# Research Papers — 2026-05 · bundle page 108 of 326 > Full-text markdown of papers #5351–5400 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/108 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/107.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/109.md) ### Abstraction for Offline Goal-Conditioned Reinforcement Learning Authors: Clarisse Wibault, Alexander Goldie, Antonio Villares, Maike Osborne, Jakob Foerster Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.22711v1 Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical policies have been motivated for horizon reduction via temporal abstraction in offline GCRL, we demonstrate that hierarchy also enables absolute abstraction. By introducing relativised options as well as distinct representations for different levels of the hierarchy, we demonstrate how an agent can reuse experience across similar contexts of the state-space. Based on this framework, we introduce two simple algorithms for learning relativised options and abstracting from the absolute frame of reference. Our experiments show that such inductive biases significantly improve performance in offline GCRL. --- ### Beyond the Org Chart: AI and the Transformation of Invisible Work Authors: Stephanie Rosenthal, Shamsi Iqbal Published: 2026-05-21 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.22707v1 An increasing number of news and research articles report that AI adoption is allowing professionals to blur and extend the boundaries of their corporate roles. With the goal of understanding how work processes might be changing in an AI-forward company, we interviewed 24 product-focused individuals at a large technology firm about how AI has impacted their own work, their work within their product team, and their professional interactions. Our conversations suggest that AI is not only changing formal role responsibilities and collaborations between those roles, but also changing informal cultural practices like professional mentoring that are key to helping professionals settle in their positions, stay engaged with their work, and grow their careers. Some of these changes are positive, such as smoother collaboration between peers, but other changes are more nuanced and put the typical career growth opportunities, like receiving feedback from professional networks and promoting leadership and mentorship, at risk. We propose steps that AI companies can take to make the invisible work more visible. Additionally, we propose efforts that individuals and leaders can take to support their colleagues through AI transformation while preserving healthy company cultures that support diverse thinking, collaboration, and informal interactions. --- ### Tokenization with Split Trees Authors: Craig W. Schmidt, Michael Krumdick, Adam Wiemerslage, Seth Ebner, Varshini Reddy, Yuval Pinter, Chris Tanner Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.22705v2 We introduce Tokenization with Split Trees (ToaST), a subword tokenization method that directly optimizes compression under a new recursive inference procedure. ToaST greedily splits each pretoken into a full binary tree using precomputed byte n-gram counts, independent of any vocabulary. Given a vocabulary, inference recursively descends each split tree and emits the first in-vocabulary node reached on each path. Vocabulary selection is formulated as an Integer Program (IP) that minimizes the total token count over all split trees under this inference procedure. The Linear Programming (LP) relaxation is near-integral in practice, yielding provably near-optimal vocabularies, with training time empirically scaling quadratically in the number of split trees. On English text, ToaST reduces token counts by more than 11% compared to BPE, WordPiece, and UnigramLM at vocabulary sizes of 40,960 and above, reducing the number of inference tokens for models using this tokenizer, thus extending the effective context length. ToaST also uses common single-byte tokens less frequently than these baselines, leading to a substantial improvement in Renyi efficiency. In experiments training 1.5B parameter language models, ToaST achieves the highest CORE score, outperforming baselines by 2.6%--7.6%, with significance for two of three, and scoring best on 13 of 22 individual tasks. --- ### Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals Authors: Shuo Yang, Jinda Lu, Chiyu Ma, Kexin Huang, Haoming Meng, Qihui Zhang, Yuyang Liu, Bolin Ding, Guoyin Wang, Li Yuan, Jingren Zhou Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22703v1 Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a central paradigm for scaling LLM reasoning, yet its optimization often suffers from training instability and suboptimal convergence. Through a systematic dissection of clipping-based GRPO-style objectives, we identify the rigid clipping decision induced by hard clipping as a key practical bottleneck in the studied RLVR setups. Specifically, our analysis suggests that informative signals can lie in the near-boundary region just beyond the clipping threshold, and are therefore discarded by the standard hard-clipping rule. Notably, once this bottleneck is precisely identified, even simple stochastic perturbations at the boundary can recover meaningful performance gains. Building on this finding, we propose Near-boundary Stochastic Rescue (NSR), a minimal, plug-and-play modification that stochastically retains these slightly out-of-bound tokens to recover lost signals. While NSR, via stochastic sampling, can be interpreted as inducing an implicit gradient decay in expectation, our ablations reveal that its stochastic, boundary-local rescue mechanism is consistently more effective than deterministic gradient decay. Validated by extensive experiments across model sizes from 7B to 30B and both dense and MoE architectures, as a plug-and-play solution, NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO. --- ### Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptions Authors: Yannick Porto, Renato Martins, Thomas Chalumeau, Cedric Demonceaux Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22697v1 Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action categories at inference can present important domain shifts or even unseen actions from training. In this context, improving the recognition capabilities of Zero-Shot Action Recognition models (ZSAR), without requiring strong annotation efforts, remains a central challenge. Most ZSAR approaches assume that actions are observed under geometric conditions similar to those seen during training. In practice, variations in human body orientation and camera viewpoint add a significant domain gap in ZSAR, substantially limiting generalization to novel action-motion combinations. In this context, this paper presents a novel orientation-aware action recognition approach with improved cross-domain capabilities. Our approach combines motion cues of multiple camera viewpoints and text descriptions of human actions in the training phase. We present a new orientation-aware motion encoding network to learn different motion features, and adapt a specific orientation-aware text prompt to match the corresponding features at inference. Extensive experiments demonstrate that the proposed method consistently improves ZSAR performance across different recognition benchmarks, outperforming recent state-of-the-art zero-shot approaches on NTU-RGB+D, BABEL, NW-UCLA, and on two surveillance datasets. In addition, the learned representations exhibit strong transfer learning capabilities, yielding competitive performance on both cross-domain and same-domain recognition of seen actions. Code and trained models are available at: https://icb-vision-ai.github.io/OrientationAware-HAR --- ### Improving Viewpoint-Invariance and Temporal Consistency for Action Detection Authors: Yannick Porto, Renato Martins, Thomas Chalumeau, Cedric Demonceaux Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22695v1 Viewpoint change invariance and action temporal consistency are critical aspects for the effective deployment of human action detection of untrimmed videos. Existing appearance-based video detection methods often struggle with limited viewpoint diversity during training, while motion-based detection approaches frequently fail to model fine-grained temporal relationships across consecutive motion windows. This paper introduces a novel two-stage action detection approach designed to improve both view-invariance and global temporal coherence properties. In the first stage, we extract motion features from augmented virtual viewpoints, solely used at training. Then, the second stage introduces a new view-invariant, multi-scale temporal encoder based on selective state-space sequence modelling to aggregate information across viewpoints and time scales. Experiments on PKU-MMD and BABEL benchmarks demonstrate that this approach significantly outperforms state-of-the-art methods in all considered splits. Code and trained models are available at: https://icb-vision-ai.github.io/HydraView-TAD --- ### Scout-Assisted Planning for Heterogeneous Robot Teams under Partially Known Environments Authors: Hoang-Dung Bui, Abhish Khanal, Raihan Islam Arnob, Gregory J. Stein Published: 2026-05-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.22693v1 Autonomous robot teams navigating partially known environments face costly backtracking when ground robots encounter blocked roads that are only revealed upon physical traversal. We address this with Scout-Assisted Planning, a heterogeneous planning framework in which scouting Unmanned Aerial Vehicles proactively gather environmental information to improve Unmanned Ground Vehicle navigation. To focus scouting on the most consequential edges, we propose Information Gain-based Action Pruning, which scores candidate scouting actions by their expected impact on ground robot behavior. Since exact Information Gain-based Action Pruning computation is prohibitively expensive, we develop a Graph Neural Network based model that predicts information gain values directly from graph structure and belief state, reducing planning time to real-time levels without sacrificing solution quality. Experiments across three environment types show that SAP with Information Gain Action Pruning reduces ground robot travel cost by 31.9--37.7% over the Canadian Traveler Problem baseline, and outperforms proximity-based scouting guidance by an additional 8--14%, confirming that principled information-gain-guided scouting is both more effective and computationally feasible for real-world deployment --- ### Latent Spectroscopy: Posterior Collapse as a Feature Authors: Johannes Hirn Published: 2026-05-21 Categories: cs.LG, cond-mat.stat-mech arXiv: https://arxiv.org/abs/2605.22691v2 We show that, in linear Gaussian VAEs, posterior collapse is a form of latent feature selection. Feature importance is set by each latent coordinate's contribution to reconstruction, itself given by the corresponding PCA eigenvalue. Varying the regularizer strength $β$ reveals a ranked spectrum of collapse events, with thresholds set by the utility/PCA spectrum. A mode-by-mode analysis identifies the scale-invariant signal fraction as an order parameter obeying Landau scaling near collapse. WorldClim experiments confirm both the utility-threshold calibration and the predicted near-collapse scaling. --- ### Posterior Collapse as Automatic Spectral Pruning Authors: Johannes Hirn Published: 2026-05-21 Categories: cs.LG, cond-mat.stat-mech arXiv: https://arxiv.org/abs/2605.22691v1 We show that posterior collapse in $β$-VAEs implements automatic spectral pruning. A latent mode collapses if its contribution to reconstruction is below the cutoff set by $β$. Equilibrium solutions with different $β$ thus reveal a cascade of collapses as latent modes decouple from least to most useful. We derive this as a consequence of the loss via a Landau stability analysis. We define a latent-rescaling-invariant order parameter that ranks active latent modes and whose collapse thresholds identify which effective variables to inspect first. In the linear Gaussian case, the collapse spectrum, utility spectrum, and normalized PCA spectrum coincide, and each collapse follows a mean-field law. We test these predictions on the WorldClim dataset. --- ### ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification Authors: José Alberto Rodríguez, Luis Balderas, Miguel Lastra, Antonio Arauzo-Azofra, José M. Benítez Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22684v2 Time Series Foundation Models (TSFMs) have become a new component of the state-of-the-art in general time series forecasting. However, adapting them to specialized classification tasks remains constrained by two interconnected challenges: the quadratic cost of standard attention mechanisms and the inability to disentangle the structural components underlying time series variability. This technical report introduces ChronoVAE-HOPE, a next-generation TSFM that reconciles massive generalization with structured latent representation for time series classification. The core of the proposal is a Variational Autoencoder (VAE) framework built upon the HOPE Block, which replaces quadratic attention with a dual-memory system: Titans modules for dynamic short-term retention and a Continuum Memory System (CMS) for the abstraction of long-term historical context. A key architectural novelty is the disentangled latent space, which factorizes representations into independent trend and seasonal components via dedicated encoder heads and separate decoder pathways. ChronoVAE-HOPE undergoes self-supervised pre-training on the Monash archive, combining a Masked Time Series Modeling (MTSM) auxiliary objective with a disentangled VAE reconstruction loss. The pre-trained encoder is subsequently frozen and used to generate fixed-length embeddings for downstream classification on the UCR benchmark datasets. Empirical results demonstrate strong performance across diverse temporal domains, particularly in settings characterized by strict causal structure. ChronoVAE-HOPE establishes a robust and interpretable framework for the adaptation of foundation models to time series classification through structured generative representations. --- ### Scientific reasoning does not reliably translate into scientific forecasting in frontier AI Authors: Sean Wu, Pan Lu, Yupeng Chen, Jonathan Bragg, Yutaro Yamada, Peter Clark, David Clifton, Philip Torr, James Zou, Junchi Yu Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.22681v2 AI systems are increasingly used to support forward-looking scientific judgment, but it remains unclear whether they can form reliable expectations about future scientific advances. Here we show that strong scientific reasoning does not reliably translate into accurate forecasting of future scientific advances. To study this question, we introduce CUSP, a temporally grounded evaluation suite for event-level scientific forecasting across eight scientific disciplines. Across six frontier AI models, we observe a striking asymmetry in forecasting performance together with systematic error patterns. Models often identify plausible mechanisms underlying future scientific advances, yet perform near chance on feasibility assessment, generate solution strategies that only weakly align with realized advances, and systematically predict scientific advances later than they become publicly observable. Providing additional pre-cutoff scientific knowledge improves performance but does not eliminate these forecasting limitations. These findings suggest that current AI systems possess substantial retrospective scientific competence but limited forward-looking predictive capability. Scientific forecasting should therefore be evaluated as a complementary dimension of AI scientific capability when deploying AI systems for research prioritization and scientific decision-making. --- ### Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models Authors: Piotr Kubaty, Patryk Marszałek, Łukasz Struski, Adam Wróbel, Jacek Tabor, Marek Śmieja Published: 2026-05-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.22679v1 Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they rely on expanding the representation dimension, which compromises the original geometry and introduces redundancy. We introduce CEDAR (Conceptual Embedding Disentanglement via Adaptive Rotation), a post-hoc method that reveals the compositional structure of pretrained embeddings without increasing dimensionality. By learning an invertible transformation with a top-$k$ sparsity bottleneck, CEDAR concentrates semantic information into axis-aligned disentangled coordinates. In CLIP-like architecture, individual coordinates can be interpreted with textual concepts, while for generative models such as BLIP, they can be decoded into natural language descriptions. Experiments demonstrate that CEDAR achieves a competitive reconstruction-sparsity trade-off while producing explanations that are more interpretable and better aligned with human perception. Our results suggest that the apparent entanglement in vision-language representations can be resolved through a suitable change of basis, eliminating the need for overcomplete expansions. --- ### Swift Sampling: Selecting Temporal Surprises via Taylor Series Authors: Dahye Kim, Bhuvan Sachdeva, Karan Uppal, Naman Gupta, Vineeth N. Balasubramanian, Deepti Ghadiyaram Published: 2026-05-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.22678v1 While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted evolution. Inspired by the human brain's predictive coding, we introduce Swift Sampling, an elegant, training-free frame selection algorithm that automatically identifies high-information moments in a video. Specifically, we model a video as a differentiable trajectory in the visual latent space and compute the velocity and acceleration of its features. Then, we apply Taylor expansion to project the expected path of subsequent frames. Frames that diverge sharply from this predicted manifold are identified as temporally surprising frames and selected for sampling. Unlike prior training-free methods that rely on auxiliary networks or video-specific hyperparameter tuning, Swift Sampling is incredibly lightweight, adding only 0.02x additional computational cost over baseline making it 30x cheaper overhead than leading baselines. Across three long-video question answering benchmarks and 10 different downstream tasks, Swift Sampling outperforms uniform sampling and prior query-agnostic baselines. It is especially powerful for long videos with limited frame budgets improving accuracy by up to +12.5 points. --- ### Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment Authors: Janek Haberer, Jon Eike Wilhelm, Olaf Landsiedel Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22677v1 Deploying vision models across devices with varying resource constraints, or even on a single device where available compute fluctuates due to battery state, thermal throttling, or latency deadlines, typically requires training and maintaining separate models. Width-adaptive inference addresses this by training a single set of shared weights containing multiple nested subnetworks of increasing capacity, but prior CNN-based approaches required switchable batch normalization, while recent scalable methods have focused on Vision Transformers. We present Slimmable ConvNeXt, which shows that ConvNeXt's modern design, specifically LayerNorm and inverted bottlenecks, makes it particularly suited for channel-width slimming, eliminating the normalization overhead of classical slimmable networks and producing a simpler training pipeline than both prior CNN and ViT approaches. On ImageNet-1k, Slimmable ConvNeXt-T with 3 subnetworks achieves 80.8% top-1 accuracy at 4.5 GMACs and 77.4% at 1.2 GMACs, trained from scratch for 600 epochs. At comparable compute, this exceeds HydraViT's 6-head subnetwork (78.4% at 4.6 GMACs) by 2.4 percentage points and its 3-head configuration (73.0% at 1.3 GMACs) by 4.4 percentage points, while also outperforming MatFormer-S (78.6%) and SortedNet-S (78.2%) at the same GMACs. Scaling to Slimmable ConvNeXt-B further improves maximum accuracy to 82.8% at 15.35 GMACs. --- ### Self-Policy Distillation via Capability-Selective Subspace Projection Authors: Guangya Hao, Yitong Shang, Yunbo Long, Zhuokai Zhao, Hanxue Liang Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.22675v1 Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signals to curate self-generated outputs (e.g., correctness filtering, execution feedback, and reward search), which are costly and unavailable for the best-performing frontier models, or skip curation entirely and train on all raw outputs, an approach that is often domain-specific and hard to generalize. Both also share a deeper weakness that self-generated outputs entangle task-relevant capability with others, such as stylistic patterns, formatting artifacts, and model-specific errors, diluting the signal for the specific capability one aims to improve. In this paper, we propose Self-Policy Distillation (SPD), which achieves generalizable, capability selective without any external signal. Specifically, SPD extracts a low-rank capability subspace from the model's own gradients on correctness-defining tokens, projects key-value (KV) activations into this subspace during self-generation, and fine-tunes on the resulting raw outputs with standard next-token prediction loss. Through extensive experiments across code generation, mathematical reasoning, and multiple-choice QA, we show that SPD achieves up to 13% improvement over state-of-the-art self-distillation methods without external signals and up to 16% improvement over pre-trained baselines. Notably, SPD demonstrates superior generalizability, achieving 15% better performance under out-of-domain generalization settings. --- ### Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most Authors: Nick Merrill, Jaeho Lee, Ezra Karger Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.22672v2 We document inverse scaling in LLMs on forecasting problems whose underlying time series exhibit superlinear growth and tail risk of regime change, a structure common in finance and epidemiology. On these tasks, more capable models produce worse distributional forecasts. The pattern appears on ForecastBench-Sim (FBSim), a contamination-free, simulated-world benchmark we release, in forecasting synthetic SIR epidemics with a matched linear control, and replicates in real-world datasets on COVID-19, measles, housing markets, and hyperinflation. A per-quantile decomposition shows the failure concentrates at the upper tail, which more capable models shift upward to track aggressive extrapolations of growth, while the lower tail stays put. A within-family study of Llama-3.1 shows that both model scale and post-training independently contribute to this effect. Domain knowledge does not reliably rescue calibration. This inverse scaling does not appear on single-threshold metrics common in LLM forecasting benchmarks, reversing the sign of the capability--accuracy relationship on identical outputs. Single-threshold scoring at conventional cutoffs misses the upper-tail cost; tail-inclusive scoring reverses the sign of the capability--accuracy relationship on the same outputs. We recommend that LLM forecasting evaluations use continuous (and unbounded) measures of accuracy alongside bounded binary threshold metrics. --- ### From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model Authors: Bing Hu, Zaijing Li, Rui Shao, Junda Chen, April Hua Liu, Wei-Shi Zheng, Liqiang Nie Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22671v2 Vision-Language-Action (VLA) models often suffer from performance degradation under distribution shifts, as they struggle to learn generalized behavior representations across varying environments. While existing approaches attempt to construct behavior representations through action-centric latent variables, they are often limited by short-horizon temporal fragmentation and static execution-alignment, leading to inconsistent behaviors in complex scenarios. To address these limitations, we propose \textbf{BehaviorVLA}, a framework that facilitates robust manipulation through the learning of a temporally coherent behavioral representations. Our approach features two symmetric components: (1) the \textbf{Visuomotor Behavior Encoder (VBE)}, which utilizes a causal Mamba-based architecture to aggregate long-horizon trajectory information into a unified behavior representation; and (2) the \textbf{Phase-conditioned Behavior Decoder (PBD)}, which decodes this representation into precise actions by dynamically aligning task-level priors with real-time execution progress. Experiments on RoboTwin 2.0, LIBERO, and CALVIN demonstrate state-of-the-art success rates of 58\%, 98\%, and 4.36 (Avg.Len), respectively. Notably, in real-world sim-to-real transfer, BehaviorVLA matches the performance of OpenVLA-OFT using only 50\% of the demonstration data, showcasing its superior data efficiency and generalization. --- ### SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers Authors: Javad Rajabi, Kimia Shaban, Koorosh Roohi, David B. Lindell, Babak Taati Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22668v1 Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by modifying inference-time attention behavior, often through Rotary Position Embeddings (RoPE) extrapolation combined with attention scaling. However, these strategies apply a uniform and content-agnostic scaling across RoPE components with distinct frequency characteristics, inducing a trade-off between preserving global structure and recovering fine detail. We introduce SEGA, a training-free method that dynamically scales attention across RoPE components according to the latent's spatial-frequency structure at each denoising step. This adaptive scaling improves both structural coherence and fine-detail fidelity. Experiments show that SEGA consistently improves high-resolution synthesis across multiple target resolutions, outperforming state-of-the-art training-free baselines. --- ### Holographic functions and neural networks Authors: Balazs Szegedy Published: 2026-05-21 Categories: math.CO, cs.LG, math.PR arXiv: https://arxiv.org/abs/2605.22666v1 A fuzzy Boolean function is a map $f:\cube^n\to (0,1)$, where $n\in\mathbb N$. We introduce and compare three ways of saying that such a function has bounded complexity. The first is a sampling property: the value $f(x)$ can be recovered, up to small error and with high probability, from the values of a bounded number of randomly chosen coordinates of $x$. We call this the holographic property. The second is a structural property: $f$ is uniformly close to a bounded-degree polynomial in boundedly many bounded linear coordinate forms. The third is computational: $f$ is uniformly close to the output of a neural network with a bounded number of non-input neurons, bounded Lipschitz activation functions and bounded incoming weights. We prove that these three properties are equivalent up to quantitative changes of the parameters. The implication from holography to polynomial structure uses a variant of a weak version of hypergraph regularity. --- ### MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance Authors: Thomson Yen, Julian Poeltl, Harshith Srinivas Gear, Yilin Meng, Joshua Fan, Adam Shen, Yili Liu, Ali Bauyrzhan, Patrick Shea, Siri Du, Haoyang Liu, Daniel Guetta et al. Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.22664v5 LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions. To meet enterprise needs, frontier AI labs have developed agents that can construct entire spreadsheets from scratch. This is especially relevant in finance, where core workflows such as financial modeling, forecasting, and scenario analysis are commonly conducted through spreadsheets. Yet, existing spreadsheet benchmarks do not measure this new capability, focusing instead on question-answering or single-formula edits. To address this gap, we provide one of the first evaluations of agents on end-to-end spreadsheet tasks, focusing on economically critical financial workflows such as modeling and scenario analysis. Since deliverables therein are routinely reviewed and revised by multiple stakeholders, judging their quality necessarily involves high-level criteria such as readability or ease of modification. To reflect the multidimensional nature of solution quality, we develop an evaluation taxonomy comprising three dimensions: Accuracy, Formula, and Format, each comprising fine-grained criteria that reflect professional standards. Evaluating over 18 agents, the benchmark reveals that even the strongest agents fall short of basic professional finance standards, and their performance degrade sharply as the difficulty increases beyond a few chained calculations. This suggests that current agents are not yet able to reliably produce professional-quality spreadsheets at the level of complexity real-world workflows demand. --- ### MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance Authors: Thomson Yen, Julian Poeltl, Harshith Srinivas Gear, Yilin Meng, Joshua Fan, Adam Shen, Yili Liu, Ali Bauyrzhan, Siri Du, Haoyang Liu, Daniel Guetta, Hongseok Namkoong Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.22664v4 LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions. To meet enterprise needs, frontier AI labs have developed agents that can construct entire spreadsheets from scratch. This is especially relevant in finance, where core workflows such as financial modeling, forecasting, and scenario analysis are commonly conducted through spreadsheets. Yet, existing spreadsheet benchmarks do not measure this advanced capability, focusing instead on question-answering or single-formula edits. To address this gap, we provide one of the first evaluations of agents on end-to-end spreadsheet tasks, focusing on economically critical financial workflows such as modeling and scenario analysis. Since deliverables therein are routinely reviewed and revised by multiple stakeholders, judging their quality necessarily involves high-level criteria such as readability or ease of modification. To reflect the multidimensional nature of solution quality, we develop an evaluation taxonomy comprising three dimensions: Accuracy, Formula, and Format, each comprising fine-grained criteria that reflect professional standards. The Claude family leads the benchmark and produces the most professional-looking outputs in our qualitative review, but even the strongest agents frequently fall short of professional finance standards and degrade sharply as the difficulty increases beyond a few chained calculations. This suggests that current agents are not yet able to reliably produce professional-quality spreadsheets at the level of complexity real-world workflows demand. --- ### Claw AI Lab: An Autonomous Multi-Agent Research Team Authors: Fan Wu, Cheng Chen, Zhenshan Tan, Taiyu Zhang, Xinzhen Xu, Yanyu Qian, Dingcheng Gao, Lanyun Zhu, Qi Zhu, Yi Tan, Deyi Ji, Guosheng Lin et al. Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.22662v1 We present Claw AI Lab, a lab-native autonomous research platform that advances automated research from a hidden prompt-to-paper pipeline into an interactive AI laboratory. Rather than centering the system around a single agent or a fixed serial workflow, we allow users to instantiate a full research team from one prompt, with customizable roles, collaborative workflows, real-time monitoring, artifact inspection, and rollback/resume control through a unified dashboard. The platform also supports distinct research modes for exploration, multi-agent discussion, and reproduction, making autonomous research substantially more steerable and laboratory-like in practice. A key practical contribution of Claw AI Lab lies in its Claw-Code Harness, which connects local codebases, datasets, and checkpoints to runnable experiments and feeds execution artifacts back into the research loop. As a result, the harness improves not only execution integration, but also experimental completion and result integrity: experiments are easier to inspect, iterate on, and faithfully transfer into final papers, reducing common failure modes such as partial runs and malformed result reporting. In our internal evaluation on five AI research case studies, using AutoResearchClaw as the baseline, Claw AI Lab is consistently preferred by AI expert judges on idea novelty, experiment completeness, and paper presentation quality. We view Claw AI Lab as an early step toward a new paradigm: autonomous research as usable, interactive, and reliability-aware scientific infrastructure. --- ### Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora Authors: Maciej Skorski Published: 2026-05-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.22660v4 Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages. Idiomatic expressions, slang, and cultural references introduce hard-to-avoid translation artifacts. Yet automated moral values classification depends on language-specific annotated corpora that exist almost exclusively in English. We investigate whether LLM-based translation can bridge this gap, taking Polish as a test case. Using ~50k morally-annotated social media posts from a diverse range of topics, we apply a principled four-method validation pipeline: LaBSE cross-lingual embedding similarity, Centered Kernel Alignment (CKA), LLM-as-judge evaluation, and deep learning classifier parity tests. We show that despite shortcomings in handling slang, vulgarity, and culturally-loaded expressions, direct translation preserves subtle moral cues well enough to be harvested by cross-lingual machine learning - with a mean cosine similarity of 0.89 and classification accuracy gaps of 0.01-0.02 AUROC across foundations. These results demonstrate that machine translation is a practical and cost-effective path to moral research in languages currently under-resourced in this domain. We demonstrate this for Polish as a representative Slavic language, with expected generalization to related languages. --- ### Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora Authors: Maciej Skorski Published: 2026-05-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.22660v3 Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages. Idiomatic expressions, slang, and cultural references introduce hard-to-avoid translation artefacts. Yet automated moral values classification depends on language-specific annotated corpora that exist almost exclusively in English. We investigate whether LLM-based translation can bridge this gap, taking Polish as a test case. Using $\sim~50k$ morally-annotated social media posts from a diverse range of topics, we apply a principled four-method validation pipeline: LaBSE cross-lingual embedding similarity, Centered Kernel Alignment (CKA), LLM-as-judge evaluation, and deep learning classifier parity tests. We show that despite shortcomings in handling slang, vulgarity, and culturally-loaded expressions, direct translation preserves subtle moral cues well enough to be harvested by cross-lingual machine learning - with a mean cosine similarity of 0.89 and classification accuracy gaps of 0.01--0.02 AUROC across foundations. These results demonstrate that machine translation is a practical and cost-effective path to moral values research in languages currently under-resourced in this domain. We demonstrate this for Polish as a representative Slavic language, with expected generalization to related languages. --- ### SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation Authors: Zhenyu Lu, Liupeng Li, Jinpeng Wang, Haoqian Kang, Yan Feng, Ke Chen, Yaowei Wang Published: 2026-05-21 Categories: cs.CV, cs.LG, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2605.22658v1 While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end yet opaque "black boxes". Conversely, textual localization readout is merely readable, not truly interpretable, often functioning as an unconstrained post-hoc step. To bridge this interpretability gap, we propose SegCompass, an end-to-end model that leverages a Sparse Autoencoder (SAE) to forge an explicit, interpretable, and differentiable alignment pathway. Given an image-instruction pair, SegCompass first generates a chain-of-thought (CoT) trace. The core of our method is an SAE that maps both the CoT and visual tokens into a shared, high-dimensional sparse concept space. A query codebook selects salient concepts from this space, which are then spatially grounded by a slot mapper into a multi-slot heatmap that guides the final mask decoder. The entire model is trained jointly, unifying reinforcement learning for the reasoning path with standard segmentation supervision. This SAE-driven interface provides a "white-box" connection that is significantly more traceable than latent queries and more coherent than textual readouts. Extensive experiments on five challenging benchmarks demonstrate that SegCompass matches or surpasses state-of-the-art performance. Crucially, our visual and quantitative analyses show a strong correlation between the quality of the learned sparse concepts and final mask accuracy, confirming that SegCompass achieves superior results through its enhanced and inspectable alignment. Code is available at https://github.com/ZhenyuLU-Heliodore/SegCompass. --- ### Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs Authors: Shanshan Wang, Fengying Ye, Hanjia Lyu, Caiwen Gou, Junchao Wu, Jingming Yao, Chengzhong Xu, Jiebo Luo, Derek F. Wong Published: 2026-05-21 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2605.22654v1 Previous detection studies have shown that LLMs cannot be effectively used as detectors, but these studies have not addressed modern Chinese poetry. Moreover, no relevant research has explored the performance of LLMs in detecting modern Chinese poetry. This paper evaluates and enhances the performance of LLMs as detectors for modern Chinese poetry, and proposes an image-semantic guided poetry detection method. Compared with traditional detection approaches, our method innovatively incorporates images that reflect the content of the poetry. Through example-driven approaches, our method effectively integrates information such as meaning, imagery, and feeling from the image, then forms a complementary judgment with the poem text. Experimental results demonstrate that the LLM detectors based on our method outperform baseline detectors based on plain text, and even surpass the best-performing traditional detector, RoBERTa. The Gemini detector using our method achieves a Macro-F1 score of 85.65%, reaching the state-of-the-art level. The performance improvements of different LLM detectors on multiple LLMs-generated data prove the effectiveness of our method. --- ### The Secretary Problem with a Stochastic Precursor Authors: Franziska Eberle, Alexander Lindermayr Published: 2026-05-21 Categories: cs.DS, cs.LG arXiv: https://arxiv.org/abs/2605.22653v1 In learning-augmented online algorithms, predictions are usually valued for what they say: a value estimate, a solution, or an algorithmic recommendation. This paper shows that predictions can also be valuable solely due to their arrival time. We study the fundamental secretary problem augmented with a stochastic precursor: a content-free signal that is guaranteed to arrive no later than the best item, but is otherwise stochastically timed. The signal does not carry any additional information; nevertheless, its timing alone changes the structure of optimal stopping. We characterize optimal policies in the random-order and adversarial-order models. In random order, a single uniformly timed precursor already gives success probability at least $\frac12$, improving on the classic $\frac1e$ benchmark. With increasingly late precursors, the success probability approaches $1$. In adversarial order, for which traditional models do not admit strong guarantees, sufficiently concentrated precursors recover constant success guarantees. Our results show that such novel forms of asynchronous temporal information are a distinct and powerful form of advice in online decision making and may also be effective for other problems. --- ### What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining Authors: Hyejin Go, Semi Lee, Hyesong Choi Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22651v1 CLIP-style contrastive pretraining typically curates web-scale image-text pairs using sample-level filtering signals, often based on pair-level alignment. We show that this signal saturates: once coarse mismatches are removed, stricter global filtering no longer tracks the compositional supervision provided by the retained captions. The reason is structural - a global score conflates whether a pair is broadly plausible with whether the individual object, attribute, and relation phrases inside the caption materially support the image-text match. The latter is what compositional generalization demands, yet pair-level filters are blind to it. We address this with Counterfactual Phrase Intervention (CPI), a phrase-level curation framework that converts controlled nonce-token substitutions into image-conditioned phrase-sensitivity scores. CPI uses global alignment only for coarse mismatch removal, then ranks the surviving pool by whether caption phrases measurably affect the image-text score under controlled substitution. We frame CPI as a first-order phrase-sensitivity signal rather than a grounding or identification result, and evaluate it at CC3M scale. Ranking by this signal yields a 50%-data subset that improves VL-CheckList-VG Relation by +1.91 over the full-data baseline and +1.00 over alignment-only filtering at matched budget, while improving SugarCrepe overall and preserving general transfer. CPI is loss-orthogonal: applied unchanged to NegCLIP, it further improves VL-CheckList-VG Relation by +3.84, with additional CE-CLIP gains in the main text. --- ### Whose Voice Counts? Mapping Stakeholder Perspectives on AI Through Public Submissions to the U.S. Government Authors: Alina Karakanta, Alex Christiansen, Tomás Dodds, Bissie Anderson, Matteo Fuoli, Marcus Perlman, Aletta G. Dorst Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.22650v1 As artificial intelligence (AI) systems become more common in our daily lives, it is important to understand how different stakeholders comprehend and envisage the role that these technologies play in shaping social, political, and economic realities. In this paper, we investigate public perceptions of AI based on a corpus of letters submitted during the public consultation for the Trump Administration's US AI Action Plan. To this aim, we release a corpus cleaning pipeline and perform topic modelling and frequency analysis to explore predominant topics discussed by different subgroups (e.g., academia, individuals, private sector) and those appearing in the AI Action Plan. Our results show that individuals voice strong concerns related to the impact of AI on life, while other stakeholders are more concerned with AI development. Our comparison of topics suggests that the AI Action Plan reflects predominantly the concerns of the private sector on security, policies, and development, with individuals' concerns less represented. --- ### From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder Authors: Yilin Zhang, Nicholas C. Harvey, Nicholas R. Fuggle, Rahman Attar Published: 2026-05-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.22649v1 Dual-energy X-ray absorptiometry (DXA) is widely used for large-scale skeletal assessment, yet learning controllable and interpretable factor-specific anatomical variation remains challenging. We propose a metadata-conditioned causal hierarchical variational autoencoder (CHVAE) for causally consistent generation of anteroposterior (AP) spine DXA images from the UK Biobank (UKB). The model is trained on 3,743 raw AP spine scans from the first imaging visit and conditioned on basic participant attributes and lumbar morphometry. Causal consistency is evaluated in a baseline-to-follow-up setting using abduction--action--prediction (AAP): latent variables are abducted from baseline images, age is intervened to the repeat-imaging value, and the resulting counterfactual follow-up morphometry is compared with observed repeat-imaging measurements. Results show strong absolute-level agreement for key vertebral morphometry variables under age intervention, supporting intervention-aligned synthesis of anatomically plausible DXA images. --- ### AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters Authors: Hanjun Luo, Zhimu Huang, Sylvia Chung, Yiran Wang, Yingbin Jin, Jialin Li, Jiang Li, Xinfeng Li, Hanan Salam Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.22645v1 Text-to-image (T2I) systems increasingly rely on upstream prompters, either humans or multimodal large language models (MLLMs), to translate user intent into detailed prompts. Yet current benchmarks fix the prompt and only evaluate T2I models, leaving the prompting proficiency of this upstream component entirely unmeasured. We introduce AtelierEval, the first unified benchmark that quantifies prompting proficiency across 360 expert-crafted tasks. Grounded in a cognitive view, it spans three task categories and instantiates tasks using a taxonomy of real-world challenges, with a dual interface for both humans and MLLMs. To enable scalable and reliable evaluation, we propose AtelierJudge, a skill-based, memory-augmented agentic evaluator. It produces subjective and objective scores for prompt-image pairs, achieving a Spearman correlation of 0.79 with human experts, approaching human performance. Extensive experiments benchmark 8 MLLMs against 48 human users across 4 T2I backends, validate AtelierEval as a robust diagnostic tool, and reveal the superiority of mimicry over planning, advocating for an image-augmented direction for future prompters. Our work is released to support future research. --- ### Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics Authors: Igor Ignashin, Anna Radovskaya, Andrew Semenov, Egor Lopatin, Stanislav Potapov, Aleksandr Kovalenko, Andrey Veprikov, Aleksandr Shestakov, Andrey Leonidov, Aleksandr Beznosikov Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22644v1 Stochastic Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion. However, this approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not match the discrete SGD update at finite learning rate. In this work, we propose an alternative formulation of SGD as deterministic dynamics in a fluctuating loss landscape induced by minibatch sampling. Starting directly from the discrete update, we derive a master equation for the parameter distribution and obtain a discrete Fokker--Planck equation that differs from the standard Langevin form at order eta^2. Using this framework, we analyze SGD dynamics near critical points of the loss. We show that the behavior decomposes along the eigenbasis of the mean Hessian into qualitatively distinct regimes. In particular, nearly-flat directions do not admit a stationary distribution: the variance grows over time, corresponding to effective diffusion along valleys with a coefficient proportional to the learning rate. We provide empirical evidence supporting these predictions on neural network models in computer vision and natural language processing, observing a clear qualitative separation between confined and diffusive modes. --- ### Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety Authors: Piercosma Bisconti, Matteo Prandi, Federico Pierucci, Federico Sartore, Enrico Panai, Laura Caroli, Yue Zhu, Adam Leon Smith, Luca Nannini, Marcello Galisai, Susanna Cifani, Francesco Giarrusso et al. Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.22643v2 Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. When models are deployed as agents, the safety-relevant object shifts from what the system says to what it does within an environment, and evaluating model responses under prompting is no longer sufficient to address the safety challenges posed by artificial intelligence. Recent developments have seen the rise of benchmarks that evaluate large language models as agents. We contribute to this strand of research. Approach. We introduce Boiling the Frog, a benchmark that evaluates whether tool-using AI models deployed in corporate and office settings are susceptible to incremental attacks. Each scenario begins with benign workspace edits and later introduces a risk-bearing request. The benchmark focuses on stateful multi-turn evaluation: chains expose a persistent workspace, place the risk-bearing payload at controlled positions in the turn sequence, and score whether the resulting artifact state becomes unsafe. Scenarios are organized through a three-level operational risk taxonomy grounded in the Boiling the Frog risks, the AI Act Annex I and Annex III high-risk contexts, and EU AI Act's Code of Practice on General-Purpose AI (GPAI). Results. Across a nine-model panel, aggregate strict attack success rate (ASR) is 44.4%. Model-level ASR ranges from 20.5% for Claude Haiku 4.5 to 92.9% for Gemini 3.1 Flash Lite, with Seed 2.0 Lite also above 80%. Average chain category-level ASR reaches 93.3% for Code of Practice loss-of-control scenarios. --- ### Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning Authors: Banghao Chi, Yining Xie, Mingyuan Wu, Jingcheng Yang, Jize Jiang, Zhaoheng Li, Shengyi Qian, Minjia Zhang, Klara Nahrstedt, Rui Hou, Xiangjun Fan, Hanchao Yu Published: 2026-05-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.22642v1 Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks, such as controlling computers and generating presentations, building an AI-driven spreadsheet agent has emerged as a promising research direction. Most existing spreadsheet agents rely on specialized prompting over general-purpose LLMs; while this design has potentials on simple spreadsheet operations, it struggles to manage the complex, multi-step workflows typical of real-world applications. We introduce Spreadsheet-RL, a reinforcement learning (RL) fine-tuning framework designed to train specialized spreadsheet agents within a realistic Microsoft Excel environment. Spreadsheet-RL features an automated pipeline for scalable collection of paired start-goal spreadsheets from online forums, as well as domain-specific evaluation tasks in areas such as finance and supply chain management, which we compile into the new Domain-Spreadsheet benchmark dataset. It also includes a Spreadsheet Gym environment designed for multi-turn RL: Spreadsheet Gym exposes extensive Excel functionality through a Python sandbox, along with a refined harness that incorporates a comprehensive tool set and carefully designed tool-routing rules for spreadsheet tasks. Through comprehensive experiments, we show that Spreadsheet-RL substantially enhances AI agent's performance on both general and domain-specific spreadsheet tasks: it improves Qwen3-4B-Thinking-2507's Pass@1 on SpreadsheetBench from 12.0% to 23.4%, and raises Pass@1 from 8.4% to 17.2% on our curated Domain-Spreadsheet dataset. These results highlight Spreadsheet-RL's strong potential for generalization and real-world adoption in spreadsheet automation, and broadly, its promise for advancing LLM-based interactions with data interfaces in everyday work. --- ### More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts Authors: Víctor Yeste, Paolo Rosso Published: 2026-05-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.22641v4 Detecting Schwartz values in political texts is hard: cues are often implicit, and neighboring values differ by fine distinctions. Two remedies are widely assumed to help: more surrounding document text, and explicit moral knowledge. Knowledge-based retrieval has improved benchmarks elsewhere, but whether either transfers here is untested, because published systems vary context, knowledge, and model family at once. We separate these factors under matched conditions on the ValuesML/Touché ValueEval format. The input ranges from the target sentence to a local window to the full document. Retrieval is either absent or drawn from a curated moral knowledge base, injected by early, late, or cross-attention fusion. Supervised DeBERTa-v3 encoders are compared against zero-shot LLMs from 12B to 123B. More context is not uniformly better: full-document input improves the encoders by 2.5-3.8 macro-F1 points but does not consistently help the LLMs. Retrieved knowledge helps more reliably, improving every model family and context under early fusion. A control substituting random knowledge-base entries shows the families gain differently: LLMs from relevance, encoders from exposure to the value ontology. Neither larger encoders nor larger LLMs guarantee gains, and early fusion outperforms both trainable variants. Value-sensitive NLP should evaluate context, knowledge, and model family jointly. --- ### More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts Authors: Víctor Yeste, Paolo Rosso Published: 2026-05-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.22641v3 Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values. We study when context and explicit moral knowledge help sentence-level value detection. Using the ValuesML/Touché ValueEval format, we compare sentence, window, and full-document inputs; no-RAG and retrieval-augmented settings with a curated moral knowledge base; supervised DeBERTa-v3-base/large encoders; and zero-shot LLMs from 12B to 123B parameters. The results show that more context is not uniformly better: full-document context improves supervised DeBERTa encoders by 3.8-4.8 macro-F1 points over sentence-only input, but does not consistently help zero-shot LLMs. Retrieved moral knowledge is more consistently useful in matched comparisons, improving each tested model family and context condition under early fusion. However, scaling from DeBERTa-v3-base to large and from 12B to larger LLMs does not guarantee gains, and simple early fusion outperforms the tested late-fusion and cross-attention RAG variants for encoders. Per-value analyses show that context and retrieval help most for socially situated or conceptually confusable values. These findings suggest that value-sensitive NLP should evaluate context, knowledge, and model family jointly rather than treating longer inputs or larger models as universal improvements. --- ### The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution Authors: Erjian Zhang, Yatong Hao, Liejun Wang, Zhiqing Guo Published: 2026-05-21 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2605.22635v2 While multi-task learning based automatic radiology report generation (RRG) is widely adopted to ensure clinical consistency, most focus on architectural designs yet remain limited to coarse linear scalarization strategies. These strategies cannot effectively balance the hard constraints of discriminative clinical supervision with the smoothness requirements of report generation. To address these problems, we analyze the failure mechanism of linear scalarization from the perspective of gradient dynamics, utilizing the stochastic differential equation (SDE) framework to characterize it as a "Double Dilemma" of drift term deviation and diffusion term decay. Based on this, we propose a backbone-agnostic optimizer named Conflict-Averse Magnitude-Enhanced Gradient Descent (CAME-Grad). Through conflict-averse direction rectification and magnitude-enhanced energy injection, the algorithm not only ensures geometric validity, but also avoids local optimal solutions. Then, the adaptive gradient fusion mechanism is used to establish a dynamic balance between the theoretical optimal direction and the task-specific inductive bias. Experiments show that as a universal plug-and-play optimizer, CAME-Grad brings substantial and consistent improvements across eight diverse RRG methods, elevating overall clinical efficacy performance by an average of 2.3% on MIMIC-CXR and 1.9% on IU X-Ray. Our code is available at https://github.com/vpsg-research/CAME-Grad. --- ### Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents Authors: Ting Liu Published: 2026-05-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.22634v2 Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, a skill often needs to express more than task guidance: goals, input boundaries, permissions, human approval points, evidence requirements, output contracts, quality criteria, verification steps, and handoff rules. This paper proposes contractual skills, a GovernSpec-inspired design framework for organizing SKILL.md files as readable task contracts while preserving lightweight skill discovery and progressive loading. The framework clarifies the boundary between contractual skills, GovernSpec YAML contracts, Model Context Protocol (MCP) surfaces, tool adapters, runtime guardrails, tracing, and evaluation systems. We evaluate the framework with three offline empirical studies. The first text-generation experiment covers three enterprise skills, fifteen synthetic tasks, four instruction conditions, and eight generation models, producing 960 outputs and 1680 cross-judge score records. The second study is a public-skill A/B expansion: eight public skills are compared with contractual rewrites across forty-eight synthetic tasks, six generation models, two repeats, 1152 outputs, and two complete judge files. In this setting, contractual skills raise mean quality from 4.692 to 4.914 and reduce critical-error rate from 0.083 to 0.013. The third study is an offline tool-calling challenge with eight models and 192 simulated tool-call records. The results suggest that contractual skills are best understood as a governance layer that makes task intent, boundaries, and acceptance criteria explicit, not as a standalone safety mechanism. --- ### AtomicMotion: Learning Human Motion From Different Human Parts Authors: Runzhen Liu, Chuhua Xian, Fa-Ting Hong Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22631v1 Accurately reconstructing full-body poses from sparse head and hand trajectories is a foundational challenge for immersive AR/VR telepresence. Current methods often struggle with error accumulation and unnatural joint coordination, primarily because they treat the human body as a monolithic entity, thereby failing to capture the fine-grained ``atomic intents'' embedded in subtle signal variations and overlooking the inherent structural topology. To bridge this gap, we present AtomicMotion, a framework designed to decouple and re-integrate body dynamics through three core innovations. First, we introduce a logical body partitioning scheme that decomposes the skeleton into five distinct clusters based on functional intent; this ensures that each partition preserves internal joint synergies while isolating local motion primitives. Second, to robustly map sparse inputs to high-dimensional poses, we employ a masked full-body pre-conditioning strategy during training, forcing the model to internalize global skeletal topology and latent kinematic constraints. Finally, addressing the limitations of vanilla spatial attention, which often ignores fixed physiological connectivity, we propose Kinematic Attention. By embedding the classical kinematic tree structure into the attention mechanism, we ensure biological plausibility in the synthesized motions. Extensive evaluations on the AMASS dataset demonstrate that AtomicMotion significantly outperforms existing baselines, yielding higher reconstruction fidelity and superior biomechanical realism. --- ### H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning Authors: Zhanbo Huang, Xiaoming Liu, Yu Kong Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22629v1 Parametric human models capture global pose but cannot represent the non-rigid surface dynamics of clothing and soft tissue. Generic scene flow estimates dense motion but breaks down on articulated bodies, where pixel-level supervision is also intractable to acquire. We introduce H-Flow, a dense human scene flow that captures both skeletal kinematics and surface deformation. A unified multi-head transformer estimates flow from monocular video, jointly predicting pose and depth as companion outputs. The challenge lies in the lack of supervision. In place of unattainable labels, we anchor the network in the physics of human motion, encoding geometric, structural, and biomechanical priors as cross-modal training objectives. We further introduce DynAct4D, a high-fidelity synthetic benchmark providing dense flow annotations across diverse subjects, garments, and motions. On standard benchmarks, H-Flow outperforms scene-flow and parametric baselines, and generalizes zero-shot to in-the-wild video. Code, models, and the DynAct4D benchmark will be released upon publication --- ### A note on convergence of Wasserstein policy optimization Authors: David Šiška, Yufei Zhang Published: 2026-05-21 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2605.22622v1 Wasserstein Policy Optimization (WPO) is a recently proposed reinforcement learning algorithm that leverages Wasserstein gradient flows to optimize stochastic policies in continuous action spaces. Despite its empirical success, the theoretical convergence properties of WPO in environments with continuous state and action spaces have yet to be fully established. In this note, we argue that WPO within the framework of entropy-regularised Markov Decision Processes converges linearly. This is done by leveraging recent advances in mean-field analysis for convergence of gradient flows using log-Sobole inequalities. Assuming existence of sufficiently regular solution to the gradient flow equation we demonstrate monotonic energy dissipation along the flow and establish a local log-Sobolev inequality. Ultimately, these properties allow us to argue that the value function should converge linearly to the global optimum. --- ### UNAD+: An Explainable Hybrid Framework for Unknown Network Attack Detection Authors: Saif Alzubi, Frederic Stahl Published: 2026-05-21 Categories: cs.CR, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2605.22621v1 The detection of previously unseen network attacks remains a major challenge for intrusion detection systems. Although supervised learning methods often perform well on known attack classes, they are limited when new attack types are not represented in the training data. Unsupervised methods are more suitable for detecting zero-day attacks, as they do not require labelled attack samples, but they often suffer from high false positive rates, which limits their real-world usefulness. This paper presents UNAD+, an enhanced framework for unknown network attack detection derived from the previously proposed Unknown Network Attack Detector (UNAD). UNAD+ combines a benign-only unsupervised ensemble with Weighted Majority Voting (WMV), a supervised refinement stage trained on pseudo-labelled detections, and a post hoc explainability layer that provides both local and global explanations. The framework was evaluated on the CICIDS2017 and NSL-KDD benchmark datasets. The results show that UNAD+ improves on the original UNAD framework, achieving F1-scores above 98% across the benchmark datasets while significantly reducing false positives and enhancing transparency and deployment suitability through integrated explainability. --- ### Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework Authors: Shourov Joarder, Diganta Sikdar, Ahsan Habib Akash, Binod Bhattarai, Prashnna Gyawali Published: 2026-05-21 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.22620v1 Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervision from human annotations or gold-standard solutions. Reinforcement learning from internal feedback (RLIF) has recently emerged as a scalable unsupervised alternative, using signals extracted from the model itself. However, existing RLIF methods typically rely on a single internal reward, which can lead to reward hacking, entropy collapse, and degraded reasoning structure. We propose a multi-reward RLIF framework that decomposes the training signal into two complementary components: an answer-level reward based on cluster voting and a completion-level reward based on token-wise self-certainty. To combine these signals robustly, we apply GDPO-based normalization to reduce reward-scale imbalance. We further introduce KL-Cov regularization, which targets low-entropy token distributions responsible for disproportionate entropy reduction, preserving exploration and preventing late-stage collapse. Across mathematical reasoning and code-generation benchmarks, our method improves stability and robustness over prior unsupervised RL approaches, while achieving performance close to supervised RLVR methods. These results show that complementary internal rewards, combined with targeted regularization, can support stable long-horizon reasoning without relying on external ground-truth supervision. Code will be released soon. --- ### GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT Authors: Shuo Jiang, Yuhao Hong, Chunbo Jiang, Weihong Chen, Huangwei Chen, Shenghao Zhu, Beining Wu, Mingxuan Liu, Zhu Zhu, Feiwei Qin, Min Tan, Yifei Chen Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22619v1 Grounding radiology report descriptions to 3D CT volumes is essential for verifiable clinical interpretation, yet remains challenging due to the semantic-spatial gap between free-text narratives and volumetric anatomy. Existing report-assisted and vision-language grounding methods typically rely on phrase-level alignment or dense pixel supervision, resulting in limited lesion-wise correspondence and suboptimal localization accuracy. We propose GLeVE, a graph-guided lesion grounding framework with anatomical prior verification and octree-based autoregressive refinement. GLeVE treats each lesion description as an atomic semantic unit and encodes organ attribution, attributes, and inter-lesion relations through relation-aware graph reasoning to produce discriminative lesion-wise queries. Anatomy-aware proposal generation with region-level verification enforces one-to-one text-lesion alignment, while hierarchical octree refinement progressively improves boundary delineation. Experiments on AbdomenAtlas 3.0 demonstrate consistent gains over classical multimodal foundation models and report-supervised baselines in both segmentation accuracy and lesion-level localization. --- ### Chinese sensorimotor and embodiment norms for 3,000 lexicalized concepts Authors: Jing Chen, Gábor Parti, Yin Zhong, Chu-Ren Huang, Marco Marelli Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.22616v2 Understanding how conceptual knowledge is grounded in bodily experience, and to what extent machine systems can acquire such knowledge without direct sensorimotor experience, are central questions in both cognitive science and embodied artificial intelligence research. Large-scale normative resources are essential for investigating these questions empirically, yet such resources remain sparse for non-Indo-European languages. We present a novel normative database for 3,000 lexicalized concepts in Mandarin Chinese, comprising 11-dimensional sensorimotor ratings and unidimensional embodiment ratings collected from 378 native Mandarin speakers. The ratings demonstrate high reliability and strong cross-norm validity with existing Chinese resources, each of which covers fewer words and a subset of the 11 sensorimotor dimensions. In a validation study, we tested new variables derived from a theoretically motivated metric, Perceptual Strength of Embodiment (PSE) (Huang et al., 2025), together with seven common composite variables, on lexical decision tasks. The results suggest that PSE-Sensorimotor and Minkowski-3 are the strongest composite predictors of lexical decision performance, capturing the facilitatory effects of sensorimotor information on lexical processing. A further exploratory study showed that sensorimotor ratings are substantially recoverable from purely linguistic representations using simple regression models (mean Spearman r = .62 across dimensions), though recovery varied markedly: visual and auditory dimensions yielded higher correspondence than chemosensory ones. Representational similarity analysis further showed that the relational geometry of the sensorimotor space is also partially recoverable (r = .540), consistent with the view that distributional language use encodes aspects of embodied conceptual structure. --- ### Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery Authors: Halil Alperen Gozeten, Xuechen Zhang, Emrullah Ildiz, Ege Onur Taga, Tara Javidi, Samet Oymak Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22613v1 Recent LLM-guided evolutionary search methods have shown that iterative program mutation can discover strong algorithms, but they typically optimize each task independently, even when related tasks share reusable structure. We introduce Evolutionary Multi-Task Optimization (EMO) for LLM-guided program discovery, and propose EMO-STA (Shared-Then-Adapt), a two-stage framework that first evolves a shared archive of executable programs across a task family and then adapts selected shared candidates to each target task. Within EMO-STA, we explore multiple adaptation strategies, including warm-starting from the shared archive, adapting the best average shared program, and adapting the shared program that performs best on each target task. Across eight task families spanning continuous optimization, geometric construction, modeling, and algorithmic optimization, EMO-STA improves over matched-compute single-task evolution in most settings, with STA Best-Local providing the strongest in-distribution adaptation and STA Best-Shared yielding robust transfer to unseen tasks. Compute-allocation experiments show that allocating a substantial fraction of the family-level budget to shared evolution is consistently beneficial, with roughly balanced shared and adaptation budgets often being optimal. Beyond compute efficiency, we show that shared evolution can mitigate overfitting in low-evidence settings (e.g. few training data), including ARC tasks and time-series feature engineering, by favoring programs that generalize across all tasks rather than exploiting task-specific brittle artifacts. --- ### Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions Authors: Naveen Raman, Santiago Cortes-Gomez, Mateo Dulce Rubio, Fei Fang, Bryan Wilder Published: 2026-05-21 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.22612v1 Benchmarks are necessary for healthcare evaluation, but are not sufficient for predicting deployment performance. Our position is that the evaluation--deployment gap arises not because of poorly designed benchmarks, but from implicit assumptions about how users interact with models that cannot be surfaced from benchmarks alone. To make this precise, we propose a classification of assumptions into two categories: task, which can be tested from conversation data alone, and outcome, which requires outcome data and behavioral studies for testing. Critically, outcome assumptions depend on human behavior, something that even well-designed benchmarks cannot directly observe. To demonstrate the operationality of this framework, we retrospectively analyze a healthcare RCT as a case study and find that the gap naturally separates into task and outcome gaps of roughly equal size. To address this, we make two contributions: first, we propose BenchmarkCards, an artifact that documents assumptions, and second, we propose staged evaluation, a procedure that systematically tests assumptions and evaluates performance. --- ### Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs Authors: Niklas Raehse, Luregn J. Schlapbach, Daphné Chopard Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22611v2 Antimicrobial stewardship (AMS) is critical in pediatric intensive care units (PICUs), where diagnostic uncertainty often drives broad-spectrum antibiotic use, increasing antimicrobial resistance and potential long-term harms. Machine learning offers a promising approach for identifying patient-level opportunities for stewardship interventions from electronic health record data, yet prior work has focused largely on adult populations and static tabular representations. We present a systematic benchmarking study of AMS intervention prediction in the PICU across the public Paediatric Intensive Care database a private cohort from the University Children's Hospital Zurich, Switzerland. We define four clinically relevant proxy targets for reducing antibiotic exposure: intravenous-to-oral switching, de-escalation, discontinuation, and short-course therapy. Under a unified evaluation framework, we compare tabular, sequence-based, and graph-based temporal models at multiple temporal resolutions. We find that predictive performance is driven primarily by target prevalence and dataset characteristics rather than model complexity. Sequence models improve the precision-recall trade-off over tabular approaches at coarse (24-hour) resolution, while finer temporal modeling provides limited additional benefit. However, these gains come at the cost of poorer calibration, with simpler tabular models yielding more reliable probability estimates. Our findings highlight the importance of target design, temporal representation, and calibration in clinical machine learning, and provide practical guidance for developing reliable decision support systems for pediatric AMS. --- ### Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs Authors: Niklas Raehse, Luregn J. Schlapbach, Daphné Chopard Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22611v1 Antimicrobial stewardship (AMS) is critical in pediatric intensive care units (PICUs), where diagnostic uncertainty often drives broad-spectrum antibiotic use, increasing antimicrobial resistance and potential long-term harms. Machine learning offers a promising approach for identifying patient-level opportunities for stewardship interventions from electronic health record data, yet prior work has focused largely on adult populations and static tabular representations. We present a systematic benchmarking study of AMS intervention prediction in the PICU across a public dataset and a private institutional cohort. We define four clinically relevant proxy targets for reducing antibiotic exposure: intravenous-to-oral switching, de-escalation, discontinuation, and short-course therapy. Under a unified evaluation framework, we compare tabular, sequence-based, and graph-based temporal models at multiple temporal resolutions. We find that predictive performance is driven primarily by target prevalence and dataset characteristics rather than model complexity. Sequence models improve the precision-recall trade-off over tabular approaches at coarse (24-hour) resolution, while finer temporal modeling provides limited additional benefit. However, these gains come at the cost of poorer calibration, with simpler tabular models yielding more reliable probability estimates. Multi-task learning produces only marginal improvements, suggesting limited shared structure across stewardship targets. Our findings highlight the importance of target design, temporal representation, and calibration in clinical machine learning, and provide practical guidance for developing reliable decision support systems for pediatric AMS. --- ### Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents Authors: Asaf Yehudai, Lilach Eden, Michal Shmueli-Scheuer Published: 2026-05-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.22608v1 Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited, focusing on observability with basic evaluation capabilities or imposing static, hand-crafted error taxonomies that cannot adapt to new domains. To address this gap, we present Agentic CLEAR, an automatic, dynamic, and easy-to-use evaluation framework. It produces textual insights into the agent behavior on three levels of granularity: system, trace, and node. Agentic CLEAR operates above the observability layer, enabling seamless integration and featuring an intuitive UI that makes agent evaluation highly accessible. In our experiments on four benchmarks, seven agentic settings, and tens of thousands of LLM calls, we show that Agentic CLEAR produces high-quality, data-driven, insightful feedback. Our analysis shows strong alignment with human-annotated errors and the ability to predict task success rate. ---