# Research Papers — 2026-01 · bundle page 20 of 189

> Full-text markdown of papers #951–1000 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/20
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/19.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/21.md)

### Failing to Explore: Language Models on Interactive Tasks

Authors: Mahdi JafariRaviz, Keivan Rezaei, Arshia Soltani Moakhar, Zahra Sodagar, Yize Cheng, Soheil Feizi
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22345v1

We evaluate language models on their ability to explore interactive environments under a limited interaction budget. We introduce three parametric tasks with controllable exploration difficulty, spanning continuous and discrete environments. Across state-of-the-art models, we find systematic under-exploration and suboptimal solutions, with performance often significantly worse than simple explore--exploit heuristic baselines and scaling weakly as the budget increases. Finally, we study two lightweight interventions: splitting a fixed budget into parallel executions, which surprisingly improves performance despite a no-gain theoretical result for our tasks, and periodically summarizing the interaction history, which preserves key discoveries and further improves exploration.

---

### Quantum-Inspired Reinforcement Learning for Secure and Sustainable AIoT-Driven Supply Chain Systems

Authors: Muhammad Bilal Akram Dastagir, Omer Tariq, Shahid Mumtaz, Saif Al-Kuwari, Ahmed Farouk
Published: 2026-01-29
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2601.22339v1

Modern supply chains must balance high-speed logistics with environmental impact and security constraints, prompting a surge of interest in AI-enabled Internet of Things (AIoT) solutions for global commerce. However, conventional supply chain optimization models often overlook crucial sustainability goals and cyber vulnerabilities, leaving systems susceptible to both ecological harm and malicious attacks. To tackle these challenges simultaneously, this work integrates a quantum-inspired reinforcement learning framework that unifies carbon footprint reduction, inventory management, and cryptographic-like security measures. We design a quantum-inspired reinforcement learning framework that couples a controllable spin-chain analogy with real-time AIoT signals and optimizes a multi-objective reward unifying fidelity, security, and carbon costs. The approach learns robust policies with stabilized training via value-based and ensemble updates, supported by window-normalized reward components to ensure commensurate scaling. In simulation, the method exhibits smooth convergence, strong late-episode performance, and graceful degradation under representative noise channels, outperforming standard learned and model-based references, highlighting its robust handling of real-time sustainability and risk demands. These findings reinforce the potential for quantum-inspired AIoT frameworks to drive secure, eco-conscious supply chain operations at scale, laying the groundwork for globally connected infrastructures that responsibly meet both consumer and environmental needs.

---

### From Retrieving Information to Reasoning with AI: Exploring Different Interaction Modalities to Support Human-AI Coordination in Clinical Decision-Making

Authors: Behnam Rahdari, Sameer Shaikh, Jonathan H Chen, Tobias Gerstenberg, Shriti Raj
Published: 2026-01-29
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.22338v1

LLMs are popular among clinicians for decision-support because of simple text-based interaction. However, their impact on clinicians' performance is ambiguous. Not knowing how clinicians use this new technology and how they compare it to traditional clinical decision-support systems (CDSS) restricts designing novel mechanisms that overcome existing tool limitations and enhance performance and experience. This qualitative study examines how clinicians (n=12) perceive different interaction modalities (text-based conversation with LLMs, interactive and static UI, and voice) for decision-support. In open-ended use of LLM-based tools, our participants took a tool-centric approach using them for information retrieval and confirmation with simple prompts instead of use as active deliberation partners that can handle complex questions. Critical engagement emerged with changes to the interaction setup. Engagement also differed with individual cognitive styles. Lastly, benefits and drawbacks of interaction with text, voice and traditional UIs for clinical decision-support show the lack of a one-size-fits-all interaction modality.

---

### Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models

Authors: Krishnakumar Balasubramanian, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan
Published: 2026-01-29
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2601.22336v1

Large-scale AI evaluation increasingly relies on aggregating binary judgments from $K$ annotators, including LLMs used as judges. Most classical methods, e.g., Dawid-Skene or (weighted) majority voting, assume annotators are conditionally independent given the true label $Y\in\{0,1\}$, an assumption often violated by LLM judges due to shared data, architectures, prompts, and failure modes. Ignoring such dependencies can yield miscalibrated posteriors and even confidently incorrect predictions. We study label aggregation through a hierarchy of dependence-aware models based on Ising graphical models and latent factors. For class-dependent Ising models, the Bayes log-odds is generally quadratic in votes; for class-independent couplings, it reduces to a linear weighted vote with correlation-adjusted parameters. We present finite-$K$ examples showing that methods based on conditional independence can flip the Bayes label despite matching per-annotator marginals. We prove separation results demonstrating that these methods remain strictly suboptimal as the number of judges grows, incurring nonvanishing excess risk under latent factors. Finally, we evaluate the proposed method on three real-world datasets, demonstrating improved performance over the classical baselines.

---

### Knowledge Gradient for Preference Learning

Authors: Kaiwen Wu, Jacob R. Gardner
Published: 2026-01-29
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.22335v1

The knowledge gradient is a popular acquisition function in Bayesian optimization (BO) for optimizing black-box objectives with noisy function evaluations. Many practical settings, however, allow only pairwise comparison queries, yielding a preferential BO problem where direct function evaluations are unavailable. Extending the knowledge gradient to preferential BO is hindered by its computational challenge. At its core, the look-ahead step in the preferential setting requires computing a non-Gaussian posterior, which was previously considered intractable. In this paper, we address this challenge by deriving an exact and analytical knowledge gradient for preferential BO. We show that the exact knowledge gradient performs strongly on a suite of benchmark problems, often outperforming existing acquisition functions. In addition, we also present a case study illustrating the limitation of the knowledge gradient in certain scenarios.

---

### DP-λCGD: Efficient Noise Correlation for Differentially Private Model Training

Authors: Nikita P. Kalinin, Ryan McKenna, Rasmus Pagh, Christoph H. Lampert
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22334v3

Differentially private stochastic gradient descent (DP-SGD) is the gold standard for training machine learning models with formal differential privacy guarantees. Several recent extensions improve its accuracy by introducing correlated noise across training iterations. Matrix factorization mechanisms are a prominent example, but they can require storing previously added noise vectors, leading to substantial memory overhead. In this work, we propose a new algorithm for correlated-noise private training that correlates noise only with the immediately preceding iteration and cancels a tunable portion of it. By regenerating the previous noise using a pseudorandom number generator rather than storing it, our method has essentially the same memory footprint as DP-SGD. We show that the computational overhead is minimal and empirically demonstrate improved accuracy over DP-SGD.

---

### Scalable Batch Correction for Cell Painting via Batch-Dependent Kernels and Adaptive Sampling

Authors: Aditya Narayan Ravi, Snehal Vadvalkar, Abhishek Pandey, Ilan Shomorony
Published: 2026-01-29
Categories: cs.LG, stat.CO
arXiv: https://arxiv.org/abs/2601.22331v1

Cell Painting is a microscopy-based, high-content imaging assay that produces rich morphological profiles of cells and can support drug discovery by quantifying cellular responses to chemical perturbations. At scale, however, Cell Painting data is strongly affected by batch effects arising from differences in laboratories, instruments, and protocols, which can obscure biological signal. We present BALANS (Batch Alignment via Local Affinities and Subsampling), a scalable batch-correction method that aligns samples across batches by constructing a smoothed affinity matrix from pairwise distances. Given $n$ data points, BALANS builds a sparse affinity matrix $A \in \mathbb{R}^{n \times n}$ using two ideas. (i) For points $i$ and $j$, it sets a local scale using the distance from $i$ to its $k$-th nearest neighbor within the batch of $j$, then computes $A_{ij}$ via a Gaussian kernel calibrated by these batch-aware local scales. (ii) Rather than forming all $n^2$ entries, BALANS uses an adaptive sampling procedure that prioritizes rows with low cumulative neighbor coverage and retains only the strongest affinities per row, yielding a sparse but informative approximation of $A$. We prove that this sampling strategy is order-optimal in sample complexity and provides an approximation guarantee, and we show that BALANS runs in nearly linear time in $n$. Experiments on diverse real-world Cell Painting datasets and controlled large-scale synthetic benchmarks demonstrate that BALANS scales to large collections while improving runtime over native implementations of widely used batch-correction methods, without sacrificing correction quality.

---

### Sparks of Rationality: Do Reasoning LLMs Align with Human Judgment and Choice?

Authors: Ala N. Tak, Amin Banayeeanzade, Anahita Bolourani, Fatemeh Bahrani, Ashutosh Chaubey, Sai Praneeth Karimireddy, Norbert Schwarz, Jonathan Gratch
Published: 2026-01-29
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.22329v1

Large Language Models (LLMs) are increasingly positioned as decision engines for hiring, healthcare, and economic judgment, yet real-world human judgment reflects a balance between rational deliberation and emotion-driven bias. If LLMs are to participate in high-stakes decisions or serve as models of human behavior, it is critical to assess whether they exhibit analogous patterns of (ir)rationalities and biases. To this end, we evaluate multiple LLM families on (i) benchmarks testing core axioms of rational choice and (ii) classic decision domains from behavioral economics and social norms where emotions are known to shape judgment and choice. Across settings, we show that deliberate "thinking" reliably improves rationality and pushes models toward expected-value maximization. To probe human-like affective distortions and their interaction with reasoning, we use two emotion-steering methods: in-context priming (ICP) and representation-level steering (RLS). ICP induces strong directional shifts that are often extreme and difficult to calibrate, whereas RLS produces more psychologically plausible patterns but with lower reliability. Our results suggest that the same mechanisms that improve rationality also amplify sensitivity to affective interventions, and that different steering methods trade off controllability against human-aligned behavior. Overall, this points to a tension between reasoning and affective steering, with implications for both human simulation and the safe deployment of LLM-based decision systems.

---

### Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations

Authors: Luca Muscarnera, Silas Ruhrberg Estévez, Samuel Holt, Evgeny Saveliev, Mihaela van der Schaar
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22328v3

Real-world scientific systems are rarely observed through complete, regularly sampled state trajectories. Instead, measurements are often partial, noisy, and heterogeneous, providing fragmented views of latent dynamical states. We introduce MAAT (Model Aware Approximation of Trajectories), a framework for knowledge-informed Kernel State Reconstruction in partially observed dynamical systems. MAAT formulates reconstruction in a reproducing kernel Hilbert space and incorporates heterogeneous observation operators together with semantic and structural priors, including non-negativity, conservation constraints, and domain-specific measurement models. This yields smooth, physically consistent state estimates with analytic time derivatives, providing a principled interface between fragmented measurements and downstream mechanistic discovery methods such as symbolic regression. Across nine scientific benchmarks, multiple noise regimes, and a real-world COVID-19 dataset, MAAT substantially reduces trajectory and derivative reconstruction error relative to strong baselines.

---

### Molecular Representations in Implicit Functional Space via Hyper-Networks

Authors: Zehong Wang, Xiaolong Han, Qi Yang, Xiangru Tang, Fang Wu, Xiaoguang Guo, Weixiang Sun, Tianyi Ma, Pietro Lio, Le Cong, Sheng Wang, Chuxu Zhang et al.
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22327v1

Molecular representations fundamentally shape how machine learning systems reason about molecular structure and physical properties. Most existing approaches adopt a discrete pipeline: molecules are encoded as sequences, graphs, or point clouds, mapped to fixed-dimensional embeddings, and then used for task-specific prediction. This paradigm treats molecules as discrete objects, despite their intrinsically continuous and field-like physical nature. We argue that molecular learning can instead be formulated as learning in function space. Specifically, we model each molecule as a continuous function over three-dimensional (3D) space and treat this molecular field as the primary object of representation. From this perspective, conventional molecular representations arise as particular sampling schemes of an underlying continuous object. We instantiate this formulation with MolField, a hyper-network-based framework that learns distributions over molecular fields. To ensure physical consistency, these functions are defined over canonicalized coordinates, yielding invariance to global SE(3) transformations. To enable learning directly over functions, we introduce a structured weight tokenization and train a sequence-based hyper-network to model a shared prior over molecular fields. We evaluate MolField on molecular dynamics and property prediction. Our results show that treating molecules as continuous functions fundamentally changes how molecular representations generalize across tasks and yields downstream behavior that is stable to how molecules are discretized or queried.

---

### Label-Efficient Monitoring of Classification Models via Stratified Importance Sampling

Authors: Lupo Marsigli, Angel Lopez de Haro
Published: 2026-01-29
Categories: cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2601.22326v1

Monitoring the performance of classification models in production is critical yet challenging due to strict labeling budgets, one-shot batch acquisition of labels and extremely low error rates. We propose a general framework based on Stratified Importance Sampling (SIS) that directly addresses these constraints in model monitoring. While SIS has previously been applied in specialized domains, our theoretical analysis establishes its broad applicability to the monitoring of classification models. Under mild conditions, SIS yields unbiased estimators with strict finite-sample mean squared error (MSE) improvements over both importance sampling (IS) and stratified random sampling (SRS). The framework does not rely on optimally defined proposal distributions or strata: even with noisy proxies and sub-optimal stratification, SIS can improve estimator efficiency compared to IS or SRS individually, though extreme proposal mismatch may limit these gains. Experiments across binary and multiclass tasks demonstrate consistent efficiency improvements under fixed label budgets, underscoring SIS as a principled, label-efficient, and operationally lightweight methodology for post-deployment model monitoring.

---

### Automatic Construction of Clinical Scoring Systems with LLM Agents

Authors: Silas Ruhrberg Estévez, Christopher Chiu, Mihaela van der Schaar
Published: 2026-01-29
Categories: cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2601.22324v3

Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable decision rules. While machine-learning models achieve strong performance, many fail to translate into routine clinical use due to misalignment with workflow constraints such as memorability, auditability, and bedside execution. We argue that this gap arises not from insufficient predictive power, but from optimizing over model classes that are incompatible with guideline deployment. Deployable guidelines often take the form of unit-weighted clinical checklists, formed by thresholding the sum of binary rules, but learning such scores requires searching an exponentially large discrete space of possible rule sets. We introduce AgentScore, which performs semantically guided optimization in this space by using LLMs to propose candidate rules and a deterministic, data-grounded verification-and-selection loop to enforce statistical validity and deployability constraints. Across eight clinical prediction tasks, AgentScore outperforms existing score-generation methods and achieves AUROC comparable to more flexible interpretable models despite operating under stronger structural constraints. On two additional externally validated tasks, AgentScore achieves higher discrimination than established guideline-based scores.

---

### Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning

Authors: Qi Cao, Shuhao Zhang, Ruizhe Zhou, Ruiyi Zhang, Peijia Qin, Pengtao Xie
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22323v2

Model routing chooses which language model to use for each query. By sending easy queries to cheaper models and hard queries to stronger ones, it can significantly reduce inference cost while maintaining high accuracy. However, most existing routers treat this as a fixed choice among a small set of models, which makes them hard to adapt to new models or changing budget constraints. In this paper, we propose SCOPE (Scalable and Controllable Outcome Performance Estimator), a routing framework that goes beyond model selection by predicting their cost and performance. Trained with reinforcement learning, SCOPE makes reasoning-based predictions by retrieving how models behave on similar problems, rather than relying on fixed model names, enabling it to work with new, unseen models. Moreover, by explicitly predicting how accurate and how expensive a model will be, it turns routing into a dynamic decision problem, allowing users to easily control the trade-off between accuracy and cost. Experiments show that SCOPE is more than just a cost-saving tool. It flexibly adapts to user needs: it can boost accuracy by up to 25.7% when performance is the priority, or cut costs by up to 95.1% when efficiency matters most.

---

### Spatially-Adaptive Conformal Graph Transformer for Indoor Localization in Wi-Fi Driven Networks

Authors: Ayesh Abu Lehyeh, Anastassia Gharib, Safwan Wshah
Published: 2026-01-29
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2601.22322v1

Indoor localization is a critical enabler for a wide range of location-based services in smart environments, including navigation, asset tracking, and safety-critical applications. Recent graph-based models leverage spatial relationships between Wire-less Fidelity (Wi-Fi) Access Points (APs) and devices, offering finer localization granularity, but fall short in quantifying prediction uncertainty, a key requirement for real-world deployment. In this paper, we propose Spatially-Adaptive Conformal Graph Transformer (SAC-GT), a framework for accurate and reliable indoor localization. SAC-GT integrates a Graph Transformer (GT) model that captures network's spatial topology and signal strength dynamics, with a novel Spatially-Adaptive Conformal Prediction (SACP) method that provides region-specific uncertainty estimates. This allows SAC-GT to produce not only precise two-dimensional (2D) location predictions but also statistically valid confidence regions tailored to varying environmental conditions. Extensive evaluations on a large-scale real-world dataset demonstrate that the proposed SAC-GT solution achieves state-of-the-art localization accuracy while delivering robust and spatially adaptive reliability guarantees.

---

### Matrix Factorization for Practical Continual Mean Estimation Under User-Level Differential Privacy

Authors: Nikita P. Kalinin, Ali Najar, Valentin Roth, Christoph H. Lampert
Published: 2026-01-29
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.22320v2

We study continual mean estimation, where data vectors arrive sequentially and the goal is to maintain accurate estimates of the running mean. We address this problem under user-level differential privacy, which protects each user's entire dataset even when they contribute multiple data points. Previous work on this problem has focused on pure differential privacy. While important, this approach limits applicability, as it leads to overly noisy estimates. In contrast, we analyze the problem under approximate differential privacy, adopting recent advances in the Matrix Factorization mechanism. We introduce a novel mean estimation specific factorization, which is both efficient and accurate, achieving asymptotically lower mean-squared error bounds in continual mean estimation under user-level differential privacy.

---

### Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations

Authors: Baris Askin, Shivam Patel, Anupam Nayak, Andrea Vigano, Jiin Woo, Gauri Joshi, Carlee Joe-Wong
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22318v1

Large language models (LLMs) are increasingly accessed as remotely hosted services by edge and enterprise clients that cannot run frontier models locally. Since models vary widely in capability and price, routing queries to models that balance quality and inference cost is essential. Existing router approaches assume access to centralized query-model evaluation data. However, these data are often fragmented across clients, such as end users and organizations, and are privacy-sensitive, which makes centralizing data infeasible. Additionally, per-client router training is ineffective since local evaluation data is limited and covers only a restricted query distribution and a biased subset of model evaluations. We introduce the first federated framework for LLM routing, enabling clients to learn a shared routing policy from local offline query-model evaluation data. Our framework supports both parametric multilayer perceptron router and nonparametric K-means router under heterogeneous client query distributions and non-uniform model coverage. Across two benchmarks, federated collaboration improves the accuracy-cost frontier over client-local routers, both via increased effective model coverage and better query generalization. Our theoretical results also validate that federated training reduces routing suboptimality.

---

### FlowSymm: Physics Aware, Symmetry Preserving Graph Attention for Network Flow Completion

Authors: Ege Demirci, Francesco Bullo, Ananthram Swami, Ambuj Singh
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22317v2

Recovering missing flows on the edges of a network, while exactly respecting local conservation laws, is a fundamental inverse problem that arises in many systems such as transportation, energy, and mobility. We introduce FlowSymm, a novel architecture that combines (i) a group-action on divergence-free flows, (ii) a graph-attention encoder to learn feature-conditioned weights over these symmetry-preserving actions, and (iii) a lightweight Tikhonov refinement solved via implicit bilevel optimization. The method first anchors the given observation on a minimum-norm divergence-free completion. We then compute an orthonormal basis for all admissible group actions that leave the observed flows invariant and parameterize the valid solution subspace, which shows an Abelian group structure under vector addition. A stack of GATv2 layers then encodes the graph and its edge features into per-edge embeddings, which are pooled over the missing edges and produce per-basis attention weights. This attention-guided process selects a set of physics-aware group actions that preserve the observed flows. Finally, a scalar Tikhonov penalty refines the missing entries via a convex least-squares solver, with gradients propagated implicitly through Cholesky factorization. Across three real-world flow benchmarks (traffic, power, bike), FlowSymm outperforms state-of-the-art baselines in RMSE, MAE and correlation metrics.

---

### Gaussian Process Bandit Optimization with Machine Learning Predictions and Application to Hypothesis Generation

Authors: Xin Jennifer Chen, Yunjin Tong
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22315v1

Many real-world optimization problems involve an expensive ground-truth oracle (e.g., human evaluation, physical experiments) and a cheap, low-fidelity prediction oracle (e.g., machine learning models, simulations). Meanwhile, abundant offline data (e.g., past experiments and predictions) are often available and can be used to pretrain powerful predictive models, as well as to provide an informative prior. We propose Prediction-Augmented Gaussian Process Upper Confidence Bound (PA-GP-UCB), a novel Bayesian optimization algorithm that leverages both oracles and offline data to achieve provable gains in sample efficiency for the ground-truth oracle queries. PA-GP-UCB employs a control-variates estimator derived from a joint Gaussian process posterior to correct prediction bias and reduce uncertainty. We prove that PA-GP-UCB preserves the standard regret rate of GP-UCB while achieving a strictly smaller leading constant that is explicitly controlled by prediction quality and offline data coverage. Empirically, PA-GP-UCB converges faster than Vanilla GP-UCB and naive prediction-augmented GP-UCB baselines on synthetic benchmarks and on a real-world hypothesis evaluation task grounded in human behavioral data, where predictions are provided by large language models. These results establish PA-GP-UCB as a general and sample-efficient framework for hypothesis generation under expensive feedback.

---

### Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment

Authors: Yavuz Bakman, Duygu Nur Yaldiz, Eleni Triantafillou, Peter Kairouz, Salman Avestimehr, Sai Praneeth Karimireddy
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22313v2

Large Language Models (LLMs) are rarely static and are frequently updated in practice. A growing body of alignment research has shown that models initially deemed ``aligned'' can exhibit misaligned behavior after fine-tuning. These works typically assume that the initial model is aligned based on static black-box evaluation, i.e., the absence of undesired responses to a fixed set of queries. However, the limits of black-box evaluation for post-update scenarios is not explored sufficiently. In this work, we formalize model alignment in both the static and post-update settings and uncover a fundamental limitation of black-box evaluation. We theoretically show that, due to overparameterization, static alignment provides no guarantee of post-update alignment for any update dataset. Moreover, we prove that static black-box probing cannot distinguish a model that is genuinely post-update robust from one that conceals an arbitrary amount of adversarial behavior which can be activated by even a single benign gradient update. We further validate these findings empirically in LLMs across three core alignment domains: privacy, jailbreak safety, and behavioral honesty. We demonstrate the existence of LLMs that pass all standard black-box alignment tests, yet become severely misaligned after a single benign update. Finally, we show that the capacity to hide such latent adversarial behavior increases with model scale, confirming our theoretical prediction that post-update misalignment grows with the number of parameters. Together, our results highlight the inadequacy of static evaluation protocols and emphasize the urgent need for post-update--robust alignment evaluation. Code can be found at: https://github.com/Ybakman/safety_benign_update.

---

### SCALAR: Quantifying Structural Hallucination, Consistency, and Reasoning Gaps in Materials Foundation Models

Authors: Can Polat, Erchin Serpedin, Mustafa Kurban, Hasan Kurban
Published: 2026-01-29
Categories: cs.LG, cond-mat.mtrl-sci, cs.CE
arXiv: https://arxiv.org/abs/2601.22312v1

Large language models are increasingly applied to materials science reasoning, yet their behavior under physically structured distribution shifts remains poorly understood. We introduce SCALAR (Structural Consistency And Logic Across Regimes), a benchmark for evaluating geometric scale generalization and its connection to structural hallucination, consistency, and reasoning in materials foundation models. Given canonical crystal representations, models must reason about derived nanoparticle structures obtained through supercell expansion and geometric truncation across length scales spanning a few atoms to over 18,000 atoms, totaling $\approx$100,000 structures from DFT-validated unit cells. SCALAR defines three tasks. (i) CIF to property prediction. (ii) A Chain-of-Thought variant with explicit physics-grounded reasoning. (iii) Inverse retrieval identifying crystals from candidates given target properties. Outputs are evaluated via structured metrics capturing numeric error, hallucination, cross-prompt consistency, monotonic reasoning, output validity, and retrieval regret. Experiments across diverse foundation models reveal large, model-dependent shifts under explicit reasoning, often reducing hallucination and error, but frequently destabilizing consistency or validity. These results demonstrate that geometric scale generalization cannot be inferred from accuracy alone. Supplementary materials are available at https://github.com/KurbanIntelligenceLab/SCALAR.

---

### Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents

Authors: Zehong Wang, Fang Wu, Hongru Wang, Xiangru Tang, Bolian Li, Zhenfei Yin, Yijun Ma, Yiyang Li, Weixiang Sun, Xiusi Chen, Yanfang Ye
Published: 2026-01-29
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.22311v1

Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horizons. We argue that this failure reflects a fundamental mismatch: step-wise reasoning induces a form of step-wise greedy policy that is adequate for short horizons but fails in long-horizon planning, where early actions must account for delayed consequences. From this planning-centric perspective, we study LLM-based agents in deterministic, fully structured environments with explicit state transitions and evaluation signals. Our analysis reveals a core failure mode of reasoning-based policies: locally optimal choices induced by step-wise scoring lead to early myopic commitments that are systematically amplified over time and difficult to recover from. We introduce FLARE (Future-aware Lookahead with Reward Estimation) as a minimal instantiation of future-aware planning to enforce explicit lookahead, value propagation, and limited commitment in a single model, allowing downstream outcomes to influence early decisions. Across multiple benchmarks, agent frameworks, and LLM backbones, FLARE consistently improves task performance and planning-level behavior, frequently allowing LLaMA-8B with FLARE to outperform GPT-4o with standard step-by-step reasoning. These results establish a clear distinction between reasoning and planning.

---

### Stealthy Poisoning Attacks Bypass Defenses in Regression Settings

Authors: Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer, Emil C. Lupu
Published: 2026-01-29
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2601.22308v2

Regression models are widely used in industrial processes, engineering, and in natural and physical sciences, yet their robustness to poisoning has received less attention. When it has, studies often assume unrealistic threat models and are thus less useful in practice. In this paper, we propose a novel optimal stealthy attack formulation that considers different degrees of detectability and show that it bypasses state-of-the-art defenses. We further propose a new methodology based on normalization of objectives to evaluate different trade-offs between effectiveness and detectability. Finally, we develop a novel defense (BayesClean) against stealthy attacks. BayesClean improves on previous defenses when attacks are stealthy and the number of poisoning points is significant.

---

### Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method

Authors: Simon Kuang, Xinfan Lin
Published: 2026-01-29
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2601.22307v2

We study the problem of propagating the mean and covariance of a general multivariate Gaussian distribution through a deep (residual) neural network using layer-by-layer moment matching. We close a longstanding gap by deriving exact moment matching for the probit, GeLU, ReLU (as a limit of GeLU), Heaviside (as a limit of probit), and sine activation functions; for both feedforward and generalized residual layers. On random networks, we find orders-of-magnitude improvements in the KL divergence error metric, up to a millionfold, over popular alternatives. On a variational Bayes neural network, we show that our method attains hundredfold improvements in KL divergence from Monte Carlo ground truth over a state-of-the-art deterministic inference method. We also give a smooth-distance error bound showing that, under regularity assumptions, moment matching removes the leading low-variance errors and propagates higher-order local accuracy through the layers of a network.

---

### Sylber 2.0: A Universal Syllable Embedding

Authors: Cheol Jun Cho, Nicholas Lee, Alan W Black, Gopala K. Anumanchipalli
Published: 2026-01-29
Categories: eess.AS, cs.CL
arXiv: https://arxiv.org/abs/2601.22306v1

Scaling spoken language modeling requires speech tokens that are both efficient and universal. Recent work has proposed syllables as promising speech tokens at low temporal resolution, but existing models are constrained to English and fail to capture sufficient acoustic detail. To address this gap, we present Sylber 2.0, a self-supervised framework for coding speech at the syllable level that enables efficient temporal compression and high-fidelity reconstruction. Sylber 2.0 achieves a very low token frequency around 5 Hz, while retaining both linguistic and acoustic detail across multiple languages and expressive styles. Experiments show that it performs on par with previous models operating on high-frequency baselines. Furthermore, Sylber 2.0 enables efficient TTS modeling which can generate speech with competitive intelligibility and quality with SOTA models using only 72M parameters. Moreover, the universality of Sylber 2.0 provides more effective features for low resource ASR than previous speech coding frameworks. In sum, we establish an effective syllable-level abstraction for general spoken language.

---

### BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation

Authors: Bo Yuan, Yun Zhou, Zhichao Xu, Kiran Ramnath, Aosong Feng, Balasubramaniam Srinivasan
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22305v1

Automatic workflow generation is the process of automatically synthesizing sequences of LLM calls, tool invocations, and post-processing steps for complex end-to-end tasks. Most prior methods cast this task as an optimization problem with limited theoretical grounding. We propose to cast workflow generation as Bayesian inference over a posterior distribution on workflows, and introduce \textbf{Bayesian Workflow Generation (BWG)}, a sampling framework that builds workflows step-by-step using parallel look-ahead rollouts for importance weighting and a sequential in-loop refiner for pool-wide improvements. We prove that, without the refiner, the weighted empirical distribution converges to the target posterior. We instantiate BWG as \textbf{BayesFlow}, a training-free algorithm for workflow construction. Across six benchmark datasets, BayesFlow improves accuracy by up to 9 percentage points over SOTA workflow generation baselines and by up to 65 percentage points over zero-shot prompting, establishing BWG as a principled upgrade to search-based workflow design. Code will be available on https://github.com/BoYuanVisionary/BayesFlow.

---

### ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learning

Authors: Amirhossein Taherpour, Xiaodong Wang
Published: 2026-01-29
Categories: cs.LG, cs.CR, cs.DC
arXiv: https://arxiv.org/abs/2601.22302v1

Federated learning (FL) enables collaborative model training while preserving data privacy, yet both centralized and decentralized approaches face challenges in scalability, security, and update validation. We propose ZK-HybridFL, a secure decentralized FL framework that integrates a directed acyclic graph (DAG) ledger with dedicated sidechains and zero-knowledge proofs (ZKPs) for privacy-preserving model validation. The framework uses event-driven smart contracts and an oracle-assisted sidechain to verify local model updates without exposing sensitive data. A built-in challenge mechanism efficiently detects adversarial behavior. In experiments on image classification and language modeling tasks, ZK-HybridFL achieves faster convergence, higher accuracy, lower perplexity, and reduced latency compared to Blade-FL and ChainFL. It remains robust against substantial fractions of adversarial and idle nodes, supports sub-second on-chain verification with efficient gas usage, and prevents invalid updates and orphanage-style attacks. This makes ZK-HybridFL a scalable and secure solution for decentralized FL across diverse environments.

---

### Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes

Authors: Gonzalo Gomez-Nogales, Yicong Hong, Chongjian Ge, Peiye Zhuang, Marc Comino-Trinidad, Dan Casas, Yi Zhou
Published: 2026-01-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22301v3

Traditional rendering pipelines rely on complex assets, accurate materials and lighting, and substantial computational resources to produce realistic imagery, yet they still face challenges in scalability and realism for populated dynamic scenes. We present C2R (Coarse-to-Real), a generative rendering framework that synthesizes real-style urban crowd videos from coarse 3D simulations. Our approach uses coarse 3D renderings to explicitly control scene layout, camera motion, and human trajectories, while a learned neural renderer generates realistic appearance, lighting, and fine-scale dynamics guided by text prompts. To overcome the lack of paired training data between coarse simulations and real videos, we adopt a two-stage synthetic-real domain-hedging strategy that first learns a strong generative prior from large-scale real footage, and then introduces controllability by using a small amount of paired synthetic coarse-to-fine data to anchor shared implicit spatio-temporal features across domains. The resulting system supports coarse-to-fine control, generalizes across diverse CG and game inputs, and produces temporally consistent, controllable, and realistic urban scene videos from minimal 3D input. We will release the model and project webpage at https://gonzalognogales.github.io/coarse2real/.

---

### Toward all-optical unsupervised Hebbian learning in deep photonic neuromorphic networks

Authors: Xi Li, Disha Biswas, Peng Zhou, Wesley H. Brigner, Anna Capuano, Joseph S. Friedman, Qing Gu
Published: 2026-01-29
Categories: physics.optics, cond-mat.dis-nn, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2601.22300v4

We propose a deep photonic neuromorphic network (PNN) architecture based on phase-change material (PCM) synapses and local optical feedback for online, unsupervised Hebbian learning. The proposed architecture combines optical vector-matrix multiplication, non-volatile PCM synaptic weighting, and local coincidence-driven synaptic adaptation within a multilayer photonic crossbar framework compatible with photonic integrated circuits. Unlike conventional PNNs that rely on externally computed gradients, repeated optical-electrical-optical conversions, or global backpropagation, the proposed framework employs local Hebbian learning governed directly by correlated pre- and post-synaptic optical activity. To investigate the feasibility of the proposed learning mechanism, we implemented the PNN design using fiber-optic components, programmable variable optical attenuators, and real-time software control that incorporates PCM thermal dynamics. Supervised and unsupervised learning behaviors were experimentally evaluated under both offline and online learning conditions using representative image-recognition tasks. The experimental results demonstrate adaptive synaptic evolution, successful optical inference, and autonomous pattern encoding through local Hebbian learning under realistic fiber-optic hardware conditions. These results establish a pathway toward future integrated photonic neuromorphic systems capable of scalable and energy-efficient online Hebbian learning.

---

### Conformal Prediction for Generative Models via Adaptive Cluster-Based Density Estimation

Authors: Qidong Yang, Qianyu Julie Zhu, Jonathan Giezendanner, Youssef Marzouk, Stephen Bates, Sherrie Wang
Published: 2026-01-29
Categories: cs.LG, cs.AI, physics.ao-ph
arXiv: https://arxiv.org/abs/2601.22298v1

Conditional generative models map input variables to complex, high-dimensional distributions, enabling realistic sample generation in a diverse set of domains. A critical challenge with these models is the absence of calibrated uncertainty, which undermines trust in individual outputs for high-stakes applications. To address this issue, we propose a systematic conformal prediction approach tailored to conditional generative models, leveraging density estimation on model-generated samples. We introduce a novel method called CP4Gen, which utilizes clustering-based density estimation to construct prediction sets that are less sensitive to outliers, more interpretable, and of lower structural complexity than existing methods. Extensive experiments on synthetic datasets and real-world applications, including climate emulation tasks, demonstrate that CP4Gen consistently achieves superior performance in terms of prediction set volume and structural simplicity. Our approach offers practitioners a powerful tool for uncertainty estimation associated with conditional generative models, particularly in scenarios demanding rigorous and interpretable prediction sets.

---

### Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate

Authors: Chenxi Liu, Yanshuo Chen, Ruibo Chen, Tianyi Xiong, Tong Zheng, Heng Huang
Published: 2026-01-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22297v2

The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reasoning through Multi-Agent Debate (MAD) has emerged as a promising approach for enhancing LLM performance. However, current RLVR methods typically train LLMs to solve problems in isolation, without explicitly preparing them to synthesize and benefit from different rationales that arise during debate. In this work, we propose Self-Debate Reinforcement Learning(SDRL), a training framework where models learn from self-debate, equipping a single LLM with both strong standalone problem-solving ability and the capability to process diverse reasoning trajectories in MAD. Given a prompt, SDRL first samples multiple candidate solutions, then constructs a debate context with diverse reasoning paths and generates second-turn responses conditioned on this context. Finally, SDRL jointly optimizes both the initial and debate-conditioned responses, yielding a model that is effective as both a standalone solver and a debate participant. Experiments across multiple base models and reasoning benchmarks show that SDRL consistently improves MAD performance across diverse debate protocols and agent configurations, while simultaneously strengthening single-model reasoning.

---

### ParalESN: Enabling parallel information processing in Reservoir Computing

Authors: Matteo Pinna, Giacomo Lagomarsini, Andrea Ceni, Claudio Gallicchio
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22296v2

Reservoir Computing (RC) has established itself as an efficient paradigm for temporal processing. However, its scalability remains severely constrained by the need to process temporal data sequentially and the prohibitive memory footprint of high-dimensional reservoirs. To address these limitations, we revisit RC through the lens of structured operators and state space modeling, introducing Parallel Echo State Network (ParalESN). Leveraging diagonal linear recurrence in the complex domain, ParalESN enables parallel processing of temporal data and the construction of efficient, high-dimensional reservoirs. A thorough theoretical analysis demonstrates that the Echo State Property and the universality guarantees of traditional Echo State Networks are preserved, while also admitting an equivalent representation of arbitrary linear reservoirs in the complex diagonal form. Empirically, ParalESN achieves competitive predictive accuracy with traditional RC and with fully trainable sequence models, while delivering computational savings by orders of magnitude. Overall, ParalESN offers a scalable and principled pathway for integrating RC within the deep learning landscape.

---

### Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas

Authors: Manuela Chacon-Chamorro, Luis Felipe Giraldo, Nicanor Quijano
Published: 2026-01-29
Categories: cs.MA, cs.LG
arXiv: https://arxiv.org/abs/2601.22292v2

Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-being, making these systems highly vulnerable to collapse under disruptions. In this context, this work studies cooperative resilience, understood as the system-level ability to maintain collective well-being under perturbations through adaptive agent behavior. We propose a framework for learning incentive structures aligned with collective well-being in multi-agent reinforcement learning systems, where reward functions shape individual decision-making and collective behavior. A resilience metric is used to score and rank agent trajectories, allowing the inference of reward functions that promote resilient collective behavior. These inferred reward functions are integrated into the multi-agent reinforcement learning process to shape agent interactions in social dilemma settings. The approach is evaluated in resource-sharing environments subject to disruptions, using three incentive structures: individual incentives, resilience-aligned incentives, and a hybrid incentive structure that combines both individual and collective components. The results show that the hybrid incentive structure promotes sustained collective behavior, reduces collapse events associated with resource depletion, and preserves system performance under disruption. These findings highlight the role of incentive design as a mechanism for promoting resilient collective behavior and provide a computational framework for multi-agent social dilemmas under disruptions.

---

### The Six Sigma Agent: Achieving Enterprise-Grade Reliability in LLM Systems Through Consensus-Driven Decomposed Execution

Authors: Khush Patel, Siva Surendira, Jithin George, Shreyas Kapale
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22290v1

Large Language Models demonstrate remarkable capabilities yet remain fundamentally probabilistic, presenting critical reliability challenges for enterprise deployment. We introduce the Six Sigma Agent, a novel architecture that achieves enterprise-grade reliability through three synergistic components: (1) task decomposition into a dependency tree of atomic actions; (2) micro-agent sampling where each task is executed n times in parallel across diverse LLMs to generate independent outputs; and (3) consensus voting with dynamic scaling, clustering outputs and selecting the answer from the winning cluster with maximum votes. We prove that sampling n independent outputs with error rate p achieves system error O(p^{ceil(n/2)}), enabling exponential reliability gains. Even using cheaper models with 5% per-action error, consensus voting with 5 agents reduces error to 0.11%; dynamic scaling to 13 agents achieves 3.4 DPMO (Defects Per Million Opportunities), the Six Sigma standard. Evaluation across three enterprise use cases demonstrates a 14,700x reliability improvement over single-agent execution while reducing costs by 80%. Our work establishes that reliability in AI systems emerges from principled redundancy and consensus rather than model scaling alone.

---

### PersonaCite: VoC-Grounded Interviewable Agentic Synthetic AI Personas for Verifiable User and Design Research

Authors: Mario Truss
Published: 2026-01-29
Categories: cs.HC, cs.AI, eess.AS, eess.IV
arXiv: https://arxiv.org/abs/2601.22288v1

LLM-based and agent-based synthetic personas are increasingly used in design and product decision-making, yet prior work shows that prompt-based personas often produce persuasive but unverifiable responses that obscure their evidentiary basis. We present PersonaCite, an agentic system that reframes AI personas as evidence-bounded research instruments through retrieval-augmented interaction. Unlike prior approaches that rely on prompt-based roleplaying, PersonaCite retrieves actual voice-of-customer artifacts during each conversation turn, constrains responses to retrieved evidence, explicitly abstains when evidence is missing, and provides response-level source attribution. Through semi-structured interviews and deployment study with 14 industry experts, we identify preliminary findings on perceived benefits, validity concerns, and design tensions, and propose Persona Provenance Cards as a documentation pattern for responsible AI persona use in human-centered design workflows.

---

### Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success

Authors: Luca Zhou, Bo Zhao, Rose Yu, Emanuele Rodolà
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22285v9

Model merging combines knowledge from separately fine-tuned models, yet the factors driving its success remain poorly understood. While recent work treats mergeability as an intrinsic property of the models, we show with an architecture-agnostic framework that it fundamentally depends on both the merging method and the partner tasks. Using L1-regularized linear optimization over a set of interpretable pairwise metrics (e.g., gradient L_2 distance), we uncover properties correlating with post-merge normalized accuracy across five merging methods. We find architecture- and method-specific variation in success drivers (64.0% average top-5 metric overlap; 79.3% sign agreement), with certain methods, notably TIES, exhibiting distinct ``fingerprints'' that diverge from the broader consensus. Crucially, however, gradient alignment metrics consistently emerge as the most fundamental signals of compatibility. These findings provide a diagnostic foundation for understanding mergeability and motivate future merge-aware fine-tuning strategies.

---

### Riemannian Lyapunov Optimizer: A Unified Framework for Optimization

Authors: Yixuan Wang, Omkar Sudhir Patil, Warren E. Dixon
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22284v1

We introduce Riemannian Lyapunov Optimizers (RLOs), a family of optimization algorithms that unifies classic optimizers within one geometric framework. Unlike heuristic improvements to existing optimizers, RLOs are systematically derived from a novel control-theoretic framework that reinterprets optimization as an extended state discrete-time controlled dynamical system on a Riemannian parameter manifold. Central to this framework is the identification of a Normally Attracting Invariant Manifold (NAIM), which organizes training dynamics into two distinct stages: rapid alignment of the speed state to a target graph, followed by controlled evolution within it. We formalize this by constructing a strict Lyapunov function that certifies convergence to a target manifold. This perspective yields a constructive ``optimizer generator" that not only recovers classic algorithms but enables the principled design of RLOs. We validate our theory via geometric diagnostics and demonstrate that grounding optimizer design in control theory yields state-of-the-art performance in large-scale benchmarks. Overall, RLOs bridge control theory and modern machine learning optimization, providing a unified language and a systematic toolkit for designing stable, effective optimizers.

---

### SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models

Authors: Mingyu Lu, Soham Gadgil, Chris Lin, Chanwoo Kim, Su-In Lee
Published: 2026-01-29
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2601.22276v2

As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data marketplaces. While the Shapley value offers a theoretically grounded approach to attribution, it faces a dual computational bottleneck: (i) the prohibitive cost of exhaustive model retraining for each sampled subset of players (i.e., data contributors) and (ii) the combinatorial number of subsets needed to estimate marginal contributions due to contributor interactions. To this end, we propose SurrogateSHAP, a retraining-free framework that approximates the expensive retraining game through inference from a pretrained model. To further improve efficiency, we employ a gradient-boosted tree to approximate the utility function and derive Shapley values analytically from the tree-based model. We evaluate SurrogateSHAP across three diverse attribution tasks: (i) image quality for DDPM-CFG on CIFAR-20, (ii) aesthetics for Stable Diffusion on Post-Impressionist artworks, and (iii) product diversity for FLUX.1 on Fashion-Product data. Across settings, SurrogateSHAP outperforms prior methods while substantially reducing computational overhead, consistently identifying influential contributors across multiple utility metrics. Finally, we demonstrate that SurrogateSHAP effectively localizes data sources responsible for spurious correlations in clinical images, providing a scalable path toward auditing safety-critical generative models.

---

### VMonarch: Efficient Video Diffusion Transformers with Structured Attention

Authors: Cheng Liang, Haoxian Chen, Liang Hou, Qi Fan, Gangshan Wu, Xin Tao, Limin Wang
Published: 2026-01-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22275v1

The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiTs can be naturally represented by the Monarch matrix. It is a class of structured matrices with flexible sparsity, enabling sub-quadratic attention via an alternating minimization algorithm. Accordingly, we propose VMonarch, a novel attention mechanism for Video DiTs that enables efficient computation over the dynamic sparse patterns with structured Monarch matrices. First, we adapt spatio-temporal Monarch factorization to explicitly capture the intra-frame and inter-frame correlations of the video data. Second, we introduce a recomputation strategy to mitigate artifacts arising from instabilities during alternating minimization of Monarch matrices. Third, we propose a novel online entropy algorithm fused into FlashAttention, enabling fast Monarch matrix updates for long sequences. Extensive experiments demonstrate that VMonarch achieves comparable or superior generation quality to full attention on VBench after minimal tuning. It overcomes the attention bottleneck in Video DiTs, reduces attention FLOPs by a factor of 17.5, and achieves a speedup of over 5x in attention computation for long videos, surpassing state-of-the-art sparse attention methods at 90% sparsity.

---

### Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfer

Authors: Longtao Xu, Jian Li
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22274v2

Real-world federated systems seldom operate on static data: input distributions drift while privacy rules forbid raw-data sharing. We study this setting as Federated Domain-Incremental Learning (FDIL), where (i) clients are heterogeneous, (ii) tasks arrive sequentially with shifting domains, yet (iii) the label space remains fixed. Two theoretical pillars remain missing for FDIL under realistic deployment: a guarantee of backward knowledge transfer (BKT) and a convergence rate that holds across the sequence of all tasks with partial participation. We introduce SPECIAL (Server-Proximal Efficient Continual Aggregation for Learning), a simple, memory-free FDIL algorithm that adds a single server-side ``anchor'' to vanilla FedAvg: in each round, the server nudges the uniformly sampled participated clients update toward the previous global model with a lightweight proximal term. This anchor curbs cumulative drift without replay buffers, synthetic data, or task-specific heads, keeping communication and model size unchanged. Our theory shows that SPECIAL (i) preserves earlier tasks: a BKT bound caps any increase in prior-task loss by a drift-controlled term that shrinks with more rounds, local epochs, and participating clients; and (ii) learns efficiently across all tasks: the first communication-efficient non-convex convergence rate for FDIL with partial participation, O((E/NT)^(1/2)), with E local epochs, T communication rounds, and N participated clients per round, matching single-task FedAvg while explicitly separating optimization variance from inter-task drift. Experimental results further demonstrate the effectiveness of SPECIAL.

---

### JAF: Judge Agent Forest

Authors: Sahil Garg, Brad Cheezum, Sridhar Dutta, Vishal Agarwal
Published: 2026-01-29
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.22269v1

Judge agents are fundamental to agentic AI frameworks: they provide automated evaluation, and enable iterative self-refinement of reasoning processes. We introduce JAF: Judge Agent Forest, a framework in which the judge agent conducts joint inference across a cohort of query--response pairs generated by a primary agent, rather than evaluating each in isolation. This paradigm elevates the judge from a local evaluator to a holistic learner: by simultaneously assessing related responses, the judge discerns cross-instance patterns and inconsistencies, whose aggregate feedback enables the primary agent to improve by viewing its own outputs through the judge's collective perspective. Conceptually, JAF bridges belief propagation and ensemble-learning principles: overlapping in-context neighborhoods induce a knowledge-graph structure that facilitates propagation of critique, and repeated, randomized evaluations yield a robust ensemble of context-sensitive judgments. JAF can be instantiated entirely via ICL, with the judge prompted for each query using its associated primary-agent response plus a small, possibly noisy set of peer exemplars. While kNN in embedding space is a natural starting point for exemplars, this approach overlooks categorical structure, domain metadata, or nuanced distinctions accessible to modern LLMs. To overcome these limitations, we develop a flexible locality-sensitive hashing (LSH) algorithm that learns informative binary codes by integrating semantic embeddings, LLM-driven hash predicates, supervision from categorical labels, and relevant side information. These hash codes support efficient, interpretable, and relation-aware selection of diverse exemplars, and further optimize exploration of CoT reasoning paths. We validate JAF with an empirical study on the demanding task of cloud misconfigs triage in large-scale cloud environments.

---

### Privacy-Preserving Sensor-Based Human Activity Recognition for Low-Resource Healthcare Using Classical Machine Learning

Authors: Ramakant Kumar, Pravin Kumar
Published: 2026-01-29
Categories: cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2601.22265v1

Limited access to medical infrastructure forces elderly and vulnerable patients to rely on home-based care, often leading to neglect and poor adherence to therapeutic exercises such as yoga or physiotherapy. To address this gap, we propose a low-cost and automated human activity recognition (HAR) framework based on wearable inertial sensors and machine learning. Activity data, including walking, walking upstairs, walking downstairs, sitting, standing, and lying, were collected using accelerometer and gyroscope measurements. Four classical classifiers, Logistic Regression, Random Forest, Support Vector Machine (SVM), and k-Nearest Neighbors (k-NN), were evaluated and compared with the proposed Support Tensor Machine (STM). Experimental results show that SVM achieved an accuracy of 93.33 percent, while Logistic Regression, Random Forest, and k-NN achieved 91.11 percent. In contrast, STM significantly outperformed these models, achieving a test accuracy of 96.67 percent and the highest cross-validation accuracy of 98.50 percent. Unlike conventional methods, STM leverages tensor representations to preserve spatio-temporal motion dynamics, resulting in robust classification across diverse activities. The proposed framework demonstrates strong potential for remote healthcare, elderly assistance, child activity monitoring, yoga feedback, and smart home wellness, offering a scalable solution for low-resource and rural healthcare settings.

---

### Predicting Intermittent Job Failure Categories for Diagnosis Using Few-Shot Fine-Tuned Language Models

Authors: Henri Aïdasso, Francis Bordeleau, Ali Tizghadam
Published: 2026-01-29
Categories: cs.SE, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.22264v2

In principle, Continuous Integration (CI) pipeline failures provide valuable feedback to developers on code-related errors. In practice, however, pipeline jobs often fail intermittently due to non-deterministic tests, network outages, infrastructure failures, resource exhaustion, and other reliability issues. These intermittent (flaky) job failures lead to substantial inefficiencies: wasted computational resources from repeated reruns and significant diagnosis time that distracts developers from core activities and often requires intervention from specialized teams. Prior work has proposed machine learning techniques to detect intermittent failures, but does not address the subsequent diagnosis challenge. To fill this gap, we introduce FlaXifyer, a few-shot learning approach for predicting intermittent job failure categories using pre-trained language models. FlaXifyer requires only job execution logs and achieves 84.3% Macro F1 and 92.0% Top-2 accuracy with just 12 labeled examples per category. We also propose LogSift, an interpretability technique that identifies influential log statements in under one second, reducing review effort by 74.4% while surfacing relevant failure information in 87% of cases. Evaluation on 2,458 job failures from TELUS demonstrates that FlaXifyer and LogSift enable effective automated triage, accelerate failure diagnosis, and pave the way towards the automated resolution of intermittent job failures.

---

### Tabular Foundation Models Can Do Survival Analysis

Authors: Da In Kim, Wei Siang Lai, Kelly W. Zhang
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22259v2

While tabular foundation models have achieved remarkable success in classification and regression, adapting them to model time-to-event outcomes for survival analysis is non-trivial due to right-censoring, where data observations may end before the event of interest occurs. We utilize a classification-based framework that reformulates both static and dynamic survival analysis as a series of binary classification problems by discretizing event times. Censored observations are naturally handled as examples with missing labels at certain time points. This classification formulation enables existing tabular foundation models (TFMs) to perform survival analysis through in-context learning without explicit training. In contrast to classical approaches that use binary classifiers to model discrete-time hazards, our approach directly models cumulative failure probabilities, which we find empirically to be more robust to the number of discretization bins by avoiding multiplicative accumulation of per-bin errors. We prove that under standard censoring assumptions, minimizing our binary classification loss recovers the true survival probabilities as the training set size increases. We demonstrate through evaluation across 48 real-world datasets (43 static and 5 dynamic) that off-the-shelf TFMs with this classification formulation outperform classical and deep learning baselines on average over multiple survival metrics.

---

### Symmetry Breaking in Transformers for Efficient and Interpretable Training

Authors: Eva Silverstein, Daniel Kunin, Vasudev Shyam
Published: 2026-01-29
Categories: cs.LG, hep-th
arXiv: https://arxiv.org/abs/2601.22257v1

The attention mechanism in its standard implementation contains extraneous rotational degrees of freedom that are carried through computation but do not affect model activations or outputs. We introduce a simple symmetry-breaking protocol that inserts a preferred direction into this rotational space through batchwise-sampled, unlearned query and value biases. This modification has two theoretically motivated and empirically validated consequences. First, it can substantially improve the performance of simple, memory-efficient optimizers, narrowing -- and in some cases closing -- the gap to successful but more complex memory-intensive adaptive methods. We demonstrate this by pretraining 124M parameter transformer models with four optimization algorithms (AdamW, SOAP, SGDM, and Energy Conserving Descent(ECD)) and evaluating both validation loss and downstream logical reasoning. Second, it enables an interpretable use of otherwise redundant rotational degrees of freedom, selectively amplifying semantically meaningful token classes within individual attention heads. Overall, our results show that minimal, principled architectural changes can simultaneously improve performance and interpretability.

---

### AI Narrative Breakdown. A Critical Assessment of Power and Promise

Authors: Rainer Rehak
Published: 2026-01-29
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.22255v1

This article sets off for an exploration of the still evolving discourse surrounding artificial intelligence (AI) in the wake of the release of ChatGPT. It scrutinizes the pervasive narratives that are shaping the societal engagement with AI, spotlighting key themes such as agency and decision-making, autonomy, truthfulness, knowledge processing, prediction, general purpose, neutrality and objectivity, apolitical optimization, sustainability game-changer, democratization, mass unemployment, and the dualistic portrayal of AI as either a harbinger of societal utopia or dystopia. Those narratives are analysed critically based on insights from critical computer science, critical data and algorithm studies, from STS, data protection theory, as well as from the philosophy of mind and semiotics. To properly analyse the narratives presented, the article first delves into a historical and technical contextualisation of the AI discourse itself. The article then introduces the notion of "Zeitgeist AI" to critique the imprecise and misleading application of the term "AI" across various societal sectors. Then, by discussing common narratives with nuance, the article contextualises and challenges often assumed socio-political implications of AI, uncovering in detail and with examples the inherent political, power infused and value-laden decisions within all AI applications. Concluding with a call for a more grounded engagement with AI, the article carves out acute problems ignored by the narratives discussed and proposes new narratives recognizing AI as a human-directed tool necessarily subject to societal governance.

---

### FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation

Authors: Ruiyi Zhang, Peijia Qin, Qi Cao, Eric Xue, Pengtao Xie
Published: 2026-01-29
Categories: cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2601.22249v1

Code generation is a core application of large language models (LLMs), yet LLMs still frequently fail on complex programming tasks. Given its success in mathematical reasoning, test-time scaling approaches such as Process Reward Model (PRM)-based Best-of-N selection offer a promising way to improve performance. However, existing PRMs remain ineffective for code generation due to the lack of meaningful step decomposition in code and the noise of Monte Carlo-estimated partial-solution correctness scores (rewards). To address these challenges, we propose FunPRM. FunPRM prompts LLMs to encourage modular code generation organized into functions, with functions treated as PRM reasoning steps. Furthermore, FunPRM introduces a novel meta-learning-based reward correction mechanism that leverages clean final-solution rewards obtained via a unit-test-based evaluation system to purify noisy partial-solution rewards. Experiments on LiveCodeBench and BigCodeBench demonstrate that FunPRM consistently outperforms existing test-time scaling methods across five base LLMs, notably achieving state-of-the-art performance on LiveCodeBench when combined with O4-mini. Furthermore, FunPRM produces code that is more readable and reusable for developers.

---

### MirrorMark: Generalizable Mirrored Sampling for Multi-bit LLM Watermarking

Authors: Ya Jiang, Massieh Kordi Boroujeny, Surender Suresh Kumar, Kai Zeng
Published: 2026-01-29
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.22246v3

As large language models (LLMs) become integral to applications such as question answering and content creation, reliable content attribution has become increasingly important. Watermarking is a promising approach, but most existing methods either provide only binary signals or achieve multi-bit embedding by distorting the generation distribution. We propose MirrorMark, a generalizable mapping-centric approach for multi-bit LLM watermarking. MirrorMark separates the symbol mapping rule from the base watermarking sampler and maps each symbol to a mod-1 mirroring transformation of a detector-reproducible pseudorandom object, such as sampling values or permutation ranks. A binary-tokenizer analysis shows that complementary mappings yield larger matched--mismatched score gaps than independent-key or shift-based mappings. When composed with a distortion-free base sampler, MirrorMark preserves the token probability distribution by design and maintains text quality in practice. To support practical payload embedding, we introduce a Context-Anchored Balanced Scheduler (CABS), which balances token assignments across message positions while localizing edit effects. We further provide theoretical EER analyses for two representative sampler instantiations. Experiments show that MirrorMark achieves strong detectability and bit accuracy while maintaining text quality comparable to non-watermarked generation.

---

### Is Hierarchical Quantization Essential for Optimal Reconstruction?

Authors: Shirin Reyhanian, Laurenz Wiskott
Published: 2026-01-29
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.22244v2

Vector-quantized variational autoencoders (VQ-VAEs) are central to models that rely on high reconstruction fidelity, from neural compression to generative pipelines. Hierarchical extensions, such as VQ-VAE2, are often credited with superior reconstruction performance because they split global and local features across multiple levels. However, since higher levels derive all their information from lower levels, they should not carry additional reconstructive content beyond what the lower-level already encodes. Combined with recent advances in training objectives and quantization mechanisms, this leads us to ask whether a single-level VQ-VAE, with matched representational budget and no codebook collapse, can equal the reconstruction fidelity of its hierarchical counterpart. Although the multi-scale structure of hierarchical models may improve perceptual quality in downstream tasks, the effect of hierarchy on reconstruction accuracy, isolated from codebook utilization and overall representational capacity, remains empirically underexamined. We revisit this question by comparing a two-level VQ-VAE and a capacity-matched single-level model on high-resolution ImageNet images. Consistent with prior observations, we confirm that inadequate codebook utilization limits single-level VQ-VAEs and that overly high-dimensional embeddings destabilize quantization and increase codebook collapse. We show that lightweight interventions such as initialization from data, periodic reset of inactive codebook vectors, and systematic tuning of codebook hyperparameters significantly reduce collapse. Our results demonstrate that when representational budgets are matched, and codebook collapse is mitigated, single-level VQ-VAEs can match the reconstruction fidelity of hierarchical variants, challenging the assumption that hierarchical quantization is inherently superior for high-quality reconstructions.

---

### Aligning Microscopic Vehicle and Macroscopic Traffic Statistics: Reconstructing Driving Behavior from Partial Data

Authors: Zhihao Zhang, Keith Redmill, Chengyang Peng, Bowen Weng
Published: 2026-01-29
Categories: cs.MA, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2601.22242v2

A driving algorithm that aligns with good human driving practices, or at the very least collaborates effectively with human drivers, is crucial for developing safe and efficient autonomous vehicles. In practice, two main approaches are commonly adopted: (i) supervised or imitation learning, which requires comprehensive naturalistic driving data capturing all states that influence a vehicle's decisions and corresponding actions, and (ii) reinforcement learning (RL), where the simulated driving environment either matches or is intentionally more challenging than real-world conditions. Both methods depend on high-quality observations of real-world driving behavior, which are often difficult and costly to obtain. State-of-the-art sensors on individual vehicles can gather microscopic data, but they lack context about the surrounding conditions. Conversely, roadside sensors can capture traffic flow and other macroscopic characteristics, but they cannot associate this information with individual vehicles on a microscopic level. Motivated by this complementarity, we propose a framework that reconstructs unobserved microscopic states from macroscopic observations, using microscopic data to anchor observed vehicle behaviors, and learns a shared policy whose behavior is microscopically consistent with the partially observed trajectories and actions and macroscopically aligned with target traffic statistics when deployed population-wide. Such constrained and regularized policies promote realistic flow patterns and safe coordination with human drivers at scale.

---

### Investigating the Interplay of Parameterization and Optimizer in Gradient-Free Topology Optimization: A Cantilever Beam Case Study

Authors: Jelle Westra, Iván Olarte Rodríguez, Niki van Stein, Thomas Bäck, Elena Raponi
Published: 2026-01-29
Categories: cs.NE, cs.CE
arXiv: https://arxiv.org/abs/2601.22241v2

Gradient-free black-box optimization (BBO) is widely used in engineering design and provides a flexible framework for topology optimization (TO), enabling the discovery of high-performing structural designs without requiring gradient information from simulations. Yet, its success depends on two key choices: the geometric parameterization defining the search space and the optimizer exploring it. This study investigates this interplay through a compliance minimization problem for a cantilever beam subject to a connectivity constraint. We benchmark three geometric parameterizations, each combined with three representative BBO algorithms: differential evolution, covariance matrix adaptation evolution strategy, and heteroscedastic evolutionary Bayesian optimization, across 10D, 20D, and 50D design spaces. Results reveal that parameterization quality has a stronger influence on optimization performance than optimizer choice: a well-structured parameterization enables robust and competitive performance across algorithms, whereas weaker representations increase optimizer dependency. Overall, this study highlights the dominant role of geometric parameterization in practical BBO-based TO and shows that algorithm performance and selection cannot be fairly assessed without accounting for the induced design space.

---