# Research Papers — 2026-09 · bundle page 66 of 266 > Full-text markdown of papers #3251–3300 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/66 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/65.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/67.md) ### Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency Authors: Xinhan Yang, Lu Lu, Shancong Mou Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32797v1 Derivative-informed training improves neural operators by directly supervising their input-output sensitivities, which is crucial when neural operators are used as differentiable surrogates for inverse problems, PDE-constrained optimization, design, and control. However, existing methods rely on offline-generated derivative labels, making data generation slow, storage-intensive, and difficult to adapt across datasets, resolutions, or perturbation bases. We propose sketched tangent consistency loss (sTCL), an on-the-fly derivative-informed training objective that, for PDEs with a known and differentiable residual, enforces sensitivity consistency directly from the governing equation without offline tangent labels or neural-operator architecture changes. sTCL uses randomly sketched input perturbations to provide a lightweight derivative-level physics constraint during training. However, raw forward-sensitivity residual penalties can fail for stiff, ill-conditioned, indefinite, or coupled saddle-point tangent operators. To address this, we introduce lightweight operator-aware loss-conditioning mechanisms selected by a simple tangent-operator decision rule. Across Helmholtz, nonlinear diffusion-reaction, Burgers, Allen-Cahn, and Navier-Stokes, with the same neural-operator backbone for all methods, the PDE-specific sTCL losses achieve solution and Jacobian accuracy comparable to offline derivative-informed training (DIFNO) while eliminating the offline derivative-data generation and storage pipeline. These results show that on-the-fly derivative-informed training need not merely amortize offline tangent-solve cost into training; with appropriate sketching and loss design, sTCL provides an effective drop-in path to derivative-informed neural operators. Code is available at https://github.com/yang9579/Derivative-informed-traning-on-the-fly. --- ### AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks Authors: Woojung Song, Hoyeol Yang, Jeonghoon Shim, Sungjib Lim, Jonggeun Lee, Yunho Choi, Yohan Jo Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32795v1 Large language model (LLM) agents assist users with everyday tasks that can be completed in many reasonable ways. Even when their answers are useful, how agents carry out these tasks may not match users' preferences and needs. For example, agents differ in whether they ask clarifying questions or search the web. We introduce HABIT, a taxonomy of 23 behavioral axes in five categories, which three authors and three LLMs derive bottom-up from 408 agent trajectories across 17 domains. On held-out tasks, HABIT distinguishes models more clearly than existing taxonomies of human values and agent actions while supporting comparably consistent annotation. Building on HABIT, we construct AgentHABIT, a benchmark that profiles each agent's behavioral tendencies from its trajectories on 86 everyday tasks. Profiling 18 models with AgentHABIT reveals a range of distinctive tendencies. For example, most GPT and Claude models state their assumptions and offer alternatives when requirements conflict, whereas Qwen and Google's models more often leave assumptions or changes to requirements unstated. These profiles remain recognizable even when built from entirely different sets of tasks, indicating that they reflect general tendencies rather than task-specific behavior. Prompting agents to adopt specific behaviors shifts some axes readily but barely changes others, while fine-tuning on another model's trajectories changes only part of a model's profile and leaves much of it intact. Overall, HABIT and AgentHABIT provide a systematic framework for characterizing how agents carry out everyday tasks beyond task success, offering insights to guide the development of agents whose behavior better fits users' needs. --- ### Latent Space Is Not Flat: Rethinking Latent Structure for 3D Medical Image Synthesis Authors: Haowen Xue, Hao Chen, Hexuan Hu, Qian Huang, Yi Han, Qing Meng, Zaipeng Xie, Chao Li, Haoli Xu Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32794v1 Latent generative models make 3D medical image synthesis computationally practical by generating in a compressed space. However, we show that the common flat Euclidean assumption induced by $\ell_2$ objectives is imprecise: latent-space geometry is so strongly anisotropic that equal-magnitude errors can produce drastically different decoded distortions. We further find that this anisotropy has a clear feature: sensitive variation concentrates in a low-rank subspace. The dominant low-rank components capture the overall structure, encoding long-range, spatially coordinated variation while remaining resistant to local noise. Its orthogonal residual, in contrast, mainly captures local and image-specific variation. Motivated by this asymmetry, we introduce Latent Structure Flow (LSF). At each block, LSF decomposes the latent state into structure and residual, models structural changes with global context, and predicts residual variation locally while preserving a direct path for the input structure. LSF changes only the generator, leaving the frozen codec and pointwise training objective unchanged. Across cross-modality synthesis and tumor inpainting tasks, LSF outperforms all compared baselines on both global and tumor-specific metrics, demonstrating the benefit of explicitly modeling latent-space structure for 3D medical image synthesis. --- ### Understanding and Exploiting Anisotropy in Post-Training Authors: Samyak Jha, Harshvardhan Saini, Yizhen Liao, Yiming Tang, Dianbo Liu Published: 2026-09-26 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.32792v1 LLM post-training combines supervised fine-tuning (SFT), a mode-covering forward-KL objective, with reinforcement learning (RL), a mode-seeking reverse-KL objective. Frequency-weighted likelihood training leaves a well-known signature: \emph{anisotropy}, in which a few residual channels carry disproportionately large activations. Anisotropy is widely documented and usually treated as a defect, yet its function and its interaction with post-training remain unclear. We first analyze it. A label-free outlier rule isolates about 5\% of residual channels that are essential for language modeling: removing them raises perplexity from 10 to over $10^6$, versus 35 for count-matched random channels. Yet they barely distinguish correct from incorrect reasoning. SFT reshapes them, whereas RL leaves them largely intact and adapts the complementary channels. These channels therefore form the model's \emph{coherence substrate}, and reasoning adaptation happens elsewhere. We then exploit this. \textsc{SphereGate} learns one bounded gain per residual channel on a frozen backbone. Its activation-weighted gradients provably limit movement of high-energy coherence channels and leave the remaining channels free. With 0.1M trainable parameters, \textsc{SphereGate} outperforms parameter-efficient baselines by 2.0--7.3 points on MATH-500 across Qwen2.5 (0.5B--7B) and Llama-3-8B, is comparable or exceeds full-model GRPO. Anisotropy is not a defect but a division of labor that post-training can exploit. --- ### $T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training Authors: Nan Qiao, Yebin Yang, Weinong Wang, Shuning Wang, Shangpin Peng, Fengyuan Lu, Xinming Wang, Zhehan Kan, Ruixu Zhang, Songyang Zhang, Sheng Yue, Yonglong Tian et al. Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32791v1 Reinforcement mid-training lets language models learn internal thoughts from unlabeled text, but efficient token-level credit assignment remains challenging. Existing group-relative methods require costly repeated generation. Learned critics offer single-rollout feedback, but accurate return prediction alone does not ensure reliable policy updates. Our analysis shows how training--inference mismatch and PPO clipping prevent a common offset in advantage estimates from cancelling out, introducing additional update drift. We propose \tfour{}, a twin-critic method that calibrates token-level advantages from a single generated trajectory. After warmup and held-out qualification, the critics provide two advantage estimates, combined using action-dependent weights learned through a conditional-moment saddle-point objective. This objective brings the average advantage at each prefix toward zero, while a signal-retention constraint prevents the correction from erasing the learning signal. Sharing information across text positions avoids repeated sampling of each prefix. Theoretically, we characterize optimal mixing under the signal-retention constraint and establish an upper bound on residual mean-induced drift. Experiments show that, compared with the state-of-the-art critic-free method, \tfour{} improves mean benchmark performance by 7.8\% and reduces mean training-step time by up to 63.4\%. --- ### FedHV: Low-Overhead Hypervolume Weighting for Federated Multi-Objective Optimization Authors: Amirardalan Dehghanpour, Seyed Mohammad Azimi-Abarghouyi, Christopher G. Brinton Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32790v1 Task-wise federated multi-objective optimization (FedMOO) trains a shared model for competing prediction objectives under heterogeneous data, partial participation, and communication constraints. Existing methods commonly derive task weights from gradient or update geometry. This requires task-specific information or iterative server-side optimization. We introduce FedHV, which maps reference-relative objective slacks to closed-form inverse-slack weights. Each client optimizes one weighted loss and returns objective estimates with its model update. The protocol adds exactly 2m auxiliary scalars per participating client, yielding Theta(d + m) total per-client communication, compared with the Theta(md) task-specific communication of FSMGDA, and requires no additional synchronization stage. We analyze the resulting one-round-delayed weights under client heterogeneity, multi-step local updates, partial participation, and finite-sample objective reports. Under a fixed-horizon positive-slack reference condition, with the prescribed horizon-dependent step size and vanishing report error, FedHV achieves an O(T^(-1/2)) rate for the average squared log-hypervolume gradient norm; persistent report error determines the resulting stationarity neighborhood. The same bound controls the squared Pareto-stationarity residual. Across six Dirichlet-partitioned non-IID settings from four vision benchmark families and three training seeds, FedHV exceeds FSMGDA and FedCMOO in mean accuracy in five settings. Among these methods and uniform scalarization, it achieves the highest worst-task accuracy in four settings and improves the difficult CIFAR-10 objective in both CIFAR10-MNIST settings. --- ### Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds Authors: Manlin Yao, Jiabin Liu, Guan Wang, Haixu Liu, Hui Li Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32789v1 Large-scale point cloud representations of complex geome tries incur prohibitive computational and memory costs, necessitating compressed implicit representations. To ad dress this, we propose a unified framework comprising im plicit geometric field representation, hierarchical frequency domain compression, and conditional high-frequency predic tion. Specifically, an unordered point cloud is mapped to an implicit field defined within its physical bounding box. A smooth Fourier pyramid is then constructed, where com pact low-frequency components capture the global geometry. Inter-scale high-frequency residuals are encoded to preserve the spatial information required for reconstructing fine geo metric details. To restore the high-frequency information lost during compression, we develop a hierarchical 3D neural net work. The reconstructed implicit field is converted back into a point cloud through isosurface extraction. Experiments on a complex-boundary point cloud with more than eight mil lion points demonstrate that the proposed method achieves a higher compression ratio than existing point cloud compres sion methods while maintaining comparable reconstruction quality. --- ### Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts Authors: Chao Peter Yang, Cynthia Rudin, Yue Jiang, Simon Mak, Stephen Ni-Hahn Published: 2026-09-26 Categories: cs.LG, cs.AI, cs.MM, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2609.32788v1 Deep learning has transformed symbolic music generation by borrowing the training paradigms of large language models, with systems such as NotaGen now producing complete, stylistically convincing classical scores from a short prompt. These systems could become powerful creative partners, helping musicians generate endless possibilities. However, current systems expose almost no control handles on the music itself. In principle, control handles could be built into a foundation model trained from scratch, but this is rarely practical without massive amounts of quality annotated data and compute resources. We therefore present MotiGen, a recipe for retrofitting pretrained symbolic music models to use new instruction prompts. MotiGen injects a musical motif as a structured prompt line, reinforces it with a scalar attention bias toward the motif tokens, and learns the association with a two-phase curriculum. First, it learns from focused excerpts cropped around motif occurrences in the training data, then full scores including the motifs. Our experiments show that our model composes with the prompted motif in over 92.3\% of generated pieces. Generated pieces using a variety of motifs are included in our sample site: https://motigen-site.github.io/. --- ### CLAIRE: A Schema-Grounded Hybrid Workflow for Healthcare Administrative Form Completion Authors: Garapati Keerthana, Manik Gupta Published: 2026-09-26 Categories: cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2609.32787v1 Healthcare administrative staff transfer structured information from electronic health records, referrals, claims systems, provider rosters, and work queues into dynamic forms. We developed and evaluated CLAIRE (Clinical Language and Agentic Intelligence for Reasoning and Entry), a hybrid workflow that separates field-state discovery, source-to-field mapping, deterministic validation, bounded correction, escalation, and audit tracing. We tested five synthetic healthcare administrative schemas, 1,000 source records, four interface variants, two data-quality suites, and six comparators, yielding 24,000 benchmark episodes. A separate strict-output audit evaluated direct mappings from Qwen2.5-1.5B and Qwen2.5-7B, and a trace-derived operational simulation covered 6,000 episodes. Under the evaluated synthetic benchmark conditions, full CLAIRE achieved 1.000 episode success, field accuracy, required-field completion, and dependency completion in both suites; removing validation reduced stress-suite success to 0.500. In the simulation, 100.0% of clean and validation-stress episodes reached a staff-reviewable draft, compared with 68.6% of escalation challenge episodes, unsupported cases were blocked. Scenario-based savings were 149.7-165.5 seconds per case, not observed staff times. The findings support schema-grounded, validation-first healthcare administrative automation in which language-model components assist mapping but do not authorize unsupported or consequential actions. --- ### Learning When to Recur: Token-Adaptive Recursion for Imbalanced Ophthalmic Domain Incremental Learning Authors: Nanxi Yu, Kang Li, Ye Du, Xiaowei Hu, Weihua Yang, Shujun Wang Published: 2026-09-26 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.32785v1 Domain incremental learning is essential for adapting ophthalmic deep learning models to sequential clinical domains while preserving diagnostic expertise. Existing domain incremental learning methods predominantly address the domain shift induced by style variations. However, they often overlook the severe class imbalance inherent in real-world clinical scenarios, such as clinical referral systems. Institutions in these systems encounter drastic fluctuations in class priors, resulting in label distribution shift, a critical form of domain shift that triggers severe catastrophic forgetting. To address these challenges, we propose ToRe, a rehearsal-free and parameter-efficient framework that leverages frozen ophthalmic foundation models for robust incremental adaptation. ToRe employs a parameter isolation strategy to decouple domain-specific optimization paths, thereby helping mitigate catastrophic forgetting driven by both label distribution shift and style variations. Simultaneously, it introduces token-adaptive recursion that adaptively allocates additional computational depth across tokens, allowing simple tokens to exit the recursion loop early while subjecting complex tokens, such as those associated with lesions, to deeper recursive processing. This mechanism enhances the feature representations for minority classes, thereby supporting generalization throughout the domain incremental learning process. Extensive evaluations on nine heterogeneous datasets demonstrate that ToRe consistently outperforms state-of-the-art methods in overall performance across the three benchmarks, while maintaining near-zero forgetting. Together, these results support the applicability of ToRe to dynamic and imbalanced clinical environments. The code is available at https://github.com/Nancyolo/ToRe --- ### CollisionGAT: Controller-Agnostic One-Step Collision Screening for Multi-Agent Motion Authors: Alan Debbas, Edwin Meriaux, Gregory Dudek Published: 2026-09-26 Categories: cs.RO, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.32783v1 Before a team of robots moves, each proposed step must be checked for collisions with other robots and with obstacles. We present CollisionGAT, a graph-attention network that reads the current and proposed states of moving agents together with locally relevant stationary obstacles and returns one collision-risk score per moving agent. Any controller can use these scores to accept, repair, replan, or postpone a proposed step. We mount CollisionGAT on a continuous path-following controller and on GATeD, an obstacle-blind D* Lite planner that uses typed vetoes to update its planning graphs. Exact geometric checks supply the training labels and independently audit every executed step. --- ### Learning response-aware patient dynamics for respiratory support Authors: Xiaolei Lu, Shamim Nemati Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32782v1 Respiratory support can shape the short-term physiological trajectory of critically ill patients, but patients receiving the same intervention may follow different physiological trajectories. Clinical patient dynamics models typically predict future states from recent physiology and recorded interventions, while physiological change is mainly represented through the predicted future state. We propose a response-aware patient dynamics model that explicitly represents physiological change during autoregressive state updating. The model decomposes predicted physiological change into state-dependent baseline dynamics and respiratory-support-associated deviations, with room air providing a reference for the decomposition. We provide a formal analysis of this reference-anchored formulation. A response pathway encodes the predicted physiological change and uses it to update the latent patient state across the forecast horizon. Across ICU cohorts from two independent institutions, the proposed model achieves comparable overall trajectory prediction to patient dynamics baselines, with more consistent improvements when physiological states are changing. --- ### CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Models Authors: Long Qian, Bingke Zhu, Jiaqi Wei, Yu Li, Yingying Chen, Jinqiao Wang Published: 2026-09-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.32781v1 Diffusion vision-language models generate answers by gradually resolving masked tokens, making accurate conditional prediction in partially resolved states central to post-training. Masking completed answers yields coherent contexts and targets, but prescribed masks do not reflect the model's reveal decisions. Its trajectories capture these decisions, yet their provisional visible tokens can conflict with the target response. Outcome-based reinforcement learning follows these trajectories but provides only response-level feedback, which loses contrast when sampled rewards tie. To align coherent token-level supervision with the model's reveal decisions, we introduce Counterfactual Trace On-Policy Distillation (CT-OPD), which combines completed teacher responses with trajectory masks from the current student. CT-OPD retokenizes each teacher response in the student's vocabulary and extracts unresolved-position masks at successive stages of the student's reverse process. For each mask, it discards provisional rollout values and reconstructs the partial state from the teacher endpoint, so the supervised positions follow the current trajectory while the visible context and targets remain consistent with the same response. The student is trained on these reconstructed states with its native categorical loss, and trajectories are refreshed as the model evolves. Across dense and sparse diffusion architectures, CT-OPD consistently enhances multimodal understanding and reasoning capabilities, with gains of up to 9.80 points on the nine-benchmark average. On the unified understanding-and-generation architecture, it also improves both visual understanding and image generation, showing that the same principle transfers across architectures and modalities. Ablations further attribute these gains to coherent reconstruction and current-model trajectory masks. --- ### OmniMoE-VL: A Sparse Vision-Language Model with Coupled Visual-Depth Routing Authors: Long Qian, Bingke Zhu, Jiaqi Wei, Yingying Chen, Jinqiao Wang Published: 2026-09-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.32780v1 Vision-language models (VLMs) increasingly use sparse mixture-of-experts (MoE) to scale language-side computation, yet visual information is typically routed only after passing through a fixed cross-modal interface. This leaves an important decision unresolved: which intermediate visual representations should be exposed to language computation for a given question? We introduce OmniMoE-VL, a sparse VLM with a coupled visual-depth routed projector. For each image-prompt pair, the projector selects a sparse set of intermediate visual depths and reuses the resulting global preference to guide both local patch fusion and dynamic visual injection into the language model. This design enables question-dependent visual access while preserving the native visual-token sequence, and complements token-level expert routing in the vision and language stacks. Across eight image-based benchmarks, OmniMoE-VL achieves an average score of 85.9 with 28B total and 9B activated parameters. Controlled comparisons show that the routed visual interface provides the dominant architectural gain, while matched route and component controls, same-image route analysis, and route interventions further support the value of coupling and question-conditioned visual access. --- ### Copper-Policy: Focus on the Representation for Robust Robot Manipulation Authors: Zexin Feng, Yixu Feng, Lingyu Xiao, Shang Su, Kexin Zheng, Chang Xu, Mengkai Shi, Shuo Feng, Xintao Yan Published: 2026-09-26 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.32779v1 World Action Models (WAMs) acquire behavioral priors by modeling future scene evolution, but predicting detailed futures in pixel or latent space incurs substantial cost. Recent evidence that co-training gains persist without test-time generation raises a question: what must a WAM learn to improve control? We introduce Copper-Policy, which learns a compact World representation with the policy rather than relying on a predefined target space. Through temporal joint-embedding prediction, it predicts future observation embeddings conditioned on task intention without reconstructing pixels. This prediction and action decoding shape the representation jointly, while the policy retains access to current-frame spatial detail for execution. Representation analyses show that the learned features better separate task-driven change from perturbations and provide complementary information for control. Compact prediction targets reduce training tokens per sample, enabling a 2B-parameter model trained in 9.67 hours on 8$\times$ RTX 5090 GPUs and 6$\times$ faster than Fast-WAM on matched A100 GPUs. Copper-Policy outperforms every compared method without embodied pretraining on RoboTwin and several embodied-pretrained VLAs on LIBERO-Plus (80.85%). On three challenging real-robot tasks, it performs comparably to $π_{0.5}$ and attains a higher average score. Together, these results show that Copper-Policy combines strong control performance with efficient training. --- ### Agentic Network Traffic Monitoring Authors: Manuel Tsoukatos, Hayden Jananthan, Jeremy Kepner Published: 2026-09-26 Categories: cs.AI, cs.CR, cs.DB, cs.DC, cs.NI arXiv: https://arxiv.org/abs/2609.32778v1 As the use of agentic artificial intelligence increases in nearly every industry, there exists a widening attack surface. It is necessary to monitor agents to ensure that agents are acting in a way that is aligned with the users intent. Auditing an agent's network traffic provides a clear record of the agent interactions. This work presents a novel approach to monitoring the network traffic of agentic systems using complex valued hypersparse traffic matrices by integrating DBOS (DataBase OS), the OneSparse PostgreSQL database, and the GraphBLAS math library. To develop these concepts an agentic simulator was constructed, allowing a varying numbers of AI agents to collectively survey a virtual environment using different strategies. The resulting network traffic matrices enable easy monitoring of the AI agents. --- ### On the Behavioral Traits of LLM Agents Authors: Haokai Zhao, Jie Gao, Yunze Xiao, Xintao Wang, Weihao Xuan, Aditya Joshi, Mark Dredze, Jen-tse Huang Published: 2026-09-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.32776v1 Users increasingly describe different AI agents as distinct colleagues to work with. AI personality research aims to quantify such impressions by attributing human-like "traits" to agents. However, existing measures fall short: models' self-reports (S-data) diverge from their actual behavior, while informant ratings from LLM judges (I-data) are costly to scale and cover few everyday scenarios. In this paper, we propose A-B-D to infer traits bottom-up from behavioral data (B-data), namely how agents act on their environment and communicate with users, as recorded in existing trajectories. From 345,667 real-world trajectories spanning 80 models, 12 tasks, and 50 harnesses, we extract 318 candidate features that capture both the actions an agent takes at each step (functional) and the language accompanying them (linguistic). We retain only features that show instance-level stability, cross-task consistency, and model discriminability. Factor analysis of the remaining 79 features uncovers six stable, model-attributable factors, two functional and four linguistic. For example, Kimi-K3 exhibits the most planfulness, whereas GPT-5.5 and GPT-5.6 are the least energetic. Moreover, we quantify the "knowledge-action gap" in the wild: these factors correlate only weakly with self-reported Big Five scores, even for conceptually matched pairs such as extroversion and energetic (r = 0.07, p = 0.58). Our work offers a new lens for understanding AI personality, with implications for users, developers, and researchers from both computer science and social science. --- ### Robust Bayesian Optimization with Q-Exponential Surrogates Authors: Richard Cornelius Suwandi, Zhidi Lin, Feng Yin, Abdelhak M. Zoubir Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32775v1 Bayesian optimization (BO) is a widely used framework for optimizing expensive black-box objectives, but standard BO methods often use Gaussian process (GP) surrogates whose Gaussian assumption is sensitive to outliers and heavy-tailed noise. We introduce q-ED-BO, a robust BO method whose surrogate follows a univariate q-exponential (q-ED) distribution, preserving GP-BO's closed-form posterior mean and variance while a shape parameter q controls the tail behavior, recovering the GP at q = 2 and growing heavier-tailed with wider confidence bounds as q decreases. This tractability yields a closed-form q-upper confidence bound (q-UCB) with sublinear regret, and an exact closed-form q-expected improvement (q-EI) that generalizes EI to the heavy-tailed predictive, recovering classical EI at q = 2. Experiments on beamformer and adaptive filter tuning with impulsive outliers show that q-ED-BO matches or exceeds existing baselines on clean data, and under corruption, improves the strongest baseline by approximately 0.7 dB in output SINR and 1.1 to 1.2 dB in misalignment reduction. --- ### Beyond Gaussian Assumptions: Distribution-Aware Channel Capacity for Effective Connectivity Authors: Jianan Jian, Jacob Kang, Nurahmed Multezem, Benjamin Li, Nan Xu Published: 2026-09-26 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2609.32774v1 Effective-connectivity estimation from brain signals often relies on Gaussian residual modeling, which enables tractable estimation but can discard informative distributional structure and distort inferred directed interactions when empirical residuals are non-Gaussian. We show across multiple modalities, species, and experimental conditions that both brain signals and fitted channel residuals frequently deviate from Gaussianity. We therefore introduce a distribution-aware, information-theoretic measure of effective connectivity based on channel capacity under general residual distributions. To estimate the resulting capacity from empirical, potentially non-Gaussian residuals, we develop a dual-flow min-max estimator based on normalizing flows, in which a generator searches over admissible input distributions under a power constraint while an observer estimates output entropy. We provide a theoretical characterization of the estimator, showing that the observer objective recovers differential entropy up to a KL approximation term, that the formulation reduces to classical Gaussian capacity as a special case, and that residual entropy can alter achievable information rates beyond variance; game-gap and error analyses further characterize optimization and approximation sources. In brain-like simulations with known directed connectivity, Dual-flow achieves the highest AUROC and AUPRC across ten conditions spanning diverse network topologies, hidden drivers, feedback, and heterogeneous hemodynamics, compared with Gaussian capacity, Granger causality, VAR-LiNGAM, and GIMME. Applied to multimodal brain signals, the method reveals time- and condition-resolved directed interactions consistent with known neurobiological circuitry. Together, these results establish a principled distribution-aware framework for effective-connectivity estimation beyond Gaussian residual modeling. --- ### Forecasting Intraday USD/CAD Exchange Rate with News-Derived Monetary-Policy Signals Authors: Maya Kodeih, Aliaa Alnaggar, Mucahit Cevik Published: 2026-09-26 Categories: cs.AI, cs.LG, q-fin.CP arXiv: https://arxiv.org/abs/2609.32773v1 Monetary-policy announcements and central-bank communications play a central role in foreign exchange markets, yet their qualitative, unstructured form makes their forecasting value difficult to quantify. While prior research has largely focused on sentiment extracted from financial news, comparatively little is known about the relative contribution of different dimensions of monetary-policy communication. Existing studies primarily evaluate whether textual information improves overall forecasting performance but provide limited insight into which communication channels drive such improvements. To address this gap, this paper introduces a statistical attribution methodology that decomposes monetary-policy communication into interpretable channels and quantifies their incremental forecasting contribution under false-discovery-rate control. Monetary-policy news is transformed into structured communication signals using large language models (LLMs) and temporal feature engineering. These signals are evaluated using rolling-window experiments with tree-based machine-learning models. The results show that monetary-policy communication contains measurable predictive information. Attribution analysis shows that predictive value is concentrated in a small subset of signals, with communication timing providing the strongest individual feature-level contribution, targeted communication-activity measures also contributing positively, and LLM-derived sentiment providing complementary information at the group level. The findings indicate that communication-based forecasting value extends beyond sentiment alone and that attribution, rather than aggregate accuracy alone, is central to evaluating news-derived signals. --- ### Learnable Randomization as Commitment Against Adaptive Optimizers Authors: Zihan Deng, Chuanzhi Xu, Xiaozhen Zhong, Haoyang Li, Junjie Huang Published: 2026-09-26 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2609.32772v1 A pricing page can walk the posted price up to the last amount a buyer still accepts, a recommender can hold back a better item for a barely acceptable promoted one, and a classifier can shift its boundary once applicants change their features. The system predicts the response and then picks the menu that serves its own objective, so the surplus above the user's cutoff is taken. Playing the single best action publishes that cutoff, while noise on actions the user would never take throws away payoff and teaches the platform that a worse menu is still acceptable. We study unpredictable near-optimal policies (UNOP), which mix uniformly on near-best actions that remain individually rational. The mixture is a commitment about the response. On a finite price grid, when the best sure-demand price strictly out-earns the randomized band, a seller who already knows the curve posts below the band, and the purchase that occurs is deterministic. Knowing that curve is not the same as predicting the next draw. The mixture can be learned and the optimizer can match its best response, while the user's payoff stays higher because the mixture changes which action is targeted. In pricing and in policy-aware recommendation this leaves more surplus than greedy play when the platform optimizes against the curve and more than one action is acceptable. The gain goes away under quality ranking, a singleton near-optimal set, a wrong utility estimate, or a short-horizon explorer. That is also where mixing should be turned off if the other side is trying to cooperate. --- ### Continual Learning via Self-Probe Gradients Authors: Dongkyu Cho, Rumi Chunara, Sungmin Cha Published: 2026-09-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.32771v1 Adapting pretrained models to new data can cause catastrophic forgetting of previously learned behavior. When only a few past samples remain, they give continual learning methods sparse and narrow evidence about what to preserve. We show that language models can expand this evidence through self-probing, in which the frozen model generates new inputs from the retained samples and records its own predictions on them. Unlike prior work that replays such data as training examples, our method, CPLUS uses self-probe and past-sample gradients to scale down parameter updates that conflict with prior behavior. Experiments with five language models on four benchmarks show three results. First, the same probes preserve more prior behavior as gradient signals than as replay data. Second, CPLUS learns the new data while consistently reducing forgetting more than existing baselines, especially when past data are scarce, and this protection extends to benchmarks not used for training. Third, we observe that CPLUS also becomes more effective as models grow: within the Qwen3 model family, it recovers an increasing share of the forgetting caused by standard fine-tuning. --- ### C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text Authors: Qing Yang, Zixiang Luo, Zhenyu Mao, Zezheng Wu, Xinghe Cheng, Haibo Chen, Qinggang Zhang, Jiapu Wang, Jingwei Zhang Published: 2026-09-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.32770v1 Large Language Models (LLMs) increasingly participate in writing by modifying or extending human drafts, causing machine involvement to vary in both form and extent. Yet most Machine-Generated Text (MGT) detectors are evaluated only on fully human-written versus fully AI-generated text. Because human--AI collaboration can weaken or redistribute cues associated with machine generation, strong performance under this binary setting may overstate detector reliability. This mismatch remains underexplored in Chinese: detection cues are shaped by tokenization and language-specific text distributions, yet controlled resources spanning production settings, domains, and generators remain limited. To fill this gap, we present a Chinese Human-AI Collaborative Text Detection Benchmark (C-HAT-Bench), a unified benchmark that links $5,000$ human-written source texts from five domains to more than $240,000$ variants produced using six generative models under Prefix-Conditioned Continuation as a reference setting and three collaborative production modes. We evaluate $21$ detectors through four protocols spanning zero-shot and pretrained supervised document-level detection, boundary localization, and cross-condition generalization. Relative to Prefix-Conditioned Continuation, mean AUROC across document-level detectors is $12.0\%$ lower on the collaborative production modes, with the largest detector-specific relative decrease reaching $44.4\%$. Transfer across collaborative production modes is also asymmetric, indicating that performance in a given production setting is not a reliable predictor of performance in other production settings. --- ### Structuring Relations Among Learning Paradigms via Protocol--Objective--Resource Reductions Authors: Junwei Su, Changjie Wang, Dongyang Chang Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32766v1 Modern machine learning spans supervised, transfer, continual, meta-learning, and related regimes that often reuse the same hypothesis classes, architectures, and optimizers but differ in information access, objectives, memory, adaptation, and sample accounting. This makes it difficult to determine whether one paradigm is genuinely distinct, a special case of another, or part of a broader structural hierarchy. We introduce a protocol-objective-resource (POR) framework that separates representational capacity from these design choices. A paradigm is specified by an environment class, observation protocol, admissible learners, performance functional, and resource accounting rule. POR reductions combine environment embeddings, learner compilers, threshold maps, and calibrated resource overheads. Our main theorem shows that such reductions imply worst-case complexity domination on embedded comparison classes, transferring upper bounds forward and lower bounds backward; under labeled-example accounting, this yields sample complexity domination. We also show that calibrated nontrivial accuracy regimes are necessary to avoid vacuous comparisons, and that strengthening the objective can strictly increase minimax sample complexity even with unchanged protocols and learner classes. Instantiating the framework for supervised, transfer, continual, and meta-learning yields canonical special-case relations: continual contains transfer, transfer contains supervised, and meta-learning contains supervised under aligned raw-example accounting. We further derive a non-exact episode-to-example reduction for episodic meta-learning and capture within-paradigm refinements such as replay memory and task identifiers. The framework thus provides a unified language for structuring learning paradigms and transferring complexity guarantees across them. --- ### AnchorMixGAN: Anchor-Aligned Generative Semi-Supervision for DDoS Detection in Cloud-Integrated IoT Networks Authors: Jin Yang, Xufeng Liu, Yong Hu, Xueyang Wang, Honglu Yang, Gang Li Published: 2026-09-26 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2609.32764v1 Detecting distributed denial-of-service (DDoS) attacks in cloud-integrated IoT networks is difficult when labeled traffic is scarce. Generative semi-supervised learning can supplement the available training data, but prediction shifts induced by synthetic views may affect the targets assigned to real unlabeled flows. We propose AnchorMixGAN, a generative semi-supervised framework that addresses this problem through anchor-aligned target construction. Its Anchor-MAS module treats each real unlabeled flow as an anchor and creates alternative views by replacing one field group at a time with values from generated traffic. A frozen reference classifier predicts the anchor and its views; averaging and sharpening these predictions produces a soft target for the original flow. The flow and its target are then mixed with a labeled example using MixUp, allowing the detector to learn from both the original labeled records and the mixed examples. We analyze how reference-classifier error, view construction, and sharpening affect the target, and derive a bound on the resulting change in cross-entropy at a fixed detector prediction. At the reported 90% training setting with 20% of the training records labeled, AnchorMixGAN attains accuracies of 97.3%, 97.4%, and 96.5% on NSLKDD, BoT-IoT, and CICIoT2023, respectively, exceeding the corresponding MixGAN results by 1.6, 1.0, and 4.4 percentage points. --- ### Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them Authors: Yicheng Bao, Zhenkun Gao, Xiahui Guo, Mingqian Yang, Xueheng Li, Bangwei Liu, Mingang Chen, Lijun Li, Xuhong Wang, Xin Tan Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32763v1 Historical photographs and other canonical images can now be edited seamlessly with a single instruction, often leaving no reliable pixel-level trace. In such cases, the only evidence of manipulation may be a fact about what the image depicts. Existing benchmarks instead rely on generator artefacts, image-caption inconsistencies, visual implausibilities, or external references, and therefore do not test whether a model can use its own world knowledge to verify a recognized image. We introduce Mandela-Bench, containing 1,507 edits of canonical images: 1,359 knowledge-only forgeries, each contradicting one verifiable fact, and 148 anchor-free controls that preserve the editing process without introducing a factual contradiction, together with 474 untouched originals. We score not only whether a model detects a forgery, but whether its explanation identifies the inserted entity or the fact being violated. Across 36 multimodal models, from 0.8B parameters to frontier scale, we find a consistent failure mode. When a public figure is removed from a familiar photograph, models still name that person in up to 72.7% of responses. Some models can distinguish the replacement face from the original when shown in isolation, yet still judge the full edited photograph as authentic. Providing the true event and date does not improve knowledge-grounded detection, whereas providing the same information after cropping away the recognizable composition does. Even under explicit verification prompts, only one of the 36 models meets the KGR criterion on at least half of the forged images. These results suggest that the failures cannot be explained by missing knowledge or inadequate perception alone. Instead, they are consistent with recognition biasing verification toward the remembered canonical image rather than the observed edit. --- ### An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learning Authors: Mino Nakura, Sriram Krishna, Yufei Wang, Shubham Tulsiani, Zackory Erickson, David Held Published: 2026-09-26 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.32762v1 Visual imitation learning is a promising approach to training robot manipulation policies capable of completing a wide variety of tasks. However, policies today remain brittle to viewpoint perturbations, making deployment in diverse environments a challenge. We present a controlled empirical study of which design choices allow visuomotor policies to generalize across viewpoints. We find that viewpoint generalization improves when dense visual tokens are retained and the action head participates in geometric reasoning. On a suite of simulated tasks that span a wide range of camera poses, we show that these design choices yield a policy that remains performant across viewpoints. As a practical consequence, a policy trained with these design choices also transfers zero-shot from simulation to the real world under random camera configurations. --- ### From Feed-Forward to Flow: Unifying Reconstruction and Generation Is Easier Than You Think Authors: Haoru Wang, Qianfan Shen, Kai Ye, Wenzheng Chen, Baoquan Chen Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32761v1 Reconstruct where the images provide evidence, and generate where they do not: recent success of spatial world models such as Atlas (World Labs Team, 2026) highlights the value of unifying reconstruction and generation in one model. Yet the two have long lived in separate paradigms with distinctive failure modes: feed-forward reconstruction averages ambiguity into blur, while conditional generation invents plausible but scene-inconsistent detail. In this work, we present a unified flow-based formulation for reconstruction and generation, where a shared clean-target predictor performs direct reconstruction at its single-step endpoint and unfolds conditional generation through multi-step flow. A controlled toy study reveals the mechanism: with a single step, the predictor collapses to the conditional mean just like feed-forward methods, favoring consistency over diversity. With multi-step inference, the fidelity of generated details grows with context richness: closer observations reduce ambiguity and yield better-matched details. We further instantiate the formulation in appearance and geometry 3D tasks. JiT-LVSM improves perceptual and distributional quality in novel view synthesis, while JUSt3R retains competitive single-step geometry prediction with additional multi-step inference capabilities that reduces veil and flying-pixel artifacts, producing cleaner surface structure with greater test-time compute. Together, they show that reconstruction and generation can share both a formulation and a backbone, with their behavior governed by denoising configuration---making unification surprisingly simple. --- ### The Extender: A Log-Structured Transformer Authors: Jakob Eriksson Published: 2026-09-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.32759v1 We introduce the Extender, a log-structured variant of the standard Transformer architecture. In a standard Transformer, each layer communicates with subsequent layers exclusively via the residual $\mathbf{h}$, a superposition channel. The Extender adds a concatenation channel $\mathbf{x}$: each layer $\ell$ emits both a residual update $δ_\ell$ which is added to $\mathbf{h}$, and a much smaller extension $ε_\ell$ which is appended to $\mathbf{x}$. While both the FFN and $\mathbf{q}$ see $\mathbf{h}$, the attention $\mathbf{kv}$ projections take only $\mathbf{x}$ as input. As a result, the fully extended $\mathbf{x}$ contains the complete input for the $\mathbf{kv}$ projections of all layers, reducing the persistent attention memory footprint from $2Ld_{model}$ to $\sum|ε_\ell|$. We find that with $|ε_\ell|=32$, the Extender matches Transformer accuracy on short-context (CORE) tasks at 199M-924M parameters, and exceeds Transformer accuracy on long-context (RULER) workloads, again at 924M parameters. For our 1664-wide, 924M model, the Extender's persistent attention memory footprint is $104\times$ smaller than MHA. The memory savings grow with model width. --- ### How Far Do Persona Effects Generalize in Language Models? Authors: Yufan Zhou, Yuxuan Liu, Enze Ma, Lyumanshan Ye, Zhongqi Yue, Robin De Croon, Yucheng Jin, Katrien Verbert, Zhao Wang Published: 2026-09-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.32758v1 Persona prompts ask language models to answer as particular kinds of people. We test whether relationships learned from these effects predict responses to new questions and remain useful across models and prompts. Across 57 attributes, three behavioral domains, and seven pairs of open 7 to 9B checkpoints, persona effects can be predictable without being portable. Separate attribute and task gains improve prediction beyond shared scaling significantly in OLMo-3 and Qwen2.5, with the most robust evidence in OLMo-3. In that model, target refitting significantly outperforms gains borrowed from each of the other six pairs. Across model transfers, borrowed gains with one amplitude underperform shared scaling in most directions; allowing two target parameters removes the significant losses but yields no significant benefit over target shared scaling. After rewording, refitting significantly outperforms reuse with one amplitude in all six tested pairs, while changes of examples or country context often preserve reuse value. In the tested prompt transfers, regularized updates outperform both reuse strategies in median at 64 target questions per attribute. A separate survey comparison finds that selecting the more responsive checkpoint can worsen human fit; responsiveness is confounded with training status, and temperature calibration largely removes this cost but not errors in group ordering. Within the tested gain representation, apparent transfer can come from target calibration; source relationships must add predictive value beyond calibration and regularization. Code and data are available at https://github.com/thzva/persona-gain --- ### Readout is not Recovery: Dissociating Coordinate Emission from Visual-Corruption Repair in Vision-Language Models Authors: Drandreb Earl Juanico Published: 2026-09-26 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.32757v1 VLM bounding-box localization is both language generation and spatial commitment. Parseable fields such as bbox_2d make localization easy to score, but dimensions that emit coordinate tokens need not repair localization after visual evidence is damaged. We study this readout/recovery separation in Qwen3-VL-4B-Instruct on single-object COCO grounding. We compare clean coordinate-token readout rankings with corruption-derived repair rankings, using object-mask endpoint replacement for recovery and clean-input flooring for depth localization. In Qwen3-VL, coordinate-token rankings are inert through layer 24, load-bearing from layers 32-35, and peak at layer 34; corruption-derived rankings harm layers 16-24 but become beneficial near layer 35/final. A Kimi-VL-A3B diagnostic shows a matching output-proximal transition despite a different box format. Object-mask recovery separates rank budgets: $k=250$ shows necessity, $k=500$ shows Top-$k$ restoration above random, and $k=d/2$ is largely capacity-driven. Partial-occlusion sweeps reveal that high-overlap coordinate-token sets can hurt at $k=1000$ and help mainly at half-width, while population corruption-derived sets provide no reliable fixed repair set. Edge-attribution patching shows coordinate-token paths are high precision but low recall for detection recovery, and RMSNorm quasi-layer controls do not close the endpoint-repair gap. Endpoint coordinate triage is therefore a useful circuit prior, but occlusion recovery requires a separate benchmark. --- ### Reuse or Relearn? A Spectral View of Earth Observation Foundation Models Authors: Mehmet Ozgur Turkoglu, Valerio Marsocci, Dominik J. Mühlematter, Dominik Senti, Konrad Schindler, Helge Aasen Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32756v1 Foundation models are rarely used as generic, frozen feature extractors; instead, they are fine-tuned for the target downstream application. This practice is particularly prevalent in Earth observation (EO), and it raises a question that downstream accuracy alone cannot answer: does fine-tuning reuse the pretrained representation, or does it relearn a new one? We study this with spectral diagnostics that compare a model before and after adaptation, quantifying how well its dominant singular subspaces are preserved, how broadly the weight update is distributed, and how large it is. Using natural image models such as CLIP and DINO as a reference, we find that, under the evaluated fine-tuning settings, EO models undergo far larger, higher-rank updates and retain much less of their pretrained structure, so their downstream performance is often obtained with substantial changes to the pretrained weight structure. The diagnostics further provide insight into how cheaply a model can be adapted: where the pretrained subspaces are preserved, adapting a small fraction of the parameters can match full fine-tuning, and where they are not, it can fall behind. More broadly, foundation models, and EO foundation models in particular, should be assessed not only by benchmark accuracy, but also by how reusable their pretrained representation is. --- ### SAGE: Semantic Audio Generative Encoder Authors: Francesco Brigante, Luca Cerovaz, Davide Marincione, Giorgio Strano, Luca Zhou, Emanuele Rodolà, Michele Mancusi Published: 2026-09-26 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2609.32755v1 Audio autoencoders compress waveforms into compact latent representations that serve as the interface between raw audio and downstream models. Current systems navigate a three-way trade-off between reconstruction quality, semantic structure of the latent space, and inference speed, typically favoring one or two of these at the expense of the others. This paper introduces SAGE, Semantic Audio Generative Encoder: a compact variational autoencoder, trained solely on publicly available music, that shapes its latent by distilling embeddings from a pretrained audio-text model. This 105M-parameter model runs at the inference cost of Stable Audio Open and reaches the listening-test quality of SAME-L, an autoencoder 8x larger and 4x slower, while surpassing both on objective perceptual and distributional metrics of reconstruction. Furthermore, it sets the state of the art on all nineteen probing tasks of latent semantics, in domain and out of domain. These results establish SAGE as a lightweight audio autoencoder that strikes the best balance of the three-way trade-off among those we evaluate, combining high reconstruction fidelity, state-of-the-art semantic structure, and fast inference. --- ### Adaptive Consistency Graph for Long-Horizon Agents Authors: Jiecong Wang, Hao Peng, Zhanyi Wang Published: 2026-09-26 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.32754v2 Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequences of dependent actions and tool calls. During execution, task requirements, historical evidence, and the current execution state may gradually become disconnected, so later decisions can drift from the original objective. We study this problem by introducing the Adaptive Consistency Graph (ACG) for long-horizon execution. ACG incrementally organizes execution evidence and its provenance in a persistent graph, then constructs a temporary requirement-centered view for each decision under a bounded context budget. Rather than replacing the base agent's planner or tool executor, ACG provides a structured and traceable context view for each decision. In the matched evaluation, ACG improves GPT-5.6-luna's average success from 44.5\% with ReAct to 50.2\%, with the largest gain on BrowseComp-Plus (73.5\% versus 62.4\%). We further analyze trajectory structure and inference cost to characterize this improvement. Our code is available at https://github.com/yunsaijc/Adaptive-Consistency-Graph. --- ### Action Shaping: Policies Absorb What They Can Express Authors: Yanjun Chen, Jinghan Wang, Xiaoyu Shen, Wenjie Li, Wei Zhang Published: 2026-09-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.32752v1 Reward shaping has a theorem: a potential-based term can be removed without changing the optimal policy. The same practice on the action channel, an offset added in training and dropped at deployment, has no theorem. Nothing cancels an action offset, so the correction is kept at deployment or removed without a guarantee. We call it action shaping and state its principle. A trainable policy absorbs an offset its own output layer can reproduce exactly, which is what we mean by express; what is absorbed can be removed with the return intact. Its minimal instance is a zero-initialized linear head behind a learnable gate, added to an actor that trains through a learned action-value function, with no penalty or schedule. The gate rises and then falls on its own, for deterministic and stochastic actors alike, and on 20 tasks removing the head costs almost nothing. The condition is exact reproduction, not capacity: a nonlinear head with more parameters is not absorbed, and in a paired control, one linear path added to a nonlinear base head restores absorption. Exact reproduction gives the loss a flat direction that gradient noise drifts along, and the offset's amplitude indicates, before removal, what dropping the head will cost. Action shaping thus gains the counterpart of the shaping theorem, a condition for absorption, together with the mechanism behind it and a diagnostic that reads it. Policies absorb what they can express, and only that. --- ### CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning Authors: Xin Yan, Zhengbo Jiao, Jiaqi Liu, Zhenglin Wan, SiYuan Ma, Xuliang Yu, Tianyi Jiang, Chubin Zhang, Pengfei Zhou, Wangbo Zhao, Xingrui Yu, Bo An et al. Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32750v1 Reinforcement learning enables computer-use agents to improve through interaction with real software environments, including websites and desktop applications. However, conventional deployments replicate an initialized runtime for each independent rollout, even when trajectories use the same software, incurring repeated memory and initialization costs as the number of parallel environments grows. Does an independent computer-use environment require an independent execution runtime? Our key observation is that trajectories require independent mutable state, while initialized application runtimes can be reused across concurrently evolving environments, making state the natural unit of environment independence. Guided by this observation, we introduce CUA-Sandbox, which separates private state capsules from shared runtimes through state-scoped execution and transactional lifecycle operations, including resets and branches, while retaining the original software interfaces and task evaluators. Experiments show comparable or improved task success relative to Docker, while substantially reducing rollout and resource costs. CUA-Sandbox achieves up to a 6.20x increase in rollout throughput, a 9.2x reduction in per-environment memory, and a 504x reduction in incremental storage. --- ### Retrospective Distillation Attribution via Normalized Response Similarity Authors: Minwoo Jang, Jaechang Kim, Minhyeon Oh, Jeongyeon Hwang, Jungseul Ok Published: 2026-09-26 Categories: cs.AI, cs.CL, cs.CR, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.32749v1 Model distillation transfers capabilities through supervised fine-tuning (SFT) on teacher responses, often collected from commercial APIs, raising questions of model provenance. Existing distillation attribution methods have been largely evaluated on students immediately after the SFT step. However, a distilled model may undergo further SFT, preference optimization, or reinforcement learning before release, while an auditor may lack access to the pre-distillation checkpoint required by reference-based attribution. To close this gap, we propose SCOUT, an output-only method that aggregates recurring *syntactic patterns* into candidate profiles, filters low-contrast patterns, and calibrates student--candidate distances against inter-candidate distances. SCOUT supports attribution and abstention using only current texts, without model weights, token likelihoods, or historical checkpoints. Auditing publicly released descendants of distilled models spanning diverse post-training objectives, SCOUT consistently identifies the distillation source. Furthermore, tracing teacher-associated *syntactic signatures* along training trajectories reveals that they emerge during distillation and persist through subsequent preference optimization and reinforcement learning. --- ### Self-Evolving Multi-Agent Symbolic Discovery for Financial Fundamental Analysis Authors: Kelvin J. L. Koa, Filip Orestav, Shengqiong Wu, Michael J. Wooldridge, Ke-Wei Huang Published: 2026-09-26 Categories: cs.MA, cs.AI, cs.LG, q-fin.CP arXiv: https://arxiv.org/abs/2609.32746v1 While symbolic regression (SR) has been successfully used in science to discover new equations, its use in financial valuation is hindered by several limitations. Whereas the natural sciences provide objectively correct relationships, financial valuation constitutes a distinct class of symbolic discovery problems, as it admits multiple valid perspectives, operates under non-stationary market conditions, and involves noisy, continuous performance signals. In this work, we propose Multi-Agent Fundamental Analysis with Symbolic Adaptive learning (MUFASA), a hierarchical multi-agent framework for symbolic discovery in finance. MUFASA introduces (1) disentangled equation discovery via specialized agents representing distinct valuation perspectives, (2) a meta-coordinator that performs hierarchical-level reasoning over market context information, and (3) a memory mechanism that reasons over statistical performance summaries (e.g., accuracy, stability, and tail risk) to guide learning under noisy feedback. Experiments across datasets from multiple countries show that MUFASA achieves state-of-the-art performance on the valuation task compared to classical finance methods, financial large language models, and SR approaches, while simultaneously producing interpretable equations, which we share with the community. We also make publicly available the distilled learnings across evolution iterations and context-dependent strategy weights, which might offer useful insights for future research on financial fundamental analysis. --- ### Benchmarking EEG Foundation Models at Scale: Lessons from 20,000 Evaluations Authors: Zhige Chen, Shu Peng, Chengxuan Qin, Rui Liu, Rui Yang, Kay Chen Tan, Jibin Wu Published: 2026-09-26 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.32743v1 Electroencephalography (EEG) foundation models (FMs) promise transferable neural representations, yet their advantages over strong supervised baselines and their prospects for further scaling remain unclear. To address these questions, we introduce EEG-Arena, an open-source benchmark covering 30 EEG FMs and 25 supervised baselines evaluated on 57 downstream tasks from 23 public datasets. Through more than 20,000 evaluations across five experimental protocols, we assess downstream performance, pretraining benefits, model size scaling, pretraining data scaling, and robustness to channel configuration. We find that (1) EEG FMs outperform strong task-specific supervised baselines on most evaluated tasks, particularly under non-bipolar settings; (2) compared with architecture-matched supervised training from scratch, pretraining improves both early optimization and final downstream performance, with larger and more consistent gains as more labeled downstream data become available; (3) existing EEG FMs do not exhibit a consistent positive relationship between parameter count and downstream performance; (4) under a fixed architecture, increasing the pretraining data scale yields sustained downstream gains; and (5) channel-flexible FMs achieve higher absolute performance than channel-constrained models across most evaluated channel configurations. Together, these findings demonstrate the downstream value of EEG FMs and identify pretraining data expansion as a promising direction for further progress. To support continued research, we release EEG-Arena as an open-source evaluation framework that provides shared infrastructure for reproducible benchmarking, model comparison, and community-driven development. --- ### LoCoVSR: Local Context Diffusion Posterior Sampling for Video Super-Resolution Authors: Matan Ben Chorin, Michael Elad Published: 2026-09-26 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2609.32742v1 Video super-resolution (VSR) is an ill-posed inverse problem that aims to reconstruct a high-resolution (HR) video from a noisy, low-resolution (LR) version of it. We present LoCoVSR, a diffusion-based VSR framework that leverages pixel-space denoising diffusion probabilistic models. LoCoVSR integrates the Diffusion Posterior Sampling technique with spatio-temporal context learning, operating in a moving-average form. A localized window of adjacent LR frames is used for recovering each center frame, while applying a shared noise trajectory across all frames. The localized windowing enables processing of long videos without length limitations, supports parallel inference, and prevents error accumulation that may occur in recursive processing. Unlike prior methods, LoCoVSR offers a simple yet very effective VSR solution, avoiding explicit optical flow estimation, or information loss caused by latent space processing. Trained on the VFHQ face dataset, LoCoVSR achieves accurate, temporally consistent and high-quality upscaling with competitive results against recent diffusion-based VSR approaches. --- ### Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach Authors: Jianna Hur, Sagar Samtani Published: 2026-09-26 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2609.32741v1 Modern semiconductor production relies on a globally distributed, multi-tier supply chain in which financial stress at one firm spreads with a delay and eventually affects the revenue, inventory, and profitability of the companies that design AI chips. Most firms see only their direct partners, and prior predictive research has mainly targeted market-based risk measures, so few tools forecast how supply chain stress will appear in reported financials. In this study, we propose a heterogeneous graph patch transformer that forecasts these quarterly changes one and two quarters ahead. Learning from a 15,186-company network over 60 quarters, the proposed model fuses quarterly fundamentals with macro-trade, event, and disaster signals through learned gates, carries risk across supplier, customer, ownership, and headquarters relations through typed, direction-specific propagation, and encodes the propagated histories with patch-based tokenization. In preliminary experiments on 116 focal semiconductor firms, the proposed model achieves the lowest error on every target at both horizons, and its profitability advantage widens at the two-quarter horizon. These forecasts can help supply chain managers and investors act before disruptions appear in reported financials. --- ### AnesTRACE: Benchmarking Intraoperative Anesthesia from Multimodal Perception to Multi-step Decision-Making Authors: Ziwei Huang, Qi Gao, Zhe Ji, Yuanyuan Yao, Fengjiang Zhang, Min Yan, Zhongle Xie, Gang Chen Published: 2026-09-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.32740v1 Intraoperative anesthesia requires systems to interpret evolving multimodal evidence, recommend timely management, and revise decisions as patient states change, yet existing benchmarks usually isolate perception or single-point reasoning. We introduce AnesTRACE, an evaluation suite comprising AnesTRACE-Bench and AnesTRACE-Eval. Built from public perioperative datasets with anesthesiologist annotation, AnesTRACE-Bench evaluates Intraoperative Perception, Single-point Anesthesia Decision-Making, and Multi-step Anesthesia Decision-Making. AnesTRACE-Eval assesses open-ended responses through anesthesiologist-defined criteria for Clinical Correctness, Evidence Grounding, Task Completeness, and Safety, with Temporal Consistency for multi-step decisions; its domain-specific evaluator is trained by supervised fine-tuning and preference alignment on expert-reviewed judgments. Across more than 30 models, fine-grained visual grounding and intervention selection remain difficult: the leading model reaches only 32.2 mIoU for TEE visual grounding and retains a 17.5\% Major/Critical Safety Error Rate in multi-step management. Evaluator alignment with anesthesiologists improves across both training stages, while the best decision quality is accompanied by a 74.3-second P95 Latency. These results show that aggregate performance alone does not establish safe, timely longitudinal decision-making. We release our code at https://github.com/zjuDBxAI/AnesTRACE. --- ### Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models Authors: Dongdong Wang, Deepak Balakrishnan, Ravi Srinivasan, Shenhao Wang Published: 2026-09-26 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.32737v1 Existing geospatial vision-language models (Geo-VLMs) typically optimize diverse geospatial tasks through a unified multi-task adaptation paradigm without explicitly accounting for the heterogeneous optimization characteristics. Our empirical observations reveal heterogeneous gradient characteristics across tasks, including vision-language differences, intra-branch gradient relationships, and task interference, which hinder effective multi-task optimization. Motivated by these observations, we propose Gradient-Guided Decoupled Adaptation (G2DA), a gradient-aware optimization framework for multi-task Geo-VLM learning. G2DA first partitions tasks into vision- and language-centric groups through gradient-guided cross-modal decoupling. It then constructs modality-specific curricula based on task gradient similarity and employs bidirectional rehearsal to mitigate the recency effects introduced by sequential optimization. We evaluate G2DA on three Geo-VLM benchmarks using six InternVL3 and Qwen3.5-VL variants, along with GeoChat and GeoLLaVA. Across all 24 benchmark-model combinations, G2DA consistently outperforms representative baselines, improving over the strongest competitor by 3.08, 4.30, and 2.81 percentage points on UrBench-MCQ, XLRS-Bench-Lite, and VRS-Bench-VQA, respectively. These results demonstrate the effectiveness of gradient-guided task organization for Geo-VLM adaptation. --- ### REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection Authors: Aleksandr Gushchin, Khaled Abud, Georgii Bychkov, Ekaterina Shumitskaya, Artem Filippov, Sergey Lavrushkin, Dmitriy S. Vatolin, Anastasia Antsiferova Published: 2026-09-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.32734v1 AI-generated image detectors are often evaluated on benchmarks where real and synthetic images differ in content, quality, or generation artifacts, allowing models to rely on dataset-specific cues and fail on unfamiliar generators or processed images. Existing datasets provide limited support for evaluating these challenges jointly across diverse visual content. We introduce REALIS, a dataset of 1.43 million real and synthetic images generated by 42 modern text-to-image models, including the latest proprietary systems such as Nano Banana 2. REALIS combines prompts derived from real images, quality filtering, and stratified sampling to reduce class-specific shortcuts while preserving content diversity. We further introduce REALIS-Expert, a stress-test subset for high-quality synthetic images, where real and generated samples are selected with closely matched semantic and visual characteristics. We also propose a robustness protocol covering 35 transformations at five severity levels to analyze detector behavior under image processing. Based on REALIS, our benchmark evaluates pretrained detectors, fine-tuned models, and zero-shot vision-language models under generator and post-processing shifts. On the hardest processed split, the best pretrained conventional detector achieves 0.550 ROC-AUC, compared with 0.752 for the best REALIS-trained detector. REALIS provides a unified framework for measuring and improving the reliability of AI-image detectors under conditions that better reflect real-world use. --- ### Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching Authors: Zhoufu Wang, Baoshen Guo, Zhiqing Hong, Junyi Li, Kailai Sun, Heye Huang, Alok Prakash, Shenhao Wang, Jinhua Zhao Published: 2026-09-26 Categories: cs.SI, cs.LG arXiv: https://arxiv.org/abs/2609.32732v1 Human mobility generation aims to synthesize realistic point-of-interest (POI) visitation trajectories and has become an important tool for travel behavior modeling, transportation management, and urban planning. Existing diffusion-based methods achieve high fidelity but require per-city generation, given the inherent heterogeneity of geospatial locations and POI categories, while large language model-based methods generalize across cities but remain too costly at scale, especially for long-horizon trajectory generation. To address this, we propose SeMoFlow, a Semantic human Mobility generation framework based on latent Flow matching. We first encode heterogeneous POIs from different cities into a shared cross-city representation space via hierarchical Semantic IDs, where shared prefixes capture transferable semantics, and successive codes progressively refine the representation toward individual POIs. Building on the semantic IDs, SeMoFlow follows a plan-to-synthesis hierarchical generation paradigm, in which an autoregressive planner generates coarse-grained semantic and recurrence patterns, and a flow matching realizer synthesizes fine-grained suffix latents. The generated latents are subsequently decoded and grounded to concrete POIs. Extensive experiments on large-scale multi-city datasets show that SeMoFlow achieves higher trajectory fidelity than existing baselines, preserves city-specific mobility motifs, and supports both joint multi-city generation and effective cross-city transfer. --- ### SkillVine: Agent Skill Evolution via Branching Exploration Authors: Kaiwei Liu, Jiqian Dong, Liran Dong, Shuai Mao, Mingming Zhao, Bufang Yang, Jie Chuai, Zhitang Chen, Guoliang Xing, Zhenyu Yan Published: 2026-09-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.32731v1 Agent skills encapsulate reusable procedural knowledge that enables LLM agents to perform tasks, and they can be improved automatically using trajectories from interactions with the environment. This is the classic problem of skill evolution. Existing approaches predominately follow a linear evolution paradigm, in which updates are sequentially applied to the latest skill-library version. As a result, they inevitably fall into local optima, leaving many promising evolution paths unexplored. We propose SkillVine, an automatic skill-evolution framework that formulates skill evolution as a graph search problem and employs a branching exploration strategy. Equipped with a trunk-branch collaborative searching mechanism, an intelligent parent-node selector, and an adaptive-granularity update rule, SkillVine achieves a balance between exploration and exploitation. We evaluate SkillVine on 5 benchmarks with two LLMs. Results show that SkillVine discovers better skill-library versions along branches than along the linear trunk and achieves the best test performance in nine of ten benchmark-model combinations. --- ### Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization Authors: David Kepplinger, Anand N. Vidyashankar Published: 2026-09-26 Categories: stat.ML, cs.IT, cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2609.32730v1 Domain Adaptation (DA) often lacks worst-case guarantees, while Distributionally Robust Optimization (DRO) based only on source data centers its ambiguity set at the source law and ignores available target structure. To bridge this gap, we introduce a doubly-anchored DRO framework whose ambiguity set is the intersection of $φ$-divergence balls centered at the source law and a source-completed target reference law, the latter pairing the target covariate law with the source conditional law. We derive dual-induced adversarial bridge geometries for symmetric and asymmetric divergence pairings, notably introducing a Kullback--Leibler/squared-Hellinger (KL/HD) bridge. This asymmetric formulation yields a Lambert-$W$ geometry in which source-side exponential risk tilting and target-side Hellinger stabilization enter through distinct terms, attenuating, but not bounding, the effect of large likelihood ratios. Furthermore, without imposing covariate shift, we establish finite-sample generalization bounds for the minimizer of a structural, loss-agnostic density-bridge risk under bounded-overlap conditions; these bounds do not apply directly to the loss-aware DRO min--max estimator. We translate our framework into a bridge-weighted Nadaraya--Watson estimator, proving uniform consistency for the source regression function and pointwise asymptotic normality, with target recovery when the source and target regression functions coincide, as under covariate shift. Finally, an empirical evaluation on a domain-shifted Fashion-MNIST dataset illustrates the finite-sample stability of the asymmetric KL/HD bridge under severe synthetic target-covariate corruption. --- ### Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds Authors: Weiming Ou, Xiao Wang Published: 2026-09-26 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2609.32729v1 AdaGrad and AdaGrad-Norm are widely used adaptive methods, but their precise behavior in stochastic convex optimization remains less understood. We first show that AdaGrad-Norm and AdaGrad do not admit any universal \textbf{last-iterate} rate, even under sub-Gaussian noise and bounded iterates. We then prove that bounded variance alone is too weak: even with bounded iterates, it cannot yield \textbf{high-probability average-iterate} rates, and without bounded iterates it may not even guarantee convergence in expectation. Besides, we construct tight $Ω(\log T/\sqrt T)$ lower bounds for both AdaGrad-Norm and AdaGrad under sub-Gaussian noise, showing that $\log T$ in existing average-iterate upper bounds is unavoidable. Finally, we show that this $\log T$ loss disappears once bounded-iterate condition is imposed: under a general ABC condition, both methods achieve rates ${O}(1/\sqrt{T})$. --- ### Distributionally Robust Average-Reward Reinforcement Learning: Finite-Sample Guarantees under Weak Communication Authors: Chenyu Lu, Zijun Chen, Nian Si Published: 2026-09-26 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2609.32727v1 We study distributionally robust reinforcement learning (DR-RL) in the average-reward setting under weak communication. Our main result provides finite-sample guarantees for estimating the robust optimal average reward and learning a near-optimal policy, covering both SA-rectangular and S-rectangular structures with divergence-based and distance-based uncertainty sets. Specifically, for Kullback--Leibler and $f_k$-divergence balls, we establish explicit radius conditions under which the robust average-reward Bellman equation admits a constant-gain solution, while for total variation and Wasserstein balls, any positive radius suffices without requiring the nominal MDP to be weakly communicating. Our algorithm is prior-knowledge-free and achieves sample complexities of $\widetilde O(|\mathcal{S}||\mathcal{A}|p_{\wedge}^{-1}\operatorname{Span}^{2}(u_δ^{\ast})ε^{-2})$ for estimating the robust optimal average reward and $\widetilde O(|\mathcal{S}||\mathcal{A}|p_{\wedge}^{-2}\operatorname{Span}^{2}(u_δ^{\ast})ε^{-2})$ for learning an $ε$-optimal policy. Here, $p_{\wedge}$ is the smallest positive nominal transition probability and $u_δ^{\ast}$ is a robust optimal bias function. We further provide an almost-tight explicit upper bound on $\operatorname{Span}(u_δ^{\ast})$. Finally, we validate the predicted $n^{-1/2}$ convergence rate through numerical experiments. --- ### Scaling Properties of Same-Family On-Policy Distillation Authors: Yuntai Bao, Qinfeng Li, Guoqing Jiang, Liwei Chen, Zhiheng Qin, Xuanping Li, Wenqi Zhang, Xuhong Zhang Published: 2026-09-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.32722v1 *Reinforcement learning (RL)* can induce substantial reasoning capabilities in large language models (LLMs), but how much of this capability transfers across model scales, and how quickly, remains unclear. We study the scaling properties of *on-policy distillation (OPD)* across *weak-to-strong*, *same-base*, and *strong-to-weak* teacher--student setups. We find that early OPD training dynamics uniformly exhibit a regular *useful-transfer* regime, in which held-out accuracy (the *gold score*, $G$) rises approximately linearly in $d=\sqrt{\mathrm{KL}(π_θ\Vert π_{\mathrm{ref}})}$, the square root of token-level reverse KL divergence from the student initialization. In every observed weak-to-strong pair, the student's peak gold score exceeds its teacher's own, so a compact RL expert can transfer capability to a much larger student via OPD. To estimate OPD outcomes, we fit *power laws* for how $G_{\mathrm{peak}}$ and the slope of the useful-transfer regime scale with student and teacher parameter counts and with teacher gold score. These laws show that peak gold score improves with teacher scale only up to roughly the student's scale, and that at a matched gold score smaller teachers transfer better, so a teacher's score alone does not define its supervision value. We also study the scaling effects of two OPD variants, bootstrapping weak-to-strong OPD, and the degree of on-policy supervision. ---