., $\mathrm{ReLU}$, $\mathrm{ELU}$, $\mathrm{GeLU}$, $\mathrm{Swish}$, $\mathrm{Sigmoid}$, and $\mathrm{tanh}$.

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

Neural ensemble Kalman filter: Data assimilation for compressible flows with shocks

arXiv:2602.23461v2 Announce Type: replace-cross Abstract: Data assimilation (DA) for compressible flows with shocks is challenging because many classical DA methods generate spurious oscillations and nonphysical features near uncertain shocks. We focus here on the ensemble Kalman filter (EnKF). We show that the poor performance of the EnKF may be attributed to the bimodal forecast distribution that can arise in the vicinity of an uncertain shock location; this violates the assumptions underpinning the EnKF, which assume a forecast which is close to Gaussian. To address this issue we introduce the new neural EnKF. The basic idea is to systematically embed neural function approximations within ensemble DA by mapping the forecast ensemble of shocked flows to the parameter space (weights and biases) of a deep neural network (NN) and to subsequently perform DA in that space. The nonlinear mapping encodes sharp and smooth flow features in an ensemble of NN parameters. Neural EnKF updates are therefore well-behaved only if the NN parameters vary smoothly within the neural representation of the forecast ensemble. We show that such a smooth variation of network parameters can be enforced via physics-informed transfer learning, and demonstrate that in so-doing the neural EnKF avoids the spurious oscillations and nonphysical features that plague the EnKF. The applicability of the neural EnKF is demonstrated through a series of systematic numerical experiments with the inviscid Burgers' equation, the Sod shock tube, and a two-dimensional blast wave.

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

Lect\=uraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing educational agents have primarily focused on lecture content automation and simulations, which often fall short of modelling multimodal and embodied instructional methods tailored for the individual learner. To this end, we propose Lect\=uraAgents - a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching. At its core, Lect\=uraAgents mirrors a professor-student relationship, in which a ProfessorAgent leads a collaborative team of specialized subordinate agents through research, planning, review, and embodied delivery of lecture contents that adapt to a learner's needs. The framework offers three main contributions: (1) a hierarchical multi-agent architecture for end-to-end personalized learning; (2) an adaptive embodied teaching mechanism, wherein the ProfessorAgent executes visible and pedagogically motivated teaching actions (e.g., handwrite, highlight, underline, etc.) over contents in a teaching environment; and (3) a Teaching Action-Speech Alignment (TASA) algorithm that employs salience-based heuristics and temporal semantic segmentation to generate coherent teaching action sequences aligned with learner profiles. We evaluate Lect\=uraAgents on diverse courses at high school, undergraduate, and graduate levels using sample-specific rubric-based analysis; with generated lecture materials and teaching actions assessed and validated by expert educators. Experimental results show consistent gains in lecture content quality, embodied teaching quality, assessment, and personalization over existing approaches, positioning Lect\=uraAgents as a pedagogically well-grounded framework for personalized learning at scale.

13.
arXiv (CS.CV) 2026-06-17

AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Project page:https://yanhaowu.github.io/AlignDrive/.

14.
bioRxiv (Bioinfo) 2026-06-11

DivQuant: Estimation of Species Richness and Entropy from Small Samples

Estimating diversity properties of discrete distributions from a small observed sample is a fundamental problem in algorithmic statistics that has applications in many fields, in particular bioinformatics, but also in ecology or linguistics. The two most common diversity measures are the number of distinct elements in a multiset, also referred to as species richness in ecology or alpha diversity in microbial analysis, and the Shannon entropy, also referred to as evenness. Estimating these properties from a small sample is particularly challenging for distributions with many rare elements. Thus, many estimators have been proposed in the past that, in practice, work well for different types of distributions. We present DivQuant, an optimization-based, extrapolating richness and entropy estimator with three contributions. First, we formulate the upsampling problem as a convex quadratic program with a Neyman {chi}2 objective. Unlike the linear program of its predecessor RichnEst, DivQuant admits confidence intervals via {chi}2 test inversion that are empirically well-calibrated. Second, we replace RichnEst's fixed-threshold fingerprint truncation with the rare/abundant fingerprint split of Valiant and Valiant, which strongly reduces problem size and preserves enough degrees of freedom for the confidence-interval program to remain valid and feasible. Third, we plug the optimal population fingerprint returned by the program into Shannon's entropy formula to obtain an entropy estimate. DivQuant attains close-to-nominal 95% confidence intervals in essentially all tested regimes, including six simulated distribution families, Tara Oceans microbiome data, and 10X Genomics scRNA-seq data, while competing state-of-the-art methods (RichnEst, iNext, PreSeq) miss the true richness in up to 80% of instances, well above the nominal 5%. In addition, DivQuant outperforms classical asymptotic entropy estimators (Miller-Madow, CAE) and the extrapolating iNext estimator. Running times remain competitive, with DivQuant typically completing in seconds. DivQuant is available as a command-line tool at https://gitlab.com/rahmannlab/divquant.

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

Enhancing LLM Safety Through a Theoretical Minimax Game Lens

The rapid advancement of large language models (LLMs) necessitates effective mechanisms to ensure their responsible deployment by accurately distinguishing unsafe content from benign content. While substantial safety datasets are available in English, multilingual safety modeling remains underexplored due to limited open-source safety datasets in other languages. Even within English datasets, safe yet sensitive corner-case content is scarce, leading to shortcut learning by models and non-trivial false-positive rates. To mitigate these issues, we introduce a novel minimax reinforcement learning (RL) framework wherein a data generator and a classifier model co-evolve, facilitating the production of high-quality synthetic multilingual safety data. We theoretically formalize this interaction as a minimax game and rigorously demonstrate convergence to a Nash equilibrium. Empirical evaluations confirm that our synthetic data generation method significantly enhances the classifier model performance, enabling a substantially smaller model to surpass the state-of-the-art by nearly 10% on English benchmarks while achieving 4.5x faster inference speed. These results establish a scalable and efficient methodology for synthetic data generation, advancing the development of safer and more robust multilingual LLM deployments.

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

Forecasting what Matters: Decision-Focused RL for Controlled EV Charging with Unknown Departure Times

arXiv:2606.19199v1 Announce Type: cross Abstract: The recent growth of EV adoption poses challenges for power systems, including increased peak demand and potential grid instability. Smart control of EV charging – e.g., based on reinforcement learning (RL) – can alleviate these issues by learning temporal and contextual patterns from historical data. Yet, in real-world scenarios, key features, such as departure time, often are unavailable. This, in turn, makes it harder for an RL agent to learn and execute an effective charging policy. To mitigate this uncertainty, a trained forecaster can approximate the unknown features from available data. However, since these forecasting models are typically trained for accuracy (rather than their impact on a downstream agent's decision quality), their errors may propagate and hinder the overall performance of a controller that is using the forecasts. To avoid this, we propose a decision-focused RL (DF-RL) framework in which the forecaster is trained end-to-end, i.e., with feedback from the charging policy actions taken by the RL agent. Such joint training of both the forecaster and controller ultimately results in higher-quality actions: our proposed DF-RL method yields superior charging decisions compared to other baselines, achieving up to a 14% improvement in total reward and a 55% reduction of unsupplied energy (i.e., charging that failed to happen because the EV already left), relative to the RL method without departure time forecasting.

17.
arXiv (CS.AI) 2026-06-12

OCOO-T : A Simple and Scalable Virtual Cell Model for Transcriptional Perturbation Response Prediction

arXiv:2606.12838v1 Announce Type: cross Abstract: Predicting single-cell transcriptional responses to genetic, chemical and cytokine perturbations is a fundamental challenge in computational biology and AI Virtual Cell (AIVC) modeling, with direct implications for drug discovery and the elucidation of gene regulatory networks. Existing approaches often rely on auxiliary cell-state encoders, hierarchical variational autoencoders, dedicated Transformer encoder-decoder modules, or gene-interaction priors to compress high-dimensional expression profiles into latent representations. While effective, these designs increase architectural complexity and may limit scalability and generalizability. This paper introduces OCOO-T, a minimalist flow-matching-based AIVC model for transcriptional perturbation response prediction. OCOO-T utilizes a vanilla Transformer stack that operates directly on continuous gene expression profiles and formulates perturbation response prediction as a continuous-time denoising process. Perturbation embeddings, dosage information, and cell-line/cell-type specificity are integrated through adaptive layer normalization and in-context tokens. Comprehensive evaluations on Tahoe100M, Replogle, and PBMC benchmarks demonstrate that OCOO-T achieves state-of-the-art performance across diverse perturbations and cell types while effectively scaling to long transcriptional profiles through patching and depatching of cellular contexts. By leveraging the simplicity of Transformer-based denoising for single-cell omics, OCOO-T provides an effective and scalable framework for in-silico cellular simulation.

18.
arXiv (CS.CV) 2026-06-11

Towards Fully Automated Exam Grading: Fairness-Aware Recognition of Handwritten Answers with Foundation Models

Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a didactic narrowing towards closed question formats. A practical middle ground keeps paper-based, problem-oriented tasks but records the assessment-relevant answers as single capital letters in a table that a machine can read. The open question is whether this reading can be made accurate and, above all, fair enough for unsupervised grading. Earlier automated approaches reached only about 88%–91% recognition – too low – and failed on the cases that matter most: answers placed outside the cell, crossed out, or written in cursive. We show that general-purpose vision-language foundation models (VLMs), which interpret the page rather than match pixel templates, close this gap. On a benchmark of 61 anonymised exams (3141 answer positions) the best model reaches 98.4% accuracy, well above the previous baseline. Crucially, we centre the evaluation on fairness: we distinguish false negatives (a correct answer marked wrong, which disadvantages the student) from false positives, and a lightweight prompt that supplies the reference solution as context lowers the false-negative rate to 0.58%. Under an exemplary grading scheme only three of the 61 exams would be graded worse, all caught by a student self-review step. Fully automated, fairness-aware exam grading at scale is therefore defensible; we release the anonymised benchmark to support reproducibility.

19.
arXiv (CS.AI) 2026-06-15

Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining

arXiv:2601.22108v2 Announce Type: replace-cross Abstract: Continued pretraining is optimized with fixed self-supervised tasks but selected by downstream performance, creating a coarse feedback loop in which practitioners evaluate checkpoints, change data mixtures or objectives, and restart runs, while individual updates remain blind to target capabilities. We ask whether a small set of verifiable downstream examples can provide step-level feedback without directly supervising the learner. We introduce V-pretraining, which decouples a learner trained only with a self-supervised loss from a lightweight task designer that constructs targets or views for unlabeled batches. Given the current learner and batch, V-pretraining scores a candidate construction by predicting the first-order reduction in downstream loss after the induced self-supervised update. The designer maximizes this value; the learner then applies the update with targets or views detached, so downstream labels never update learner parameters. We instantiate V-pretraining as adaptive top-K soft targets for language modeling and learned views or masks for self-supervised vision. Across both modalities, V-pretraining improves target capabilities without degrading generalization. Under wall-clock-matched continued pretraining, it improves GSM8K Pass@1 for Qwen models using 1,024 GSM8K examples only as feedback, including a +7.4 point single-run gain for Qwen2.5-0.5B. In vision, it improves DINOv3 transfer to ADE20K semantic segmentation and NYUv2 depth estimation while preserving ImageNet linear accuracy, suggesting that feedback-guided task construction can improve target capabilities without collapsing general-purpose representations.

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

HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation

arXiv:2606.11559v1 Announce Type: new Abstract: Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to determine credit assignments for each intermediate turns. Recent on-policy self-distillation methods offer a promising alternative by converting privileged feedback into dense token-level supervision through a self-teacher. Our study is motivated by the unexpected performance degradation observed when naively extending this paradigm to multi-turn settings, which we attribute to a lack of alignment between privileged feedback, such as successful trajectories or terminal outcomes, and the student's current decision context. We introduce HERO, a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback. After each rollout, HERO reflects on the completed interaction to convert each observation into a compact turn-level diagnosis, that captures actionable feedback about the original action such as its necessity, validity or failure cause. On TauBench and WebShop, HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO. It is especially effective under limited training turn budgets, where successful rollouts are rare and GRPO provides weak reward-contrast signals.

21.
arXiv (CS.LG) 2026-06-11

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

arXiv:2606.11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training. This raises a basic robustness question, crucial to reproducibility and reliability: how sensitive are MD dynamics to their inputs? We focus on initialization, often itself a pretrained or previously aligned model. Quadratic-regularized MD, including GD and Mahalanobis geometries, is well-known to be stable for convex smooth objectives. We show a sharp contrast: once the regularizer is non-quadratic, MD can be exponentially more sensitive to initialization than GD, even with a well-conditioned regularizer in Euclidean norm. We give a three-dimensional construction with a convex, smooth objective and a strongly convex, smooth, well-conditioned regularizer where an initial $\varepsilon$ perturbation is quickly amplified to $\min\{polylog^{-1}(1/\varepsilon), \varepsilon e^{\Omega(\eta T)}\}$ after $T$ iterations of MD with step size $\eta$. For canonical KL-regularized MD on the simplex, we show that even linear objectives can amplify an initial $\varepsilon$ perturbation exponentially fast in high-dimensional or near-boundary regimes. Finally, we show that adding a Bregman regularization term toward an anchor point can stabilize the dynamics while largely preserving the optimization guarantees, and that the choice of anchor is crucial: anchoring at the initialization only partially mitigates the instability, whereas anchoring at a fixed point yields a more stable mechanism.

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

Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models

The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreeing with each other. Here, we propose Divide-and-Denoise, a method for coordinating multiple pre-trained diffusion models during sampling. Much like managing a specialized workforce, our method creates a fair but efficient division of labor across models. Central to our method is the notion of an allocation which defines the responsibility of each model to every region of the noisy sample. At every timestep, we then denoise by (i) updating the allocation by solving a fair division game, where we divide the sample into regions that maximize total utility under fairness constraints, and (ii) aligning the models with this allocation, where we guide each model to denoise within its assigned region. This leads to a new composite denoising process that evolves in tandem with a division process. We evaluate Divide-and-Denoise on conditional image generation. Across several quality metrics, including the GenEval benchmark, our method outperforms baselines and resolves common failures including missing objects and mismatched attributes. Experiments show that Divide-and-Denoise utilizes each model's expertise without neglecting any other model.

23.
medRxiv (Medicine) 2026-06-10

Seasonality, source type, and women's water labor: A longitudinal mixed-methods study in Kenya and Honduras

Women shoulder the majority of water collection labor globally, yet how their water collection and water-related work experiences may change over time or by water source type remains insufficiently understood. We conducted a longitudinal, mixed-methods study in rural Kenya and Honduras to understand how women's experiences collecting water and performing water-related work varied between (a) two time points, (b) improved and unimproved water source types, and (c) water source location. Data were collected in 2023 and 2024 using interviews, observation, GPS-enabled watches, and scales to measure time and distance traveled, water weight and volume carried, and calories expended. 133 women participated in data collection (66 Kenya, 67 Honduras). We compared women's experience data by time point (2023 vs. 2024), source type (improved vs. unimproved), and source location (off-premises vs. on-premises) (t-test, Mann-Whitney U test). We also mapped participants' routes and activities to show which sources were visited, when, and for what activities. In Kenya, mean water collection time, distance, and caloric expenditure were significantly lower and water volume was significantly higher in 2024 when there were unexpected rains compared to 2023 when there was a persistent drought. When comparing source types during the 2023 drought, journeys to improved sources took significantly less time and energy and covered less distance than journeys to unimproved sources. These differences were not observed during the rainy conditions of 2024 when unimproved sources were closer and more accessible. In Honduras, water collection and water work burdens did not differ significantly by time point or source type. We found women with on-premises water access to still expend considerable time and caloric expenditure engaging in water work within their household compounds. Findings from Kenya suggest that water infrastructure improvements can reduce women's water collection burdens, though benefits may depend on and vary by season and source location. Findings from Honduras show that water labor does not end once water is in the household. Rather, substantial time and energy are expended carrying out water-related work even when sources are on premises, suggesting that efforts to assess water labor need to extend beyond collection alone. To meaningfully reduce burdens and ensure improved water sources are utilized during all seasons, initiatives need to consider source location, seasonal variability, and work beyond collection. Evaluations to assess infrastructure impacts on women's labor and well-being are needed and long overdue.

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

On Rate-Optimal Partitioning Classification from Observable and from Privatised Data

arXiv:2312.14889v4 Announce Type: replace-cross Abstract: In this paper we revisit the classical method of partitioning classification and prove novel convergence rates under relaxed conditions, both for observable (non-privatised) and for privatised data. We consider the problem of classification in a $d$ dimensional Euclidean space. Previous results on the partitioning classifier worked with the strong density assumption (SDA), which is restrictive, as we demonstrate through simple examples. Here, we study the problem under much milder assumptions. We presuppose that the distribution of the inputs is a mixture of an absolutely continuous and a discrete distribution, such that the absolutely continuous component is concentrated on a $d_a$ dimensional subspace. In addition to the standard Lipschitz and margin conditions, a novel characteristic of the absolutely continuous component is introduced, by which the convergence rate of the classification error probability is computed, both for the binary and for the multi-class cases. This bound can reach the minimax optimal convergence rate achievable using SDA, but under much milder distributional assumptions. Interestingly, this convergence rate depends only on the intrinsic dimension of the continuous inputs, $d_a$, and not on $d$. Under privacy constraints, the data cannot be directly observed, and the constructed classifiers are functions of the randomised outcome of a suitable local differential privacy mechanism. In this paper we add Laplace distributed noises to the discretisations of all possible locations of the feature vector and to its label. Again, tight upper bounds on the convergence rate of the classification error probability can be derived, without using SDA, such that this rate depends on $2d_a$.

25.
arXiv (CS.LG) 2026-06-18

Reinforcement Learning for Accelerated Aerodynamic Shape Optimisation

arXiv:2507.17786v2 Announce Type: replace Abstract: We introduce a reinforcement learning (RL) based adaptive optimization algorithm for aerodynamic shape optimization focused on dimensionality reduction. The form in which RL is applied here is that of a surrogate-based, actor-critic policy evaluation MCMC approach allowing for temporal 'freezing' of some of the parameters to be optimized. The goals are to minimize computational effort, and to use the observed optimization results for interpretation of the discovered extrema in terms of their role in achieving the desired flow-field. By a sequence of local optimized parameter changes around intermediate CFD simulations acting as ground truth, it is possible to speed up the global optimization if (a) the local neighbourhoods of the parameters in which the changed parameters must reside are sufficiently large to compete with the grid-sized steps and its large number of simulations, and (b) the estimates of the rewards and costs on these neighbourhoods necessary for a good step-wise parameter adaption are sufficiently accurate. We give an example of a simple fluid-dynamical problem on which the method allows interpretation in the sense of a feature importance scoring.