# Research Papers — 2026-09 · bundle page 72 of 266 > Full-text markdown of papers #3551–3600 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/72 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/71.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/73.md) ### HeroFrame-Bench: Reference-Anchored Evaluation via Rubric--Ranking Co-Evolution for Movie Hero Frame Selection Authors: Weitai Kang, Hanieh Deilamsalehy, Yumo Xu, Dewang Sultania, Serdar Cellat, Yan Yan Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32280v1 Hero frames are in-film stills used as source imagery for theatrical posters, streaming cover art, film database listings, and other promotional placements. As the first visual entry point, they shape audiences' initial impressions of the movie and their subsequent willingness to watch it. Selecting these frames, a task we term hero frame selection, requires balancing content relevance with aesthetic appeal. A related task is keyframe selection, yet its benchmarks prioritize relevance over aesthetics, using either finite annotations that exclude valid alternatives or VideoQA that entangles selection quality with downstream model capability. We therefore introduce HeroFrame-Bench, built through a scalable VLM-as-a-Judge framework. We construct multimodal contexts from diverse metadata to ground a VLM judge that scores selected frames using our Reference-anchored Percentile. The percentile is obtained by inserting each frame into reusable, pre-ranked reference chains, enabling direct, extensible, and reliable evaluation. To reduce ambiguity and improve consistency in these subjective judgements, we further propose Rubric-Ranking Co-Evolution, which generates movie-specific rubrics to condition the VLM judge and refines rubrics jointly with the resulting rankings. Within this process, we introduce several verifiable signals, most notably the Inverted Rubric Attack, to select robust rubrics. Finally, HeroFrame-Bench is instantiated over 204 movies with 2,031 reference chains and 1,970 learned rubrics. We build an annotation interface for human-alignment studies which show that our construction design improves VLM agreement with human from 77.56% to 83.78%. Evaluation on multiple methods show that hero frame selection remains challenging. --- ### SIMANF: Sample Free Learning of Unnormalized Distributions via Simulated Annealing in Normalizing Flows Authors: Vikas Kanaujia Published: 2026-09-26 Categories: cs.LG, hep-lat arXiv: https://arxiv.org/abs/2609.32279v1 Efficiently learning and sampling from high dimensional, multimodal unnormalized distributions without target samples remains a challenging problem. Although normalizing flows can generate samples efficiently, training based on the reverse KL divergence using only the unnormalized target density may suffer from mode collapse. We introduce SIMANF, a sample free framework that integrates simulated annealing with normalizing flows. SIMANF progressively transforms the target distribution from a smooth initial form to the original target distribution and trains the flow sequentially across these stages. By transferring the learned representation between stages, the method promotes mode coverage while progressively capturing finer features of the target distribution. Following annealing, a final refinement stage combines the reverse KL divergence with an importance weighted forward KL objective using samples generated by the flow. SIMANF requires no target samples during training and uses only the unnormalized density. We demonstrate its effectiveness on Many-Well distributions and high dimensional Scalar Phi4 lattice field theory distribution. --- ### HyperLabel: Multi-Label Classification via Hypergraph-Based Label Correlation Modeling Authors: Peiyu Zhang, Heng Ping, Nikos Kanakaris, Yucheng Zhao, Shixuan Li, Wei Yang, Xiongye Xiao, Paul Bogdan Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32276v1 Multi-label classification (MLC) requires predicting multiple relevant labels for each instance, where a central challenge is modeling complex label dependencies arising from co-occurrence patterns. Existing approaches are limited in capturing high-order label correlations, relying on implicit learning through contrastive objectives or pairwise attention mechanisms without structural guidance. We propose HyperLabel, an encoder-decoder framework that explicitly models label dependencies through hypergraph neural networks. Our contributions are twofold: (i) We construct a label hypergraph where sample-defined hyperedges naturally encode multi-way co-occurrence patterns, providing explicit structural prior knowledge that captures relationships beyond pairwise interactions. (ii) We propose a unified cross-modal learning approach where HGNN+ performs bidirectional message passing to integrate feature information with label structure, and a shared cross-attention decoder processes both modalities through complementary learning objectives. Extensive experiments on seven benchmark datasets demonstrate that HyperLabel achieves state-of-the-art performance, with particularly significant improvements on macro-F1 scores (+10.3% on Delicious, +8.2% on Bibtex), validating that explicit hypergraph structure effectively captures complex label relationships. The code is available at https://github.com/iZHpy/Multi-label_hypergraph . --- ### Topology-Adaptive Hyperbolic Graph Attention Networks Guided by the Hyperbolic Sombor Index Authors: Haifang Cao, Boan Tao, Xiyuan Gao, Timing Li, Yu Wang, Pengfei Zhu Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32275v1 Hyperbolic geometry has emerged as a principled space for representing hierarchical graphs. However, existing hyperbolic graph neural networks typically rely on shared curvature configurations and feature-driven attention, failing to explicitly exploit local hierarchical topological patterns. To bridge this gap, we introduce the Hyperbolic Sombor Index (HSO) as a lightweight structural prior for capturing hierarchy-indicative degree stratification. Building on this, we propose \textbf{HSO-GAT}, a topology-adaptive hyperbolic graph attention network that unifies geometric adaptation and message propagation. Specifically, it comprises two complementary modules: HSO-Guided Local Curvature Adaptation, which performs adaptive node-wise geometric scaling from aggregated node-level HSO signals, and HSO-Gated Hyperbolic Graph Attention, which enables structure-aware message passing through feature-conditioned gating. Theoretically, we establish the monotonic sensitivity of edge-level HSO to degree imbalance and analyze the validity and radial scaling properties of node-adaptive hyperbolic mappings. Extensive experiments on eight benchmark datasets demonstrate that HSO-GAT consistently achieves state-of-the-art performance in both node classification and link prediction tasks. --- ### When Does a Skill Add Value? Task-Conditional Gain Prediction for Selective Skill Use Authors: Anjie Xu, Zhiyu Zhang, Ruiqing Ding, Fengli Xu, Leye Wang Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32274v1 Agent skills are expected to improve task performance. Yet we find that they often provide no benefit, and can even hurt performance while incurring additional token costs. Can we predict whether a skill will help before the agent acts? We introduce SkillDelta, a framework for predicting task-conditional skill gains from paired executions of the same agent with and without the skill. A local predictor transfers these historical gains to new tasks without retraining the agent. Under explicit transfer assumptions, our analysis links support coverage, representation mismatch, and execution noise to prediction error and decision regret. Across five benchmarks and three target agents, paired history improves observed-gain ranking over skill-assisted outcomes alone in 12 of 15 settings. At matched expected skill-use rates, SkillDelta improves success over random activation in all 15 settings, with an average absolute gain of 4.3%. Most of this advantage comes from allocation across task groups. Evidence for additional within-group selection value is strongest on ToolQA and weaker elsewhere. Code is available at https://github.com/TankTechnology/skilldelta. --- ### FSS-UBrain: Multi-region Few-Shot Brain Tumor MRI Segmentation Authors: Truong Viet Vu, Nguyen Phuc Nguyen, Dang Thi Thu Hang, Tran Thien Thanh, Vo Nguyen Quoc Bao, Nguyen Thai Anh, Ngo Hoang Tu Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32273v1 Accurate delineation of whole tumor (WT), tumor core (TC), and enhancing tumor (ET) from multimodal magnetic resonance imaging remains challenging under limited annotation, cross-cohort variation, and severe target sparsity. We propose FSS-UBrain, a region-wise one-shot segmentation framework that uses a labeled positive support slice to condition binary query segmentation separately for WT, TC, and ET. Support-derived foreground and background descriptors guide query-feature adaptation, bottleneck interaction, decoder-side reconstruction, and boundary refinement. Episodic training additionally incorporates hard-negative and fully negative queries with empty-query regularization to suppress spurious foreground activation when the selected region is absent. Although inference operates on two-dimensional support--query slice pairs, checkpoint selection, threshold calibration, and final evaluation are performed after volumetric reconstruction. FSS-UBrain is evaluated on a held-out BraTS 2020 split and under target-supported cross-cohort protocols on BraTS 2023 and BraTS-Africa. Cases used as target support are excluded from the query cohorts, and no target-domain fine-tuning or test-time parameter updates are performed. On BraTS 2020, FSS-UBrain achieves volumetric Dice scores of 89.82%, 82.14%, and 77.42% for WT, TC, and ET, respectively, with corresponding 95th-percentile Hausdorff distance (HD95) values of 11.12, 9.01, and 4.46 mm. It also achieves the highest mean Dice and lowest finite-pair mean HD95 point estimates on BraTS 2023 and BraTS-Africa among the compared few-shot methods. These findings support target-conditioned few-shot segmentation while highlighting sensitivity to support selection and cohort-specific variation. --- ### Learning Through Game: Skewed Transfer of Tabular Knowledge to Strengthen Image Model Authors: Longfei Huang, Shangdong Yang, Yang Yang Published: 2026-09-26 Categories: cs.LG, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2609.32272v1 Multimodal tabular-image learning is gaining growing attention, yet it faces challenges due to tabular data unavailable at test time. A practical solution involves transferring tabular knowledge to images during training to enhance the performance of image models at inference. However, the overlooked yet important challenges lie in the modality imbalance between images and tables, as well as their asymmetric modality relationship in cross-modal transfer, which limits the auxiliary role of tabular data. To address these issues, we propose Skewed Knowledge Transfer (SKT), which asymmetrically transfers tabular knowledge to improve the image model by adaptive integration of modality gradients in a shared parameter space. Specifically, we first introduce a multimodal shared head, which allows the model to benefit from cross-modal structure without adding additional parameters. We then design a two-step Nash Bargaining strategy to effectively leverage tabular gradients. In the first step, SKT seeks a point of modality balance and uses preference awareness in the second step to steer combined gradients toward image-beneficial directions. Furthermore, we theoretically analyze the Pareto improvement and convergence of SKT. To this end, tabular knowledge is explicitly transferred to enhance image models. Empirical experiments on widely used tabular-image datasets reveal that SKT consistently improves image unimodal performance by using tabular data as auxiliary information. --- ### Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancing Authors: Joyanta Jyoti Mondal, Ibne Farabi Shihab Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32271v1 Post-hoc Bayesian fine-tuning places Gaussians around trained low-rank adapters, yet a calibrated posterior does not by itself yield a useful generalization certificate. Such a posterior admits an informative PAC-Bayes certificate only when both the loss of its sampled predictors and its KL divergence from an admissible prior are small. In this research, we characterize this certification frontier for Gaussian LoRA posteriors and separate three interventions: changing the prior, changing the stochastic predictor, and changing only how its complexity is counted. First, an exact isotropic KL envelope eliminates the prior scale and yields a width threshold that excludes posterior widths before sampling, while a zero-KL floor identifies targets that no complexity reduction can reach at a measured risk bound. Second, we minimize KL in closed form over the full $GL(r)$ symmetry of the low-rank factors, leaving every sampled adapter product unchanged, and derive the noncentral objective required when the prior center is trained on an independent split. On a small-pool RoBERTa audit of 567 configurations, the recorded 64-draw summaries imply a certificate floor of $0.7298$ even with zero KL and Chernoff accounting, so reducing complexity alone cannot certify these posteriors at the recorded budgets. For a stable posterior in a controlled Gaussian-factor task, Chernoff accounting certifies risk below $0.1$ on 20 of 20 datasets with 1024 draws, whereas Hoeffding certifies none. On deliberately deformed synthetic rank-four factors, matrix balancing reduces KL by $29.3\%$ on average beyond scalar balancing without changing any prediction. Numerical split-prior scenarios make the remaining risk and complexity budgets explicit. --- ### Overfitting of Spectral Gradient Descent: How Matrix Geometry shapes Generalization and Implicit Bias Authors: Guillaume Braun, Ichiro Hashimoto, Masaaki Imaizumi Published: 2026-09-26 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.32270v1 We study the generalization of spectral gradient descent (SpecGD) in overparameterized matrix classification with corrupted labels. Each input combines a shared low-rank signal with a rank-one sample-specific perturbation, referred to as a shortcut, that enables memorization but does not generalize. We contrast collapsed shortcuts, which share a singular direction, with dispersed shortcuts, which occupy distinct singular directions. Changing only this geometry can reverse the relative generalization of GD and SpecGD: collapsed shortcuts can favor SpecGD, while dispersed shortcuts can favor GD. In the dispersed regime, exact shortcut orthogonality eliminates the signal from the late-stage SpecGD direction, while vanishing random correlations collectively generate a small but generalization-relevant signal through a second-order effect. To identify the direction selected by SpecGD, which the spectral max-margin problem alone does not determine, we combine a refined analysis of its dual with the exponentiated-gradient dynamics of normalized loss weights. Finally, we show that a single SpecGD step can already interpolate and generalize well, while continued training converges to a direction with substantially worse generalization. --- ### Before Answering: Evidence Sufficiency under Size-Matched Memory Construction Authors: Joyanta Jyoti Mondal, Md. Shifatul Ahsan Apurba, Mridul Banik, Md Masud Al Mahmud, Ibne Farabi Shihab Published: 2026-09-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.32269v1 Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory. Benchmarks for this task usually create insufficient-evidence examples by deleting supporting passages. We show that this construction leaks the label through memory size: on MuSiQue, a classifier that only counts paragraphs reaches an area under the ROC curve (AUROC) of $0.979$ for detecting unsafe memory, higher than the lexical estimator we initially evaluated. We propose a size-matched construction that provably removes this shortcut, and use it to study MemSafe, an estimator that cross-encodes the query with each memory unit and aggregates the units with a set transformer. Across three multi-hop question answering datasets and five seeds, MemSafe reaches $0.968$ and $0.983$ AUROC on MuSiQue and HotpotQA, $0.26$ to $0.39$ above a lexical baseline, while the third dataset, 2WikiMultiHopQA, is saturated. A frozen pretrained cross-encoder with a logistic head already closes $41\%$ of the MuSiQue gap between the lexical baseline and MemSafe. At the same time, MemSafe degrades more than a weak baseline on the unanswerable questions released with MuSiQue, reaches only $0.639$ AUROC on SQuAD~2.0, and needs several thousand clinical training examples before it outperforms a feature-based estimator. Used as a gate for a 7B reader, it reduces the error rate on answered questions from $0.850$ to $0.631$ at $5\%$ coverage, outperforming both reader confidence and, on average, the ground-truth integrity label, although a 7B LLM judge is the better gate at $10\%$ coverage. These results indicate that the way insufficient evidence is constructed matters as much as the estimator that detects it. --- ### Self-Reconstruction Dynamics for Autoencoder Reconstruction Refinement Authors: Hitoshi Iyatomi Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32268v1 Standard autoencoder (AE) inference uses a single encoder-decoder pass, though the latent may not be optimal for each sample under a fixed decoder. We ask whether a trained AE can reveal information for improving its own reconstruction. Repeated application of a frozen AE to its reconstruction produces transient image- and latent-space trajectories, termed Self-Reconstruction Dynamics (SRD). Although this degrades fidelity in the AEs studied here, SRD contains sample-specific information for correcting the reconstruction. We propose SRD-guided Reconstruction Refinement (SRD-RR), which predicts a latent correction from a short SRD with the AE frozen and no per-sample test-time optimization. We also introduce MSE-recov, an MSE recovery ratio relative to an empirical decoder-optimized reference. Across six datasets, SRD-RR recovers 38.6% of the empirically recoverable MSE gap with one transition and 45.3% with two. A two-transition variant trained without direct access to original images, using an SRD-derived pseudo-target, achieves 40.7% recovery and a 1.74 dB average PSNR gain. Removing trajectory information reduces the gain, while cross-sample trajectory assignment causes severe degradation, confirming strong sample specificity. Nonlinear SRD-conditioned refinement consistently outperforms fixed and trained linear latent correction. On a pretrained DINOv2-based representation autoencoder (RAE) with substantially different latent dynamics, SRD conditioning again improves a matched trajectory-free predictor. However, pixel-MSE latent refinement reveals a strong mismatch between pixel fidelity and perceptual quality, while the SRD-derived pseudo-target mitigates this degradation. Overall, SRD is a useful sample-specific refinement signal, while the objective determines how it translates into pixel and perceptual quality. --- ### When Can Old Evaluations Certify a New Model? Label-Efficient Release Decisions under Evaluator Drift Authors: Joyanta Jyoti Mondal, Mridul Banik, Md. Shifatul Ahsan Apurba, Md Masud Al Mahmud Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32267v1 Releasing a model update requires certifying that its current-population risk stays below a threshold. Trusted labels are expensive, while a cheap evaluator, such as an LLM judge, scores every example. Reusing evaluator errors from earlier audits is tempting, but when may such evidence replace current labels? It depends on the status of history. If the errors can change invisibly, no label-free test detects the change, and every valid, useful certifier must keep buying labels at a rate we characterize; if a bound on the change is assumed, label-free certification is valid at an explicit error cost. For the middle ground, where history is informative but untrusted, we propose \emph{portfolio vigilance}, a sequential certifier mixing a betting expert guided by history with one that learns only from current labels; history affects only how it bets, so validity holds for any history. The contribution is not prior-informed betting or expert mixtures, but separating history that may enter validity from history that may only guide label collection. In a canonical model, accurate history shortens decisions but never raises the evidence growth rate; stale history can destroy it. On held-out CIFAR-10N and DICES-990 data, portfolio vigilance needs 0.465 (95\% CI $(0.327,0.575)$) and 0.740 ($(0.618,0.877)$) times the labels of a matched prediction-powered monitor, with no observed false certification, and fewer labels on all six external blocks. Under corrupted advice it stays within 8.0\% of its better component, while trusting history alone costs up to 1.66 times as much. In post-confirmatory repeated-judge experiments on DICES-990 and ToxicChat, changing a fixed LLM judge's rubric moves its scores beyond run-to-run variation; the portfolio then needs 0.790 ($(0.667,0.909)$) and 0.631 ($(0.520,0.770)$) times the labels of the matched monitor, and fewer than trusting history alone. --- ### LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models Authors: Pavel Tikhonov, Elena Tutubalina, Ivan Oseledets, Dmitry I. Ignatov, Mikhail Seleznyov Published: 2026-09-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.32264v1 Language models can now prove theorems, but people still decide which problems to pursue. We ask whether a model's internal representations can help identify promising mathematical connections. We develop LANTERN, a fast, cost-efficient pipeline that uses a classifier over pretrained-model activations to rank candidate relations, followed by staged filtering, hypothesis generation, executable verification, and analytical checking. Applied to the On-Line Encyclopedia of Integer Sequences (OEIS), LANTERN ranked 50 million pairs among 10,000 frequently referenced sequences and produced 62 verified relations between pairs without an existing OEIS cross-reference. A content screen retained 13 relations worth presenting; nine of these are informative or insightful, including four which are entirely novel to the best of our knowledge: none appears in the OEIS or in our targeted literature search. The entire end-to-end process including classifier training, candidate ranking, filtering and verification took under 8 hours. --- ### Representation Editing for Multimodal Test-Time Adaptation Authors: Longfei Huang, Xiangyu Wu, Yang Yang Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32263v1 Multimodal test-time adaptation (TTA) aims to adapt a pretrained multimodal model online to distribution shift across modalities using unlabeled test data, showing broad potential in real-world applications. However, existing methods primarily focus on adjusting fused features to bridge the source-target gap, lacking explicit control over intermediate representation misalignment, which is a key driver of performance drop under distribution shift. In this work, we tackle this challenge from the perspective of representation engineering. Unlike previous TTA methods that update fusion weights in place, we propose FourIer Representation Editor (FIRE), a novel multimodal TTA approach that directly edits semantically rich intermediate representations. Specifically, we first adopt representation editors into each intermediate layer of the unimodal encoders, enabling layer-wise calibration of unimodal representations. To further enhance the diversity and stability of the low-rank editing subspaces, each representation editor performs frequency domain mixing via the fast Fourier transform to construct structured bases. Moreover, we introduce multi-level adaptation objectives to optimize these editors, jointly promoting cross-modal semantic alignment, source-target statistical alignment, and asymmetric prediction consistency. In this way, FIRE yields aligned unimodal representations for fusion and further improves prediction reliability. Extensive experiments on two widely used multimodal benchmarks under various corruption types demonstrate the superiority of FIRE over existing multimodal TTA methods. --- ### Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs Authors: Vincent-Daniel Yun, Woosang Lim, Haneul Yoo, Sungjoo Yoo, Murali Annavaram, Sai Praneeth Karimireddy Published: 2026-09-26 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.32259v1 Recent multi-agent LLM systems increasingly combine heterogeneous models for specialized agent roles. However, text-based communication requires each receiver to prefill shared context already processed by the sender. Reusing the sender's key-value (KV) cache avoids this redundancy, but prefill-free transfer across model families must handle differences in tokenization, model depth, and KV representations. To address these issues, we propose \textit{HeteroFold}, a prefill-free cross-family KV cache transfer method that keeps both the sender and receiver frozen. HeteroFold aligns model structures, maps the sender cache into the receiver space, and calibrates it to preserve receiver behavior. Across six transfer directions, HeteroFold achieves the best cache-transfer performance on all four long-context benchmarks and most short-context settings. It also matches text-based communication on the multi-agent benchmark. At 32K context length, Llama-3.1-8B$\rightarrow$Ministral-3-14B transfer is $10.7\times$ faster than Native Prefill and $1.18$--$1.47\times$ faster than the state-of-the-art prefill-free baselines, Dense Latent and KV Ridge. These results show that HeteroFold enables efficient cross-family KV reuse without receiver prefill. --- ### LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound Authors: Baixi Sun, Le Chen, Anjir Ahmed Chowdhury, Xiaolong Ma, Chih-Hsuan Yang, Mingze Xia, Syed Zawad, Sheng Di, Rajkumar Kettimuthu, Huihuo Zheng, Rajeev Thakur, Venkatram Vishwanath et al. Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32256v1 Agent memory grows as agents read inputs, reason, and call tools. Longer histories increase inference cost and eventually exceed the context window. LLM-based summarization reduces this history but adds latency and provides no explicit bound on information loss. We propose LAM, a Lossy Agent Memory system with three components: a deterministic deduplication rule with a substitution bound on retrieval scores - a bound on score perturbation, not a certificate of unchanged ranking; a memory manager that preserves the cached prefix and overlaps compaction with inference; and a performance model that estimates compaction costs before deployment. On 600 agent trajectories, LAM removes 22.47% of observation tokens while retaining 99.984% of the measured gold-patch evidence. At a fixed deletion set, the performance model predicts a 71.4x-91.6x end-to-end speedup from removing records before prefill instead of deleting them from a prefilled context. That benefit comes from the schedule rather than the rule and applies to any prefix-preserving test. --- ### Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents Authors: Zhaofeng Li, Xuan Zhang, Xiaokui Xiao, Yang Deng Published: 2026-09-26 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.32255v1 Tool-using LLM agents must decide not only whether additional information is needed, but also which source can resolve the uncertainty. Existing proactive approaches often specialize in either user clarification or environment verification, without explicitly determining the appropriate information source for each decision. We formulate this problem as uncertainty routing among ACT, CLARIFY, and VERIFY, and propose PROUR, a proactive uncertainty routing framework. PROUR decomposes action uncertainty into disagreement across plausible user-goal interpretations, which signals user-side ambiguity, and the entropy remaining within each interpretation, which signals missing world-side evidence. To acquire information from the routed source, a query generator is trained with a mode-conditioned information-gain reward, targeting user-goal identification under CLARIFY and next-action identification under VERIFY. On $τ$-bench, PROUR achieves 28.17% average success rate across retail and airline, outperforming the strongest prior method by 4.57% while using 2.17 fewer interaction steps. The learned policy further generalizes to stronger task agents and transactional domains of $τ^3$-bench without retraining, demonstrating the benefit of source-aligned uncertainty resolution for proactive agents. --- ### Why Directly Learning Periodic Trajectories Can Fail Authors: Kaixin Zheng, Anita Layton Published: 2026-09-26 Categories: cs.AI, math.CA, math.NA arXiv: https://arxiv.org/abs/2609.32254v1 Operator learning of periodic solutions requires deciding how simulation data should be recorded and represented. A natural choice is to integrate long enough for transients to decay and record a window wide enough to contain at least one full period of all trajectories. We find that these conservative choices can make the resulting trajectories difficult to learn, even when the underlying periodic orbits vary regularly with system parameters. Unaligned trajectories generalize poorly even within the training distribution. Phase alignment substantially improves in-distribution generalization, but models trained on a fixed physical-time window still have large errors on trajectories with periods outside the training range. We explain both failures through a common mechanism: frequency differences accumulate over time, so the target phase varies rapidly with the parameters. Predictors that cannot track this variation incur a population MSE floor in both settings; for fixed window prediction, we also derive a per-sample lower bound. We then study one of the simplest representations that escape these floors: learning an aligned, normalized waveform and its period separately. We establish regularity of the decoupled targets under ODE assumptions and show experimentally that this approach avoids both failures in ODE systems and a PDE case study. --- ### DS-VLA: A Dendritic-inspired Vision-Language-Action Model for Robust Action Control Authors: Yaxing Lyu, Jingyi Li, Mingkun Xu, Yujie Wu Published: 2026-09-26 Categories: cs.RO, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2609.32253v1 Vision-language-action (VLA) models have achieved strong performance in language-conditioned manipulation, yet success under nominal evaluation does not necessarily translate into robust closed-loop behavior when executed actions are transiently corrupted. We introduce DS-VLA, a dendritic-inspired action architecture that incorporates dendritic spiking dynamics into VLA control to address this limitation. Specifically, to enable modularized feature processing and temporal information integration, DS-VLA equips action neurons with multiple sparsely connected dendritic branches, each featuring heterogeneous, learned decay factors. Furthermore, to suppress unreliable state updates while preserving task-relevant historical information, we introduce a neuron-wise inhibitory gate that adaptively regulates the admission of new multimodal evidence into dendritic states prior to somatic dynamics. We evaluate DS-VLA on all four LIBERO suites under both nominal rollouts and a unified closed-loop action-perturbation protocol. DS-VLA achieves a 91.6\% average nominal success rate and an 87.35\% average perturbed success rate, retaining 95.4\% of its nominal performance. Under the same reported perturbation setting, OpenVLA-OFT, FAST, $π_0$, and GR00T achieve 39.45\%, 23.90\%, 28.55\%, and 30.75\%, respectively. A controlled ablation isolates the contribution of neuron-wise shared inhibition, while analyses of neural dynamics and post-perturbation trajectories associate robust performance with selective evidence suppression and effective behavioral recovery. Together, these results demonstrate that integrating brain-inspired computational mechanisms offers a promising architectural prior for robust embodied intelligence beyond merely scaling vision-language backbones or generative action decoders. --- ### Active Data Acquisition with Side Information via Discrete Diffusion Priors Authors: An Vuong, Thinh Nguyen Published: 2026-09-26 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2609.32252v1 Acquiring data is costly: higher measurement fidelity costs power and storage and risks collecting irrelevant content, while aggressive cost reduction can discard information that later analysis needs. We address this trade-off with an information-theoretic framework that acquires data relevant to a broad set of tasks rather than to one model. A mask policy, conditioned on side information, chooses which pixels to measure so as to maximize the mutual information between a discrete image and its partial observation under a budget; since the image entropy does not depend on the mask, this is equivalent to minimizing the conditional entropy. A frozen discrete denoising diffusion model (D3PM) supplies the posterior, and we use it in two ways: as an entropy surrogate for training a one-shot mask generator, and as the criterion for sequential greedy acquisition. The one-shot generator outperforms random masks only with care, including an unbiased gradient estimator for binary masks. With sequential acquisition, on MNIST the prior makes $8\times$ fewer errors than random at a $10\%$ budget, and on CIFAR-10 it gains $0.9$--$3.4$~dB. On fastMRI, our proposed technique using a static mask outperforms the well-known methods such as variable density and LOUPE. --- ### RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots Authors: Yujia Zeng, Chensheng Peng, Yuxin Chen, Alex Shao, Nathan Jew, Masayoshi Tomizuka Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32250v1 Sign-language interpretation in public communication relies on qualified professional interpreters and can be difficult to scale, motivating robotic signing as a complementary accessibility interface. We present RoBoSTAR, a text-conditioned sign language production (SLP) framework for generating human-centric sign motion that can be retargeted for robotic execution, with speech supported optionally through an external ASR front end. Conventional autoregressive approaches flatten motion into a single full-resolution token sequence, forcing long-range and local dependencies to be modeled at a uniform temporal granularity. RoBoSTAR instead combines part-wise Finite Scalar Quantization with next-scale autoregression, generating motion over progressively finer temporal resolutions while predicting synchronized body and hand tokens in parallel within each step. This coarse-to-fine formulation provides compact long-range context before progressively refining motion details, while self-conditioning and context corruption improve robustness to cross-scale prediction errors. The generated motion is subsequently retargeted for physical humanoid execution. Extensive qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of RoBoSTAR. --- ### Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes Authors: Hongfu Gao, Songxin Zhang, Zejian Xie, Bingyi Jing, Zhou Wang, Yiming Liu Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32248v1 Large language model (LLM) leaderboards compare model capabilities by ranking models according to their mean performance on fixed benchmarks. However, variability in evaluation outcomes across runs may produce unsupported claims of model superiority on the benchmark, a risk compounded by leaderboard updates. In this paper, we propose BB-EDGE (Benchmark-Weighted and Block-Factorized e-processes for Directed Graph Evaluation), a principled framework that represents an LLM leaderboard as a directed graph whose edges certify pairwise mean-performance advantages, with anytime-valid family-wise error rate (FWER) control. Concretely, for each direction, BB-EDGE constructs an empirical-Bernstein e-process by factorizing evidence over protocol-defined blocks and assigning stakes proportional to the corresponding block weights, then applies direct e-Holm across these $e$-processes to certify directional advantages as edges. Theoretically, we characterize weight-proportional linear stakes under heterogeneous benchmark-average nulls and prove anytime FWER control under arbitrary within-block and cross-pair dependence. BB-EDGE further supports anytime-valid Top-$k$ certification and simultaneous rank intervals. Extensive experiments on synthetic data and four real-world benchmarks demonstrate that BB-EDGE maintains anytime FWER control while achieving high efficiency. --- ### Certifying Interventional Agreement Among Observationally Equivalent Causal Models Authors: Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie, Hossein Rahnama Published: 2026-09-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.32247v1 Observationally equivalent causal models can still disagree about what happens under intervention, because interventions create inputs that never occur in observational data. We introduce Interventional Separation Selection (ISS), which repeatedly queries the true system with an admissible intervention on which the surviving candidate models disagree, discards the candidates the outcome contradicts, and stops once no intervention within a cost bound separates the survivors. If the true system is among the candidates, this stopping condition certifies that every survivor agrees with it on every admissible intervention within the bound, a guarantee that no observational learner can give, however much data it sees. The stopping condition depends only on the survivors, so it can be checked without knowing the truth. For continuous variables the candidates form an infinite version space, and mixed-integer linear programs decide the stopping condition exactly over all of it, with agreement holding up to a tolerance. On a three-digit colored MNIST causal abstraction task in which ink hue tracks digit size, plain convolutional networks trained on examples reach zero held-out error, yet disagree with shape-based labels on 26% of single-digit edits, as often as hue-based labels do. Auditing the causal abstractions of networks observed only on such images, ISS certifies what each network perceives with 13.6 interventions per image on average, and each certificate, checked against every admissible intervention, holds whenever the network's true abstraction is among the candidates. When a network bypasses a unit that every candidate abstraction relies on, certificates covering interventions on that unit can be silently void, and twenty random validation interventions refute 69% of them. --- ### AutoPDEBench: Benchmarking LLM Auto-Research for Neural PDE Solver Design Authors: Ruoyan Li, Wei Wang, Yizhou Sun Published: 2026-09-26 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2609.32245v1 Partial differential equations (PDEs) are essential for modeling complex physical systems, and neural solvers have recently emerged as powerful data-driven tools for numerically solving them. However, existing neural solvers struggle with domain-specific challenges, such as varying parameters and high-speed flows, necessitating specialized architectures. Manually designing these specialized solver architectures is a highly iterative, time-consuming process requiring deep expertise, creating a significant bottleneck in scientific discovery. We propose leveraging autonomous AI research agents to automate the synthesis of specialized solvers. To support this, we introduce AutoPDEBench, a benchmark dedicated to LLM-driven automated research for PDE solver design. The benchmark includes 25 challenging datasets featuring both novel and actively studied physical scenarios. We evaluate a suite of general-purpose models (transformer, ROM, and graph-based) alongside a multi-agent instantiation of the iterative automated research pipeline, which serves as an agentic baseline. Empirical results show that the iterative automated research system significantly outperforms the general-purpose neural solver baselines. Our findings demonstrate the viability of using AI agents to automatically design neural solvers for complex physical systems. AutoPDEBench provides a foundational testbed to accelerate agent-driven scientific discovery in physics and engineering. --- ### Two-Stage Multi-View Gait Recognition with a Re-Embedding Network Authors: Long Hoang Le, Trung Thanh Ngo Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32244v1 Gait recognition always remains challenging due to severe overfitting and the rigid view constraints common in single-stage approaches. We propose a two-stage framework, termed Translate-First-Then-Reason (TFTR), to address these issues. In the first stage, a shallow Siamese convolutional network with triplet loss maps Gait Energy Images (GEIs) into a 128-dimensional view-specific embedding space. In the second stage, these per-view embeddings are treated as tokens and processed by a 12-layer Transformer encoder, which re-projects them into a new space with improved cosine separability. This design enables flexible fusion of an arbitrary number of views at inference, overcoming the fixed-input limitations of prior methods. Trained on the OU-MVLP dataset (6,000 subjects) and evaluated on unseen CASIA-B across normal, bag-carrying, and coat-wearing conditions, our pipeline achieves 96.91\% single-view and 99.49\% three-view accuracy on OU-MVLP, and attains 100\% accuracy on CASIA-B with three views. --- ### Residual Transferability in Neural Image Watermarking Authors: Ziping Dong, Qi Li, Xinchao Wang Published: 2026-09-26 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2609.32241v1 Neural image watermarks can be forged by extracting watermark-bearing residuals from released images and transferring them to unrelated content. While prior work has demonstrated this vulnerability, what makes these residuals transferable remains poorly understood. We formalize this vulnerability with \textbf{residual transferability (RT)}, a metric that quantifies how well watermark evidence remains decodable after transfer across unrelated images. Through comparative analyses and controlled interventions, we find that common training-side variations do not account for the large RT differences across watermarking systems; instead, architectural design plays a central role. By contrasting high- and low-RT systems and validating their architectural differences through controlled interventions, we identify two mechanisms that strengthen the dependence of watermark evidence on the cover image, thereby suppressing the residual transferability. These findings provide concrete design guidance for developing more forgery-resistant watermarking architectures. Complementarily, for existing watermarking systems where architectural redesign is impractical, we introduce \textbf{CoverLock}, a plug-and-play strategy for existing watermarking systems that strengthens such image dependence without architectural redesign. Across representative watermarking systems exhibiting high residual transferability, CoverLock achieves a more favorable security--robustness trade-off than both traditional handcrafted defenses and learned classifier-based defenses. --- ### Arithmetic Simplicity in Stochastic Gradient Methods Authors: Bin Fu, Pengfei Gu, Jose Nunez, Fabian Vazquez Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32240v1 A gradient descent method is arithmetically simple if the operations are limited to $+,-, \times$, and division $x/2^t$ with integer $t$. An arthmetically simple gradient method is easy to implement in chip design. We show how to transform AdaGrad, Adam, and AdamW into arithmetically simple. AdamW is based on the recursion $x_{t+1}=(1-λη)x_t-\frac{η}{s}m_t$ and Adam is the special case of AdamW with $λ=0$. We transform them into a static case with $s=S(T)$, where $T$ is the number of iterations, and $S(T)$ is a fixed function. The convergence analysis is given for a static Adam, which is also arithmetically simple. --- ### Federated Subspace Guided Vision-Language-Action Policy Distillation for Non-IID Multi-Robot Manipulation Authors: Biprodip Pal, Kaushik Roy, Yanming Zhu, Brendan Tidd, Alan Wee-Chung Liew, Peyman Moghadam Published: 2026-09-26 Categories: cs.RO, cs.CV, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.32239v1 Federated learning offers a natural way for multiple robots to jointly improve manipulation policies without requiring centralized access to training demonstrations. However, non-IID task and environment distributions can induce representation drift and mutually incompatible robot-policy updates, making naive parameter aggregation destructive. We present FedDRMan, a federated subspace-guided distillation framework for heterogeneous robot manipulation. At each communication round, the server model provides a frozen teacher for local behavior cloning, while low-rank multimodal subspace and action-distribution distillation preserve globally useful representation geometry and policy behavior. To address heterogeneous aggregation, FedDRMan groups clients by update compatibility and maintains a persistent model for each cluster. The server then spectrally rebalances each compatible aggregate to mitigate attenuation of weaker task-relevant robot-policy update directions. Extensive experiments on LIBERO across diverse non-IID settings, heterogeneity levels, client participation variation, together with ablations and aggregation analyses, show that FedDRMan substantially improves knowledge transfer and consistently outperforms strong federated baselines achieving a peak mean success rate of 80.7%, 11.6 percentage points above the strongest evaluated federated baseline. --- ### Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning Authors: Zhuohan Wang, Haoran Ma, Tianyu Wu, Yuanlin Duan, Zichun Liao, Jieming Yu Published: 2026-09-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.32235v1 Large language models (LLMs) can solve every intermediate step of a multi-step math problem on its own and still fail the full problem, even when given a roadmap of the steps and all of their answers. We introduce OracleLadder, a diagnostic evaluation that locates where LLM math reasoning fails by giving the model increasing levels of oracle help. For each problem, a teacher model writes a fixed roadmap of intermediate sub-goals (milestones), and a deterministic symbolic verifier grades every answer. Testing the model with no help, with the roadmap, with the roadmap plus the milestone answers, and on each milestone alone sorts each failure into one of five reasoning gaps. On 354 NuminaMath problems and six models from 8B to 671B parameters (Qwen3, gpt-oss, Llama 3.3, DeepSeek-V3.1), the largest gap for every model is the composition gap, a stricter form of the compositionality gap. It covers 33-48% of problems, and 24-37% after removing problems that an LLM review flags as grading errors. Accuracy and milestone-help recovery rank the two strongest models differently, and two RLVR runs with similar accuracy gains move problems differently. The roadmap effect replicates on MATH500 and AIME 2024/25, per-problem recovery agrees for 83-87% of problems under an independent second teacher, and the help ladder carries over to code generation. We release the data, roadmaps, prompts, and code at https://github.com/slark-prime/OracleLadder. --- ### KinyaMed: Seeds, Not Rows -- What a Corpus Requirement Written in the Wrong Unit Fails to Constrain Authors: Marius Bayizere Published: 2026-09-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.32234v1 Triage decides who is seen first. Building an urgency classifier for patient-voice Kinyarwanda, we found our specification could be met without producing anything it was meant to secure. We report that, and the instruments that detect it, instead of a classifier. Designed for the four languages a Rwandan health centre receives, with every instrument per-language: sentences are authored in all four arms and rows generate in one, because the frame slots those three need do not exist. Our requirement asked for one million examples; generation produced them in 130 seconds. It fails four of the nine quality gates in that specification, six when rows are attributed to their source sentence. The binding gate counts distinct authored seed phrases, not rows: at our 165, no corpus passes at any row count. Two shortfalls follow and differ: 2,835 further sentences to pass the seed-count gate, 19,835 to reach the stated million rows, because a separate gate caps a seed at 50 rows. Rows come from a machine at 7,700 per second; seeds from clinicians. A row count constrains the cheap quantity, leaves the expensive one free, and so does not constrain quality at all. Two further negatives follow. An evaluation set of 17,942 rows built from nine distinct sentences supports no verdict: our gate, which counts distinct sentences, refuses 38 of its cells and reports nothing. A model trained on a corpus of uniform surface form changes its predicted urgency for 31.5% of inputs under capitalisation and 21.0% under a single typo, reported as measurement and not attribution. A model directory shipped without its tokenizer loads without error and answers its class prior on input it cannot read, with well-formed probabilities. No figure here is evidence of model quality; the contribution is the apparatus and the negative results it produced, reproducible from a clean clone except where marked NOT REPRODUCIBLE. --- ### Skeletons in Flow: Graph Structured Flow Matching for Human Motion Prediction Authors: Yixuan Wang, Brandon C. Fallin, Warren E. Dixon Published: 2026-09-26 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.32231v1 Human motion prediction requires diverse future trajectories that remain consistent with observed motion and the articulated physical structure of the body. Skeletal constraints restrict individual poses, while coordinated motion depends on spatial interactions (between connected joints) and temporal interactions (between time instants). To facilitate human motion prediction in light of these constraints and interactions, we introduce Graph Structured Flow Matching (GSFM), which transports the complete future skeletal trajectory through a single conditional velocity field. The trajectory produces a spatiotemporal skeleton graph, and spatial and temporal attention couple its evolution according to skeletal relations and physical time offsets. Bone directions lie on unit spheres relative to a root joint, and tangent evolution preserves input bone lengths throughout generation. We train a learned velocity field through conditional flow matching along geodesic paths connecting random trajectories centered on the last-observed pose to recorded future trajectories. Experiments on the Archive of Motion capture As Surface Shapes (AMASS) dataset evaluate prediction accuracy, diversity calibration, and motion statistics. We demonstrate the contributions of spatial and temporal message passing in the developed architecture through an ablation study. GSFM models trained on AMASS also perform competitively on the Human3.6M skeleton without parameter updates or retraining, demonstrating applicability to an unseen skeletal structure. --- ### "Where Can I Trust You?": Boundary-Aware Evaluation of Surrogate Fidelity Authors: Jackson Eshbaugh Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32230v1 Surrogate models are commonly evaluated by how often they agree with their teacher model over an evaluation set. Local variation in this agreement is well known, but its structure and consequences are less clear. We ask whether disagreement is systematically concentrated near the teacher's decision boundary and whether retaining that structure provides information beyond a single global score. Across several datasets and surrogate model classes, we find substantially lower fidelity near teacher decision boundaries under two different methods of identifying near-boundary examples. Moreover, conditioning agreement on confidence-defined regions improves prediction of teacher--surrogate agreement when evaluation-set composition changes, relative to the global score alone. Yet surrogates that agree equally well with the teacher both globally and near the decision boundary can respond very differently to changes selected using the surrogate itself. Finally, we show that independently trained deep teachers can agree on most predictions while identifying different examples as lying near their decision boundaries, complicating the use of those boundaries as stable reference regions for evaluating surrogates. Together, these results show that surrogate fidelity depends not only on how often a surrogate agrees with its teacher, but also on where that agreement holds and, for deep models, how stable the teacher's decision boundary is across training runs. --- ### CompassPlay: Rewarding the Proposer for Where It Moves the Solver Authors: Sophia Xiao Pu, Ximeng Sun, Jiang Liu, Jialian Wu, Emad Barsoum, Zicheng Liu, William Yang Wang Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32228v1 In self-play, a proposer generates verifiable tasks to train a solver. Proposer rewards often depend on the solver's success rate, but equally difficult tasks can differ in their training value. We introduce CompassPlay, a self-play method that rewards the proposer through gradient alignment. The reward favors tasks whose solver loss gradients align with those of reference tasks representing the target capabilities. It draws on a first-order approximation to learning progress and scores each eligible task without additional solver training. Our experiments show gains in performance and training efficiency. In coding self-play with Qwen2.5-Coder-7B, a small external reference set guides task generation. CompassPlay improves average accuracy over AZR's difficulty reward by 1.5 percentage points on in-domain coding and 2.7 on out-of-domain mathematics. In Lean4 theorem proving, CompassPlay matches the difficulty baseline's 150-iteration cumulative coverage with 40\% fewer GPU-hours. --- ### OptiArena: Can LLMs Improve Executable Algorithms under Fixed Resource Budgets? Authors: Wenjun Peng, Xinyu Wang Published: 2026-09-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.32227v1 Static QA and code-generation benchmarks only partially capture the role that large language models (LLMs) now play as coding agents and research tools. We introduce OptiArena, a budget-controlled testbed for studying whether LLMs can improve executable game-playing algorithms through five rounds of code edits within a fixed minimal scaffold and under bounded evaluator feedback and fixed resource budgets. The testbed uses two optimization regimes, surface obfuscation controls, calibrated references, held-out/stress splits, and diagnostics for degradation and exceptional failures, with LLM API cost reported separately from local evaluator wall-clock. The empirical study asks three questions: whether models can close the calibrated gap between a designated weak starter and an editable competent baseline, whether they can refine editable competent baselines without damaging them, and whether gains survive surface obfuscation controls. Across twelve frontier LLMs and five games, models improve designated weak starters more consistently than they refine editable competent baselines, with substantial variation across games and models. OptiArena provides a practical testbed for measuring bounded-resource algorithm optimization within the five-edit, fixed-scaffold setting studied here. Code is available at https://github.com/WJ-Peng/OptiArena. --- ### Toward Agentic Optical Networks: A Vision of LLM Agent-Driven Autonomous Lifecycle Management Authors: Yao Zhang, Shengnan Li, Yuchen Song, Yidi Wang, Yue Pang, Wenbin Chen, Xiaotian Jiang, Xiao Luo, Meixia Fu, Min Zhang, Yongli Zhao, Shanguo Huang et al. Published: 2026-09-26 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2609.32226v1 As optical networks continue to expand in scale, complexity, and service diversity, the implementation of automation has become essential for ensuring agility, efficiency, and reliability in lifecycle management (LCM) of optical networks. Large language model (LLM) Agent, distinguished by its progressively sophisticated capabilities in logical reasoning, adaptive decision-making, complex problem solving, and multi-task orchestration, presents great opportunities to advance network automation beyond traditional AI techniques. Nevertheless, the application of LLM Agent in optical networks remains in its early exploratory stage, challenged by the lack of multi-task coordination, high computational demands, data dependence, and reliability concerns. In this paper, we envision a conceptual roadmap toward Agentic Optical Networks (AONs) by integrating LLM Agents throughout the LCM with high-level autonomy. First, we trace the evolution from manual operations to AI-empowered frameworks and distill key technologies in Agent, providing actionable insights into leveraging its strengths for addressing practical network automation challenges. A core contribution of this paper is the proposal of a hierarchical multi-Agent framework, which is specifically developed to manage every phase in LCM of AONs, including planning, deployment, operation, maintenance, upgrade, and decommission, thereby enabling more cohesive and comprehensive automation throughout the entire lifecycle. In addition, future directions and underlying challenges are also discussed at the intersection of LLM and optical networks. By aligning the LLM Agent with the specialized requirements of AONs, this work aims to explore the potential for the evolution of optical networks moving from task-level semi-automatic execution toward lifecycle-level full autonomy. --- ### LaMET-Agent: An Agent Framework for Large-Momentum Effective Theory Analysis Authors: Jinchen He, Xiangyu Jiang, Fei Yao, Dian-Jun Zhao Published: 2026-09-26 Categories: hep-lat, cs.AI, hep-ph arXiv: https://arxiv.org/abs/2609.32225v1 Large-momentum effective theory (LaMET) provides a first-principles framework for computing the $x$ dependence of light-cone parton distributions from lattice QCD. Over the past decade, theoretical and numerical advances have established a mature multi-stage workflow for systematic calculation of parton physics, although its implementation still requires expert judgment and substantial repeated effort. We present lamet-agent, an open-source large language model (LLM) agent framework that organizes this workflow into an executable, reproducible, and inspectable analysis pipeline. The present release supports collinear quark distributions and implements correlator analysis, renormalization, Fourier transformation, perturbative matching, continuum, physical pion mass and infinite-momentum extrapolations, and automated result review. We validate it on four end-to-end analyses: pion parton distribution functions in the gauge-invariant and Coulomb-gauge formulations, and pion and kaon distribution amplitudes, obtaining results consistent with the published calculations. Extensions to transverse-momentum-dependent distributions, generalized transverse-momentum-dependent distributions, and gluonic distribution functions are planned for subsequent releases. --- ### RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation Authors: Qilang Ye, Meng Liu, Yu Zhou Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32224v1 We explore whether Omni-Language Models (OLMs) can be directly applied to zero-shot Semantic Audio-Visual Navigation (SAVN). Recent work demonstrates that even state-of-the-art specialized models still struggle to achieve generalist multimodal navigation, despite extensive task-specific training. In this paper, we introduce RAO-Nav, short for Reasoning All-in-One OLM, a deployment pipeline for zero-shot SAVN. By leveraging the rich implicit audio-visual knowledge encoded in OLMs, the embodied agent is enabled to ``hear'', ``see'', ``reason'', and ``act'' in the environment. To further elicit the built-in thinking ability of OLMs, we propose a test-time Latent Navigation Reasoning (LNR) module that can be seamlessly integrated into the decoding space. LNR encourages the model to retrieve more target-relevant observations and make effective navigation decisions. Through comprehensive experiments, we show that our framework surpasses existing state-of-the-art baselines on public SAVN benchmarks without using any training data. Moreover, we introduce a new \emph{Global Navigation Instruction} setting to further evaluate the ability of OLMs to serve as embodied navigation agents. Code: https://github.com/rikeilong/OmniAV\_Nav. --- ### Geometry-Preserving Blind Watermarking for Raw 3D Point Clouds Authors: Rungui Zhou, Chuanzhi Zhou, Ruihuan Wang, Peng-Shuai Wang Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32222v1 Raw 3D point clouds are a core geometric representation. Establishing their ownership is challenging because point sets are irregular, unstructured, and frequently altered by resampling and geometric preprocessing. We present a blind watermarking framework that operates directly on xyz coordinates and supports both object-level shapes and scene-scale scans. At verification time, the embedded message is recovered from the observed point cloud alone, without access to the original point cloud, color, normals, or mesh connectivity. The method jointly learns watermark embedding and extraction through a feed-forward octree-based architecture, enabling efficient multi-scale geometric reasoning on large point sets. During training, a stochastic transformation layer exposes the decoder to common geometric perturbations, while progressive pose alignment improves robustness to pose changes. Experiments on object-level and scene-level benchmarks demonstrate reliable message recovery under common geometric processing while maintaining low geometric distortion. Qualitative comparisons further show that the learned perturbations are less visually conspicuous and less spatially structured than those of handcrafted alternatives. --- ### A bilingual AI audiologist built through rubric-guided playbook induction outperforms human audiologists in a blinded evaluation of simulated cases Authors: Linkai Li, Changgeng Mo, Hanlin Yu, Congxi Lu, Shangqiguo Wang, Matthew B Fitzgerald, Shan X Wang Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32220v1 Audiology consultation requires structured history-taking, audiometric interpretation and patient-centred communication, yet real-world case material is scarce. We present a bilingual AI audiologist pairing a general-purpose large language model with rubric-guided playbook induction, multimodal audiogram interpretation and retrieval-augmented grounding, without fine-tuning the language-model backbone. Using a 21-item rubric and an AI patient simulator, we induced a 19-rule consultation policy from 73 training cases (43 English, 30 Chinese) and evaluated the system on 58 independent simulated cases (30 Chinese, 28 English) in a pre-specified, source-blinded comparison with 17 practising audiologists. The AI audiologist outperformed human audiologists on every case (58/58; mean paired $Δ$ = +1.35 on a 5-point composite, Cohen's d = 1.84, $P = 4.5 \times 10^{-20}$), on 20 of 21 rubric items and in both languages. Component ablation identified the playbook as the largest contributor, offering a practical route to specialist consultation agents in low-data medical domains. --- ### A model of rational interlocutors: Unification of comprehension and production Authors: Hanlin Wu, Zhenguang G. Cai Published: 2026-09-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.32216v1 Who we communicate with influences both our interpretation of their utterances and the design of our own. Such adjustment to the conversational partner is studied as speaker modeling in comprehension and as audience design in production, with the two literatures having developed largely separately. We argue that both adjustments express one rational computation and propose the rational interlocutor (RI) model, a computational account unifying comprehension and production. An interlocutor maintains a model of their partner, defined by three parameters: an identity parameter Π sets the messages and forms expected from the partner; a fidelity parameter Φ sets how reliably messages and utterances map onto each other for them; a knowledge parameter Λ sets how knowledgeable the partner is believed to be. Comprehension and production are thus mirror-image modes of one computation over the partner model. Comprehension chooses the message the partner most likely intends to convey, weighing how well each candidate fits the utterance against how likely this partner is to mean it. Production chooses the utterance from which the partner will best recover the message, weighed against the effort of saying it. This explains why comprehenders appear to rely less on the forms produced by a linguistically less competent speaker, while producers tend to invest more effort in designing forms for them. We conjecture that perceived linguistic competence decomposes into two of these quantities: fidelity and knowledge. Their contrasting profiles across second-language (L2) adults, children, and artificial partners produce distinct and testable predictions. --- ### DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation Authors: Dwipam Katariya, Thomas Caputo, Akshat Shreemali, Juan Manuel Origgi, Nikita Seleznev, Pranab Mohanty, Kalanand Mishra, Nam Nguyen, James Montgomery Published: 2026-09-26 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.32215v1 Transformers have redefined sequential recommendation by effectively modeling dynamic user behaviors and long-range dependencies. However, they remain inherently inefficient: standard architectures operate at a fixed rate, allocating comparable computation to every item in a user's history regardless of its information content. This leads to prohibitive computational overhead on long sequences and increased sensitivity to behavioral noise. To address this, practitioners often resort to lossy sequence compression, staged modeling, or truncation. This limits the model's ability to leverage the full context of long histories during inference. Inspired by the recent success of Byte Latent Transformer, we propose DP-Rec, a dynamic latent patching architecture for recommendation. DP-Rec shifts from item-level modeling to patch-level modeling by segmenting interaction sequences using contrastive entropy surprise to identify informative behavioral boundaries. A lightweight patch encoder compresses these temporally contextualized segments into a reduced set of dynamic latent behavior vectors, which are then processed by a larger latent transformer and decoded for next-item prediction. Extensive experiments show that, under constrained computational budgets, DP-Rec scales effectively to long sequences and achieves a superior efficiency-accuracy trade-off over both non-compressed and fixed-size compression baselines. --- ### HM-ROUTER: Joint Model and Harness Routing for Agentic Systems Authors: Hao Mark Chen, Royson Lee, Yasuyuki Okoshi, Dimitris Anastasiou, Wayne Luk, Hongxiang Fan Published: 2026-09-26 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.32213v1 Agent performance depends on both the underlying model and the harness that manages its tool use and execution. Selecting a suitable pair requires accounting for their compatibility, yet training samples may cover only a subset of the growing combination space. We introduce HM-Router, a routing method that jointly selects a model and harness for each query. It learns separate model and harness representations shared across routes, with an interaction term inspired by canonical polyadic (CP) tensor decomposition to capture how their compatibility varies with the query. This sharing allows training samples from observed pairs to inform predictions for unobserved combinations. We curate a benchmark from 12 public agent benchmarks, covering 293 routes, 73 models, and 25 harnesses. HM-Router exceeds the strongest evaluated learned baseline by 7.3 percentage points in mean routing accuracy and leads at all seven evaluated cost budgets on the six-benchmark subset. When 90% of routes have their training outcomes withheld, allowing unobserved combinations improves normalized accuracy by 15.8 points over restricting the same router to observed routes. HM-Router has also demonstrated training sample efficiency for new routes and components and generalization to unseen benchmarks. Our code and data are open-sourced at https://github.com/hmarkc/HM-Router. --- ### Rank Confidence Sequences:Anytime-valid Leaderboards Authors: Hamed Khosravi, Xiaoming Huo Published: 2026-09-26 Categories: stat.ME, cs.AI arXiv: https://arxiv.org/abs/2609.32211v1 Leaderboards rank models by their average scores on benchmark items, and they are consulted repeatedly while the evaluation is still running. Existing confidence intervals for a model's rank control their error rate only if they are computed once, after a number of items chosen in advance. If they are recomputed as results arrive, and the evaluation stops once they look decisive, their error rate exceeds its nominal level. Anytime-valid methods keep their guarantees at all sample sizes simultaneously and hence under any stopping rule. They exist for the accuracy of one model, for one pair of models and for the set of models that may be best. For pairwise battles they also give ranks. None gives ranks when all models are scored on the same items, which makes their scores dependent. We construct rank confidence sequences: for every model, a set of ranks that contains its true rank, simultaneously for all models and at all times, at a chosen error level $α$, in finite samples. The construction combines betting e-processes, one for each ordered pair of models, with closed testing over the possible orderings of the models. It allows any dependence between the models' scores on an item. The method has two advantages. A leaderboard can be inspected after every item without inflating its error rate. The evaluation of each model can stop as soon as the question asked about it is answered, which saves compute. When results are examined only once, halfway through or later, little power is lost relative to fixed-sample methods. The paper quantifies these advantages in simulations and on public leaderboard data. --- ### Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters Authors: Tianxiang Zhan, Huanyao Zhang, Yuanpeng He Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32209v1 Time series foundation models must preserve multi-domain breadth, probabilistic output, and multiple temporal scales, but parameter count grows when each scale receives a separate representation. We introduce Fracast-0, a probabilistic forecasting foundation model that exploits temporal self-similarity to reuse one operator across scales. A parameter-free detector extracts significant seasonal structure. The encoder applies a shared local block along a geometric dilation ladder with scale conditioning, while the decoder combines context-gathered states with an explicit seasonal future state and reuses a second block along another ladder before emitting nine quantiles. Pretraining across six corpora preserves multi-domain breadth within 85,001 parameters. On 97 GIFT-Eval configurations without per-dataset fine-tuning, Fracast-0 is the smallest of 28 evaluated checkpoints and remains non-dominated in the aggregate parameter-accuracy plane with MASE 0.808 and WQL 0.564. It uses 42.0% fewer parameters than TinyCast, whose MASE and WQL are 4.2% and 3.3% lower. These results support cross-scale weight reuse as a practical route to further time series foundation model compression. --- ### Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments Authors: Guanghan Ning, Ping Liu, Linyi Li, Huangjie Zheng, Arjun Neervannan, Huu Nguyen, Michael Sklar, Deniz Zorlu, Nicolai Ouporov Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32208v1 Automated science needs agents that can work out the rules of an unfamiliar environment by interacting with it. Interactive rule-discovery puzzles offer a controlled setting for studying this ability: an agent infers hidden rules through experimentation and uses what it has inferred to reach a stated goal. We ask what limits current language models on these puzzles and whether reinforcement learning (RL) improves performance on rules held out from training. To study both, we introduce WITNESS, a 2D grid-based puzzle environment with ground-truth ASCII observations and controlled access to rules. An agentic pipeline generates games for WitnessGym, the RL training suite, and WitnessBench, comprising public validation and private test games. The validation set separately tests new compositions of trained rule primitives and primitives absent from training. Under a shared harness, the best of 18 frontier proprietary and open-weight models solves only 24\% of private test level slots, with scores sensitive to the observation interface and agent configuration. Providing ground-truth rules raises Opus-5's validation RHAE-L5 (relative human action efficiency over the first five levels) from 59.9 to 97.8, whereas a 27B open-weight model gains only 2.1 points and remains limited even with the rules provided. RL on WitnessGym raises the 27B model's private test RHAE-L5 from 2.1 to 5.4 and yields a mean gain of 4.1 points on four external discovery benchmarks. Together, these results point to rule acquisition as a major difficulty for frontier models like Opus-5 while smaller models further struggle on rule-based execution, and indicate that RL on hidden-rule puzzles transfers to broader rules and real-world tasks beyond training. Benchmark is available at: https://witnessbench.ai --- ### DegreeSpar: Structured Degree Sparsity for Efficient Secure Transformer Inference Authors: Yifei Cai, Zhuoran Li, Xiaozuo Shen, Hongyi Wu, Chunsheng Xin Published: 2026-09-26 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.32204v1 Secure Transformer inference protects sensitive inputs but incurs substantial cryptographic overhead, with nonlinear operations such as Softmax and GeLU becoming major bottlenecks. Existing compression methods reduce nonlinear complexity, sequence-dependent computation, or model structure through separately defined compression variables. Under aggressive compression, however, these independently optimized perturbations can accumulate: at a matched compression level, stacking representative approximation, token-pruning, and model-pruning methods reduces ViT-S accuracy from 80.20% to 76.41%. We introduce DegreeSpar, which formulates secure Transformer compression as structured sparsification over nonlinear polynomial degrees. Polynomial degree directly controls the cost of secure nonlinear evaluation, while computation-aligned zero-degree structures expose token-level and model-dimension computation as removable within the same optimization space. DegreeSpar further incorporates approximation-aware training for low-degree Softmax and GeLU, enabling aggressive degree reduction and creating the optimization headroom required for structured computation removal. Across vision and language Transformers, DegreeSpar consistently improves the accuracy-latency trade-off across model scales, tasks, and sequence lengths, achieving speedups from 2.29x to 6.63x over the corresponding baselines. Under the same network setting, DegreeSpar achieves 92.68% accuracy on BERT/SST-2 in 110.55 s, compared with 92.66% in 167.26 s for CipherPrune, the closest prior hybrid secure-inference approach. These results establish structured polynomial degree as an effective shared optimization space for secure Transformer compression. --- ### Kernel-Based Steering of CLIP with Vision-Language Model Preferences Authors: Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Sina Mansouri, Mahnoosh Alizadeh, Farzan Farnia, Ramtin Pedarsani Published: 2026-09-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.32203v1 Large vision-language models (VLMs) can judge visual similarity, but their judgments are not directly available as compact image embeddings for efficient comparison. We study how to transfer these preferences into CLIP while retaining its image--text capabilities. We introduce ASK, a kernel-based steering method that learns from elicited pairwise judgments without accessing teacher embeddings or collecting new human similarity annotations. ASK constructs positive semidefinite target kernels within small image groups and combines visual kernel matching with an image--text distributional anchor. Low-rank adapters jointly update the visual and text encoders while regularizing predictions toward frozen CLIP. After adaptation, retrieval uses CLIP image embeddings and cosine similarity, with no VLM calls. Experiments across five image domains, four CLIP backbones, and six judges evaluate teacher agreement, retrieval, and recognition retention. For ViT-B/16, mean retrieval mAP on classes excluded from adaptation increases from 53.8 to 75.0, compared with 71.7 for DINOv2 targets with KL anchoring. Mean zero-shot accuracy with jointly adapted encoders increases from 61.8\% to 62.4\%, averaged over 12 benchmarks and the five adaptation domains. Prompting provides an additional capability: selecting which visual distinctions the student learns. Human-annotated evaluations across four datasets support this criterion-specific control. --- ### Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation Authors: Hantao Yu, Sandy Han, Udaya Ghai, Ferhat Erata, Joe Lilien, Aman Goel, Ali Torkamani Published: 2026-09-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.32201v1 On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement. In OPCD, the teacher is conditioned on privileged information, and the goal is to minimize the Kullback-Leibler (KL) divergence between the privileged teacher and the student, evaluated on student-generated tokens. Many existing studies show that using instance-specific gold answers or gold demonstrations as the default privilege can hurt training performance, especially out-of-distribution (OOD). In this work, we instead design general instructions that target common student mistakes observed on the training samples, and show that such simple instructions can outperform gold as the OPCD privilege. In autoformalization tasks, using a matched formatting instruction as the privilege could outperform gold in OOD accuracy by a large margin. In 7 out of 8 experiments using ProverQA, ProofWriter, and ProntoQA as datasets, and Qwen3-Thinking and Olmo3-Thinking families as models, matched instruction privileges outperform gold in OOD by 4 to 17 points, while remaining on par with gold in-domain. Each instruction is only a few sentences (and thus contains much less information compared to all instance-specific gold) and is applied uniformly to every training sample. These results indicate that a general instruction, which applies equally to source and target domain examples, can be substantially more transferable than instance-specific gold in OPCD while maintaining in-domain performance. --- ### Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization Authors: Wang Bojun, Holly Jenkins, Elizabeth Wonnacott Published: 2026-09-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.32199v1 We investigate how generalization and memorization develop along the learning trajectory of neural language models. Using controlled synthetic grammars, we examine both the geometry of representation space and model behaviour over training. We find that continuous regions of representation space not occupied by observed tokens become systematically structured from the earliest stages of learning, forming category-level geometric organization that supports generalization to unattested combinations. Generalization therefore emerges from the beginning of learning rather than only after extensive memorization. With prolonged training, larger models increasingly distinguish observed from unobserved grammatical combinations. At the same time, the continuous geometric structure supporting category-level generalization is gradually destructed. Together, these results suggest that neural language models initially learn through categorization-based generalization, followed by a gradual transition toward more exemplar-specific memorization. --- ### Agents as Software: A Programming Languages Agenda for Agent Reliability Authors: Shraddha Barke, Adithya Murali Published: 2026-09-26 Categories: cs.PL, cs.AI arXiv: https://arxiv.org/abs/2609.32198v1 AI agents increasingly resemble software systems: they call tools, remember facts, follow policies, delegate work, and take actions with real consequences. % Yet the ``program'' of an agent is scattered across prompts, tools, memories, workflows, and execution traces, making its behavior difficult to inspect through ordinary testing and debugging alone. % This essay argues that a programming-systems perspective offers a natural lens for making agents reliable. % We recast agents as programmable artifacts whose behavior can be specified over traces and state, checked before deployment, monitored during execution, and improved from observed failures. % The goal is not to make probabilistic agents behave like deterministic programs, but to give them enough structure that their behavior can be reasoned about, controlled, and repaired. ---