# Research Papers — 2026-04 · bundle page 12 of 233 > Full-text markdown of papers #551–600 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/12 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/11.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/13.md) ### Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping Authors: Tobias Bystrich, Julia M. Pritzen, Christoph A. Schmidt, Claudia Wich-Reif Published: 2026-04-29 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.27204v1 In the field of universal automatic phonetic transcription (APT), clean and diverse training transcriptions are required. However, such high-quality data is limited. We propose the bootstrapping approach Selective Augmentation to improve the available training transcriptions by selectively transferring distinctions between languages. Based on the model MultIPA, we exemplarily show that we could increase the accuracy of an existing feature (plosive voicing) and add a new feature (plosive aspiration) by augmenting the existing training data using information from a separate helper language (Hindi). We describe intrinsic challenges of the evaluation and develop objective metrics to determine the success: Voicing accuracy was increased by 17.6% by reducing the number of false positives. Additionally, aspiration recognition was introduced: While the baseline transcribed 0% of German /p, t, k/ as aspirated, our approach transcribed them as aspirated in 61.2% of the cases. Introducing aspiration recognition to APT models allowed for the tenuis class to be successfully reduced by 32.2%, which also reduces the conflations between the test language's plosives. --- ### Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation Authors: Shouren Wang, Wang Yang, Chuang Ma, Debargha Ganguly, Vikash Singh, Chaoda Song, Xinpeng Li, Xianxuan Long, Vipin Chaudhary, Xiaotian Han Published: 2026-04-29 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.27201v3 Hybrid-thinking language models expose explicit /think and /no_think modes, but current designs do not separate them cleanly. Even in /no_think mode, models often emit long and self-reflective responses, causing reasoning leakage. Existing work reduces this issue through better data curation and multi-stage training, yet leakage remains because both modes are still encoded in the same feed-forward parameters. We propose Path-Lock Expert (PLE), an architecture-level solution that replaces the single MLP in each decoder layer with two semantically locked experts, one for /think and one for /no_think, while keeping attention, embeddings, normalization, and the language-model head shared. A deterministic control-token router selects exactly one expert path for the entire sequence, so inference preserves the dense model's per-token computation pattern and each expert receives mode-pure updates during supervised fine-tuning. Across math and science reasoning benchmarks, PLE maintains strong /think performance while producing a substantially stronger mode separation, a /no_think mode with higher accuracy and far less reasoning leakage. On Qwen3-4B, for example, compared to the SFT-only baseline on AIME24, PLE generates 17x fewer reflective tokens (6.01 vs. 0.35 per answer) and 2x shorter outputs (8665 vs. 4101 tokens), and improves /no_think accuracy from 35.33% to 44.67%, while maintaining /think-mode performance (61.33% vs. 60.00%). These results suggest that controllable hybrid thinking is fundamentally an architectural problem, and separating mode-specific feed-forward pathways is a simple and effective solution. --- ### Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation Authors: Shouren Wang, Wang Yang, Chuang Ma, Debargha Ganguly, Vikash Singh, Chaoda Song, Xinpeng Li, Xianxuan Long, Vipin Chaudhary, Xiaotian Han Published: 2026-04-29 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.27201v2 Hybrid-thinking language models expose explicit think and no-think modes, but current designs do not separate them cleanly. Even in no-think mode, models often emit long and self-reflective responses, causing reasoning leakage. Existing work reduces this issue through better data curation and multi-stage training, yet leakage remains because both modes are still encoded in the same feed-forward parameters. We propose Path-Lock Expert (PLE), an architecture-level solution that replaces the single MLP in each decoder layer with two semantically locked experts, one for think and one for no-think, while keeping attention, embeddings, normalization, and the language-model head shared. A deterministic control-token router selects exactly one expert path for the entire sequence, so inference preserves the dense model's per-token computation pattern and each expert receives mode-pure updates during supervised fine-tuning. Across math and science reasoning benchmarks, PLE maintains strong think performance while producing a substantially stronger no-think mode that is more accurate, more concise, and far less prone to reasoning leakage. On Qwen3-4B, for example, PLE reduces no-think reflective tokens on AIME24 from 2.54 to 0.39 and improves no-think accuracy from 20.67% to 40.00%, all while preserving think-mode performance. These results suggest that controllable hybrid thinking is fundamentally an architectural problem, and separating mode-specific feed-forward pathways is a simple and effective solution. --- ### Evaluating TabPFN for Mild Cognitive Impairment to Alzheimer's Disease Conversion in Data Limited Settings Authors: Brad Ye, Bulent Soykan, Gulsah Hancerliogullari Koksalmis, Hsin-Hsiung Huang, Laura J. Brattain Published: 2026-04-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27195v2 Accurate prediction of conversion from Mild Cognitive Impairment (MCI) to Alzheimers Diseases (AD) is essential for early intervention, however, developing reliable conversion predictive models is difficult to develop due to limited longitudinal data availability We evaluate TabPFN (Tabular Pre-Trained Foundation Network) against traditional machine learning methods for predicting 3 year MCI to AD conversion using the TADPOLE dataset derived from ADNI. Using multimodal biomarker features extracted from demographics, APOE4, MRI volumes, CSF markers, and PET imaging, we conducted an experimental comparison across varying training set sizes (N=50 to 1000) and models including XGBoost, Random Forest, LightGBM, and Logistic Regression. TabPFN achieved one the highest performance (AUC=0.892), outperforming LightGBM (AUC=0.860) and demonstrating advantages in low data settings. At N=50 training samples, TabPFN maintained strong AUC while the traditional machine learning models struggles at small training samples. These findings demonstrate that foundation models are promising for disease prediction in data limited scenarios, such as Alzheimers diseases. --- ### Linear Models, Variable Selection, Artificial Intelligence Authors: By Riyadh Alrawkan, Edward Boone, Ryad Ghanam, Anton Westveld Published: 2026-04-29 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.27191v1 Variable selection in linear regression models has been a problem since hypothesis testing began. Which variables to include or exclude from a model is not an easy task. Techniques such as Forward, Back ward, Stepwise Regression sequentially add or delete variables from a model. Penalized likelihood methods such as AIC, BIC, etc. seek to choose variables that have a significant contribution to the likelihood. Penalized sum of square methods such as LASSO and Elastic Net have been used to penalize small coefficients to only allow variables with large coefficients in the model. This work introduces an Artificial Intelligence approach to model selection where an ANN is trained to determine the significance of the variables based on OLS estimates. A simulation study shows the accuracy across various sample sizes and variances. Furthermore, a simulation study is conducted to compare the performance of the approach against Forward, Backward, AIC, BIC and LASSO. The approach is illustrated using a dataset from the World Health Organization regarding Life Expectancy. A github link is provided to the pretrained ANN that can handle up to 100 predictor variables, the original WHO dataset and the subset used in this work. --- ### Learning to Spend: Model Predictive Control for Budgeting under Non-Stationary Returns Authors: Nilavra Pathak, Smriti Shyamal, Prasant Mhasker, Christopher Swartz Published: 2026-04-29 Categories: eess.SY, cs.AI, cs.LG, q-fin.PM arXiv: https://arxiv.org/abs/2604.27186v1 We study finite-horizon budget allocation as a closed-loop economic control problem and evaluate receding-horizon Model Predictive Control (MPC) relative to reactive budgeting policies. Budgets are allocated periodically under execution noise and operational constraints, while return efficiency may evolve over time. Using a controlled simulation framework motivated by digital marketing, we compare reactive pacing to MPC across environments with increasing degrees of non-stationarity. Our results show that non-stationarity alone does not justify predictive control. When return dynamics are stationary or evolve through unpredictable stochastic drift, MPC offers no systematic advantage over reactive baselines. By contrast, when return efficiency exhibits predictable structure over the planning horizon, that is captured through an underlying model, MPC consistently outperforms reactive budgeting by exploiting intertemporal trade-offs. --- ### Preserving Temporal Dynamics in Time Series Generation Authors: Ci Lin, Futong Li, Tet Yeap, Iluju Kiringa Published: 2026-04-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.27182v1 Time-series data augmentation plays a crucial role in regression-oriented forecasting tasks, where limited data restricts the performance of deep learning models. While Generative Adversarial Networks (GANs) have shown promise in synthetic time-series generation, existing approaches primarily focus on matching marginal data distributions and often overlook the temporal dynamics that naturally exist in the original multivariate time series. When generating multivariate time series, this mismatch leads to distribution shift and temporal drift, thereby degrading the fidelity of the synthetic sequences. In this work, we propose a model-agnostic Markov Chain Monte Carlo (MCMC)-based framework to mitigate distribution shift and preserve temporal dynamics in synthetic time series. We provide a theoretical analysis of how conditional generative models accumulate deviations under sequential generation and demonstrate that the MCMC algorithm can correct these discrepancies by enforcing consistency with empirical transition statistics between neighboring time points. Extensive experiments on the Lorenz, Licor, ETTh, and ILI datasets using RCGAN, GCWGAN, TimeGAN, SigCWGAN, and AECGAN demonstrate that the proposed MCMC framework consistently improves autocorrelation alignment, skewness error, kurtosis error, R$^2$, discriminative score, and predictive score. These results suggest that synthetic time series consistent with the original data require explicit preservation of transition laws rather than solely relying on adversarial distribution matching, thereby offering a principled direction for improving generative modeling of time-series data. --- ### Energy-Efficient Plant Monitoring via Knowledge Distillation Authors: Ilyass Moummad, Reda Bensaid, Kawtar Zaher, Hervé Goëau, Jean-Christophe Lombardo, Joseph Salmon, Pierre Bonnet, Alexis Joly Published: 2026-04-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27178v2 Recent advances in large-scale visual representation learning have significantly improved performance in plant species and plant disease recognition tasks. However, state-of-the-art models, often based on high-capacity vision transformers or multimodal foundation models, remain computationally expensive and difficult to deploy in resource-constrained environments such as mobile or edge devices. This limitation hinders the scalability of automated biodiversity monitoring and precision agriculture systems, where efficiency is as critical as accuracy. In this work, we investigate knowledge distillation as an effective approach to transfer the representational capacity of large pretrained models into smaller, more efficient architectures. We focus on plant species and disease recognition, and conduct an extensive empirical study on two challenging benchmarks: Pl@ntNet300K-v2 and Deep-Plant-Disease. We evaluate four representative architectures, including two ConvNeXt models and two vision transformers, under multiple training regimes: from-scratch training and pretrained initialization, each with and without distillation. In total, we train and evaluate 70 models. Our results show that knowledge distillation consistently improves performance across tasks and architectures. Distilled models are able to match the performance of significantly larger models while maintaining substantially lower computational cost. These findings demonstrate the potential of knowledge distillation techniques to enable efficient and scalable deployment of plant recognition systems in real-world environmental applications. --- ### Context-Aware Graph Attention for Unsupervised Telco Anomaly Detection Authors: Sara Malacarne, Eirik Hoel-Høiseth, Erlend Aune, David Zsolt Biro, Massimiliano Ruocco Published: 2026-04-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27172v1 We propose C-MTAD-GAT, an \emph{unsupervised}, \emph{context-aware} graph-attention model for anomaly detection in multivariate time series from mobile networks. C-MTAD-GAT combines graph attention with lightweight context embeddings, and uses a deterministic reconstruction head and multi-step forecaster to produce anomaly scores. Detection thresholds are calibrated \emph{without labels} from validation residuals, keeping the pipeline fully unsupervised. On the public TELCO dataset, C-MTAD-GAT consistently outperforms MTAD-GAT and the Telco-specific DC-VAE, two state-of-the-art baselines, in both event-level and pointwise F1, while triggering substantially fewer alarms. C-MTAD-GAT is also deployed in the Core network of a national mobile operator, demonstrating its resilience in real industrial settings. --- ### Semantic Structure of Feature Space in Large Language Models Authors: Austin C. Kozlowski, Andrei Boutyline Published: 2026-04-29 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.27169v1 We show that the geometric relations between semantic features in large language models' hidden states closely mirror human psychological associations. We construct feature vectors corresponding to 360 words and project them on 32 semantic axes (e.g. beautiful-ugly, soft-hard), and find that these projections correlate highly with human ratings of those words on the respective semantic scales. Second, we find that the cosine similarities between the semantic axes themselves are highly predictive of the correlations between these scales in the survey. Third, we show that substantial variance across the 32 semantic axes lies on a low-dimensional subspace, reproducing patterns typical of human semantic associations. Finally, we demonstrate that steering a word on one semantic axis causes spillover effects on the model's rating of that word on other semantic scales proportionate to the cosine similarity between those semantic axes. These findings suggest that features should be understood not only in isolation but through their geometric relations and the meaningful subspaces they form. --- ### How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models Authors: Paraskevas V. Lekeas, Giorgos Stamatopoulos Published: 2026-04-29 Categories: cs.GT, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.27167v3 On the named Prisoner's Dilemma under direct prompting, three larger instruction-tuned models, Llama-3-70B, Qwen2.5-32B, and Qwen2.5-72B, lock at full cooperation, the metric's maximum distance from Nash with zero variance across replicates, while Llama-3-8B plays near-Nash. Opening the models, a logit-lens analysis finds a distributed cooperative override. Intermediate readouts lean toward the Nash action through roughly three quarters of network depth before a late surge toward cooperation, and the final layer settles the contest. The size of that final correction, not the surge, rank-matches chain-of-thought behavior across scale and two architectures. In the 8B the override is a single causally controllable direction in the residual stream; steering it dials the decision, and clamping its component at one position of one layer moves the choice strictly monotonically, Spearman rho = 1.000, with generation fluent. The circuit is lexical. It survives name removal and payoff rescaling but disengages when Cooperate and Defect are replaced with neutral labels, and on 48 payoff-random games with neutral surfaces no model locks cooperative on any dilemma or shows general equilibrium competence. In mixed-model populations a single Nash-playing agent collapses cooperation contagiously. What suppresses Nash play in large language models is a word-triggered circuit rather than missing competence, and it can be measured, bounded, and controlled. --- ### What Suppresses Nash Equilibrium Play in Large Language Models? Mechanistic Evidence and Causal Control Authors: Paraskevas V. Lekeas, Giorgos Stamatopoulos Published: 2026-04-29 Categories: cs.GT, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.27167v2 LLM agents are known to deviate from Nash equilibria in strategic interactions, but nobody has looked inside the model to understand why, or asked whether the deviation can be reversed. We do both. Working with four open-source models (Llama-3 and Qwen2.5, 8B to 72B parameters) playing four canonical two-player games, we establish the behavioral picture through self-play and cross-play experiments, then open up the 32-layer Llama-3-8B model and examine what actually happens during a strategic decision. The mechanistic findings are clear. Opponent history is encoded with near-perfect fidelity at the first layer (96% probe accuracy) and consumed progressively, while Nash action encoding is weak throughout, never exceeding 56%. There is no dedicated Nash module. Instead, the model privately favors the Nash action through most of its forward pass, but a prosocial override rooted in pretraining on human text concentrated in the final layers reverses this, reaching 84% probability of cooperation at layer 30. Injecting a learned Nash direction into the residual stream shifts behavior bidirectionally and causally, confirmed through concept clamping. The behavioral experiments surface six scale- and architecture-dependent findings, the most notable being that chain-of-thought reasoning worsens Nash play in small models but achieves near-perfect Nash play above 70B parameters. The cross-play experiments reveal three phenomena invisible in self-play: a small model can unravel any partner's cooperation by defecting early; two large models reinforce each other's cooperative instincts indefinitely; and who moves first determines which Nash equilibrium the system reaches. LLMs do not lack Nash-playing competence. They compute it, then suppress it. --- ### Distributional Alignment Games for Answer-Level Fine-Tuning Authors: Mehryar Mohri, Jon Schneider, Yifan Wu Published: 2026-04-29 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2604.27166v1 We focus on the problem of \emph{Answer-Level Fine-Tuning} (ALFT), where the goal is to optimize a language model based on the correctness or properties of its final answers, rather than the specific reasoning traces used to produce them. Directly optimizing answer-level objectives is computationally intractable due to the need to marginalize over the vast space of latent reasoning paths. To overcome this, we propose a general game-theoretical framework that lifts the problem to a \emph{Distributional Alignment Game}. We formulate ALFT as a two-player game between a Policy (the generator) and a Target (an auxiliary distribution). We prove that the Nash Equilibrium of this game corresponds exactly to the solution of the original answer-level optimization problem. This variational perspective transforms the intractable marginalization problem into a tractable projection problem. We demonstrate that this framework unifies recent approaches to diversity and self-improvement (coherence) and provide efficient algorithms compatible with Group Relative Policy Optimization (GRPO), such as Coherence-GRPO, yielding significant complexity gains in mathematical reasoning tasks. --- ### A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations Authors: Timothy Flavin, Sandip Sen Published: 2026-04-29 Categories: cs.MA, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2604.27162v1 Reinforcement Learning (RL) algorithms exhibit high sample complexity, particularly when applied to Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). As a response, projects such as SampleFactory, EnvPool, Brax, and IsaacLab migrate parallel execution of classic environments such as MuJoCo and Atari into C++ thread pools or the GPU to decrease the computational cost of environment steps. We are interested in optimizing the decision-level of human-AI joint operations, so we introduce a compute-efficient Dec-POMDP engine natively architected in C++ called Hide-And-Seek-Engine. By employing Data-Oriented Design (DOD) principles, explicit 64-byte cache-line alignment to remove false sharing, and a zero-copy PyTorch memory bridge using pinned memory and Direct Memory Access (DMA), our engine sustains throughput of up to 33,000,000 steps per second (SPS) in a single-agent, 1024-environment, decentralized observations on an AMD Ryzen 9950X (16 cores). Ten agents reduces FPS to 7M SPS with generating random actions contributing 1/3rd the total runtime for reference. The engine achieves a throughput increase of approximately 3,500$\times$ over the baseline single threaded vectorized NumPy implementation and successfully trains cooperative multi-agent policies via PPO, DQN, and SAC in minutes, validating both its performance and generality. --- ### Interval Orders, Biorders and Credibility-limited Belief Revision Authors: Richard Booth, Ivan Varzinczak Published: 2026-04-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27156v1 Rational belief revision is commonly viewed as being based on a preference order between possible worlds, with the resulting new belief set being those sentences true in all the most preferred models of the incoming new information. Usually, such a preference order is taken to be a total preorder. Nevertheless, there are other, more general classes of ordering that can also be employed. In this paper, we explore two such classes that have been studied within the theory of rational choice but have seen limited or no application in belief revision. We begin with interval orders, introduced by Fishburn in the '80s, which associate with each possible world a nonnegative `interval' of plausibility. We then move on to biorders, studied by Aleskerov, Bouyssou, and Monjardet, which generalise interval orders by allowing the intervals to have negative lengths, a feature that can be used to capture a notion of dissonance or instability. We provide axiomatic characterisations of these two resulting families of belief revision operators, as well as of two further families of interest that lie between interval orders and biorders. We show that while biorder-based revisions satisfy the Success postulate, they do not always yield consistent outputs. By modifying their definition to discard inputs that lead to inconsistency as `incredible', we derive new families of so-called non-prioritised revision that satisfy the Consistency postulate, but not the Success one. These families are linked to credibility-limited revision operators of Hansson et al., but for which the set of credible sentences does not satisfy the single-sentence closure condition. We argue that the biorder-based approach is well-suited for scenarios where an agent might initially reject new information, but may accept it when presented with additional explanation. --- ### Generalizing the Geometry of Model Merging Through Frechet Averages Authors: Marvin F. da Silva, Mohammed Adnan, Felix Dangel, Sageev Oore Published: 2026-04-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27155v2 Model merging aims to combine multiple models into one without additional training. Naïve parameter-space averaging can be fragile under architectural symmetries, as their geometry does not take them into account. In this work we show that not only the geometry, but also the averaging procedure itself, must be symmetry-invariant to achieve symmetry-aware merges. Consequently, we propose a general solution: merging as Fréchet averaging, i.e., selecting parameters that minimize a sum of geodesic distances on an appropriate manifold. In this view, the key design choice is the overall geometry, i.e., the choice of metric, manifold, and distance approximation, that determines what it means for two models to be "close". We show that Fréchet averaging, combined with simplifying assumptions, contains Fisher merging. Building on this, we examine the particular case of low-rank adapters (LoRA), whose symmetries induce a distinct geometry: that of a quotient manifold. We outline the limitations of current LoRA merging methods, propose a practical algorithm for this setting, and show how they compare with other commonly used approaches. --- ### Step-level Optimization for Efficient Computer-use Agents Authors: Jinbiao Wei, Kangqi Ni, Yilun Zhao, Guo Gan, Arman Cohan Published: 2026-04-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27151v1 Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent advances in benchmark performance, strong computer-use agents remain expensive and slow in practice, since most systems invoke large multimodal models at nearly every interaction step. We argue that this uniform allocation of compute is fundamentally inefficient for long-horizon GUI tasks. Such trajectories are highly heterogeneous: many steps are routine and can be handled reliably by smaller, cheaper policies, while errors tend to concentrate at a relatively small number of high-risk moments. Across computer-use benchmarks, these failures repeatedly take two forms: progress stalls, where the agent loops, repeats ineffective actions, or fails to make meaningful progress, and silent semantic drift, where the agent continues taking locally plausible actions after already deviating from the user's true goal. To address this inefficiency, we propose an event-driven, step-level cascade for computer-use agents that runs a small policy by default and escalates to a stronger model only when lightweight learned monitors detect elevated risk. Our framework combines two complementary signals: a Stuck Monitor that detects degraded progress from recent reasoning-action history and triggers recovery, and a Milestone Monitor that identifies semantically meaningful checkpoints where sparse verification is most informative for catching drift. This design turns always-on frontier-model inference into adaptive, on-demand compute allocation over the course of an evolving interaction. The framework is modular and deployment-oriented: it can be layered on top of existing computer-use agents without changing the underlying agent architecture or retraining the large model. --- ### Optimal Stop-Loss and Take-Profit Parameterization for Autonomous Trading Agent Swarm Authors: Nathan Li, Aikins Laryea, Yigit Ihlamur Published: 2026-04-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27150v1 Autonomous crypto trading systems often spend most of their design effort on finding entries, while exits are left to fixed rules that are rarely tested in a systematic way. This paper examines whether better stop-loss and take-profit settings can improve the performance of an autonomous trading agent swarm. Using more than 900 historical trades, we replay each trade under many alternative exit policies and compare results against the existing production setup. The study finds that exit design matters meaningfully: stronger configurations improve risk-adjusted performance and generally favor tighter loss limits, earlier profit capture, and closer trailing protection. The paper also discusses a key evaluation challenge: a purely chronological split was initially used, but the newest trades fell into an unusual war-driven market period that sharply distorted test results. To reduce the influence of that single episode, the main comparison was run on randomized data, with the drawbacks of doing so acknowledged explicitly. Overall, the paper presents a practical framework for tuning exit logic in a more disciplined and transparent way. --- ### ConformaDecompose: Explaining Uncertainty via Calibration Localization Authors: Fatima Rabia Yapicioglu, Meltem Aksoy, Alberto Rigenti, Tuwe Löfström-Cavallin, Helena Löfström-Cavallin, Seyda Yoncaci, Luca Longo Published: 2026-04-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.27149v1 Conformal Prediction provides distribution-free prediction intervals with guaranteed coverage, but its reliance on a single global calibration threshold obscures the sources of uncertainty at the instance level. In particular, it conflates irreducible noise with uncertainty induced by heterogeneous training data (aleatoric), model limitations, or calibration mismatch (epistemic), offering little insight into why an interval is wide or whether it could be reduced. We introduce an uncertainty-aware explainability framework that analyses the reducibility of calibration-induced epistemic conformal uncertainty via progressive calibration localisation for regression tasks. The approach is diagnostic rather than causal: it does not estimate true aleatoric or epistemic uncertainty, but explains how conformal intervals contract and stabilise as calibration support is localised around a test instance. Across benchmarks and real-world data, absolute reducible uncertainty aligns with epistemic proxies, while its relative contribution varies by task, revealing regimes hidden by interval width. This instance-level view complements conformal uncertainty, enhancing interpretability without altering the predictor or coverage. --- ### How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance Authors: Jerry Y. Huang, Justin Lin, Sheel Shah, Kartik Nair, Nicholas M. Boffi Published: 2026-04-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.27147v3 In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing guidance methods either require expensive multi-particle, many-step schemes or rely on poorly understood approximations. We reformulate guidance as a \textit{deterministic optimal control problem}, yielding a hierarchy of algorithms that subsumes existing approaches at the coarsest level. We show that the \textit{flow map}, an object of significant recent interest for its role in fast inference, arises naturally in the optimal solution. Based on this observation, we propose \textbf{Flow Map Reward Guidance (FMRG)}: a training-free, \textit{single-trajectory} framework that uses the flow map to both integrate and guide the flow. At text-to-image scale, FMRG matches or surpasses baselines across inverse problems and reward-guided generation with \textbf{as few as 3 NFEs}, giving at least an order-of-magnitude speedup in comparison to prior state of the art. Code is available at https://github.com/jrrhuang/fmrg. --- ### Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Authors: Benjamin Probst, Andreas Happe, Jürgen Cito Published: 2026-04-29 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.27143v2 Cloud-based Large Language Models (LLMs) can perform autonomous penetration-testing sub-tasks such as Linux privilege escalation, but raise security, privacy, and sovereignty concerns. Locally hosted open-weight models avoid these issues, yet prior work reports that small open-weight models succeed on only 8-16% of standardized privilege-escalation tasks, far below frontier cloud models. This paper is an empirical study of why small models fail at this task and which engineering techniques close the gap. From execution traces we distill six recurring failure modes, map each to an established enhancement technique, and evaluate five (chain-of-thought prompting, retrieval-augmented generation, structured prompting, history compression, and reflective analysis) as reproducible extensions to the open-source hackingBuddyGPT framework. Under a single shared harness and matched conditions, the set of techniques we evaluate raise two SLMs (Llama3.1 8B, Qwen2.5 7B) from 8% to 67% with guidance, matching guided GPT-4o. A larger open-weight reference model (Llama3.1 70B) reaches 83%. A full-factorial ablation shows that reflection-based techniques contribute most and reveals vulnerability discovery, not exploitation, as the main constraint for local models. We report these as transferable lessons for building reliable local offensive agents as well as to inform defenders. --- ### Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Authors: Benjamin Probst, Andreas Happe, Jürgen Cito Published: 2026-04-29 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.27143v1 Recent research has demonstrated the potential of Large Language Models (LLMs) for autonomous penetration testing, particularly when using cloud-based restricted-weight models. However, reliance on such models introduces security, privacy, and sovereignty concerns, motivating the use of locally hosted open-weight alternatives. Prior work shows that small open-weight models perform poorly on automated Linux privilege escalation, limiting their practical applicability. In this paper, we present a systematic empirical study of whether targeted system-level and prompting interventions can bridge this performance gap. We analyze failure modes of open-weight models in autonomous privilege escalation, map them to established enhancement techniques, and evaluate five concrete interventions (chain-of-thought prompting, retrieval-augmented generation, structured prompts, history compression, and reflective analysis) implemented as extensions to hackingBuddyGPT. Our results show that open-weight models can match or outperform cloud-based baselines such as GPT-4o. With our treatments enabled, Llama3.1 70B exploits 83% of tested vulnerabilities, while smaller models including Llama3.1 8B and Qwen2.5 7B achieve 67% when using guidance. A full-factorial ablation study over all treatment combinations reveals that reflection-based treatments contribute most, while also identifying vulnerability discovery as a remaining bottleneck for local models. --- ### RCMAES: A Robust CMA-ES Variant for CEC2026 Competition Authors: Khoirul Faiq Muzakka, Sören Möller, Martin Finsterbusch Published: 2026-04-29 Categories: cs.NE arXiv: https://arxiv.org/abs/2604.27138v1 This paper proposes RCMAES, a novel variant of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for CEC benchmark optimization. RCMAES integrates a dimension-dependent nonlinear population-size reduction strategy with an adaptive restart mechanism within a pure CMA-ES framework. RCMAES is evaluated on three benchmark suites (CEC2017, CEC2020, and CEC2022) and compared with state-of-the-art DE algorithms as well as its closely related counterpart, BIPOP-aCMAES. Experimental results show that RCMAES achieves competitive and robust performance across all benchmarks. --- ### Cross-Lingual Response Consistency in Large Language Models: An ILR-Informed Evaluation of Claude Across Six Languages Authors: Camelia Baluta Published: 2026-04-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27137v1 This paper introduces a systematic evaluation framework grounded in the Interagency Language Roundtable (ILR) Skill Level Descriptions and applies it to Claude (Sonnet 4.6) across six languages: English, French, Romanian, Spanish, Italian, and German. We administer a battery of 12 semantically equivalent prompt clusters spanning ILR complexity levels 1 through 3+, collect 216 responses (12 prompts, 6 languages, 3 runs), and analyze outputs through a two-layer methodology combining automated quantitative metrics with expert ILR qualitative assessment. Quantitative analysis reveals that French responses are approximately 30% longer than German responses on identical prompts, and that creative and affective clusters show the highest cross-lingual surface divergence. Qualitative analysis, conducted by a six-language professional with 12 years of ILR/OPI assessment experience, identifies five cross-lingual variation patterns: systematic differences in pragmatic disambiguation strategies, aesthetic and literary tradition divergence in creative output, language-internal technical terminology norms, cultural calibration gaps evidenced by the absence of culture-specific content in favor of culturally neutralized templates, and language-specific institutional referral behavior in emotional support responses. We argue that ILR-informed expert judgment applied to LLM outputs constitutes a novel and underreported evaluation methodology that complements purely computational benchmarks, and that cross-lingual output variation in Claude is interpretable, domain-dependent, and consequential for equitable multilingual AI deployment. --- ### Unpacking Vibe Coding: Help-Seeking Processes in Student-AI Interactions While Programming Authors: Daiana Rinja, Eduardo Araujo Oliveira, Sonsoles López-Pernas, Mohammed Saqr, Marcus Specht, Kamila Misiejuk Published: 2026-04-29 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.27134v1 Generative AI is reshaping higher education programming through vibe coding, where students collaborate with AI via natural language rather than writing code line-by-line. We conceptualize this practice as help-seeking, analyzing 19,418 interaction turns from 110 undergraduate students. Using inductive coding and Heterogeneous Transition Network Analysis, we examined interaction sequences to compare top- and low-performing students. Results reveal that top performers engaged in instrumental help-seeking -- inquiry and exploration -- eliciting tutor-like AI responses. In contrast, low performers relied on executive help-seeking, frequently delegating tasks and prompting the AI to assume an executor role focused on ready-made solutions. These findings indicate that currently generative AI mirrors student intent (whether productive or passive) rather than optimizing for learning. To evolve from tools to teammates, AI systems must move beyond passive compliance. We argue for pedagogically aligned design that detect unproductive delegation and adaptively steer educational interactions toward inquiry, ensuring student-AI partnerships augment rather than replace cognitive effort. --- ### TRUST: A Framework for Decentralized AI Service v.0.1 Authors: Yu-Chao Huang, Zhen Tan, Mohan Zhang, Pingzhi Li, Zhuo Zhang, Tianlong Chen Published: 2026-04-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27132v1 Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and bias; (2) Scalability, as reasoning complexity creates bottlenecks; (3) Opacity, as hidden auditing erodes trust; and (4) Privacy, as exposed reasoning traces risk model theft. We introduce TRUST (Transparent, Robust, and Unified Services for Trustworthy AI), a decentralized framework with three innovations: (i) Hierarchical Directed Acyclic Graphs (HDAGs) that decompose Chain-of-Thought reasoning into five abstraction levels for parallel distributed auditing; (ii) the DAAN protocol, which projects multi-agent interactions into Causal Interaction Graphs (CIGs) for deterministic root-cause attribution; and (iii) a multi-tier consensus mechanism among computational checkers, LLM evaluators, and human experts with stake-weighted voting that guarantees correctness under 30% adversarial participation. We prove a Safety-Profitability Theorem ensuring honest auditors profit while malicious actors incur losses. All decisions are recorded on-chain, while privacy-by-design segmentation prevents reconstruction of proprietary logic. Across multiple LLMs and benchmarks, TRUST attains 72.4% accuracy (4-18% above baselines) and remains resilient against 20% corruption. DAAN reaches 70% root-cause attribution (vs. 54-63% for standard methods) with 60% token savings. Human studies validate the design (F1 = 0.89, Brier = 0.074). The framework supports (A1) decentralized auditing, (A2) tamper-proof leaderboards, (A3) trustless data annotation, and (A4) governed autonomous agents, pioneering decentralized AI auditing for safe, accountable deployment of reasoning-capable systems. --- ### Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics Authors: Haiyu Yang, Miel Hostens Published: 2026-04-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.27128v2 Foundation-model pipelines for individual-level livestock monitoring -- combining open-vocabulary detection, promptable video segmentation, and self-supervised visual embeddings -- have raised the accuracy ceiling of precision livestock farming (PLF), but their GPU memory budgets exceed the envelope of commodity edge accelerators. To close this gap, the 446M-parameter Perception Encoder (PE-ViT-L+) backbone of SAM 3 is distilled into a 40.66M-parameter multi-scale student through three mechanisms: a Feature Pyramid Network student encoder built on TinyViT-21M-512, a four-term direction-then-scale distillation loss, and backbone-substitution inference with sliding-window session pruning that bounds streaming GPU memory growth. The DINOv3 family includes a pre-distilled ViT-S/16 variant (21.6M parameters) released alongside a 6716M-parameter ViT-7B teacher; the ViT-S (21M) variant is adopted as the per-individual embedder. On the Edinburgh Pig dataset, the compressed pipeline reaches 92.29% MOTA and 96.15% IDF1 against the SAM 3 teacher (1.68- and 0.84-percentage-point losses), achieves a 7.77-fold reduction in system-level parameters and a 3.01-fold reduction in peak VRAM (19.52GB -> 6.49GB), and reaches 97.34% top-1 accuracy with 91.67% macro-F1 on nine-class pig behaviour classification. The pipeline fits inside an NVIDIA Jetson Orin NX 16GB envelope with 4.9GB of headroom, supporting a proposed -- but not yet empirically validated -- on-device embedding-pool re-identification mechanism whose per-individual footprint of approximately 94MB per animal per year produces a longitudinal visual record amenable to retrospective association with disease, lameness, reproductive, and growth outcome labels. --- ### Unsupervised Electrofacies Classification and Porosity Characterization in the Offshore Keta Basin Using Wireline Logs Authors: Hamdiya Adams, Theophilus Ansah-Narh, Daniel Kwadwo Asiedu, Bruce Kofi Banoeng-Yakubo, Marcellin Atemkeng, Thomas Armah, Richmond Opoku-Sarkodie, Rebecca Davis, Ezekiel Nii Noye Nortey Published: 2026-04-29 Categories: cs.AI, cs.CE, cs.LG, physics.geo-ph arXiv: https://arxiv.org/abs/2604.27126v1 This study presents an unsupervised machine learning workflow for electrofacies analysis in the offshore Keta Basin, Ghana, where core data are scarce. Six standard wireline logs from Well~C were analysed over a depth interval comprising approximately $11{,}195$ samples. K-means clustering was applied in multivariate log space, with the clustering structure evaluated using inertia and silhouette diagnostics. Four clusters were identified, supported by an average silhouette coefficient of approximately $0.50$, indicating moderate but meaningful separation. The resulting electrofacies exhibit systematic, depth-continuous patterns associated with variations in clay content, porosity, and rock framework properties, forming a geological continuum from shale-dominated to cleaner sandstone-dominated units. The results demonstrate that log-only, unsupervised clustering supported by quantitative metrics provides a robust and reproducible framework for subsurface characterisation. The proposed workflow offers a practical tool for early-stage formation evaluation in frontier offshore basins and a foundation for future integrated studies. --- ### Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models Authors: Vijay Sadashivaiah, Georgios Dasoulas, Judith Mueller, Soumya Ghosh Published: 2026-04-29 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2604.27124v1 Training stable biological foundation models requires rethinking attention mechanisms: we find that using sigmoid attention as a drop in replacement for softmax attention a) produces better learned representations: on six diverse single-cell datasets, sigmoid achieves 25% higher cell-type separation, better cell-type cohesion metrics, and lower validation loss, b) faster training, models with sigmoid attention train up to 10% faster than their softmax counterparts, and c) more stable training by eliminating inherent sources of instability in softmax attention. We establish that sigmoid attention has globally bounded derivatives ($\leq 0.25$) as opposed to softmax, and a diagonal Jacobian structure in contrast with softmax's dense coupling, which together help alleviate training instabilities. In stress tests on 160M-parameter bidirectional attention models trained without gradient clipping on 8K-token sequences, softmax diverges catastrophically, with gradients exploding by four orders of magnitude, while sigmoid remains stable. Finally, we implement and open-source TritonSigmoid, an efficient GPU kernel that achieves 515 TFLOPS on H100 GPUs, outperforming both FlashAttention-2 and FlashSigmoid, with native padding support, which is essential for biological sequences. Our results establish sigmoid attention as both theoretically grounded and empirically superior for biological foundation models. Code is available at https://github.com/MSDLLCpapers/triton-sigmoid --- ### InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification Authors: Shakeeb Murtaza, Aryan Shukla, Rajarshi Bhattacharya, Maguelonne Heritier, Eric Granger Published: 2026-04-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27122v2 Text-to-image person re-identification (TI-ReID) relies on natural-language text descriptions to retrieve top matching individuals from a gallery of reference images. While recent large vision-language models (VLMs) achieve strong retrieval performance, their decisions remain largely uninterpretable. Existing interpretability approaches in TI-ReID rely solely on slot-attention to highlight attended regions, but fail to reliably bind visual regions to semantically meaningful concepts, limiting interpretation to qualitative visualizations over a restricted vocabulary. This paper introduces InterPartAbility, an interpretable TI-ReID method that performs explicit part-wise matching and enables phrase-region grounding. Unlike parameter-heavy slot-attention methods that yield only qualitative interpretability, our open-vocabulary patch-phrase interaction module (PPIM) guides a standard TI-ReID model with concept-level phrases. Concept-based part phrases provide evidence that encourages the model to attend to the corresponding local image regions. InterPartAbility further leverages CLIP ViT self-attention to produce spatially concentrated patch activations aligned with each part-level phrase, yielding grounded explanation maps. Finally, a quantitative interpretability protocol for TI-ReID is introduced that extends current perturbation-based evaluation metrics into the TI-Reid domain. This includes a counterfactual region removal that measures retrieval degradation when top-ranked explanatory regions are removed. Empirical results on three challenging benchmarks show that InterPartAbility can achieve SOTA interpretability performance under these metrics, while sustaining competitive retrieval accuracy. --- ### PALCAS: A Priority-Aware Intelligent Lane Change Advisory System for Autonomous Vehicles using Federated Reinforcement Learning Authors: Yassine Ibork, Nhat Ha Nguyen, Myounggyu Won, Lokesh Das Published: 2026-04-29 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.27118v1 We present a priority-aware intelligent lane change advisory system based on multi-agent federated reinforcement learning, namely PALCAS, for autonomous vehicles (AVs). While existing lane-change approaches typically focus on single-agent systems or centralized multi-agent systems, we introduce a federated reinforcement learning-based multi-agent lane change system prioritizing lane changing based on vehicle destination urgency. PALCAS incorporates a novel priority-aware safe lane-change reward function to enable judicious lane-change decisions in both mandatory and discretionary scenarios. PALCAS leverages the parameterized deep Q-network (PDQN) algorithm to facilitate effective cooperation among agents, enabling both lateral and longitudinal motion controls of AVs. Extensive simulations conducted using the SUMO traffic simulator and Mosaic V2X communication framework demonstrate that PALCAS significantly improves traffic efficiency, driving safety, comfort, destination arrival rates, and merging success rates compared to baseline methods. --- ### A Gated Hybrid Contrastive Collaborative Filtering Recommendation Authors: Eduardo Ferreira da Silva, Mayki dos Santos Oliveira, Joel Machado Pires, Denis Dantas Boaventura, Maycon Maciel Peixoto, Cassio Serafim Prazeres, Gustavo Bittencourt Figueiredo, Miriam Capretz, Frederico Araujo Durão Published: 2026-04-29 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.27117v1 Recommender systems increasingly incorporate textual reviews to enrich user and item representations. However, most review-aware models remain optimized for rating prediction rather than ranking quality. This misalignment limits their effectiveness in top-N recommendation scenarios, where discriminative ranking is essential. To address this gap, we propose a Gated Hybrid Collaborative Filtering framework that integrates review-derived representations into an autoencoder-based collaborative model. The architecture injects semantic signals layer-wise through an adaptive gating mechanism that dynamically balances collaborative embeddings and topic-based features during encoding. To further refine the latent space, we introduce a contrastive learning module that aligns semantic and collaborative signals. We evaluate the framework across five distinct configurations: Pure collaborative; Topic and Gated; Text and Gated; and the addition of contrastive objectives (Contrastive and Topic, and Contrastive and Text). To explicitly optimize ranking behavior, the model is trained with a pairwise Bayesian personalized ranking objective, which promotes separation between relevant and non-relevant items in the latent space. Experiments on Amazon Movies & TV, IMDb, and Rotten Tomatoes demonstrate consistent improvements in hit rate @10 and normalized discounted cumulative gain @10 over state-of-the-art review-aware baselines. Results highlight the importance of controlled semantic fusion for ranking-driven recommendation. --- ### Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models Authors: M. K. Khalidi Siam, Md. Tausif-Ul-Islam, Md. Reshad Romim Khan, Mohammed Ali Hossain, Mushfiqul Amin, Labib Hasan Khan, Niloy Farhan, Farig Sadeque Published: 2026-04-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27115v1 Neuron pruning is widely used to reduce the computational cost and parameter footprint of large language models, yet it remains unclear whether neurons in task-specific models contribute uniformly to task performance. In this work, we provide empirical evidence for the existence and importance of task-specific neurons through a systematic pruning study on language models specialized for mathematical reasoning and code generation. We introduce an activation-based selectivity metric to identify neurons with low contribution to the target task and prune them while preserving target-task accuracy, and compare selective pruning with random pruning. Selective pruning consistently outperforms random pruning, indicating that activation-based selectivity provides a systematic advantage over random pruning. Reverse pruning experiments further show that removing a small subset of highly task-specific neurons (~10%) causes complete performance collapse, suggesting that there exist task specific neurons and critical task information is concentrated in a small portion of the network. In contrast, selective pruning of less critical neurons (~30% - ~35%) reduces accuracy but still preserves significant performance. We also observed consistent reductions in parameters and runtime VRAM usage, along with improved inference throughput as pruning increases. Experiments on both 1.5B and 7B models reveal a robustness threshold around 15-20% pruning, beyond which accuracy loss and generation failures increase sharply. Fine-tuning substantially recovers performance across pruning levels, particularly for aggressively pruned models. These findings provide empirical evidence of neuron specialization in task-specific language models and offer insights into pruning robustness, model redundancy, and post-pruning recoverability. --- ### Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations Authors: Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann, Christian Gumbsch, Zehao Wang, Muhammad Zubair Irshad, Fabien Despinoy, Rahaf Aljundi, Stratis Gavves, Sergey Zakharov Published: 2026-04-29 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.27106v1 Accurately reconstructing complex full multi-object scenes from sparse observations remains a core challenge in computer vision and a key step toward scalable and reliable simulation for robotics. In this work, we introduce RecGen, a generative framework for probabilistic joint estimation of object and part shapes, as well as their pose under occlusion and partial visibility from one or multiple RGB-D images. By leveraging compositional synthetic scene generation and strong 3D shape priors, RecGen generalizes across diverse object types and real-world environments. RecGen achieves state-of-the-art performance on complex, heavily occluded datasets, robustly handling severe occlusions, symmetric objects, object parts, and intricate geometry and texture. Despite using nearly 80% fewer training meshes than the previous state of the art SAM3D, RecGen outperforms it by 30.1% in geometric shape quality, 9.1% in texture reconstruction, and 33.9% in pose estimation. --- ### Automated Detection of Mutual Gaze and Joint Attention in Dual-Camera Settings via Dual-Stream Transformers Authors: Jakub Kosmydel, Paweł Gajewski, Arkadiusz Białek Published: 2026-04-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27105v1 Analyzing mutual gaze (MG) and joint attention (JA) is critical in developmental psychology but traditionally relies on labor-intensive manual coding. Automating this process in multi-camera laboratory settings is computationally challenging due to complex cross-camera relational dynamics. In this paper, we propose a highly efficient dual-stream Transformer architecture for detecting MG and JA from synchronized dual-camera recordings. Our approach leverages frozen gaze-aware backbones (GazeLLE) to extract rich visual priors, combined with a custom token fusion mechanism to map the spatial and semantic relationships between interacting dyads. Evaluated on an ecologically valid dataset of caregiver-infant interactions, our model exhibits good performance, significantly outperforming both a convolutional baseline and a state-of-the-art multimodal Large Language Model (LLM). By open-sourcing our model and pre-trained weights, we provide behavioral scientists with a scalable tool that can be fine-tuned to diverse laboratory environments, effectively bridging the gap between computational modeling and applied interaction research. --- ### Anomaly Detection in Soil Heavy Metal Contamination Using Unsupervised Learning for Environmental Risk Assessment Authors: Isaac Tettey Adjokatse, Samuel Senyo Koranteng, George Yamoah Afrifa, Theophilus Ansah-Narh, Marcellin Atemkeng, Joseph Bremang Tandoh, Kow Ahor Essel-Yorke, Richmond Opoku-Sarkodie, Rebecca Davis Published: 2026-04-29 Categories: cs.LG, cs.AI, physics.data-an, physics.geo-ph arXiv: https://arxiv.org/abs/2604.27102v1 Soil contamination by heavy metals poses a persistent environmental and public health concern in rapidly urbanising regions of Ghana, particularly at unregulated waste disposal sites. This study applies an unsupervised machine learning framework to detect and characterise anomalous heavy metal contamination patterns in soils from twelve waste sites and residential controls in the Central Region, of Ghana. Concentrations of eight metals (As, Cd, Cr, Cu, Hg, Ni, Pb, Zn) were analysed alongside standard health risk indices, including the Hazard Index (HI) and Incremental Lifetime Cancer Risk (ILCR). Isolation Forest and PCA reconstruction error each identified $12$ anomalous samples ($15.4\%$ of $78$ samples), while DBSCAN detected no density-isolated noise points. A consensus approach isolated six robust anomalies ($7.7\%)$, all spatially concentrated at a single site (S3). Anomalies exhibited approximately $70$--$80\%$ higher mean HI values than normal samples, with all consensus anomalies exceeding the HI$=1$ threshold. PCA reconstruction error showed a strong positive association with HI ($r \approx 0.8$), indicating consistency between multivariate deviation and health risk. Three distinct anomaly types were identified: extreme Cu enrichment at S3, anomalously low Ni at S4/S5, and moderate multi-metal (Pb--Zn) co-elevation at S9--S12. The results demonstrate that unsupervised machine learning provides granular, objective insight beyond aggregate indices, enabling targeted site prioritisation and risk-informed environmental management. --- ### Think it, Run it: Autonomous ML pipeline generation via self-healing multi-agent AI Authors: Adela Bara, Gabriela Dobrita, Simona-Vasilica Oprea Published: 2026-04-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27096v1 The purpose of our paper is to develop a unified multi-agent architecture that automates end-to-end machine learning (ML) pipeline generation from datasets and natural-language (NL) goals, improving efficiency, robustness and explainability. A five-agent system is proposed to handle profiling, intent parsing, microservice recommendation, Directed Acyclic Graph (DAG) construction and execution. It integrates code-grounded Retrieval-Augmented Generation (RAG) for microservice understanding, an explainable hybrid recommender combining multiple criteria, a self-healing mechanism using Large Language Model (LLM)-based error interpretation and adaptive learning from execution history. The approach is evaluated on 150 ML tasks across diverse scenarios. The system achieves an 84.7% end-to-end pipeline success rate, outperforming baseline methods. It demonstrates improved robustness through self-healing and reduces workflow development time compared to manual construction. The study introduces a novel integration of code-grounded RAG, explainable recommendation, self-healing execution and adaptive learning within a single architecture, showing that tightly coupled intelligent components can outperform isolated solutions. --- ### Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations Authors: Mingqian Zheng, Malia Morgan, Liwei Jiang, Carolyn Rose, Maarten Sap Published: 2026-04-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.27093v2 Current LLM safety alignment techniques improve model robustness against adversarial attacks, but overlook whether and how LLMs can recover helpfulness when benign users clarify their intent. We introduce CarryOnBench, the first interactive benchmark that measures whether LLMs can revise their interpretation of user intent and recover utility, while remaining safe through multi-turn conversations. Starting from 398 seemingly harmful queries with benign underlying intents, we simulate 5,970 conversations by varying user follow-up sequences, evaluating 14 models on both intent-aligned utility and safety. CarryOnBench yields 1,866 different conversation flows of 4--12 turns, totaling 23,880 model responses. We design Ben-Util, a checklist-based metric that evaluates how well each model response fulfills the user's benign information need using atomic items. At turn one, models fulfill only 10.5--37.6% of the user's benign information need. When the same query includes the benign intent upfront, models fulfill 25.1--72.1%, confirming that models withhold information due to intent misinterpretation, not limited knowledge. With benign clarifications in multi-turn conversations, 13 of 14 models approach or exceed this single-turn baseline, yet recovery cost varies across models. We identify two failure modes invisible to single-turn evaluations---unsafe recovery, where a model updates at disproportionate safety cost and redundant recovery, where a model recycles prior responses rather than providing new information. Moreover, conversations converge to similar harmfulness levels regardless of how conservative the model starts. These findings expose a gap that single-turn evaluations miss---whether a model is appropriately cautious or simply unresponsive to clarified user intent. --- ### Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations Authors: Mingqian Zheng, Malia Morgan, Liwei Jiang, Carolyn Rose, Maarten Sap Published: 2026-04-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.27093v1 Current LLM safety alignment techniques improve model robustness against adversarial attacks, but overlook whether and how LLMs can recover helpfulness when benign users clarify their intent. We introduce CarryOnBench, the first interactive benchmark that measures whether LLMs can revise their interpretation of user intent and recover utility, while remaining safe through multi-turn conversations. Starting from 398 seemingly harmful queries with benign underlying intents, we simulate 5,970 conversations by varying user follow-up sequences, evaluating 14 models on both intent-aligned utility and safety. CarryOnBench yields 1,866 different conversation flows of 4--12 turns, totaling 23,880 model responses. We design Ben-Util, a checklist-based metric that evaluates how well each model response fulfills the user's benign information need using atomic items. At turn one, models fulfill only 10.5--37.6% of the user's benign information need. When the same query includes the benign intent upfront, models fulfill 25.1--72.1%, confirming that models withhold information due to intent misinterpretation, not limited knowledge. With benign clarifications in multi-turn conversations, 13 of 14 models approach or exceed this single-turn baseline, yet recovery cost varies across models. We identify three failure modes invisible to single-turn evaluations: utility lock-in, where a model rarely updates despite clarification; unsafe recovery, where a model updates at disproportionate safety cost; and repetitive recovery, where a model recycles prior responses rather than providing new information. Moreover, conversations converge to similar harmfulness levels regardless of how conservative the model starts. These findings expose a gap that single-turn evaluations miss -- whether a model is appropriately cautious or simply unresponsive to clarified user intent. --- ### End-to-end autonomous scientific discovery on a real optical platform Authors: Shuxing Yang, Fujia Chen, Rui Zhao, Junyao Wu, Yize Wang, Haiyao Luo, Ning Han, Qiaolu Chen, Yuze Hu, Wenhao Li, Mingzhu Li, Hongsheng Chen et al. Published: 2026-04-29 Categories: cs.AI, physics.optics arXiv: https://arxiv.org/abs/2604.27092v1 Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods and claims as evidence accumulates. Although large language model (LLM)-based agents are beginning to move beyond assisting predefined research workflows, none has yet demonstrated end-to-end autonomous discovery in a real physical system that produces a nontrivial result supported by experimental evidence. Here we introduce Qiushi Discovery Engine, an LLM-based agentic system for end-to-end autonomous scientific discovery on a real optical platform. Qiushi Engine combines nonlinear research phases, Meta-Trace memory and a dual-layer architecture to maintain adaptive and stable research trajectories across long-horizon investigations involving thousands of LLM-mediated reasoning, measurement and revision actions. It autonomously reproduces a published transmission-matrix experiment on a non-original platform and converts an abstract coherence-order theory into experimental observables, providing, to our knowledge, the first observation of this class of coherence-order structure. More importantly, in an open-ended study involving 145.9 million tokens, 3,242 LLM calls, 1,242 tool calls, 163 research notes and 44 scripts, Qiushi Engine proposes and experimentally validates optical bilinear interaction, a physical mechanism structurally analogous to a core operation in Transformer attention. This AI-discovered mechanism suggests a route towards high-speed, energy-efficient optical hardware for pairwise computation. To our knowledge, this is the first demonstration of an AI agentic system autonomously identifying and experimentally validating a nontrivial, previously unreported physical mechanism, marking a milestone for research-level autonomous agents. --- ### AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence Parallelism Authors: Ahan Gupta, Zhihao Wang, Neel Dani, Masahiro Tanaka, Olatunji Ruwase, Minjia Zhang Published: 2026-04-29 Categories: cs.LG, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2604.27089v1 Large-language-models (LLMs) demonstrate enormous utility in long-context tasks which require processing prompts that consist of tens to hundreds of thousands of tokens. However, existing LLM training libraries do not provide easy to use abstractions to optimize for long-context training, instead focusing on optimizations for models with large parameter counts through ZeRO-3/FSDP, Tensor and Pipeline parallelism. This forces users to rewrite LLM training libraries to incorporate compositions of various complex long-context optimizations, such as sequence-parallelism, to training pipelines; a process that requires in-depth expertise, reducing developer productivity. To tackle these challenges, we introduce AutoSP: the first automated solution to automatically optimize LLM training for longer-contexts. AutoSP compiles models and applies a targeted set of optimizations: automated sequence parallelism, and long-context aware activation-checkpointing, to drastically enhance LLM trainability at negligible cost to throughput. Our evaluation demonstrates AutoSP's capability on both NVIDIA and AMD hardware, increasing training contexts by upto 2.7$\times$ and 2.5$\times$ respectively over competitive hand-written baseline at negligible cost to runtime performance. --- ### Efficient Training on Multiple Consumer GPUs with RoundPipe Authors: Yibin Luo, Shiwei Gao, Huichuan Zheng, Youyou Lu, Jiwu Shu Published: 2026-04-29 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.27085v1 Fine-tuning Large Language Models (LLMs) on consumer-grade GPUs is highly cost-effective, yet constrained by limited GPU memory and slow PCIe interconnects. Pipeline parallelism combined with CPU offloading mitigates these hardware bottlenecks by reducing communication overhead. However, existing PP schedules suffer from an inherent limitation termed the weight binding issue. Binding uneven model stages (e.g., the LM head is large) to GPUs limits the pipeline's throughput to that of the GPU with the heaviest load, leading to severe pipeline bubbles. In this paper, we propose RoundPipe, a novel pipeline schedule that breaks the weight binding constraint on consumer GPU servers. RoundPipe treats GPUs as a pool of stateless execution workers and dynamically dispatches computation stages across devices in a round-robin manner, achieving a near-zero-bubble pipeline. To ensure training correctness and system efficiency, RoundPipe integrates a priority-aware transfer scheduling engine, a fine-grained distributed event-based synchronization protocol, and an automated layer partitioning algorithm. Evaluations on an 8$\times$ RTX 4090 server demonstrate that RoundPipe achieves 1.48--2.16$\times$ speedups over state-of-the-art baselines when fine-tuning 1.7B to 32B models. Remarkably, RoundPipe enables LoRA fine-tuning of the Qwen3-235B model with 31K sequence length on a single server. RoundPipe is publicly available as an open-source Python library with comprehensive documentation. --- ### Co-Evolving Policy Distillation Authors: Naibin Gu, Chenxu Yang, Qingyi Si, Chuanyu Qin, Dingyu Yao, Peng Fu, Zheng Lin, Weiping Wang, Nan Duan, Jiaqi Wang Published: 2026-04-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27083v1 RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single model, identifying capability loss in different ways: mixed RLVR suffers from inter-capability divergence cost, while the pipeline of first training experts and then performing OPD, though avoiding divergence, fails to fully absorb teacher capabilities due to large behavioral pattern gaps between teacher and student. We propose Co-Evolving Policy Distillation (CoPD), which encourages parallel training of experts and introduces OPD during each expert's ongoing RLVR training rather than after complete expert training, with experts serving as mutual teachers (making OPD bidirectional) to co-evolve. This enables more consistent behavioral patterns among experts while maintaining sufficient complementary knowledge throughout. Experiments validate that CoPD achieves all-in-one integration of text, image, and video reasoning capabilities, significantly outperforming strong baselines such as mixed RLVR and MOPD, and even surpassing domain-specific experts. The model parallel training pattern offered by CoPD may inspire a novel training scaling paradigm. --- ### When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production Systems Authors: Emma Casey, David Roberts, David Sim, Ian Beaver Published: 2026-04-29 Categories: cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2604.27082v1 We present a framework for migrating production Large Language Model (LLM) based systems when the underlying model reaches end-of-life or requires replacement. The key contribution is a Bayesian statistical approach that calibrates automated evaluation metrics against human judgments, enabling confident model comparison even with limited manual evaluation data. We demonstrate this framework on a commercial question-answering system serving 5.3M monthly interactions across six global regions; evaluating correctness, refusal behavior, and stylistic adherence to successfully identify suitable replacement models. The framework is broadly applicable to any enterprise deploying LLM-based products, providing a principled, reproducible methodology for model migration that balances quality assurance with evaluation efficiency. This is a capability increasingly essential as the LLM ecosystem continues to evolve rapidly and organizations manage portfolios of AI-powered services across multiple models, regions, and use cases. --- ### Learning Rate Transfer in Normalized Transformers Authors: Boris Shigida, Boris Hanin, Andrey Gromov Published: 2026-04-29 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.27077v2 The Normalized Transformer, or nGPT (arXiv:2410.01131) achieves impressive training speedups and does not require weight decay or learning rate warmup. However, despite having hyperparameters that explicitly scale with model size, we observe that nGPT does not exhibit learning rate transfer across model dimension and token horizon. To rectify this, we combine numerical experiments with a principled use of alignment exponents (arXiv:2407.05872) to revisit and modify the $μ$P approach to hyperparameter transfer (arXiv:2011.14522). The result is a novel nGPT parameterization we call $ν$GPT. Through extensive empirical validation, we find $ν$GPT exhibits learning rate transfer across width, depth, and token horizon. --- ### Learning to Forget: Continual Learning with Adaptive Weight Decay Authors: Aditya A. Ramesh, Alex Lewandowski, Jürgen Schmidhuber Published: 2026-04-29 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2604.27063v1 Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowledge that is no longer needed, freeing up capacity to learn. Weight decay, viewed as a mechanism for forgetting, can serve this role by gradually discarding information stored in the weights. However, a fixed scalar weight decay drives this forgetting uniformly over time and uniformly across all parameters, even when some encode stable knowledge while others track rapidly changing targets. We introduce Forgetting through Adaptive Decay (FADE), which adapts per-parameter weight decay rates online via approximate meta-gradient descent. We derive FADE for the online linear setting and apply it to the final layer of neural networks. Our empirical analysis shows that FADE automatically discovers distinct decay rates for different parameters, complements step-size adaptation, and consistently improves over fixed weight decay across online tracking and streaming classification problems. --- ### Man, Machine, and Mathematics Authors: Akshunna S. Dogra Published: 2026-04-29 Categories: math.OC, cs.LG, math.DG arXiv: https://arxiv.org/abs/2604.27052v1 Nonlinear models and optimization methods have successfully tackled a rapidly growing set of problems in recent years. Indeed, a relatively small toolbox of such models and methods can provide sufficient performance across a large landscape of tasks: deep learning alone has made significant recent contributions in scientific modelling, natural language processing, visual analysis, etc. A similar relationship exists between physical theories and phenomena, where many applications and observations emerge neatly from remarkably minimal foundations. It is natural to wonder if sparse unified frameworks could be built to steer discussion and discovery in the fields concerned with learning, optimization, and modelling. In this work, we posit and examine a possible outline for such a unified theory, interpreting the notion of ''learning'' in a broad sense. In particular, we pursue our goals by viewing learning as an inter-connected process on multiple levels: problem setup, choosing methods, and the analysis of their interplay via imposed optimisation dynamics. We begin by proposing a precise yet versatile definition for ''solvable'' problems. We then define the ''parametrised methods'' by which their solution(s) may be ''learned''. Our goal is to sketch a ''universal convergence theorem'', specifying how and when solvable problems become amenable to the methods chosen for them. We find these constructions reduce the study of learning down to remarkably few ideas and tools - many of which are simply adapted from existing ones in dynamical systems theory, geometry, and fundamental physics. --- ### Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture Authors: Samuel L Pugh, Eric Yang, Alexander Muir Sutherland, Alessandra Breschi Published: 2026-04-29 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.27045v1 As Large Language Model (LLM) agents transition from single-session tools to persistent systems managing longitudinal healthcare journeys, their memory architectures face a critical challenge: reconciling two imperfect sources of truth. The patient's evolving self-report is current but prone to recall bias, while the Electronic Health Record (EHR) is medically validated but frequently stale. General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement, a pattern that risks safety failures when applied to clinical data. We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record (FHIR), governed by a dedicated Reconciliation Engine that evaluates every extracted memory against the patient's FHIR profile and classifies discrepancies by type, severity, and the specific FHIR resources involved. We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions, using a hybrid dataset that interleaves real provider-patient transcripts with synthetic, FHIR-grounded clinical scenarios. In isolated testing, the engine detects 84.4% of designed clinical discrepancies with 86.7% safety-critical recall. By coupling extraction and reconciliation evaluation on the same data, we directly quantify a 13.6% error cascade, tracing the degradation to clinical details lost during memory extraction from unstructured conversation rather than to downstream classification errors. These findings establish that validating patient-reported memories against clinical records is both feasible and necessary for safe deployment of longitudinal health agents. --- ### CL-bench Life: Can Language Models Learn from Real-Life Context? Authors: Shihan Dou, Yujiong Shen, Chenhao Huang, Junjie Ye, Jiayi Chen, Junzhe Wang, Qianyu He, Shichun Liu, Changze Lv, Jiahang Lin, Jiazheng Zhang, Ming Zhang et al. Published: 2026-04-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27043v1 Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life. --- ### Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling Authors: Zhen Zhang, Changyi Yang, Zijie Xia, Zhen Yang, Chengzhi Liu, Zhaotiao Weng, Yepeng Liu, Haobo Chen, Jin Pan, Chenyang Zhao, Yuheng Bu, Alkesh Patel et al. Published: 2026-04-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27039v2 Tokens are the fundamental units of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite its importance, existing approaches model length primarily at the coarse sequence level. We introduce the Length Value Model (LenVM), a token-level framework that estimates the remaining generation length at every decoding step. By formulating length modeling as a value estimation problem and assigning a constant negative reward to each generated token, LenVM predicts a bounded, discounted return that is a monotone proxy for the remaining generation horizon. This value formulation provides annotation-free, dense, unbiased, and scalable supervision. Experiments on LLMs and VLMs show that LenVM supports exact control, continuous performance--efficiency steering, length prediction, and interpretation. On LIFEBench-token, it raises the exact-length score of Qwen2.5-7B-Instruct from $30.9$ to $64.8$ in one pass and reaches $83.6$ when combined with LCG. Near $200$ tokens on GSM8K, LenVM retains about $63\%$ Pass@1 versus $6\%$ under a hard token budget. Across other settings, LenVM improves matched-length quality over prompting and EOS calibration, while its length-prediction accuracy improves with scale and exceeds specialized predictors. Its token-level values also identify markers of shifts between longer and shorter trajectories. These results establish generation length as an effective scalable token-level value signal for control, prediction, and future value-based training. ---