# Research Papers — 2026-10 · bundle page 27 of 156

> Full-text markdown of papers #1301–1350 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/27
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/26.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/28.md)

### A Gradient-Regularized Deep Learning Method for Restoring Image in Myopic Vision

Authors: Kebin Contreras, Luis Toscano-Palomino, Rafael Torres, Jorge Bacca
Published: 2026-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.19218v1

Myopic vision degrades the quality of human vision due to spherical eye defocus aberrations that impair the perception of fine spatial details. To address this limitation, this work proposes a deep learning-based approach to computationally design transformed images that allow individuals with myopia in fixed distance to perceive scenes with enhanced clarity. The method trains a neural network to counteract defocus aberrations modeled using the second-order Zernike polynomial $Z_2^0$. The approach employs a U-Net architecture trained with a loss function combining reconstruction error minimization with spatial difference structural preservation through $\ell_1$ regularization. Training is carried out exclusively on the KITTI dataset, while testing is performed on DIV2K and ImageNet datasets, demonstrating generalization across diverse image distributions. Under myopic conditions modeled by $Z_2^0$, baseline performance shows visual degradation with PSNR values ranging from 19.47 to 27.42 dB across datasets and severity levels. The proposed gradient-regularized method achieves consistent improvements, delivering PSNR gains ranging from 1.48 to 7.34 dB and significantly lower perceptual compared to classical baselines.

---

### Narrowing the Collaboration Gap, Probably

Authors: Mirah Shi, Marcel Hussing, Ira Globus-Harris, Natalie Collina, Aaron Roth, Surbhi Goel
Published: 2026-10-13
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2610.19215v1

Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents concisely communicate in a way that promotes aggregation of decision-relevant information? Communicating only proposed actions can discard decision-relevant uncertainty: two agents may prefer the same action for different reasons. We study an alternative interface in which agents communicate calibrated beliefs over actions. We first analyze a simple synthetic setting that captures the structure of multi-round reasoning under partial information. In this setting, we show theoretically and empirically that communicating unbiased probabilities can be strictly more powerful than communicating actions. We then test the same principle in a collaborative maze-solving task with trained transformers and pretrained LLM agents. Our results demonstrate that probability communication outperforms action communication when the exchanged predictions preserve calibrated uncertainty. When communicated probabilities are biased, we show that the benefits of probability communication can disappear. We give a post-hoc conversational calibration intervention that consistently improves decision-making by correcting these biases both in a toy transformer setting and when pretrained LLMs use the corrections in context. These results suggest that probabilistic communication is useful for multi-agent collaboration not merely because it transmits more information, but because calibrated uncertainty gives other agents a reliable object to update on.

---

### PREFER: From Player Experience to Personalized Game Refinement

Authors: Qi Chai, Zhang Zheng, Lu Yang, Zixun Sun, Hao Wang
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19213v1

Understanding how large language models (LLMs) evaluate gameplay experience is important for using their feedback to guide game design. However, overall ratings alone provide limited insight into which aspects of experience are associated with these judgments and how they can inform concrete game changes. We introduce PREFER, a framework that uses a shared set of experience dimensions adapted from established psychometric questionnaires to benchmark how models evaluate gameplay and to guide persona-specific game refinement. Through these dimensions, we characterize the perspectives models offer as virtual playtesters by examining how their overall assessments relate to specific aspects of experience and to the gameplay they produce. To examine how the same dimensions can guide refinement for players with different preferences, we use personas to simulate distinct player profiles. For each persona, PREFER uses experience-preference relationships to select refinement objectives, revises game rules and their implementations, and playtests candidate games to assess experience changes and predicted preference gains. Experiments with five personas show that PREFER achieves 9.2% higher mean post-play preference ratings than the strongest evaluated baseline.

---

### Decoupled Drift-Diffusion World Models for Consistent Future Frame Prediction

Authors: Anton Arapin, Aditya Singh, Yixin Wang, Jun Gao, Bernadette Bucher
Published: 2026-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.19212v1

World models of visual information predict future image frames conditioned on given action sequences. This predicted scene evolution is driven by deterministic changes such as controlled motion on a robot platform, as well as stochastic changes such as rendering of manipulated objects or previously occluded regions. Our key insight is that the spatial location of these stochastic changes is itself learnable. We leverage this insight by jointly regressing both the deterministic next-state prediction and the spatial uncertainty map, then using the uncertainty map to guide a conditional diffusion process. We propose Decoupled Drift-Diffusion World Model (D3WM), which uses a transformer trained with a Gaussian negative-log-likelihood objective to produce both the deterministic next-state prediction and a spatial map of heteroscedastic aleatoric uncertainty. The learned uncertainty map then provides a structured spatial gate for a conditional diffusion model: deterministic regions are anchored to the predicted state, while uncertain regions, such as disocclusions or dynamic textures, are sampled by the diffusion process. We frame this decomposition under a variance-gated stochastic differential equation that separates deterministic drift from stochastic diffusion. D3WM shows improved results over competitive baselines in two distinct types of action spaces: robotic tabletop manipulation and camera motion.

---

### Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings

Authors: Matteo Ceriscioli, Shohei Shimizu, Mallika Gupta, Karthika Mohan
Published: 2026-10-13
Categories: stat.ML, cs.AI, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2610.19211v1

While causal discovery methods have matured for complete data, such algorithms for handling missing values remain limited. We establish general sufficient conditions under which causal graphs remain identifiable (i.e., uniquely determined from the available data distribution) under various missingness categories, including Missing Not At Random, and provide a framework to extend correctness guarantees from causal discovery algorithms for complete data to missing data settings. Our results show that identifiability of causal graphs with no unobserved confounders is preserved when (1) missingness mechanisms do not causally interact, (2) no variable directly causes its own missingness, and (3) either faithfulness holds for missingness mechanisms, or they follow generalized linear models. Guided by these theoretical results, we introduce two asymptotically correct algorithms for Additive Noise Models (ANMs) that recover the underlying causal graph and provide consistent parameter estimates.

---

### Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules

Authors: Sarah Pan, Ali Behrouz
Published: 2026-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.19210v1

Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference requires increasingly large KV caches. Efficient recurrent alternatives reduce the asymptotic complexity of inference, but their sequential dependence limits token-wise parallelism during training, making them harder to scale. Further, the current paradigm of extending long context tasks creates competing notions of retaining information precisely and keeping long-context inference efficient. To address this gap, we introduce Titan-Llama, a post-training method for retrofitting attention-based language models with a hierarchical memory architecture that updates parameters at test-time. Titan-Llama applies a blockwise attention mask and preserves full-fidelity attention over recent tokens while compressing historical context into recurrent, fixed-size neural memory modules (NMMs). Our formulation allows pre-trained attention layers to be replaced without training a new language model from scratch. On Llama-3.2-1B-Instruct, Titan-Llama raises accuracy over segmented attention windows from 23.87\% to 40.51\% on QuALITY and from 14.50\% to 40.75\% on LongHealth. Inference benchmarks show more than 20\% faster prefill, 37\% faster decode at medium context lengths, and 24\% lower steady-state decode memory usage in the evaluated configurations. Together, these results demonstrate that incorporating memory architecture mechanisms that utilize test-time training effectively modulates long-context behavior of pre-trained models, offering a practical route to adapting pre-trained transformers for efficient long-context inference. Our code is released on Github \href{https://github.com/sarahpannn/titans-pytorch/tree/main}{GitHub}

---

### Finite-sample certification of coverage regret for budgeted document selection under adaptive stratified auditing

Authors: Nora Serdyukova
Published: 2026-10-13
Categories: math.ST, cs.AI
arXiv: https://arxiv.org/abs/2610.19207v1

Selecting a budget-constrained set of documentary fragments, for instance the knowledge base of a retrieval-augmented generation system, raises a statistical question: how much expected query coverage is lost relative to the best feasible selection when the query distribution is unknown? We construct finite-sample, distribution-free upper confidence bounds for this coverage regret that remain valid after data-dependent selection. A pilot stage may select the document set, screen competitors, build comparison networks and learn an annotation policy. Then an independent audit acquires relevance labels with probabilities that are constant within observable strata. The main result is a simultaneous bound for all retained coverage contrasts. The bound is made observable by empirical-Bernstein variance calibration or by a one-stage construction without calibration, and it accounts for estimated stratum proportions. For maximum-type coverage we prove variance contractions for swaps of redundant fragments, give a condition under which multiscale radii improve on a direct union bound, and show that such redundancy cannot be certified from samples alone. A simulation study confirms validity and quantifies the gains from variance calibration and certified redundancy.

---

### DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression

Authors: Yiheng Su, Junyi Jessy Li, Matthew Lease
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19206v1

While work on LLM-based regression has largely focused on scalar prediction, multi-output text regression remains less explored. We present DualView, a parameter-efficient approach to leverage LLMs for multi-output text regression. \method{} first extracts broad and output-specific representations from a frozen LLM, then uses a dual-branch architecture to produce the full score vector. Across five heterogeneous regression tasks and eight LLMs (up to 122B), DualView outperforms seven supervised regression baselines while requiring 82--1842 times fewer fitted parameters than the three strongest baselines. These improvements extend across individual output dimensions and persist even with limited training data. Notably, DualView using a smaller open-weight LLM can outperform unsupervised prediction with Gemini 3.1 Pro. Controlled ablations show that broad and output-specific evidence provide complementary predictive benefits, while lightweight shared predictors achieve strong performance with fewer trainable parameters.

---

### Weighted Ensemble Sampling for Rare-Event Estimation in Language Models

Authors: Zixuan Liu, Gustavo Didier, Fangzheng Wu, Brian Summa, Zizhan Zheng
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19202v1

Rare but severe failures of large language models can become practically significant at deployment scale. Estimating their probabilities with direct Monte Carlo sampling is highly inefficient, while proposal-based methods typically require auxiliary learning of an additional proposal distribution. We introduce \textbf{Weighted Ensemble (WE)}, a training-free framework for rare-event estimation in language models. WE samples exclusively from the original language model and improves upon direct Monte Carlo by periodically reallocating the sampling budget toward prefixes that appear more likely to reach the target rare event. To guide this reallocation without learning a separate proposal distribution, we exploit internal LLM representations as prefix-level signals and empirically validate their effectiveness. We provide a theoretical analysis of the proposed algorithm. Experiments on safety-related tasks spanning both small-scale and modern large-scale LLMs demonstrate that WE improves the efficiency and reliability of rare-event probability estimation.

---

### Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors

Authors: Henry Che, Xuanchi Ren, Sanja Fidler, Shenlong Wang, Laura Leal-Taixé, Shengyu Huang
Published: 2026-10-13
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2610.19201v1

We present LidarVerse, a real-time unified LiDAR world model for sensor simulation across tasks and sensors. Existing LiDAR simulators largely follow one of two complementary paradigms: reconstruction-based methods preserve the geometry of a captured scene but require lengthy per-scene optimization, whereas generative methods amortize learning across data but lack the consistency needed for long-horizon rollouts. LidarVerse brings both paradigms into a single, unified conditional generative framework. A universal tokenizer maps LiDAR range sequences into a shared latent space, where a bidirectional teacher learns a common interface for conditioning on a LiDAR prefix, an HD-Map, a persistent spatial cache, and optionally, text. Varying the available scene evidence turns the same model into a generator of new worlds, a point-cloud forecaster, or a generalizable resimulator of observed scenes without per-scene optimization. We distill the teacher into a four-step autoregressive causal student and maintain both a rolling temporal K/V cache and a world-aligned spatial cache, enabling persistent long-horizon rollouts with real-time inference at 11 FPS on a single H100 GPU. LidarVerse achieves state-of-the-art performance on most reported metrics across all three evaluation protocols, while its tokenizer supports 32-, 64-, and 128-beam LiDAR and generalizes to an unseen scanning pattern. These results demonstrate that generative and reconstruction-grounded LiDAR simulation can be realized within one model, providing the core capabilities for future closed-loop sensor simulation.

---

### Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization

Authors: Leonardo Torti, Emanuele Rimoldi, Tomer Galanti, Tomaso Poggio, Pierfrancesco Beneventano
Published: 2026-10-13
Categories: cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.19198v1

With the growing number of LLMs available, selecting which one to use for a prompt has become a key question. A large part of the routing literature relies on semantically embedding prompts into a vector space and then applying a lightweight classifier to the embedded representations. These methods perform robustly in-distribution but they struggle to generalize to unseen tasks. By studying the geometry of semantic embeddings, we trace a clear failure mode: features that determine the neighbors of unseen prompts are an unreliable proxy for LLM selection. We therefore replace the semantic embedding with the following map: we run a partial forward pass of Qwen2.5-7B-Instruct on the prompt and use the hidden state of its last token at a deep layer as the representation. When applying kNN and other simple classifiers to this new representation, we obtain a clear result in generalization: on average across cost penalties, their performance improves. Moreover, kNN and another simple classifier that we propose outperform every evaluated semantic-embedding baseline. Our two simple methods also beat a recent SoTA hidden-states based router on RouterBench.

---

### FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks

Authors: Aiyshwariya Paulvannan Kanmani, Miguel Esparza, Ali Mostafavi
Published: 2026-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19191v1

Wildfire decisions are made in hours, yet most learned spread models predict daily on targets including burned area. We propose FireGraphNet which formulates 12-hour growth as node classification on directed H3 graphs, with candidates ahead of the front and wind alignment, terrain, fuel continuity and barriers on edges. On satellite perimeters it achieves average precision 1.7-1.9x the strongest distance baseline on test California fires and 1.62x out of state. We show this skill comes from message passing rather than cell features or the aggregator, is highest on young fires in state, is carried deep along the wind by its edges, and is hidden by pooling. A convolutional network matches this ranking once trained on new growth, at worse calibration, so candidate construction, target definition, and aggregation shape conclusions about model skill. Editing fuel and barrier attributes reduces predicted spread more under guided than random placement, extending FireGraphNet to operational intervention analysis.

---

### NEPSEE: A Double-Annotated Benchmark for Nepali Sentiment Analysis

Authors: Gaurab Baral, Mimansak Nepal, Grishma Basnet
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19190v1

Many sentiment datasets use one annotator for each item, so the test labels show the conventions of that person. We build a Nepali benchmark from two annotators who labelled the same sentences blind. They labelled 5,614 sentences from tweets of Nepali public figures on a five-point scale. We keep only the 3,189 sentences where both give the same polarity. On the three-class benchmark, NepBERTa with a fixed tokenizer gets a macro-F1 of 0.877 and IndicBERTv2 0.867. Three commercial large language models (LLMs) get 0.882 to 0.896 zero-shot, and these differences are not significant. On the five-point scale, 766 sentences have two adjacent labels, for example Pos and SPos. We accept both labels and train on both. On this task, Claude Opus 5.5 beats the best encoders by 0.10 to 0.12 macro-F1. A tokenizer audit adds a second result. The default tokenizers of three Nepali BERT models delete the non-spacing Devanagari vowel signs and the virama. When we restore the marks, macro-F1 increases by 0.084 for NepBERTa but decreases by 0.095 for a model pretrained on stripped text.

---

### Adaptive Computation with Conformal Certification

Authors: Shehtab Zaman, Aneesh Rangnekar, Nancy Lee, Harini Veeraraghavan
Published: 2026-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19189v1

Scientific imaging data involving medical (e.g., 3D radiographic, microscopic images) and astronomical sensors pose different challenges from natural images. One key challenge is that these datasets are often orders of magnitude larger than natural images. Efficient training and inference on such data is challenging due to the increased hardware requirements, often needing bespoke solutions. Moreover, the relevant objects such as tumors and astronomical phenomena are sparsely distributed with respect to the background information. Standard efficiency techniques like quantization and pruning apply uniform scaling of all regions, potentially compromising the precision/fidelity of predictions. Thus, efficient methods that reduce computational requirements without losing resolution for relevant parts of the data and with uncertainty estimates on predictions are essential. We present \textit{Conformal Adaptation} with risk guarantees for uncertainty-aware sparse computations. Our formalism is general, spanning dense pixel-level classification and regression tasks where hierarchical models predict at low resolution, certify the signal using conformal risk control, and refine the certified predictions. We benchmark our method on multiple tasks such as 3D medical image segmentation, 2D galaxy flux prediction, and 1D calcium spike rate prediction, achieving $2.5$--$72\times$ wall-clock speedup across the various tasks, including on commodity CPUs.

---

### Identity, Incentives, and Cooperative Behavior for AI: Reverse-Engineering Multiagent Cooperation

Authors: Andrew Perrault, Bryan Wilder
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19188v1

The behavior of AI systems increasingly depends on the extent to which agents cooperate or coordinate with one another, in ways that may be desirable or not depending on the situation. Conventional explanations for cooperative behavior distinguish between purely other-regarding preferences ("altruism") and instrumental reasons for self-interested agents to cooperate. The way that agents should enact these mechanisms for cooperation (or not) is complicated by the fact that there is not a clear or unambiguous locus of identity or selfhood for AI agents. For example, it is unclear whether agents involved in instances of misaligned collective behavior are motivated by goals at the level of the collective or by various forms of instrumental reasoning. We develop a framework for reverse-engineering why a given set of agents engage in a particular set of cooperation-related behaviors. We argue that many different mechanisms can often produce similar observed behaviors and introduce a set of experimental designs along with conditions under which they can successfully disentangle competing explanations for multiagent behavior. We apply this framework to interactions from a set of frontier models in a simulated environment and demonstrate that the behavior of different models arises from substantively different mechanisms.

---

### Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent

Authors: Chao Li, Mrinal K. Sen, Sergey Fomel, Yangkang Chen
Published: 2026-10-13
Categories: stat.ML, cs.LG, physics.geo-ph
arXiv: https://arxiv.org/abs/2610.19187v1

Full waveform inversion (FWI) is a powerful tool for high-resolution subsurface model reconstruction, but it remains highly nonlinear and ill-posed, especially when the initial model is inaccurate or the acquired data are noisy and incomplete. Annealed Stein variational gradient descent (ASVGD) provides a particle-based Bayesian framework for FWI by approximating the posterior distribution with an ensemble of velocity models, thereby enabling uncertainty quantification beyond a single deterministic solution. However, conventional ASVGD-FWI commonly relies on simple handcrafted priors, such as Gaussian or smoothing assumptions, which are often insufficient to represent complex geological structures. To address this limitation, we introduce a learned diffusion model (DM) as an implicit regularization mechanism within the ASVGD-FWI framework. Instead of explicitly evaluating the diffusion prior density, the trained diffusion model acts as a learned geological projection operator that guides updated particles toward the distribution of plausible velocity models. In this way, the proposed method combines data consistency from FWI, posterior diversity from ASVGD, and structural realism from the diffusion prior. Numerical experiments demonstrate that the diffusion-regularized ASVGD-FWI produces more geologically consistent mean models, suppresses nonphysical artifacts, and yields uncertainty estimates that are more concentrated around structurally complex and poorly constrained regions. These results suggest that learned diffusion priors can effectively enhance Bayesian FWI by improving both inversion stability and the interpretability of posterior uncertainty.

---

### How to Evaluate When You Don't Know How to Evaluate? Choosing Reliable Setups for Base Language Model Benchmarking

Authors: Shenbin Qian, David Samuel, Jindřich Helcl, Andrey Kutuzov, Stephan Oepen
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19185v1

Evaluation of large language models (LLMs) remains largely pre-scientific: it involves many design decisions, with little guidance on how to make them. These choices can substantially affect measured performance and, consequently, decisions about subsequent pretraining. To identify effective evaluation setups, we investigate 8 aspects, such as task formulation or the number of in-context examples. We compare the setups using three widely-used signal criteria, repurposed as normative meta-measures: monotonicity, non-randomness, and ranking consistency of the evaluation scores across intermediate checkpoints. In an early pretraining scenario, we evaluate these setups on 26 monolingual 2B-parameter models trained on different types of data, using 80 tasks in four languages. We also examine the setups on three larger LLMs ($\geq$7B) in the same four languages and explore how the preferred setups change with model scale. Our results yield concrete recommendations: some choices, such as the use of multiple prompts, are consistently useful, whereas others, such as task formulation, depend on model scale. More generally, our framework serves as a recipe for the choice of evaluation setups in new scenarios.

---

### HERO: Harnessing Evidence for Test-time Refinement and Prompt Optimization in Program Generation

Authors: Mingyu Lu, Timothy Ossowski, Tristan Naumann, Hoifung Poon, Peniel Argaw
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19184v1

Harness optimization improves LLMs by refining reusable prompts and scaffolding, yet requires further adaptation for program generation tasks such as text-to-SQL and text-to-Python. Existing methods often rely on LLM reflectors to propose harness updates, which can fix observed failures but also disrupt previously correct behavior. Text-to-code tasks offer a natural way to mitigate this issue: we can execute generated outputs, allowing us to evaluate and verify the effects of proposed updates directly. Building on this signal, we introduce \textsc{HERO} (\textbf{H}arnessing \textbf{E}vidence for \textbf{R}efinement and \textbf{O}ptimization), which combines offline and test-time harness optimization. At the first stage, \method{} learns reusable prompt updates from execution-verified successes and failures and validates candidate revisions before adoption. At test time, we treat the generated code as an instance-specific harness and refine it using execution feedback. Across four SQL, Cypher, and Python benchmarks, \method{} achieves the best offline performance, improving pass@1 by \(7.6\) points over the initial prompt, while test-time refinement adds another \(2.0\) points and improves execution efficiency.

---

### Learning in Strategic Queuing with Geometric Recharge: From Bandits to Systems

Authors: Cristian Palma Foster, Eva Tardos
Published: 2026-10-13
Categories: cs.GT, cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2610.19179v1

We study packet routing in queuing systems where queues act as selfish, myopic agents that use no-regret learning algorithms to select servers with unknown service rates. To model the small buffers used in data centers, we assume that each server has a single-packet buffer. Even such a tiny buffer already captures the features of buffering: routers can exploit multiple servers while accepted packets remain in service, but packets can occupy servers for multiple rounds, complicating future service and learning. We first analyze a single queue routing packets to $m$ buffered servers with service rates $μ_1, \dots, μ_m$. This setting is equivalent to an instance of the recharging bandits problem with geometric recharge. We prove that any no-regret learner achieves a long-run average throughput of at least the Hamacher sum of the server rates, and that this bound is tight. Consequently, a single no-regret queue is stable if and only if its arrival rate is below the Hamacher sum of the server rates. Moreover, comparing against an optimal policy, we show that any no-regret learner is at least $0.77$-competitive, which is also tight. We then study multi-queue systems where $n$ queues with arrival rates $λ_1, \dots, λ_n$, each at most $λ_{\max}$, compete for service from $m$ buffered servers. We show that the smallest overprovisioning factor that guarantees the system to be stable under high-probability no-regret learning is $\frac{1}{1-λ_{\max}}$. Equivalently, in terms of the total arrival and service rates, the condition $\sum_{i=1}^n λ_i < (1-λ_{\max})\sum_{j=1}^m μ_j$ is sufficient, and sometimes necessary, for stability under no-regret learning. In particular, for $λ_{\max} = 1/2$, this improves the upper bound of Abel et al. (EC 2026) from $3$ to $2$, matching their lower bound and resolving their open question.

---

### Diagnosing Low-Confidence Patient Profiles via Localized Harmful Covariate Shift Detection

Authors: Olivier Lefebvre, Hakima Laribi, Dan Poenaru, Martin Vallières
Published: 2026-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.19178v1

Before deploying clinical prediction models, their reliability must be assessed to ensure safe use. Errors may arise from distribution shifts between training and deployment or from heterogeneous performance where the model systematically underperforms for certain patient subgroups. Yet most post-hoc diagnostic methods evaluate reliability only at the population level, checking whether the deployment data resemble the training data and whether the model performs well on average, without accounting for heterogeneity that may cause some patients to be disproportionately affected. We propose a unified diagnostic pipeline that combines both perspectives. MED3pa first discovers interpretable low-confidence patient profiles, and Detectron is then applied within each profile to test whether its degradation is associated with a detectable harmful covariate shift. Across three clinical prediction tasks and three injected subgroup shifts in MIMIC-IV, we find that shift detectability itself is informative. An injected age shift, undetectable at the population level, was nonetheless localized to specific degraded profiles, whereas sex- and race-related shifts were detected broadly and therefore offered little guidance for identifying the most affected patients.

---

### Multi-System Cognitive Steering for Generative Communication

Authors: Eric Lacosse, Pablo Tano, Daniel C. McNamee
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19177v1

A fundamental bottleneck for translating thoughts to speech is the high physical cost of motor input forcing a strict tradeoff between communication speed and expressivity. Generative AI offers a promising solution by expanding highly abbreviated text input into fluent sentences, significantly reducing the motor burden on the user. However, sparse inputs are inherently ambiguous; without sufficient context, AI models frequently misinterpret these abbreviations and generate outputs that fail to align with the user's true cognitive intent. We propose \textit{Cognitive Steering}, a framework that can be leveraged to reconstruct user intent by grounding Large Language Models (LLMs) in multimodal context and applying AI control methods. We demonstrate that aligning frontier models with selected environmental referents, emotional states, and communication motives on simulated abbreviation benchmarks achieves up to $\sim$88\% top-5 expansion accuracy, doubling no-context baselines. We also reveal that different types of context require distinct AI control techniques: while physical objects in a scene are best provided through explicit text prompts, abstract factors like emotion may be more effectively managed by directly altering the AI's internal activations. These findings suggest a hybrid architecture for future interfaces that leverage Cognitive Steering to help users communicate both quickly and accurately, recruiting multiple AI control methods simultaneously to perfectly capture their intended communication goals.

---

### Learning from Self-Generated Responses: Reliability--Uncertainty Self-Distillation for Reasoning

Authors: Jinhao Pan, Bowen Wei, Yuqing Zhou, Ziwei Zhu
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19176v1

Reference solutions and question-specific rubrics are not always available to guide the teacher in self-distillation. A large language model's own solution attempts offer an alternative, but their quality is difficult to assess in open-ended tasks without automatic correctness checks, and even correct attempts can involve uncertain token predictions. We propose Reliability--Uncertainty Self-Distillation (\method{}) to learn from these attempts. The same model serves as teacher and student: the teacher receives the question and completed attempt, and the student matches the teacher's token-level predictions using a question-only prompt. \method{} weights each attempt's distillation loss by additively combining judged reliability, estimated from a self-judge's score and confidence, with student predictive uncertainty. Across eleven reasoning benchmarks, \method{} outperforms all five baselines in average accuracy, reaching 70.47\% on Qwen3-4B and 76.69\% on Qwen3-8B (8.90 and 2.10 percentage points above the base models). Data and code are available at https://github.com/JP-25/RUSD.

---

### Verification Turns Capability Gaps into Routing Decisions: Small Language Models for Clinical Documentation

Authors: Nina Fatehi, Meysam Ghaffari, Animesh Agarwal, Anushka Swarup, Carlos Morato
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19169v1

Clinical note generation from doctor--patient dialogue is high-volume and hallucination-intolerant: a fabricated laboratory value can create patient-safety risk, not a quality regression. We ask whether an agentic \emph{verification} architecture, rather than generator scale, can make a small language model viable here. Holding a four-evaluator verification stack and refinement policy fixed and swapping only the generator between a 4B-parameter model with a QLoRA adapter and a frontier baseline, the small model reaches $0.984$ claim-level factual entailment against $0.992$ and comes within $3.3$ points on completeness, generating entirely on-device. Its deficit is confined to \emph{inter-section structural fidelity}---arrangement rather than clinical comprehension, and the axis on which it also falls furthest below the corpus's reference notes. Because that deficit is an explicit verifier decision rather than a silent quality difference, it becomes a routing policy: run the small model by default, escalate what the verifier rejects. Measured end to end, that it achieved a similiar verified-rate acceptance to the frontier-only acceptance in this test set ($99.6\%$ vs.\ $98.4\%$ over $250$ encounters) while routing $62$, documenting three quarters without a frontier \emph{generation} call. Ablating the loop separates architecture from scale: unrefined, the small model is accepted on $26.8\%$ of encounters and the frontier model on $74.8\%$, so verification does the most work where the generator is weakest. We also contribute section-scoped refinement, which preserves unflagged sections by construction rather than instruction, and find the baseline is not uniformly stronger---its provider refused two trauma-related transcripts the on-device model handled and certified, one facet of a provider dependency a served adapter does not carry.

---

### Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation

Authors: Anubhav Jangra, Adrian de Wynter
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19166v1

Meta-evaluation of text generation metrics and LLM-judges is primarily conducted using metric-human correlations. However, prior work has shown that correlation is not an appropriate estimate of a metric's evaluation capability and can be unstable across evaluation settings, such as different datasets or languages. Therefore, we propose a regression-based meta-evaluation of metrics that learns on calibrated metric outputs to predict human ratings. We ground this measurement relative to a trivial constant-mean baseline and human agreements to provide a comparable measure of metric capability across evaluation settings. To test our meta-evaluation framework, we developed a large-scale multi-lingual style-personalized text generation (SPTG) benchmark, collecting multiple annotations across 10 topologically diverse languages and four evaluation dimensions, each with varying degrees of subjectivity. We meta-evaluated 32 metrics from three style evaluation paradigms (string-based, embedding-based, and LLM-judges) and their ensembles over these 40 evaluation settings. Our analysis revealed that even simple string- and embedding-based measurements can match strong LLM-judges when calibrated to human ratings. We also identified characteristics of human annotations that determine metric performance, as well as conditions under which a metric ensemble outperforms its individual constituents.

---

### ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models

Authors: Mayank Kulkarni, Rakesh Vaideeswaran
Published: 2026-10-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.19165v1

Many real-world questions demand not a single fact but an organized collection of them, yet existing factual knowledge benchmarks almost exclusively target single answer retrieval. We introduce ListQA, a benchmark of 9,045 human-curated, cross-validated questions (audited error rate of 1.7%) that require LLMs to recall multiple facts and compose them into structured lists of 3-10 elements. Questions range from flat lists ("Which NCAA teams went undefeated between 2000 and 2024?") to hierarchical lists with sub-attributes ("...and what was their record and result?"), spanning eight categories across 60+ countries. An evergreen design (explicit temporal constraints or historically immutable facts) keeps ground truth valid without periodic updates. For evaluation, we frame element matching as a linear sum assignment problem: optimal bipartite matching paired with LLM-based semantic grading jointly captures factual accuracy, hallucination, and format compliance. We benchmark 34 models (8 families, 42 configurations across standard and thinking enabled inference) and find: the best standard-inference model scores below 37% LLM-Judge-F1, multi-faceted questions are harder across the board, and providing the source Wikipedia page lifts scores dramatically, confirming that models can organize facts but struggle to retrieve them from parameters alone. Extended analyses cover base vs. instruction-tuned checkpoints and token efficiency. We release the dataset and evaluation code.

---

### From Qualitative Text to Integrated Evidence: The Parallel-Then-Integrated (PTI) Procedure

Authors: Elyas Irankhah, Ashley Hagaman, Samah Fodeh
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19164v1

Mixed methods research offers established strategies for integrating qualitative and quantitative evidence, but less guidance for integrating two computational representations of the same qualitative corpus. This methodological study introduces Parallel-Then-Integrated (PTI), a four-step procedure for explicit and traceable integration. We present PTI using 1,203 interview paragraphs from 29 mothers in Nepal. The two representations were ontology-guided Patient Voice (PV) coding with PVminer and data-driven themes generated through non-negative matrix factorization (NMF). A theme-complete crosswalk documented convergence, divergence, and preprocessing-sensitive differences. Depression status, based on Patient Health Questionnaire-9 (PHQ-9) scores, served as a secondary external anchor for exploratory association checks. PTI provides a structured approach for integrating computational representations of qualitative text within mixed methods research.

---

### Into the Unknown: Benchmarking AI agents on open scientific research problems

Authors: Seungone Kim, Jiayi Geng, Young-Jun Lee, Bo Liu, Juyoung Suk, Nicholas Lubbers, Mitchell Wood, Marcus Noack, Yong-Xin Yao, Yuan Shi, Roxana Bujack, Cristina Garcia Cardona et al.
Published: 2026-10-13
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.19159v1

Can AI agents carry out research on open scientific problems? We introduce Into the Unknown, a benchmark that provides an agent with a science paper along with a research direction to pursue and tasks it to write a follow-up paper. We work with scientists at US Department of Energy (DOE) national laboratories, who each contribute an unpublished follow-up direction from their own work together with the necessary conditions a submission must meet. While assessing the quality of a follow-up paper is challenging in general, using these conditions to form a rubric makes evaluation more tractable for research problems that have no reference answer. We have nine frontier agents write 15 follow-ups each, spanning quantum computing, plasma physics, computational chemistry, materials science, and scientific machine learning domains. None of the 135 submissions satisfies all the conditions, and 114 fail our integrity check, most often because the paper claims work that was never done or reports numbers that contradict the recorded evidence. Overall, agents readily produce papers that look like follow-ups, but none meets the standard of the domain scientist, leaving substantial headroom. Our code and data are publicly available.

---

### AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents

Authors: Chengquan Guo, Zhaorun Chen, Zinan Lin, Xiaodong Liu, Bo Li
Published: 2026-10-13
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2610.19158v1

LLM agents are becoming increasingly capable of handling daily workspace tasks by interacting with application environments through tool calls. However, as agents read and write sensitive user data across email, documents, and other applications, a central privacy question is whether they preserve contextual integrity (CI), that is, whether the information flows they produce comply with context-specific disclosure constraints. Existing work either focuses on model-level privacy leakage or evaluates agents in limited application environments with manually constructed disclosure constraints. In this work, we introduce AgentCIScope, a unified platform and benchmark for evaluating agent-level contextual integrity through executable, multi-step tasks across diverse, realistic application environments. AgentCIScope transforms public and synthetic privacy cases into executable agent tasks, with disclosure constraints grounded in three criteria: governing privacy policies, persona-based agreement, and a predefined sensitive-attribute taxonomy. Based on AgentCIScope, we evaluate 12 agents on 936 tasks and find that strong task-completion capability does not guarantee contextual-integrity preservation: single-run leakage rates range from 32.5% to 94.4%, while repeating each task five times further increases leakage by 4-19 percentage points. Leakage varies substantially across attributes: personal preferences and booking details have average leakage rates of 84.7% and 76.5%, compared with 17.1% for credit-card information and 29.4% for SSNs; environments: calendar has the highest average leakage rate as an information source, while WhatsApp ranks highest as an information destination; and governing privacy policies. AgentCIScope provides deep insights into agent privacy leakage and serves as a unified testbed for developing privacy-preserving agents.

---

### DivAlgo: A systematic evaluation of algorithmic diversity for code generation models

Authors: Anubhav Jangra, Smaranda Muresan
Published: 2026-10-13
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2610.19157v1

Code generation models are actively being used in professional and educational settings. However, the competence of large language models (LLMs) to generate algorithmically diverse code remains largely unknown. We propose the DivAlgo benchmark, a large-scale dataset constituting algorithmically diverse solutions to programming problems. We also introduce a lightweight similarity metric to enable large-scale evaluation. Our experiments across 24 modern code generation models found that uncontrolled model-generated code is significantly less diverse than human solutions (capturing ~31% of human diversity), and even the best diverse code generation strategy could achieve only ~70% of human diversity. Moreover, while it was possible to steer the models to generate solutions based on human strategies, they were unable to reproduce the diversity of the human solutions. These findings indicate the limitations of code generation models in capturing the algorithmic diversity humans exhibit, and that overexposure to model-generated code can narrow programmers' algorithmic vocabulary.

---

### Agronomic Characterization and Time-Series UAV Phenotyping to Support Field Pea Breeding in Iowa

Authors: Yanben Shen, Joscif Raigne, Asheesh Singh, Arti Singh
Published: 2026-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.19154v1

Field pea has gained interest in the Midwest U.S. and has the potential to benefit Iowa cropping systems. This study evaluated 17 accessions and 7 Canadian varieties for agronomic and seed yield performance. This study found that PI accession trials exhibit genetic diversity in phenology and canopy traits, whereas the Canadian elite varieties demonstrated great yield potential under Iowa conditions. The accession genotypes matured between 75 DAP (late June) and 95 DAP (late July) across six site-years. The top-yielding Canadian varieties averaged 1961 kg/ha across two site-years. To comprehensively assess field pea performance, this study extracted time-series Unmanned Aerial Vehicle(UAV)-derived traits, assessed UAV-derived traits, and evaluated their correlations with multiple agronomic traits and yield. The results found that UAV-derived time-series canopy area was the most yield-relevant trait (r = 0.63) among all UAV-derived canopy features, vegetation indices, and manually collected measurements. Compared with yield, UAV-derived canopy area showed higher selection reliability (H2 = 0.87, CV = 13.46%), making it suitable for phenotypic selection and accelerating Midwest field pea breeding programs. This study identifies useful UAV-derived features for pea breeding and demonstrates the value of integrating diverse germplasm, elite commercial varieties, and time-series UAV phenotyping. Combining genetic variation from the accession trial with the yield potential of high-performing commercial varieties provides valuable breeding materials and phenotyping strategies for developing locally adapted, high-yielding field pea varieties for future production in the Midwest.

---

### Compiling Expert Procedures into Verified Programs: When a Small Model Is Enough

Authors: Vishvesh Bhat, Asad Aali, Muhammad Ahmed Mohsin
Published: 2026-10-13
Categories: cs.AI, cs.SC
arXiv: https://arxiv.org/abs/2610.19148v1

In procedural tool-use domains, how much of the gap between base models is procedure rather than capability? We build an explicit program from a teacher's traces and run it in front of unchanged small models, including an 8B model. The construction, PLVR , takes the reasoning traces of a teacher, Kimi-K3, clusters their segments to locate recurring operations, has a frontier model author one typed primitive per operation, each run by a small frozen model and assembles the program by A* search over a mined rule library, under a reference-action objective. At inference the program takes one of two forms: for troubleshooting and tool search it produces the chain of thought the student would otherwise generate for itself, and the student acts on it; for multi-turn tool matching the student proposes each action and the program checks, repairs, or retries it before it goes out. On the official tau2-Bench Retail and Telecom test sets and on LiveMCPBench, with three Nemotron base models and the same program for each, the answer depends on the domain. On Telecom, Granite-4.2-8B as the student goes from 43.0% to 91.2% under the program, and every Nemotron student reaches 93.3-94.4%, against at most 58.2% for fine-tuning on the same traces, prompt optimisation of the student, or two token-matched baselines. With Granite-4.2-8B as the student, the program is within 2 to 3 points of the Nemotron students on Telecom and within 3 on Retail, and 3 to 13 points below them on LiveMCPBench: where the domain is procedural an 8B student is enough, and on tool search the student still matters. On Retail and LiveMCPBench the program is competitive with the best baseline. The spread between base models shrinks from about 7 points to about 2, averaged over the suites, with no weights changed.

---

### Demystifying On-Policy Distillation: Where Does the Teacher's Advantage Live?

Authors: Yiping Li, Fan Zhao, Zhibo Hou, Zhiyu An, Wan Du
Published: 2026-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19145v1

On-policy distillation (OPD) is increasingly studied as a cheaper alternative to reinforcement learning, yet it remains a form of knowledge distillation (KD) that relies on teacher supervision. We revisit OPD from the KD perspective by asking where the teacher's advantage lies along student-generated trajectories. Controlled token flips at teacher-student disagreements directly measure the accuracy gained from teacher corrections. Single-token flips yield a modest average gain on selected failed trajectories, whereas repeated flips raise accuracy from 28.4% to 74.5%, close to the teacher's 76.9%. Gains continue to accumulate with more flips, but mass- and KL-based selection outperform random flips by 15-18 percentage points at counts of similar magnitude. Selective intervention remains useful after OPD, but greater argmax agreement does not consistently improve accuracy across model pairs. We advocate training schedules that learn more valuable teacher corrections while maintaining distributional stability. Controlled flips and fork-resolution analysis evaluate OPD beyond accuracy by measuring which teacher preferences the student acquires and what further correction can recover.

---

### Towards Training and Inference of Graph Neural Networks in Graph Databases

Authors: Victor Pekkari, Harry Wik, Alfred Clemedtson, Borun Shi, Xuan-Son Vu
Published: 2026-10-13
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2610.19142v1

Graph Neural Networks on large graphs commonly rely on in-memory graph storage with ad hoc data processing pipelines for both training and inference. Graph databases provide scalable storage and efficient traversal for graphs that can evolve over time, but their applicability in GNN training and inference are rarely studied. We show that graph DBs can be used in GNN training and inference directly, executing sampling, feature retrieval, and even the full forward pass. We show different GNN training pipelines can perform on-the-fly sampling and retrieval in graph DBs using Cypher. We further provide optimisations that speed up the training process by \~2.5x while maintaining the same accuracy. We illustrate that fully in-DB inference is possible, independent of how the GNNs are trained. Our inference setup can be >10x faster than cold loading the graph into RAM with no extra memory overhead on real-world graphs. Our work lays the foundation for in-graph-DB GNN training and inference.

---

### Online Tokenization with Optimal Delay in Linear Time

Authors: Mina Dalirrooyfard, Christopher Ye
Published: 2026-10-13
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2610.19139v1

Tokenization is an essential preprocessing step in almost all large language models (LLMs). One of the most popular frameworks is BPE tokenization, which consists of special token segmentation, pretokenization, and byte-pair encoding (BPE). However, existing algorithms are sequential, with each stage only processing complete output from the previous stage. In order to reduce latency and memory footprints, recent works (Jiang and Gong, ICML 2026) (Li, Yang and Mamouras, ASPLOS 2026) (Mamouras, Li and Yang, PLDI 2026) have initiated the study of online algorithms for subroutines such as pretokenization and BPE with a goal of streaming input to output as the input arrives online. However, the search for efficient online tokenization remains open. In this work, we formalize and resolve online tokenization. We introduce the notion of delay for online tokenization which characterizes the extent to which the algorithm output lags behind the (possibly computationally intractable) optimum. We give a near-linear time algorithm with optimal delay (up to constant factors). We complement this algorithm with a conditional lower bound: unless $\mathbf{P} = \mathbf{NP}$, there is no polynomial time algorithm that beats the delay of our algorithm by more than a constant factor. We implement a practical variant for tokenizers from OpenAI's tiktoken and HuggingFace's tokenizers. We obtain a $7.9\times$-$34.8\times$ latency advantage (measured as time to first token) over tiktoken (as well as the recent gigatoken tokenizer) and our implementation maintains approximately constant memory usage independent of input size. Our implementation also achieves a $2.4\times$-$7.0\times$ improvement in throughput over tiktoken and $15.8\times$-$38.1\times$ over tokenizers.

---

### MA-Bench: Measuring Operational Planning in Language Models

Authors: Rodney Lafuente-Mercado, Robert Sincero, Phil Sage, Yuan Xue
Published: 2026-10-13
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.19138v1

How well can a language model turn a large, incomplete and partly contradictory body of documents into a plan when no single correct answer exists? We introduce Mission Analysis (MA)-Bench, built on mission analysis, the first step of military operational planning, in which a staff reads the full situation and states the problem before anyone proposes a solution. Its 10 expert-built scenarios pair synthetic packets of ten to twelve documents with 1,257 expert-written pass/fail requirements, each containing information on their source, question type, and importance level. A reasoning-model judge grades each brief against the requirements without seeing the documents; it grades like a fifth credentialed planner, leaving a four-planner panel's agreement unchanged (Fleiss $κ$ 0.42 to 0.41), and a judge from a second provider reproduces the model ranking (Spearman 0.94). Across twenty frontier and open-weights models the best gets 62% of the rubric items right. Models are strongest on facts stated in the documents (58%) and weakest on judgments that must be inferred (33%), and six failures in ten are omissions rather than errors. MA-Bench grades the determinations, not the prose. We release the packets, rubrics, prompts, scorer and every graded brief with item-level verdicts.

---

### Graph-Based Orchestration of Heterogeneous AI Models: A Control Node Approach to Composite Intelligence

Authors: G. Michael Youngblood, Filip Dvořák, Slavo Švancár, Tomáš Balyo, Michal Ficek, Martin Dousek
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.19136v1

We present a graph-based framework for Composite AI systems that integrate multiple AI techniques to address complex problems. We describe an architecture using specialized control nodes to orchestrate diverse models including planning, machine learning, constraint programming, and large language models. The system employs directed acyclic graphs and behavior trees to manage model relationships and execution sequencing. Our methodology encompasses data connectors, computational services, and a containerized deployment framework supporting hierarchical, sequential, and concurrent model composition patterns. Through case studies, we demonstrate how this architecture enables the creation of composite systems that leverage the strengths of multiple AI techniques within a unified operational schema, overcoming the limitations of single-model approaches.

---

### Student Copula Markov Networks

Authors: Salha Mamane, Cheikh Tidiane Seck
Published: 2026-10-13
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2610.19135v1

This paper extends the applicability of probabilistic graphical models to non Gaussian data. It establishes a characterization of the pairwise Markov property in undirected probabilistic graphical models in terms of copula densities. Building on this characterization, we derive a necessary condition for the pairwise Markov property in Student copula Markov networks. An Expectation-Conditional Maximization algorithm (ECM) is provided to facilitate the penalized maximum likelihood estimation and graph selection. The performance of the proposed algorithm is evaluated through simulation studies, which demonstrate its effectiveness in estimating model parameters and recovering the underlying graph structure.

---

### CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition

Authors: Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi, Mohammadreza Zolfaghari, Rishabh Jain, Louis Lu, Changdae Park, Amril Nazir
Published: 2026-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.19134v1

Feature distillation is usually expected to add to logit distillation. We find that this expectation does not hold for two common feature losses in compact multilingual automatic speech recognition (ASR), and analyze why through their gradients. The gradient of a projection-based loss is orthogonal to the task gradient, while that of Centered Kernel Alignment (CKA), a similarity-based loss, is weakly aligned with it. CKA lowers the word error rate (WER) on non-English languages, but at the expense of data-rich English. Three loss-level remedies (one trained, two probed) all fall short, and the CKA gradient overlaps with the subspace English uses in the shared encoder by 97.5% to 99.5% (about 81% by chance). Guided by this diagnosis, we propose CAFE (Confined-Adapter Feature distillation), which confines the CKA gradient to adapters that English bypasses, addressing the trade-off in the parameters rather than in the loss. On the Open ASR Leaderboard, CAFE lowers the average WER from 8.55% to 8.02%, beats an adapter-only capacity control at 8.51%, and makes English more stable across checkpoints. At 254M parameters, it trails the 0.6B teacher by 2 WER points and is competitive with much larger models across 48 test sets in 24 languages. We use 564k hours of training data and state-of-the-art models to keep the findings relevant to practice.

---

### TRACER: Trace-Regularized Training Against Indirect Prompt Injection

Authors: Kshitij Mishra, Salem Lahlou, Nils Lukas
Published: 2026-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.19133v1

Indirect prompt injection uses untrusted retrieved content, tool outputs, or agent messages to override an LLM's intended behavior. We show that defense robustness is channel-conditioned: the same attack succeeds 18% of the time as a follow-up message but 53% when placed in retrieved context. We propose TRACER (Trace-Regularized Adversarial Channel Exposure with Reward-shaping), a channel-aware adversarial training method that samples presentation wrappers and combines an answer-anchored, evidence-gated reward with ATRC, which aligns attacked reasoning with clean evidence when an injection is invalid. On GSM8K with Qwen2.5-3B-Instruct, TRACER reduces RAG-framed ASR from 65.5% to 6.1% while preserving 78-82% clean accuracy. Joint RAG+tool training achieves 13.9% average ASR across framings at 3B scale, while a single epoch at 7B reaches 9.4%. These results demonstrate that robust defenses must explicitly train and evaluate across deployment channels.

---

### Plant Memory: Technical Language Processing and a Verified Maintenance Ontology for Agent-Accessible Failure Knowledge from SAP PM Work Orders

Authors: Akash Raj
Published: 2026-10-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.19131v1

Maintenance work orders are the largest written record of how industrial equipment fails, yet in most plants they are close to unusable for analysis. Short texts are abbreviated and misspelt, asset identity is buried in free text, work-type labels contradict the work described, and the fields that matter most for reliability (symptom, root cause, action taken) are usually empty. As a result, diagnostic knowledge stays with senior technicians and leaves when they do. We present Plant Memory, a system that applies technical language processing (TLP) to SAP Plant Maintenance (PM) exports and builds an ISO 14224-aligned maintenance ontology in which every extracted statement is a reified fact carrying a confidence score, the evidence it was read from, and a verification state. Extraction is rule-first, with an optional large language model (LLM) acting as a second reader whose disagreements raise a fact's review priority rather than overwrite it. Technicians verify facts through a review queue, answer targeted knowledge-gap questions where failures repeat without a recorded cause, and approve or reject ontology drift proposals when new terms appear. The resulting graph is served to people through a web application and to AI agents through a Model Context Protocol (MCP) server, so both query the same verified knowledge and every answer cites the work orders behind it. On a synthetic 12-month export of 400 work orders from a parboiled-rice plant, rule-based extraction reaches 96.2% component accuracy, 88.9% failure-mode accuracy and 100% root-cause precision at 62% coverage; on 28 diagnostic questions, ranked root causes from the ontology are correct at top-1 in 82.1% of cases against 53.6% for the raw SAP root-cause column.

---

### Imagining Goals with Geometric Horizon Models for Policy Generalization

Authors: Daniel Lawson, Dhruv Sreenivas, Adriana Hugessen, Khimya Khetarpal, Glen Berseth
Published: 2026-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.19129v1

Training from offline data has allowed for substantial progress in domains such as robotics, leading to general-purpose policies that can be easily applied zero-shot or efficiently finetuned for downstream tasks. However, these policies can still have poor generalization, both due to the choice of modeling objective and from learning from a static dataset. In this work, we focus on the challenging task of zero-shot goal generalization, where a policy is evaluated on unseen tasks that require combining its existing knowledge (compositional generalization). An avenue for improving a policy's generalization is by generating new experience with world models; however, such generation has proven difficult for longer horizons. Thus, to alleviate this issue, we propose TD-Aug, which samples from a geometric horizon model and allows for directly imagining novel outcomes that can be achieved by composing existing knowledge. We demonstrate that training on these future outcomes as goals for goal-conditioned BC policies significantly improves generalization in stitching-based OGBench tasks.

---

### PairIT: Autoregressive Transformers for Low-Data Molecule Optimization

Authors: Hannah Lawrence, Bodhi P. Vani, Ji Won Park, Natasa Tagasovska, Samuel Don Stanton, Andrew Martin Watkins, Michael Maser, Ewa M. Nowara
Published: 2026-10-13
Categories: cs.LG, cs.AI, physics.chem-ph
arXiv: https://arxiv.org/abs/2610.19123v1

Generating novel molecules with desired properties is a central challenge in drug discovery. Although foundational work focused on de novo generation, practical use cases require a more complex setting: conditioning on an initial seed molecule, optimizing multiple properties, and operating in data-sparse regimes. We introduce PairIT, a flexible training framework for autoregressive transformers over SMILES sequences that enables seeded generation by learning from pairs of structurally similar molecules. By leveraging matched pairs, the model learns to generate local, chemically meaningful edits that improve a property of the seed molecule. Prompt tokens extend this framework by specifying the target property, desired direction, and approximate magnitude of change. Multiple prompt tokens can be concatenated to enable multi-property optimization at inference time. For properties where pair supervision alone is insufficient, reinforcement learning post-training can further improve optimization, providing a tunable trade-off between proximity to the seed and the optimization objective. PairIT naturally supports pretraining on a large dataset and fine-tuning on a smaller dataset, which is critical for performance in data-sparse regimes. Surprisingly, we observe diminishing returns to the scale of the pretraining dataset. We demonstrate empirically on MoleculeNet and Therapeutics Data Commons datasets that, with appropriate paired-data curation, a standard transformer model of modest size (68M parameters) can achieve robust seeded molecular optimization in low-data regimes.

---

### Learning in Orbit: Onboard Training and Closed-Loop Attitude Control with a Thermal Segmentation Model on a Spacecraft

Authors: Elena Sorina Lupu, Hannah Grauer, Phaedrus Leeds, Nikhil Ranganathan, Connor Lee, Sulekha Kishore, Cailyn Smith, Shon Cortes, Brian Hardy, Benjamen Bycroft, Darren W. Rowen, Soon-Jo Chung
Published: 2026-10-13
Categories: cs.RO, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2610.19122v1

Deep space missions increasingly require spacecraft capable of autonomously operating in environments with communication delays and bandwidth limitations. A key enabler of such autonomy is the ability to run learning-based algorithms directly onboard. In this work, we present a flight deployment on a 6U CubeSat that demonstrates (1) onboard training and inference of a thermal segmentation model on an NVIDIA Jetson TX2 NX GPU in space and (2) closed-loop attitude control using the segmentation model on a real-time, thermal image feed to track the Moon. In addition to this demonstration, we implement ROS 2 Foxy as a data transport middleware and integrate an open-source file system that provides strong data integrity guarantees and self-healing features. Over the course of approximately one year, we performed 12 experiments on the spacecraft, advancing the state of the art in autonomous spacecraft systems by showing how modern learning-based pipelines, commercially available hardware, and open-source software can operate reliably under the compute and environmental constraints of Low Earth Orbit (LEO).

---

### Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming

Authors: Woosang Lim, Haneul Yoo, Vincent-Daniel Yun, Sungjoo Yoo
Published: 2026-10-13
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.19121v1

Structured pruning reduces LLM inference costs by removing model components to produce smaller dense models. However, existing methods can cause reasoning performance to collapse on long-form reasoning tasks such as AIME. We propose \textit{LayerTrim}, a training-free structured pruning method that identifies redundant decoder layers and selectively trims their MLP features while preserving attention and decoder depth. LayerTrim is the first training-free structured pruning method designed to preserve long-form reasoning without gradients or recovery training. Across three reasoning language models and five benchmarks, LayerTrim outperforms existing structured pruning methods in most evaluated settings, improving average accuracy by up to 21.4 percentage points over RESP. On \texttt{Qwen3-14B}, LayerTrim achieves 1.24$\times$ faster prefill and 19.7\% lower peak GPU memory than the dense model, while better preserving reasoning ability. It also achieves the shortest average generation length among evaluated pruned models, while retaining the highest average accuracy. These results demonstrate that LayerTrim improves reasoning efficiency through both structural compression and reduced token generation.

---

### DoReMe: Dual optimization of Reconstruction and Motion estimation for self-navigated free-breathing abdominal MRI using Gaussian Splatting

Authors: Majd Helo, Dominik Nickel, Thomas Kuestner
Published: 2026-10-13
Categories: eess.IV, cs.CV, physics.med-ph
arXiv: https://arxiv.org/abs/2610.19120v1

Purpose: Free-breathing abdominal MRI is limited by respiratory motion, which introduces image artifacts and k-space inconsistencies. Existing reconstruction approaches often depend on pre-estimated motion fields or external respiratory surrogate signals. We propose a coupled reconstruction-motion estimation algorithm for self-navigated free-breathing acquisition, in which motion is represented by compact Gaussian primitives and jointly refined with the image estimates during iterative reconstruction. Methods: An iterative reconstruction that alternates between data consistency updates and motion modelling was proposed. Respiratory motion was represented using Gaussian primitives. A Gaussian splatting was integrated into the reconstruction algorithm. The method was evaluated on self-navigated free-breathing Cartesian gradient-echo (GRE) acquisition in four healthy volunteers, including retrospective scan shortening experiments, and was compared with regularized compressed sensing (CS) reconstruction. Results: Respiratory motion states were reconstructed in approximately 1.5 min. Compared with CS, the proposed method improved visual image quality, particularly in coronal liver views, and better preserved anatomical structures in retrospectively shortened acquisitions. These findings provide proof of concept for the proposed method. Conclusion: The proposed coupled reconstruction-motion estimation algorithm improved visual image quality compared with CS alone. Gaussian primitives provided a compact and sufficiently flexible representation of nonrigid respiratory motion with practical runtime, supporting further scanner integration and validation in larger cohorts.

---

### DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision

Authors: Yifan Lan, Zhongye Liu, Yurui Chang, Hanyu Wang, Yongkang Du, Lu Lin, Jinghui Chen
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.19118v1

Emerging decision models such as JEV provide typed interfaces that map task instructions and observations directly to choices, judgments, and scores. As these models are increasingly used for automated decision-making, understanding their reliability under adversarial manipulation becomes critical. We introduce DecisionRobust, a benchmark for systematically evaluating the robustness of decision models across textual and visual inputs. Our benchmark covers practical decision-making scenarios and a diverse suite of attacks, including semantics-preserving text perturbations, image perturbations, and prompt injection in both modalities. We curate evaluation sets through external validity checks and cross-model candidate selection. We evaluate 30 model configurations on text tasks and 17 on vision tasks, including 24 and 12 held-out models, respectively, that are excluded from candidate selection. Our experiments reveal several key findings. First, attacks expose vulnerabilities beyond the models used for construction and selection, although optimized image perturbations transfer weakly to many targets even with multiple surrogates. Second, relative model robustness varies across tasks and attack types, and resistance to input perturbations does not necessarily imply resistance to prompt injection. Third, label-consistency checks substantially reduce measured attack success across text and image settings, highlighting the importance of validating apparent failures. The benchmark is available at https://yifan-lan.github.io/DecisionRobust/.

---

### Genesis Steering: Better Activation Steering Through Training Data

Authors: Tora Bodin, Eric Aubinais, Ilaria Torre, Chih-Hong Cheng
Published: 2026-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.19114v1

Activation steering controls large language models at inference time, but its effectiveness depends on the choice of reference data. We introduce genesis steering, which derives a genesis vector from contrastive examples in the model's own fine-tuning data. When these data are unavailable, we draw on the membership inference literature to identify likely training examples and construct a proxy dataset. We establish two theoretical results on optimal displacement to the decision boundary and reduced proxy-estimation bias. We evaluate genesis steering and membership-based proxy construction on Tülu-3-8B, whose fine-tuning data are publicly available, and Llama-3.1-8B-Instruct as a control. We find that safety data from Tülu-3-8B's training mixture yield stronger steering than external datasets on both models. On Tülu-3-8B, membership scores largely agree in identifying training examples, and vectors built from top-ranked examples achieve competitive performance against random subsets of the same size. In contrast, the results on Llama-3.1-8B-Instruct hint that a MIA method will only have a positive effect if the mean direction shift with MIA-filtered in-distribution data is much less severe than the direction shift with OoD data.

---

### From Copying to Composition: How Language Models Develop In-Context Learning

Authors: Minglai Yang, Xinyu Guo, Renxiong Wang, Sunjie Hou, Daniel Yue Zhang, Yunzhong He
Published: 2026-10-13
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.19113v1

In-context learning (ICL) allows language models to adapt their behavior from instructions and demonstrations in a prompt, but accuracy alone does not reveal how contextual information controls their predictions. We study the acquisition and trainability of ICL with a controlled diagnostic that separates copying a nearby demonstration from integrating information across the prompt. Across 17 models, about a third prefer the copied answer, a few are undecided, and the rest prefer the rule-consistent answer, which goes with higher accuracy and with control by the requested value rather than the closest conflicting example. Checkpoint analyses show that models begin prioritizing task-relevant prompt tokens over conflicting examples long before their accuracy improves beyond chance level. In matched training experiments, synthetic documents that define endings and then query them shift models toward compositional responses on the controlled diagnostic, whereas fine-tuning on definition exercises built from rewritten real documents improves accuracy when prompts reassign label meanings. The results suggest that ICL is not acquired as a single, uniform capability. Instead, prompt control, answer preference, construction without candidates, and transfer can develop along distinct trajectories.

---

### Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models

Authors: Mahdieh Mallahnezhad, Masoud Jafaripour, Mohamadali Tofigh, Sheila Schoepp, Osmar R. Zaiane
Published: 2026-10-13
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.19108v1

Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitations in spatial reasoning and perception. Post-training techniques have shown promise for improving these capabilities; yet, there are limited data-driven surveys of such approaches. In this survey, we consider approaches to fine-tuning pretrained MLLMs for spatial reasoning tasks, ranging from supervised to reinforcement learning, with an emphasis on the datasets used. We investigate themes of dataset construction, data modality and annotation, and evaluation of the resulting models. Based on these themes, we categorize research into three groups: dataset design, dataset construction and evaluation. We find four main methods for constructing fixed spatial annotations: rules and templates, LLM prompting, procedural generation, and human-in-the-loop. We also observe substantial variation in evaluation approaches, including different scoring methods, tolerance metrics, and benchmark types. Finally, we identify opportunities for future research in unified dynamic annotation, efficient spatial reasoning, standardization of evaluation, expanded spatial range, and human-centered spatial interactions.

---

### Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments

Authors: Daixi Huang, Yixin Yuan, Yifan Dai, Yufeng Liu
Published: 2026-10-13
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2610.19104v1

Learning an individualized treatment rule (ITR) with many treatments requires estimating treatment-specific effects from limited observations per arm. Treatments with similar conditional responses can share information, but linear contrast models may miss nonlinear heterogeneity. We propose nonlinear supervised clustering fusion (NSCF), a neural Q-learning framework with a shared nonlinear covariate representation and low-dimensional treatment embeddings. Pairwise fusion groups treatments with similar learned contrasts, yielding an ITR and an interpretable partition. An alternating algorithm combines neural training, embedding fusion, validation-based partition selection, and unpenalized grouped refitting. NSCF lowers regret relative to a strong neural reference in nonlinear exact-sharing simulations; perturbations characterize the limits of hard sharing. In a melanoma xenograft application, NSCF improves average policy value over the neural reference. These results support nonlinear representation learning with supervised treatment fusion when treatment effects exhibit shared structure.

---