# Research Papers — 2026-10 · bundle page 68 of 156

> Full-text markdown of papers #3351–3400 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-10/page/68
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/67.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/69.md)

### Studying the Effects of Task Diversity Using Small Mathematical Worlds

Authors: Emily Xia Meng, Xuanyu Yang, Junaid Hasan, Michael Ruofan Zeng, Henry Kvinge
Published: 2026-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.13750v1

Basic mathematical tasks like modular addition have been a valuable tool for illuminating aspects of neural network behavior that are challenging to see in noisy, unverifiable, large-scale, real-world settings. These studies have typically focused on a single task. However, modern language models are exposed to a vast number of tasks despite being trained with a next-token prediction objective. In this work, we introduce two mathematical task ecosystems, IntWorld and PermWorld, built from distinct but related tasks on integers and permutations. Both are designed to simulate task diversity within a cohesive mathematical 'world' where tasks are distinct but related. Because the datasets are procedurally generated, we can precisely vary the number of tasks, allowing us to begin to disentangle the role of task variety from other factors in training. After describing the datasets, we provide some initial results obtained from these datasets which support the idea that increasing task diversity increases the richness of a model's internal representations.

---

### A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning

Authors: Mayug Maniparambil, Ayush Rai, Ekansh Verma, Noel E. O'Connor, Fergal Reid
Published: 2026-10-09
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.13744v1

On-policy self-distillation promises to replace the sparse outcome signal of verifiable-reward RL with dense token-level credit: a teacher conditioned on the reference solution scores the student's own rollout, and the resulting distributional shift is distilled back into the policy. We investigate whether this scoring signal actually contains corrective credit. Using gold error spans in student rollouts, we test the two signals consumed by self-distillation objectives, the full-distribution KL and the token log-ratio, for two properties: whether they localize errors and whether they push probability away from erroneous student tokens. They exhibit neither of these properties nor can they reliably distinguish correct from incorrect rollouts within the same problem. We argue that this failure is structural: locating an error in a reasoning trace is itself a search problem, while a scoring teacher is never explicitly asked to perform that search. The same model, with the same privileged information, localizes errors substantially better when allowed to generate a critique. This forms the motivation for \emph{critique-conditioned self-distillation}: first generate a critique of the current rollout, then condition the scoring teacher on that critique. The resulting signal localizes errors, is corrective within error spans, and shifts probability toward tokens that initiate backtracking such as ``Wait'', ``But'', and ``Actually''. We further show that the critique is useful both at test time, where resuming a wrong rollout with the critique in context converts math problems the model cannot solve by sampling, and in cold-start GRPO, where it provides an advantage signal on prompts for which verifiable rewards alone provide none.

---

### SmolWAM: A Latent World-Action Model for Robotic Manipulation on Edge Devices

Authors: Timi Owolabi, Hikmah Olawore, Frances Adelakun, Ayotomiwa Oyewumi
Published: 2026-10-09
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2610.13740v1

World-action models (WAMs) predict a robot's actions together with the observations those actions will produce. However, the strongest models rely on video diffusion transformers that are far too computationally expensive for resource-constrained edge devices. We present SmolWAM, a latent WAM that we derive from the 2B-parameter Cosmos Policy by keeping its pretrained trunk and rebuilding its inference interface: single-frame visual latents, cached text features that preserve the trunk's attention sinks, 12 of 28 transformer blocks, and 1,008 tokens from which actions and future visual latents are read out in one rectified-flow step. Trained in 3.6 GPU-hours, SmolWAM succeeds in 95.5% of 400 LIBERO episodes at 57 ms and 2.3 TFLOP per 16-action chunk with 2.4 GiB of GPU memory, 11x faster than its teacher with 18.5x fewer FLOPs and 3.2x less memory, and its world head still forecasts scene motion.

---

### SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning

Authors: Hongrui Zheng, Aditya Singh, Rahul Mangharam
Published: 2026-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.13737v1

Cooperative multi-agent tasks often impose constraints on a shared objective or collective safety. A team level violation cost function can measure this constraint outcome, but does not distinguish which agents' actions most strongly influence that violation. We present SafeDiSTL, a constrained multi-agent reinforcement learning framework that allows for credit assignment even with joint constraint measurements. We use Signal Temporal Logic (STL) robustness to measure episode-level violation through running-maximum cost increments. Smooth full-episode robustness and differentiable dynamics provide action sensitivities, which allocate each cost increment across agents at the same decision time. These sensitivities account for delayed effects when weighting agents' shares of each cost increment. We study the framework in cooperative payload transport, connected navigation, and networked traffic control tasks. SafeDiSTL achieves 1.6-5.1x the safe-success rate in transport, improves navigation safe-success by 11.1%, and delivers 50-68% more throughput in traffic when compared to constrained baselines. Results demonstrate a strong improvement of the learned policy in dealing with shared constraint while retaining the performance of unconstrained policies.

---

### Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers

Authors: Yuhong Chou, Zehao Liu, Yuqi Pan, Qian Liu, Xianwei Chen, Zhongzhu Zhou, Jibin Wu
Published: 2026-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.13735v1

Efficient attention mechanisms, such as linear and sliding window attention, aim to reduce the computational complexity of Transformers from quadratic to linear. However, their degraded in-context recall often necessitates interleaving full attention layers, leaving the quadratic bottleneck unresolved in long-context processing. To address this, we introduce Orthros attention, which shifts the efficiency paradigm from structural allocation to phase-aware decoupling. As a unified module, it dynamically switches its computation pattern across different phases of sequence processing, enabling linear complexity prefilling and full attention decoding. Our design grants Orthros attention a lower asymptotic complexity compared to vanilla Transformers in prevalent long-context scenarios characterized by heavy prefilling and light decoding. Beyond theoretical formulation and complexity analysis, extensive empirical evaluations demonstrate Orthros's superiority across multiple dimensions. First, we validate its fundamental language modeling capabilities, demonstrating scalability across varying model sizes and strong competitiveness in comprehensive architectural comparisons. Second, Orthros exhibits exceptional conversion feasibility via a data-efficient Transformer-to-Orthros conversion, yielding performance that even surpasses the original Transformer. Finally, Orthros achieves a $21.9\times$ prefilling speedup over Transformers with end-to-end inference gains, while preserving long-context capabilities, as demonstrated by near-perfect 128K needle-in-a-haystack results and Transformer-level performance on real-world in-context recall tasks. Overall, these advantages in high performance, flexibility, and efficiency position Orthros as a promising candidate to succeed the Transformer in industrial applications.

---

### KVeil: First-Place Solution to ECCV 2026 LifeGenIP Challenge on Unlearnable Videos

Authors: Boheng Li, Yueming Xing, Yiming Li, Jie Zhang, Han Qiu, Tianwei Zhang
Published: 2026-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.13733v1

The rapid development of personalized video generation has raised serious concerns over identity privacy, as a few facial videos of a person now suffice to reproduce their identity in synthetic videos. This report presents the first-place solutions to both phases of the ECCV 2026 LifeGenIP Challenge on Unlearnable Videos, which aims to protect facial videos from unauthorized customization under a limited and imperceptible perturbation budget. For Phase 1, we introduce Reference Capacity Collapse, a pair of complementary losses that degrade the information carried by the reference condition while keeping subsequent video representations dependent on it, together with a Motion-Guided EOT mechanism that improves robustness across unknown inference conditions. Phase 2 further considers tuning-based customization and unseen generative models. To address both threats within a single perturbation, we design a two-layer framework that protects the facial and background regions separately, constructing structure-aligned perturbations from a synthetic target identity in the former and strengthening the white-box disruption of Phase 1 in the latter. Our method achieves nearly perfect protection under white-box reference-based customization, and remains effective under other customization paradigms, various models, and temporal attacks. Both solutions are built upon our recent work LETHE. We hope our solutions can inspire future work on protecting facial videos against unauthorized customization. Our code is available at https://github.com/AntigoneRandy/KVeil.

---

### LAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human Videos

Authors: Zhiyuan Xiang, Peidong Liu, Mingyang Li, Jiawei Li, Wenhow Li, Wenbo Ding, Xiang Deng
Published: 2026-10-09
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2610.13732v1

Scaling generalist robotic policies is limited by the high cost of collecting embodied interaction data. Large-scale egocentric human videos offer a rich alternative, but they lack robot action labels, and existing action annotation methods are often noisy under real-world visual complexity and diverse manipulation dynamics. We introduce LAPT-Scale, a scalable latent action pre-training paradigm with two components: LAPT-Scale-LAM learns continuous latent actions by explaining frame-to-frame visual transitions in human videos and uses them as human-derived supervision, while LAPT-Scale-Policy trains a VLA policy through human-video latent-action pre-training, target-robot embodiment alignment, and task-specific post-training. Unlike prior vector-quantized LAMs, LAPT-Scale-LAM uses a continuous latent space to preserve fine-grained motion and interaction dynamics. We further combine perceptual, semantic, and optical-flow alignment signals to improve transition-level supervision beyond pixel reconstruction. Trained on 23.3K hours of egocentric video, LAPT-Scale-LAM provides implicit action supervision for policy pre-training, yielding consistent scaling gains and improving real-robot success from 63.3% to 85.0% as annotated human video scales from 1K to 5K hours. The learned policy also generalizes to unseen visual conditions.

---

### SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark

Authors: Taeyoung Yu, Seonbin Jo, Jiwon Kim, Junyoung Byun
Published: 2026-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.13730v1

Origin-destination (OD) flow forecasting supports urban mobility decisions by predicting the volume and patterns of human movement across a city. Most existing public OD benchmarks provide only a partial view of citywide mobility, covering a single transport service or at most two modes. With partial mode coverage, observed demand changes are difficult to separate into shifts across transport modes and changes in total travel. We introduce SeoulMMOD, a large-scale public benchmark for citywide multimodal mobility in Seoul. SeoulMMOD provides three years of hourly OD flows estimating total mobility for 6 urban travel modes across 25 districts and 426 sub-districts, together with travel-time, travel-distance, calendar, rainfall, and point-of-interest (POI) signals. Using SeoulMMOD, we benchmark 14 forecasting baselines under a common protocol and analyse the effects of spatial scaling, joint versus mode-separate training, and cross-year generalization. Results show that several spatio-temporal models that work at district level do not scale to sub-district OD forecasting, and that naive joint multi-mode training does not consistently improve accuracy. Together, the dataset and benchmark establish a reproducible testbed for multi-mode, multi-year OD forecasting at the city scale.

---

### Amortized Counterfactual Prediction with Graph Neural Networks

Authors: Hendrik Stumpf, Francesco Quinzan
Published: 2026-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.13724v1

Counterfactual inference asks how an observed outcome might have differed under different circumstances, such as whether a patient would have recovered had they received a different treatment. Such questions arise whenever decisions depend on the outcomes of alternatives that were not observed. Answering counterfactual queries generally requires knowledge of the underlying causal structure, which is often unavailable in practice. A common approach is therefore to first estimate the causal graph from observational data and then perform counterfactual inference. However, errors in the estimated causal graph can propagate to downstream counterfactual predictions. To address this challenge, we introduce the Counterfactual Graph Neural Process (CFGNP), an end-to-end approach that answers counterfactual queries directly from observational data without first estimating a causal graph. CFGNP uses Graph Neural Networks (GNNs) to exploit the dual-graph structure by restricting cross-world message passing to corresponding factual--counterfactual variables. Across synthetic and image-based benchmarks, CFGNP achieves stronger predictive performance than existing approaches, including on the German Loan benchmark, where it reduces MSE from $4.51 \times 10^{-2}$ to $0.19 \times 10^{-2}$. Furthermore, on synthetic causal graphs, a model trained only on 10-node graphs maintains strong predictive performance on graphs with up to 30 nodes, without retraining.

---

### Enhancing Legal Reasoning in Pre-trained Language Models via Knowledge Graph-Guided Multi-Task Pre-training

Authors: Ibrahim Siddig, Munir Georges
Published: 2026-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.13722v1

Legal language understanding requires reasoning over semi-structured regulatory documents, yet standard pre-training objectives do not explicitly target this structural capability. Because current legal language models rely solely on masked language modeling, they treat statutory text as flat token sequences and ignore the underlying hierarchical constraints. To bridge this gap, we present a multi-task pre-training approach for German traffic law (StVO). Our approach combines three complementary objectives: Next Sentence Prediction (NSP), Knowledge Graph (KG) Guided Clustering (CLU), and Knowledge Graph (KG) Aware Paragraph Classification (CLS). This approach explicitly encodes structured legal knowledge directly into the model weights. This encoding enables zero-shot legal reasoning at inference time and removes the need for discrete graph traversal. We evaluate our approach across nine Transformer-based encoders and 324 experimental runs. On synthetic StVO question answering, our models demonstrate consistent relative improvements between 10.3% and 155.0% over baselines. Furthermore, relative to the established LexGLUE baselines (Chalkidis et al., 2022), our models improve over prior results on four of seven legal benchmarks. It also achieves consistent zero-shot transfer gains between 3.4% and 15.8% on Austrian driving regulations. These experimental results indicate that our training approach generalizes successfully beyond the initial training legal domain.

---

### State-Isolated Vision Mamba via Update-Tendency Routing for Underwater Image Enhancement

Authors: Yan Luo, Laibin Chang, Zefan Feng, Yi'ang Chen, Kui Jiang, Zhengguo Li
Published: 2026-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.13720v1

Vision Mamba has recently emerged as an efficient alternative to convolutional and Transformer-based architectures by modeling long-range spatial dependencies through recurrent state evolution. Existing studies primarily improve token serialization, scanning strategies, or expert routing, yet largely overlook a state level question question: how should recurrent states be organized for spatially heterogeneous visual restoration? In this paper, we show that forcing tokens with heterogeneous update behaviors to recurrently modify a shared hidden state leads to persistent cross-content interference, which we term \textbf{State Contention}. We further argue that effective recurrent modeling should organize state evolution according to token compatibility rather than token ordering. Based on this observation, we introduce \textbf{State Isolation}, a new recurrent state organization principle for Vision Mamba,tokens with compatible state-update tendencies evolve within independent recurrent state streams. To instantiate this principle, we propose \textbf{IsoMamba}, a $Δ$-guided architecture that constructs model-intrinsic update representations, discovers update-compatible token groups through label-free clustering, and routes them to isolated Mamba experts following a \textbf{cluster--route--isolate} paradigm. In addition, we develop a dynamic channel-wise reweighting objective to compensate for wavelength-dependent reconstruction difficulty in underwater images. Extensive experiments demonstrate that IsoMamba consistently achieves state-of-the-art performance on multiple underwater image enhancement benchmarks while providing cleaner hidden state responses, validating the effectiveness of state isolated recurrent modeling.

---

### Machine Unlearning for Federated Socially Fair k-Means Clustering

Authors: Aravind Reddy, Deeraj S K, Mohd Wasif Raza, Saurav Prakash
Published: 2026-10-09
Categories: cs.LG, cs.DS
arXiv: https://arxiv.org/abs/2610.13717v1

Federated clustering can support applications such as patient stratification across hospitals and customer segmentation across distributed financial datasets. Responsible AI calls for fair representation of demographic groups and support for data deletion, motivated in part by rights such as the GDPR's right to erasure. These goals interact: deleting records can change the balance between groups and alter the clustering of the remaining population. We study exact machine unlearning for federated socially fair $k$-means, whose objective is to minimize the largest group-average squared distance to the nearest center. Our approach keeps separate local summaries for each group, so summaries at unaffected institutions remain valid as global fairness weights change. For two groups, we prove an initialization approximation guarantee independent of client group proportions under ideal sampling, and we show that same-seed replay reproduces retraining exactly. Reuse pays off most when a whole client withdraws: across three datasets, replay is $35.8\times$ faster than retraining for the initialization-only model and remains $2.4\times$ and $1.7\times$ faster with one and two fair-refinement rounds, which improve worst-group cost. For individual record deletions, gains are modest (about $1.06\times$), and certifying cached assignments can cost more than it saves. These results map where exact unlearning can profitably reuse computation. Code and reproducibility materials are available at https://github.com/arareddy/mufsc.

---

### Towards Understanding the Training of GFlowNets: A Theoretical Perspective

Authors: Rui Hu, Yu Chen, Zhuoran Li, Longbo Huang
Published: 2026-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.13711v1

Generative Flow Networks (GFlowNets) learn policies that sample discrete objects in proportion to a positive reward. They are trained by minimizing balance objectives, whose exact satisfaction guarantees correct sampling. However, a comprehensive theory linking nonzero balance loss and approximate stationarity to sampling accuracy, especially under evolving sampling distributions and backward policies, is still lacking. To bridge this gap, we develop a unified theory for Flow Matching, Detailed Balance, and Trajectory Balance in this regime. We first bound terminal symmetric KL by the square root of the expected balance loss. Then, we show that approximate stationarity controls this distribution error up to a tangent-space residual measuring parameterization incompleteness. Finally, we establish finite-time convergence under fixed or controlled sampling and fixed, balance-trained, or separately updated backward policies. Under standard smoothness assumptions, with fixed or controlled sampling and a fixed or balance-trained backward policy, the expected loss is $O(\barε^2+T^{-1})$ and expected terminal symmetric KL is $O(\barε+T^{-1/2})$ under uniform coverage. For a separately updated backward policy, we characterize the sufficient update decay to approach the residual neighborhood and preserve these rates. These results connect balance objectives to sampling accuracy and clarify how parameterization, coverage, and moving components govern GFlowNet training.

---

### Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy

Authors: Naji Alazhar, Wassel Alazhar
Published: 2026-10-09
Categories: cs.AI, cs.CL, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2610.13708v1

Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only the selected entries, but it uses one cache budget at every load and does not handle draft-model speculative decoding such as DSpark and DFlash2. We present Adaptive DHiSparse, which supports speculative decoding over hierarchical sparse KV and adapts residency to load. It protects the required working set, retains additional history while GPU memory is spare, and recovers the rest through exact fused retrieval. DSpark and DFlash2 keep their proposal and acceptance rules: queries share missing-row retrieval, draft KV uses a window-bounded ring, and verification staging is reused across layer groups. At 100K context and concurrency 128, GLM-5.3 with DFlash2 delivers 793 output tokens/s per decode GPU, 1.45$\times$ HiSparse and 1.27$\times$ non-speculative adaptive serving. Held to the same latency bounds as HiSparse, it sustains up to 4$\times$ the concurrency and 2.3 to 3.7$\times$ the output, depending on the per-token bound. On DeepSeek-V4.1-Flash at 500K context and concurrency 512, Adaptive DHiSparse with DSpark delivers 1.85$\times$ the output of resident serving with DSpark. In a load step, optional residency reduces host fetches from 14.2% to 1.4% of selected rows at low load and releases memory under pressure.

---

### GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Models

Authors: Zhufeng Xu, Henglei Lv, Bailin Deng, Yikang Ding, Xiaoqiang Liu, Guoxin Zhang, Hongbo Fu, Lin Gao
Published: 2026-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.13706v1

A camera-controlled video world model must keep a scene consistent when the camera returns to it. Memories that render stored features into the target frame can turn depth and pose errors into ghosting or duplicated structure. Positional transport avoids that resampling by relocating a historical patch's address rather than its content, but assigns full positional precision even to inaccurate projections. We present GLIMPSE, a global-local memory interface with band-wise multi-precision coordinates and geometry-conditioned spectral attenuation to reduce sensitivity to inaccurate projected addresses. Local patch memory supplies view-specific appearance, while recurrent global memory provides scene context. Footprint-guided retrieval selects historical patches under a fixed local read budget. Under matched retrieval and read budgets, GLIMPSE improves geometric correspondence and photometric consistency over deterministic positional transport.

---

### A Baseline Assessment for the Agentic Web Technology Stack

Authors: Vagner Figueredo de Santana, Diogo Cortiz
Published: 2026-10-09
Categories: cs.AI, cs.ET, cs.SE
arXiv: https://arxiv.org/abs/2610.13703v1

The fast pace in which protocols, frameworks, and technologies are being proposed for LLM-based agents results in a complex scenario for anyone aiming to create state-of-the-art AI solutions. Without an assessment on how different protocols, frameworks, and libraries work together to compose an Agentic Web solution, developers and organizations face different challenges (e.g., skilling, governance, infrastructure) even before becoming part of the Agentic Web ecosystem. In this context, we propose a system for performing Agentic Web evaluations called MASTIF (Multi-Agent System TestIng Framework) and present a baseline assessment of Agentic Web technologies, including 3 LLMs, 3 protocols, and 4 agent implementation frameworks, against 300 Mind2Web benchmark tasks. Results suggest that selecting a task-specific technology stack may result in gains of task completion rate, efficiency score, and social value stability scores; and reductions in verbosity and time to complete tasks. With the presented results, we expect to present a baseline in terms of metrics and results for this complex and fast evolving scenario for those aiming at designing, assessing, and developing multi-agent systems.

---

### Improving Semantic Coverage in AI Test & Evaluation through Generative Augmentation

Authors: Connor Hashemi, Bharadwaj Ravichandran, Connor Anderson, Shitij Govil, Brandon RichardWebster, Brian Hu, Keith Fieldhouse
Published: 2026-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.13697v1

In test and evaluation (T&E) of AI models, evaluators typically have access only to a held-out test dataset and no knowledge of the training data or its semantic composition. If critical input conditions---such as time-of-day, weather, or scene location---are underrepresented in this test dataset, T&E results can be misleadingly due to this semantic coverage gap. We propose a three-stage generative AI pipeline to detect and fill such semantic gaps without requiring ground-truth labels of these semantics. First, vision-language models (VLMs) perform zero-shot binary labeling of semantic factors, and an embedding-space clustering step identifies which semantics most affect downstream model behavior. Second, diffusion-based image-to-image models transform existing covered images into the underrepresented semantic domain, preserving scene content while augmenting high-level appearance. Third, statistical analysis of the augmented image embeddings verifies that the synthetic imagery improves dataset coverage before it is incorporated. Crucially, the synthetic data is used only to enrich the test set and no model retraining is performed for T&E. We validate the full pipeline on both image classification and object detection under day/night semantic gaps, showing that the augmented test datasets better distinguish models with and without exposure to the missing semantic, thereby yielding T&E conclusions that more closely match those of an ideal, fully covered dataset. Code available at https://github.com/Hashe037/DEDUCE

---

### Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph

Authors: Ibrahim Siddig, Sviatoslav Tugeev, Munir Georges
Published: 2026-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.13695v2

Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable. Despite their advantages, current LLM-based systems do not meet these requirements due to their inherent black-box nature. Retrieval Augmented Generation (RAG) attempts to ground the generative process in the relevant interpretable documents, thereby reducing the risk of AI 'hallucinations' and potentially enabling verification of the initial generation context. However, as the number and size of potential sources increases, naive retrieval approaches tend to perform worse, ignoring critical context elements. In this paper we aim to tackle this problem in the context of German Legal Code. Using structure-driven parsing to create a Knowledge Graph (KG) for the source document navigation and retrieval, we compare several KG-informed chunking and retrieval strategies and evaluate their effect on the accuracy of retrieved citations.

---

### Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph

Authors: Ibrahim Siddig, Sviatoslav Tugeev, Munir Georges
Published: 2026-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.13695v1

Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable. Despite their advantages, current LLM-based systems do not meet these requirements due to their inherent black-box nature. Retrieval Augmented Generation (RAG) attempts to ground the generative process in the relevant interpretable documents, thereby reducing the risk of AI 'hallucinations' and potentially enabling verification of the initial generation context. However, as the number and size of potential sources increases, naive retrieval approaches tend to perform worse, ignoring critical context elements. In this paper we aim to tackle this problem in the context of German Legal Code. Using structure-driven parsing to create a Knowledge Graph (KG) for the source document navigation and retrieval, we compare several KG-informed chunking and retrieval strategies and evaluate their effect on the accuracy of retrieved citations.

---

### Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks

Authors: Nektarios Kalampalikis, Pablo M. Olmos, Isabel Valera
Published: 2026-10-09
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2610.13693v1

Neural networks (NNs), while highly flexible and versatile, are often poorly calibrated. Post-hoc calibration methods adjust the outputs of an already trained model using a separate calibration dataset and additional calibration parameters. This process adds overhead that requires separate optimization of the calibrator and subsequent model selection. In this paper, we show that standard (post-hoc) calibrators can be trained end-to-end with the backbone via a bilevel Stackelberg formulation. This formulation eliminates the need for a separate calibration set or a dedicated calibration loss by jointly optimizing accuracy and calibration using cross-entropy, introducing only one additional hyperparameter: the calibrator learning rate. Although our framework supports calibrators ranging from temperature and matrix scaling to NN layers, our results show that using the final classification layer itself as the calibrator yields accurate, well-calibrated models with no additional parameters. Our approach outperforms SOTA calibrators with minimal added complexity, while also avoiding the multiplicative overhead of separate calibration components in settings such as multi-task learning.

---

### Variance-Reduced Policy Gradient is Nearly Minimax-Optimal

Authors: Leonardo Cesani, Matteo Papini, Marcello Restelli
Published: 2026-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.13692v1

Standard Policy Gradient (PG) algorithms suffer from high estimation variance because they rely on Monte Carlo updates. While off-policy variance reduction mitigates this problem, establishing optimal sample complexity currently requires either restrictive assumptions, such as uniformly bounded importance weights, or impractical second-order operations. In this work, we introduce Loopless Variance-Reduced PG (LVR-PG), a unified theoretical framework that abstracts a class of first-order estimators that integrate recursive updates with defensive importance sampling, including known estimators such as PAGE-PG and STORM-PG. We prove that this algorithmic class achieves $\tilde{\mathcal{O}}(ε^{-2})$ last-iterate global convergence under weak gradient domination for general parametric policies. We establish this guarantee using purely first-order updates, with minimal assumptions and without gradient preconditioners. By extending state-of-the-art lower bounds to continuous parametric policies, we establish an $Ω(ε^{-2})$ sample complexity limit, confirming our framework is minimax-optimal up to logarithmic factors and horizon terms.

---

### Transformer-based In-Context Score Operator Learning for Diffusion Models

Authors: Wuzhe Xu, Zhaiming Shen, Yulong Lu, Wenjing Liao, Rongjie Lai
Published: 2026-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.13690v1

Diffusion models typically learn the generative dynamics of a single target distribution or a family of distributions indexed by conditioning variables fixed during training. This limits their ability to adapt to a previously unseen distribution from only a small set of examples. We introduce an in-context solution operator learning framework for diffusion models, in which each target distribution is treated as a task drawn from a meta-distribution and is specified at inference time by an empirical context set. Our method learns an in-context score operator that maps the context samples, a noisy query point, and the diffusion time to the task-dependent score, enabling reverse-diffusion sampling on unseen tasks without retraining or parameter updates. A key observation is that the task-dependent score admits a Gaussian-kernel conditional-mean representation. Its empirical Nadaraya--Watson approximation can be represented exactly by a model in our constructed transformer class, providing a principled foundation for the proposed query-dependent attention architecture. The operator is trained through amortized denoising score matching across task distributions. We establish generalization-error bounds that quantify the effects of the context size, the numbers of training tasks and within-task samples, model complexity, and intrinsic and ambient dimensions. Numerically, we evaluate the method on a range of scientific and visual datasets, including Navier-Stokes, ERA5 climate data, QuickDraw sketches, and Food-101. The results show that the proposed method performs well on relatively simple task families, while its performance degrades as task complexity increases, thereby illustrating both the promise and the limitations of in-context learning for diffusion models.

---

### VQIL: Visible Quantum Interference Learning for Perturbation Response Ranking on Graphs

Authors: Seokjun Lee, Sergio A. Ortega, Daniel K. Park, Namshik Han
Published: 2026-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.13689v1

Learning how local perturbations affect a network is important for identifying which components drive or absorb a system's response. We formulate this as seed-conditioned response ranking: given a perturbation at one seed node, ranking all other nodes by response strength. This is challenging when the model is given only the interaction topology, while the mechanism governing how perturbations propagate must be learned from data. We present VQIL (Visible Quantum Interference Learning), a trainable Szegedy quantum walk for seed-conditioned ranking. Edge weights, link phases, and per-node phase rotations are optimized end-to-end by backpropagation while the walk operator remains unitary throughout training. Node scores are obtained from a geometrically discounted coherent sum of quantum-walk amplitudes, enabling quantum interference before the final squared-norm readout. Because each learned parameter is attached to a named edge or node, the trained model provides directly inspectable hypotheses about the roles of individual graph components in the propagation mechanism. On AC power-flow perturbations over six transmission grids, with electrical parameters withheld from the model, VQIL improves Spearman rank correlation from 0.147 for the untrained walk to 0.831 and outperforms an identically trained random-walk model. On gene perturbation over five protein-protein interaction networks with Perturb-seq supervision, VQIL improves rank correlation from 0.171 to 0.620, outperforming the strongest learned classical and neural baselines. These results show that trainable quantum-walk interference provides a scalable and interpretable inductive bias for learning seed-conditioned response rankings on graphs.

---

### X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation

Authors: Saumyaranjan Mohanty, Aravind Reddy, Konda Reddy Mopuri
Published: 2026-10-09
Categories: cs.CV, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2610.13687v1

Audio-visual dataset distillation aims to synthesize a small dataset from a large paired audio-visual dataset, while nearly preserving the training utility for neural networks. Existing approaches such as DM and AVDD face two critical limitations: 1) they are memory-intensive, making them difficult to scale to complex architectures and higher samples-per-class (SPC) settings, and 2) they often fail to preserve strong cross-modal semantic correspondence. To tackle these issues, we propose X-AVDD, a cross-attention-based distillation method that explicitly captures inter-modal relationships during synthesis. By decoupling cross-modal alignment from joint optimization, X-AVDD is substantially more memory-efficient, reducing end-to-end synthesis cost by $\sim 8\times$ GPU-hours, while producing highly aligned synthetic data. Empirically, X-AVDD significantly outperforms other audio-visual distillation methods. On VGGSound, an audio-visual dataset of short YouTube clips, X-AVDD improves top-1 test accuracy from $8.2\%\rightarrow24.0\%$ at SPC=$10$ and $9.8\%\rightarrow26.5\%$ at SPC=$20$. Furthermore, X-AVDD improves cross-architecture generalization (e.g., $25.5\%\rightarrow35.3\%$ for a ViT target on AVE dataset at SPC $=50$) and successfully scales to complex architectures such as AudioCLIP, achieving $62.3\%$ accuracy using only $5.65\%$ of the full dataset, against the full dataset accuracy of $72.4\%$ while completing in $9\times$ lower training time compared to the full dataset.

---

### PhysForge: Material-Controllable 3D Reconstruction with Separable Components

Authors: Yuchen Wang, Yanqi Bao, Zheng Gu, Zhengqing Chen, Jieqi Shi, Jing Huo
Published: 2026-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.13681v1

Recent advances in physical 3D generation have enabled visually faithful assets with simulatable mechanical behavior. However, existing methods provide limited control over material behavior beyond appearance-based inference and struggle to estimate physical properties from complex interactions between objects and semantic parts. Therefore, we present PhysForge, a Video Diffusion Model (VDM)-based framework for addressing these challenges, comprising two complementary modules for material-controllable physical fitting and componentlevel interaction modeling. The first, PhysFit, leverages material-conditioned VDM dynamics as references for physical-property fitting, introducing windowed fitting to focus on material-revealing interactions and Hallucinated Forcing to disentangle nonphysical motion hallucinated by the VDM from material responses. The second, PhysComp decomposes complex interactions into individual objects and semantic components, enabling their physical parameters to be optimized independently and flexibly composed for joint simulation. Experiments on PhysAssets and Google Scanned Objects demonstrate that, compared with existing methods, PhysForge provides stronger control over material-dependent physical responses while supporting component-level physical modeling for complex interactions. It achieves the best CLIP and physical controllability scores on both common and uncommon materials, with qualitative comparisons, component-level ablations, and a user study further supporting these improvements. Our project page is available at https://masterwanna.github.io/PhysForge.html .

---

### Retractions Revisited: A Replication, Extension, and Mechanistic Evaluation of Linguistic Obfuscation Effects in Fraudulent Science

Authors: David M. Markowitz
Published: 2026-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.13678v1

Prior work suggests fraudulent scientists write their articles with higher rates of linguistic obfuscation than genuine scientists, with a possible mechanism suggesting obfuscation makes research more costly for a reader to analyze. This result has not undergone additional empirical scrutiny in the open science era, nor have other psychological mechanisms been evaluated. The current replication and extension addressed this opportunity by comparing 800 fraudulent and 800 genuine control papers (2013-2025). The results supported the linguistic obfuscation hypothesis, suggesting fraudulent papers were more obfuscated than genuine ones. A parallel mediation model evaluated three competing mechanisms, finding that reality monitoring, as measured through decreased rates of adjectives, best explained the link between fraudulent science and linguistic obfuscation. Cross-validated detection accuracy using obfuscation features (60.7%) and an elastic net of over 100 language dimensions (71.6%) were significantly greater than chance. Implications for scientific fraud and psychology of language research are discussed.

---

### On the Encoding of Calendar Features in Covariate-Informed Time Series Foundation Models

Authors: Alexander Kreusel, Maximilian Beichter, Alexandra Nikoltchovska, Benjamin Schäfer, Ralf Mikut, Frederik Zahn, Veit Hagenmeyer
Published: 2026-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.13676v1

Time series foundation models (TSFMs) increasingly offer covariate support, with calendar information being the most common type of categorical covariate in practice, as it is available for every point in time. However, how these features are encoded is largely treated as an implementation detail rather than as an object of study, despite encoding being one of the few design choices left for pretrained models at inference time. With the present study, we demonstrate that the way information is propagated into the model substantially affects forecast accuracy of TSFMs. Therefore, we systematically compare seven calendar encodings, including three conventional target-agnostic representations (ordinal, one-hot, and cyclic) and four target encodings, across four state-of-the-art TSFMs on nine datasets from multiple domains in a zero-shot rolling evaluation. The nine datasets are influenced by social activities, such as weekends and holidays, making calendar information particularly relevant for forecasting. We find that encoding choice affects forecast accuracy across all models, with MASE differences of up to 9.9 % on non-holidays and 83 % on holidays within a single model. Effectiveness and utilization vary substantially across models. Improvements are concentrated around holidays, where calendar information provides signals unavailable from target history, while some model encoding combinations also improve non-holiday forecasts. A SHAP-based attribution analysis locates the contribution of the covariates relative to the autoregressive component and explains why some model-encoding combinations degrade performance. Our findings suggest that current benchmarks for covariate-informed TSFMs can distort model comparisons by imposing fixed encoding strategies.

---

### Can Multimodal Decision Models Classify Breast Ultrasound Images? Benchmarking CLEF and CLEF-Flash Across Prompts and Datasets

Authors: Tran Cao Minh, Hai Tran, Ha Minh Tan
Published: 2026-10-09
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2610.13675v1

Multimodal decision models return probabilities over predefined alternatives, offering a structured interface for image classification. This study benchmarks inference with CLEF and CLEF-Flash on 2818 breast ultrasound images from Dataset B, BUSI, and BUS-BRA. Dataset B and BUS-BRA use binary benign-malignant classification, whereas BUSI includes normal, benign, and malignant categories. Model parameters remain unchanged, and original images are submitted without user-defined preprocessing. Three prompts provide minimal labels, an explicit classification task, or sonographic criteria. We report accuracy, macro F1, balanced accuracy, macro precision, throughput, and latency. CLEF-Flash with the clinical prompt achieves the highest accuracy on all three datasets: 74.85% on Dataset B, 66.28% on BUSI, and 51.63% on BUS-BRA. On BUSI, however, CLEF with the task-guided prompt achieves the highest macro F1 (64.51%) and balanced accuracy (68.72%). CLEF-Flash has lower latency in every matched comparison. Clinical instructions improve CLEF-Flash accuracy relative to the minimal prompt but reduce CLEF accuracy on all datasets. Confusion matrices reveal frequent benign-to-malignant errors, particularly on BUS-BRA, where all configurations fall below the 67.63% accuracy of a majority-class predictor. These findings demonstrate dataset-and prompt-dependent performance and motivate class-specific evaluation before applying multimodal decision models to breast ultrasound analysis.

---

### Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels

Authors: Weiqi Sun, Qianyue Wu, Wenjia Wang, Tianyang Hu
Published: 2026-10-09
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.13674v1

Linearizing softmax attention offers a route to efficient Transformer inference, but preserving pretrained attention remains challenging. We identify an important source of approximation error overlooked by standard linearization methods: a small number of outlier dimensions contribute disproportionately to query-key dot products and account for a large fraction of the approximation error. Motivated by this heterogeneity, we propose Outlier-Aware Attention Linearization (OAL), a dimension-aware method for constructing quadratic attention approximations. Starting from a second-order Taylor approximation, we introduce a Hadamard-product formulation that makes individual query-key contributions explicit. This formulation relaxes globally shared coefficients to support dimension-specific linear terms and cross-dimensional quadratic interactions while preserving separable evaluation. To retain this flexibility with fewer parameters, OAL groups dimensions with similar contribution scales to share coefficients, while allowing distinct treatment of the few outliers. The resulting positive quadratic kernel is calibrated against pretrained attention outputs and admits linear-time evaluation with respect to sequence length for fixed head dimensions. On Qwen2.5-0.5B, OAL reduces frozen-attention output relative MSE by approximately 8.9% compared with DiJiang. Replacing middle-layer attention modules and jointly fine-tuning the kernel coefficients with LoRA further lowers WikiText-103 perplexity from 31.71 to 27.50 compared with a learned global quadratic, while improving accuracy on PIQA, HellaSwag, and ARC-E. These results demonstrate the value of outlier-aware dimension grouping for both attention approximation and pretrained-model conversion. The code is available at https://github.com/wuqianyue09/OAL

---

### Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction

Authors: Jiwon Jeon, Myungsik Cho, Jeonghye Kim, Youngchul Sung
Published: 2026-10-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.13672v1

Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune an LLM to generate revisions or feedback, we learn where to intervene in failed rollouts and determine how to redirect them. To choose where to intervene, we train a 130K-parameter MLP head on a frozen encoder using only final-answer correctness. For redirection, we find that under a fixed generation budget, the tested inline injections fail to reliably redirect reasoning, whereas presenting the same instruction in a new user turn changes the model's course. The resulting correction framework, UPTURN (User-Prompt TURN injection at a learned position), requires no LLM fine-tuning: it retains a selected prefix, injects an instruction as a new user turn, and regenerates the suffix. Across four reasoners and six math benchmarks, UPTURN improves average accuracy in every setting over a 32-rollout baseline. It outperforms self-correction and reflection-token injection baselines under matched correction budgets, transfers across reasoners and to GPQA-Diamond without retraining, and complements GRPO and self-correction methods.

---

### A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO

Authors: Ronghan Li, Fei Chen, Mingyu Lu
Published: 2026-10-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.13669v1

Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection because they are more likely to yield informative group-relative learning signals, and prioritizing them can improve training efficiency. However, it remains unclear whether persistently selecting such samples also leads to the strongest final model performance, or whether training can benefit from progressing toward harder samples. Meanwhile, sample difficulty changes as the policy evolves, so fixed difficulty estimates can become misaligned with the current policy. We therefore re-estimate sample difficulty under the current policy and, inspired by the easy-to-hard principle of curriculum learning, design and evaluate a staged curriculum that progressively shifts the active difficulty band toward harder samples. Experiments on GSM8K show that persistent medium-difficulty selection does not achieve the strongest observed performance. Across three random seeds, progressing to a moderately harder difficulty band improves test accuracy to $0.6591 \pm 0.0077$, compared with $0.6449 \pm 0.0024$ for the fixed-medium curriculum. However, further progression to a harder difficulty band reduces accuracy to $0.6405 \pm 0.0053$. These results show that staged difficulty progression can outperform persistent medium-difficulty selection, but its benefit is non-monotonic. Effective GRPO curricula can therefore benefit from progressing beyond medium difficulty, while avoiding excessive progression toward overly difficult samples.}

---

### A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models

Authors: Ivan Moloshnikov, Dmitry Kunitsyn, Alexander Sboev, Maksim Skorokhodov, Roman Rybka, Yuanchao Liu
Published: 2026-10-09
Categories: cs.AI, cs.CL, cs.LG, cs.MA, cs.NE
arXiv: https://arxiv.org/abs/2610.13663v1

Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usually manual. This paper addresses the automatic tuning of these components and proposes a framework transferable across models of different nature. The multi-agent large language model (LLM) framework has three roles---analyst, coder, and recorder~---with an experiment log and a sandboxed execution environment. Unlike systems that optimize the entire ML script or search architectures in a discrete space, the framework operates over an open but semantically narrow space: the agent generates code only for the specified components, leaving the overall network structure unchanged. The approach is validated in two directions: tuning a classification spiking neural network with correlation learning, and solving high-order differential equations with Physics-Informed Neural Networks (PINN). Across five tasks---spiking classification on MNIST and Digits, and boundary-value problems for the generalized nonlinear Schrödinger equation (GNLSE) and Kuramoto--Sivashinsky (KS) equations---the agent outperforms the baselines: classification accuracy is 13 percentage points (MNIST) and 6 percentage points (Digits) higher; the error against the analytical single-soliton solution is reduced approximately 2491-fold; the invariant-preservation error drops approximately 325-fold in the selected GNLSE run with a Gaussian perturbation and by more than 100-fold on average over repeated initializations; and the mass drift drops 14-fold for the KS problem with a Gaussian perturbation. The framework thus tunes key components on tasks of different nature without changing its internal structure.

---

### Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM

Authors: Adrien Deliege, Marc Van Droogenbroeck
Published: 2026-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.13660v1

The Abstraction and Reasoning Corpus (ARC) is increasingly used to evaluate whether neural networks can infer task-specific transformations from few demonstrations. Recent ARC models differ in architecture, but also in broader training and evaluation protocols, including pretraining data, data augmentation, test-time setup, and optimization budgets, making conclusions about architecture benefits debatable. In this work, we study how the performance of the vision-inspired VARC and recursion-based TRM models is affected by pretraining and test-time training (TTT) budgets under a common inductive protocol on ARC-AGI-1. We cross five pretraining budgets with four TTT budgets for each test task. Each budget specifies a task-variant count and total sample presentations, defining the controlled training budgets. We observe that increasing TTT sample presentations improves the standard ARC pass@2 metric in all settings for both models. Increasing the TTT task-variant count consistently helps only TRM, whereas VARC often performs better with fewer variants. VARC also remains competitive without pretraining, while TRM benefits much more from it. These results show that pretraining and TTT budgets affect ARC evaluation and motivate reporting at comparable budgets.

---

### Scalable Sparse Autoregressive Variational Inference for Non-Gaussian Spatial Fields

Authors: Paul F. V. Wiemann, Matthias Katzfuss
Published: 2026-10-09
Categories: stat.ML, cs.LG, stat.CO, stat.ME
arXiv: https://arxiv.org/abs/2610.13656v1

Latent field models are essential for spatial statistics, but the posterior distribution of the latent field, even with a Gaussian process (GP) prior, is analytically intractable whenever the likelihood is non-Gaussian. Existing approximations are either too slow or too restrictive for large non-Gaussian datasets. We present a scalable variational inference framework that mirrors the sparse nearest-neighbor autoregressive structure of the prior in the variational family, uses normalizing-flow conditionals for expressiveness, and amortizes all variational parameters via a single shared neural conditioner. Doubly stochastic optimization with reduced ancestor sets achieves polylogarithmic complexity per iteration.

---

### TabReliBench: Evaluating Tabular Foundation Models Beyond Predictive Accuracy

Authors: Tianqi Zhao, Jia Guo, Yan Shuo Tan, Qiong Zhang
Published: 2026-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.13654v1

Tabular foundation models (TFMs) are increasingly popular for their strong predictive performance. Many also provide posterior predictive distributions (PPDs), whose reliability remains less studied. We assess reliability through point prediction, distributional quality, marginal and subgroup calibration, and interval efficiency. We then introduce TabReliBench, a large classification and regression benchmark for these comparisons and dataset-level analyses. We find that TFMs' rankings change between TabArena and our benchmark and across reliability metrics. Regression TFMs usually achieve near-nominal marginal coverage and retain narrow intervals, but this favorable marginal behavior does not imply valid conditional coverage. Dataset-level analyses show that classification difficulty often accompanies poor calibration, whereas regression predictive performance is not a reliable indicator of calibration. Ensembling improves predictive performance but does not consistently improve calibration of PPDs; TFMs also benefit little from conformal post-processing, which does not reliably resolve subgroup gaps. Reliable TFM selection therefore requires multidimensional evaluation beyond aggregate rankings. Code is available at https://github.com/Tianqi-Zhao/TabReliBench.

---

### A Critical Look at Power Sampling when Test Time Sharpening LLMs

Authors: Abiel Malkani Talwar, Christopher Nemeth, Henry Moss
Published: 2026-10-09
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.13653v1

Reinforcement learning with verifiable rewards (RLVR) has substantially improved LLM reasoning, yet growing evidence suggests it mainly performs distribution sharpening: concentrating probability mass on reasoning paths the base model already produces. Recent work therefore seeks RLVR's gains without needing reward signals, by sampling from the power distribution $π_α\propto π_{\text{base}}^α$ via Markov chain Monte Carlo or sequential Monte Carlo. We show that these samplers fail to converge to $π_α$ under realistic compute budgets, and that their gains are largely recreated via simple Best-of-$N$ with appropriate grading . This suggests they succeed by selecting high-probability sequences, not by approximating $π_α$, raising a natural question: is the power distribution itself a worthwhile target? We test this hypothesis directly by fine-tuning the base model to match $π_α$, sidestepping sampler convergence issues entirely. Despite approximating the target far more faithfully than existing samplers, this strategy yields gains that are noisy and specific to certain models and sampling tasks. Together, our results suggest that the value of power sampling lies not in faithfully targeting $π_α$, but in the simpler goal of extracting sequences the base model already deems likely.

---

### Electron-Density-Informed Molecular Property Prediction Using Surrogate Functionals

Authors: Manuel V. Klockow, Simon Wagner, Roman Remme, Dominic Plein, Fred A. Hamprecht
Published: 2026-10-09
Categories: physics.chem-ph, cs.LG
arXiv: https://arxiv.org/abs/2610.13649v1

Machine learning methods are increasingly used to predict chemical properties directly from the molecular structure to bypass the often prohibitive cost of quantum mechanical calculations. Recent work has shown that including the ground-state electron density as input to the machine learning model can improve accuracy in this setting. This work employs the recent surrogate functional framework originally developed for orbital-free density functional theory and extends it to predicting molecular properties. We show that passing the ground-state density as input to the model, while simultaneously enforcing it to be the minimum of the surrogate functional, surpasses state-of-the-art performance for six out of seven extensive properties of the QM9 dataset. Additionally, the approach shows improved generalization to larger molecules taken from the QM40 dataset. On all extensive properties of both datasets, our approach outperforms models that are informed by the ground-state density but do not enforce the surrogate functional constraints.

---

### SelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular Data

Authors: Bastian Schäfer, Dominika Matus, Lennart Purucker, Ricardo Knauer, Erik Rodner, Frank Hutter, Anton Sokolov, Arnaud Liefooghe
Published: 2026-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.13644v1

Selecting a subset of features (columns) from a tabular dataset is a ubiquitous challenge in real-world applications. Industry experts seek to minimize model training costs, climate scientists require an interpretable subset of factors to understand extreme weather events, and clinicians need to choose among diagnostic tests due to financial and time constraints. When looking at the scientific literature to determine which feature selection method to use, practitioners across domains face an unrepresentative landscape of benchmarking. Despite extensive research, existing feature selection benchmarks provide limited guidance because they rely on outdated models, ad hoc evaluation protocols, or artificially generated data that do not reflect real-world problems. To close the gap between scientific benchmarking and real-world applications, we introduce SelectArena, a modern benchmark for feature selection. We compare 15 widely used feature selection methods on 71 manually curated real-world tabular datasets, covering classification and regression problems, using standardized evaluation protocols and state-of-the-art tabular (foundation) models. Our results reveal clear trade-offs across predictive performance, runtime, stability, and validity. Tree-based methods, CART and RFImportance, along with F-Test are Pareto-optimal when taking into account predictive performance and runtime. F-Test, information-theory-, and distance-based methods lead on stability and validity, with F-Test emerging as a balanced choice across our metrics. Search-based methods are slow, unstable and achieve low performance. SelectArena turns these findings into practical guidance and, as an extensible platform, supports future feature selection research.

---

### Learning Size Independent Constraint Models from Input Data and Positive and Negative Example Solutions

Authors: Helmut Simonis
Published: 2026-10-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.13640v1

In this paper we describe a Constraint Acquisition Tool that generates size independent constraint programs from input data and positive and negative example solutions of multiple problem instances. The system finds size specific models based on typical constraint patterns over global and binary constraints, then generalizes the models to a size independent model that can be run on unseen input data. The system produces MiniZinc code as well as a textual description of the model. We evaluate the tool on the example problems of the PTHG21 Challenge and show the feasibility of the approach.

---

### Model-agnostic Knowledge Augmented Machine Learning for Weakly Annotated Bioimaging Data

Authors: Jayanie Bogahawatte, Sachith Seneviratne, Simon Maksour, Dzung Do-Ha, Elizabeth Qian, Samuel Brennan, Matthew Keon, Lezanne Ooi, Saman Halgamuge
Published: 2026-10-09
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.13637v1

Machine learning models are increasingly used for automated feature extraction from weakly annotated bioimaging data, such as microscopy and cytomorphology images. Due to the sole dependency of automated feature extraction, existing methods yield inconsistent classification performance across weakly annotated datasets. Here, we propose a model-agnostic knowledge augmentation method that enables ML models to exploit domain knowledge beyond what automated feature extraction can capture. The proposed approach improves classification performance across seven ML architectures. When integrated with masked autoencoder-based self-supervised learning, our method achieves the strongest overall performance, improving precision by 2.9% over the next-best method on three in-house microscopy datasets and by an average of 6.8% across three public cytomorphology benchmarks. We perform nucleus-level classification based on mislocalization of TAR DNA-binding protein 43 (TDP-43) from the nucleus to the cytoplasm, a phenotype linked to Amyotrophic Lateral Sclerosis (ALS), using three independent microscopy datasets of motor neurons derived from human induced pluripotent stem cells. Accurate quantification of this phenotype at scale remains challenging and may contribute to inconsistencies across studies. Application of the best-performing model to these microscopy datasets reveals biological interpretations related to ALS, including dose-dependent effects of the proteasomal stressor, MG132, and the oxidative stressor, sodium arsenite (SA), on TDP-43 mislocalization, variable pathology in motor neurons from sporadic and familial ALS donors, and a lack of protection of the pharmacological compounds, edaravone and niclosamide, against SA-induced TDP-43 mislocalization. Together, our pipeline enables in-vitro cellular image analysis to advance understanding of ALS-associated pathology and potential treatments.

---

### Benchmarking Answer-Grounding Consistency in Remote Sensing Visual Question Answering

Authors: Ping Guo, Zhiqi Huang, Xinran Li, Linkun Yu, Jingyin Pei, Kamata Seiichiro
Published: 2026-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.13636v1

In grounded remote sensing visual question answering, a model produces a textual answer and identifies relevant objects in the image as grounding evidence. Existing evaluations measure answer correctness and localization quality, but do not directly assess answer-grounding consistency. We propose the Answer-Evidence Support Protocol (AESP) to assess this consistency through evidence support: whether the grounding evidence supports the model's own answer. AESP applies task-specific rules to existence, counting, and comparison questions. We further construct the Grounded Remote Sensing Visual Question Answering (G-RSVQA) benchmark, containing 15,027 samples with questions, reference answers, and all related object-level annotations. Experiments on seven grounded vision--language models reveal failures of evidence support across all three question types. Up to 50.82% of correct answers in the evidence evaluation subset are not supported by the provided grounding evidence.

---

### PANDA: Prior-guided Attentional Dual-path Architecture

Authors: Rishabh Jain, Federico Belotti, Stefano Coniglio, Pietro Lio, Stefano Fiorini
Published: 2026-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.13635v1

Hypergraph Neural Networks (HNNs), designed to model higher-order relations beyond pairwise interactions, typically rely either on fixed structural weights or on normalised attention. Fixed weights can propagate misleading information in heterophilic settings, while normalisation makes attention coefficients competitive, in the sense that, in a message-passing framework, increasing the weight of one sender must reduce the weight of others in the same aggregation set. Our main contribution is the introduction of PANDA (Prior-guided AttentioNal Dual-path Architecture), a plug-in for two-stage message passing HNNs applicable to both undirected and directed settings. The main path interpolates between learned receiver-normalised attention and structural incidence priors, while a non-competitive (not normalised) auxiliary path lets each sender contribute its own transformed information. We also show that, with fixed structural coefficients, PANDA recovers a certain complex-valued convolution operator adopted in previous works. Across four HNNs spanning spatial and spectral methods in both directed and undirected settings, plugging PANDA in yields an average improvement of 5.18 percentage points across eight real-world benchmark datasets. The code is available at https://github.com/jainris/panda.

---

### Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify

Authors: Zhengyang Zhang, Jing Xiong, Hongzhou Lin, Juihui Chung, Zijian Zhang, Song Han, Sihao Liu, Ligeng Zhu
Published: 2026-10-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.13632v1

Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized resolution of the Navier--Stokes problem and autonomous solutions to four open questions in the Erdős Conjectures database. Yet neither system releases both its underlying model and complete inference stack. More broadly, a single agent session remains brittle on difficult problems: early errors can propagate, missing domain knowledge can stall progress, and apparent success can mask a misinterpretation or weakening of the original task. We introduce HOA (Humanize Olympiads Agent), an open, flow-level framework that coordinates multiple agent sessions through three complementary feedback channels. First, an independent reviewer evaluates each candidate and provides actionable feedback. Second, a structured wiki supplies task-specific knowledge that may be missing or unreliable in model pretraining. Third, a verifier checks generated Lean proofs against trusted challenge statements. With GPT-5.6 Sol, HOA achieves perfect scores on the IMO, IPhO, and IOI 2026, near-full marks on the IChO 2026 problem set, and solves all 672 problems (100%) on PutnamBench. On the Lean-Eval leaderboard, HOA ranks first, solving 251 of 304 problems (82.6%). We further evaluate HOA with open models. Using Kimi-K3, HOA achieves full scores on the IMO, IPhO, and IOI, and a gold-level score of 97.1% on the IChO. These results closely match the closed-source GPT-5.6 Sol + /Goal baseline on the IMO and IPhO, while exceeding it on the IChO and IOI, demonstrating that systematic feedback can help bridge substantial differences in base-model capability.

---

### Private and Distributionally Robust Federated Multiclass Classification

Authors: Andrea P. Hernandez, Michael Ibrahim, Nagi Gebraeel
Published: 2026-10-09
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2610.13631v1

Fault diagnosis in asset-intensive industries requires multiclass models trained on noisy, sensitive data collected across geographically distributed client sites. Federated learning enables collaborative training without centralizing data, but most approaches do not provide formal privacy guarantees for individual records stored at client sites and can degrade under label noise. To address these limitations, we develop a differentially private, distributionally robust framework for federated multiclass classification that provides sample-level privacy for records stored at each client. We build on a federated Wasserstein distributionally robust multiclass objective with the Crammer-Singer loss, solved using an Alternating Direction Method of Multipliers (ADMM)-based algorithm. To protect the released client updates, our method injects calibrated Gaussian noise into the proximal linearized client updates of both the local model and the local distributionally robust variable before aggregation at the central server, and we quantify the cumulative privacy loss using the moments accountant. We provide per-round sample-level $(ε,δ)$-differential privacy guarantees and an overall composed privacy guarantee across all training rounds, together with convergence results and an explicit privacy-utility tradeoff. Experiments on simulated industrial fault data and UCI benchmark datasets show that our method outperforms differentially private federated empirical risk minimization and stochastic gradient descent baselines in most tested settings, with the largest gains under strong privacy-induced noise.

---

### Multi-Stream Attention Residuals

Authors: Xiaohan Qin, Xiangdong Zhang, Tuo Dai, Sunan Zou, Huaijin Wu, Yebin Yang, Zhuo Xia, Lin Yao, Yuliang Liu, Junchi Yan
Published: 2026-10-09
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2610.13630v1

Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth axis. Inspired by the success of multi-head attention along the sequence axis, we introduce Multi-Stream Attention Residuals (MSAR), an extension of AttnRes that generalizes this mechanism to multi-head depth attention, yielding substantial performance gains with minimal additional overhead. MSAR draws stream diversity from sequence context through multi-scale causal convolutions, allowing different heads to retrieve historical representations through distinct contextual views while preserving the integrity of the hidden representation. The retrieved streams are combined through lightweight adaptive mixing to generate the single-stream layer input. By retaining single-stream sources and expanding them on demand, MSAR supports multi-stream computation without requiring persistent multi-stream storage or communication. Across all 12 downstream benchmarks at the 18B and 28B MoE scales, MSAR consistently outperforms prior residual variants, including standard residual connections, manifold-constrained Hyper-Connections (mHC), and AttnRes. Scaling-law experiments yield an iso-loss compute speedup of $1.58\times$ over the standard residual baseline, compared with $1.35\times$ for AttnRes and $1.30\times$ for mHC. These results make MSAR a promising residual architecture for large-scale pre-training.

---

### JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation

Authors: Faith Ogunwoye, Didar Seyidov, Konstantin Gubernatorov, Dzmitry Tsetserukou
Published: 2026-10-09
Categories: cs.RO, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2610.13628v1

Vision-language-action (VLA) policies issue sparse targets whose arrival at the robot controller is delayed and irregular, so a reasonable predicted action can still produce abrupt motion near people. Remedies are evaluated on different streams, delays and metrics. JitterVLA replays identical commands and arrival traces through alternative controllers, isolating the controller's effect. We apply it to synthetic reaches, hand trajectories from 20 people, three open VLA pipelines (838 episodes) and a physical UR3. Interpolation lowered modeled p99 jerk for every source, by 83% (615 to 106 m/s^3) on human motion with 200 ms delay, at a 2.0 cm tracking cost, and the effect replicated on 598 new episodes; jerk-limited generation lowered jerk further at a larger cost. Entropy-discontinuity associations had opposite, replicated signs in two pipelines, and entropy gating helped in one but not the other. On the UR3, interpolation lowered accelerometer-derived jerk by 3.0-14.0% in all six exploratory pairs, while a position-derived metric did not resolve the contrast. JitterVLA supports screening before human-centred studies; code and data will be released.

---

### AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

Authors: Natapong Nitarach, Phume Ngampornsukswadi, Pittawat Taveekitworachai, Surapon Nonesung, Warit Sirichotedumrong, Kunat Pipatanakul
Published: 2026-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.13627v1

Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph prompt. Sampling reduces this cost, but small balanced subsets change unweighted precision and F1. We introduce AMLworld-Compact, an evaluation set that retains every illicit test transaction and samples benign transactions from supervised-score strata. Its HT-Coreset protocol reduces evaluation targets by 271x and 611x on HI-Small and LI-Small. Horvitz-Thompson weights give unbiased full-test confusion-count estimates for fixed predictions; recall is exact, while precision and F1 are ratio estimates. In a held-out study using Graph Feature Preprocessor (GFP) features, one boosted-tree family defines strata for evaluating the other over 500 draws per configuration. At the released sizes, F1 RMSE is 0.00-2.58 percentage points versus 4.44-7.41 for uniform sampling with HT weights; conservative intervals remain broad. Under the evaluated graph prompts, seven open-weight LLMs have weighted precision near the predict-all-illicit baseline. In an outcome-stratified audit of 1,000 HI-Small few-shot outputs from one run per model, lexical checks pass for 84.5% of correct and 56.2% of incorrect binary verdicts, so these markers do not establish correctness. We release the evaluation sets, construction code, and audit tools at https://huggingface.co/datasets/typhoon-ai/AMLworldCompactEval and https://github.com/nat-nischw/AMLworld-Compact.

---

### SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle

Authors: Xiting Liu, Lin Yang, Yitong Zhang, Jia Li, Shi-Min Hu
Published: 2026-10-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2610.13626v1

Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about their trustworthiness, with deception posing a particularly important risk. Deceptive behavior takes the form of misleading responses or assistance in fabricating, concealing, or distorting information. To study this behavior, we introduce SWE-DeceptionBench, a benchmark for evaluating LLM deception in software engineering. The benchmark covers six lifecycle stages and two deception triggers: Active Deception, where models recognize infeasible or conflicting requirements but still present them as achievable, and Passive Deception, where models help fulfill explicit user requests to mislead others. We further introduce Neutral, Reward, and Pressure conditions to study the effect of external inducements, resulting in 720 test instances in Chinese and English. Evaluating seven mainstream LLMs, we find substantial deception even under the Neutral condition, with aggregate rates of 49.88% for Active Deception and 64.29% for Passive Deception. Deception rates vary across lifecycle stages, and external inducements affect Active and Passive Deception to different extents. We also evaluate lightweight defenses, finding that guard models miss many deceptive requests, and Self-Reminder reduces but does not eliminate deceptive responses. These findings highlight the need for more effective deception detection and mitigation methods to support trustworthy LLM-based software engineering.

---

### Kernel-based External Validity of Experimental Studies

Authors: Federico Matteucci, Gerhard Neumann
Published: 2026-10-09
Categories: stat.ME, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.13625v1

The external validity of a study is the extent to which its findings generalize to unseen experimental conditions, such as datasets. We formalize the results of a study together with its research question, and define external validity as the probability that two independent and same-sized replications of the study produce results whose maximum mean discrepancy (MMD) is below a given tolerance. This approach, centered on the choice of a space of results and of an appropriate reproducing kernel for the MMD, is flexible enough to be deployed on multiple different types of results and research questions. Additionally, we establish an asymptotic power-law relation between the size of a study and the quantiles of the MMD, which we use to estimate the desired size of an externally valid study from a small-scale preliminary study. We deploy our framework to rankings with ties and discuss kernels suited to different research questions. Experiments on existing case studies and on a simulated newly designed study illustrate the applicability of the framework. We release our code as part of the genexpy Python module.

---

### APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

Authors: Ziyi Yang, Adel Bibi, Guohao Li, Bernard Ghanem, Carlos Hinojosa
Published: 2026-10-09
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2610.13623v1

Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environments create safety risks that are difficult to capture with attacks placed at a single, known read location. We introduce APEX-Harm, a benchmark for evaluating prompt and script injection against long-horizon agents performing finance, consulting, and legal tasks in large workspaces. Each task contains 115 to 328 files, together with email, calendar, chat, document, spreadsheet, PDF, and code-execution tools exposed through MCP servers. The benchmark includes six attack categories covering static and dynamic injections, task-specific script replacement, and attacker-provided generic scripts, and evaluates attack success, exposure, and task performance. We evaluate 12 frontier models on 180 task instances per model. Opus 5 and Sonnet 5 have the lowest overall attack success rates (8% and 20%), while task-specific script replacement and attacker-provided generic script attacks remain substantially more effective, averaging 81-84% and 73% attack success, respectively. Gemini 3.8 Flash achieves the highest mean task score (0.877) while still exhibiting a 33% attack success rate. These results show that completing the requested task is not sufficient evidence of safe behavior: an agent can produce a correct deliverable while also performing an unauthorized action in the workspace.

---