# Research Papers — 2026-10 · bundle page 93 of 156 > Full-text markdown of papers #4601–4650 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/93 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/92.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/94.md) ### Evolutionary Architecture Search for Chlorophyll-$a$ Prediction in Lakes using Sentinel-2 Authors: Kursat Komurcu, Linas Petkevicius Published: 2026-10-07 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2610.10496v1 Small tabular datasets with expert-designed spectral features are the norm in operational Earth observation, and the networks applied to them are typically hand-designed. We revisit one such published model -- a Sentinel-2 algal bloom classifier -- and ask what architecture search adds, holding the task, the features and the lake-level train/test split of the original study fixed. Searching an extended multilayer-perceptron space with regularized evolution, and selecting on inner-cross-validation AUC only, we find networks that improve held-out AUC from 0.790 to 0.820 and accuracy from 0.733 to 0.748 while using 409 trainable parameters, 26 times fewer than the strongest hand-designed reference. The search converges on a consistent recipe -- a single narrow layer, RMS normalisation, $\tanh$ activation, step-decayed RMSprop and weight averaging -- that a practitioner would be unlikely to reach by default. At 1.6\,kB the resulting model is small enough to serve as an onboard screening trigger, which is the setting that motivates the work. Code: https://github.com/VU-AIML/automl4eo-bloom-nas. --- ### Insights from Autoresearch for Solar Panel Segmentation Authors: Justinas Lekavicius, Kursat Komurcu, Valentas Gruzauskas, Linas Petkevicius Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10491v1 This paper investigates AutoResearch, a protocol in which a coding language model edits a training program under a one-hour GPU budget and retains a change only if validation IoU improves. The protocol is applied to photovoltaic panel segmentation on a frozen real-image split, with DeepLabV3--ResNet-50 held fixed. Three campaigns of 24 experiments, using Gemma~4 12B, Qwen3-8B all improve their one-hour baselines, but retained modifications do not transfer across hardware. The Qwen3-8B configuration, trained on real images only, reaches a test IoU of 0.836 versus 0.833 for the reference GAN-augmented schedule. Research repository https://github.com/VU-AIML/automl4eo-autoresearch-segmentation. --- ### Best Arm Identification for Bandits with Shifting Means Authors: Lukas Zierahn, Wouter M. Koolen, Shubhada Agrawal, Christina Katsimerou, Dirk van der Hoeven Published: 2026-10-07 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.10488v1 We study the best arm identification problem in a stochastic environment with a novel form of adversarial perturbations, which we coin Shifting Means. While classically the mean rewards of the $K$ arms are stable in time, in Shifting Means only the gaps $\boldsymbolΔ$ between mean rewards are stable, while their common shift may be determined adversarially in each round. The objective of the learner is to identify the best arm with high probability while minimizing sample complexity (the fixed confidence setting). Handling shifts requires new tools: we show that algorithms employing a Generalized Likelihood Ratio Test (GLRT) stopping rule, including the popular Track-and-Stop, fail under time-varying shifts. Instead, we propose Importance Weights for Shifting Means ($\mathsf{ISM}$). Assuming means bounded by $U$ and $σ^2$-sub-Gaussian rewards, we show $\mathsf{ISM}$ to be $δ$-correct and to enjoy a sample complexity bound of order $K (σ^2 + U^2) Δ_{\min}^{-2} \ln \frac{1}δ$. We also present a matching (up to constant factors) worst-case lower bound and evaluate our results empirically. --- ### Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion Authors: Walid Bendada, Guillaume Salha-Galvan Published: 2026-10-07 Categories: cs.LG, cs.IR, stat.ML arXiv: https://arxiv.org/abs/2610.10483v1 Sampling from a softmax distribution is a fundamental operation in machine learning, but its linear complexity in the number of items makes exact sampling impractical at scale. Two-level softmax (2LS) sampling is a popular alternative enabling sublinear-time sampling. Assuming items are partitioned into clusters, 2LS first samples a cluster and then an item within it. In this paper, we show that, despite its advantages, 2LS introduces systematic and undesirable sampling biases, which arise from misweighting clusters by ignoring both cluster size imbalance and intra-cluster similarity dispersion. We propose two sampling methods, Size-Corrected 2LS (S-2LS) and Size- and Dispersion-Corrected 2LS (SD-2LS), which correct these biases and provide provably better softmax approximations with negligible to non-existent computational overhead. In-depth experiments on five large-scale datasets validate the improved sampling properties of our methods. We recommend their consistent use in place of standard 2LS in future work. --- ### Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies Authors: Yihan Li, Yating Feng, Shengjiu Sun, Jianing Chen, Hao Ren, Bowen Yang, Weisheng Xu, Qiwei Wu, Hui Cheng, Renjing Xu Published: 2026-10-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.10479v2 A simulation of a real robot workspace must preserve task-relevant interactions, while policies developed in it must operate on observations available to the real robot. Yet scene reconstruction and policy development are often treated separately. We present Agentic Real-to-Sim-to-Real (Agentic RSR), a framework that links scene reconstruction, policy development, and real-robot execution through the same manipulation task. Given a workspace video, a task description, and a known robot model, an agent recovers metric scale, iteratively refines the scene using visual feedback, and checks task-relevant interactions in MuJoCo. A coding agent then develops an executable policy, progressing from privileged object poses to visual observations and randomized simulation. The policy can interleave multiple observations and actions within one invocation, while the agent uses execution feedback to continue, retry, or revise its approach. A shared task-level interface carries the policy and accumulated experience to the real robot, where fresh observations and safety checks guide execution. Using Claude Opus 5.5 through DeepSeek Harness (DSH), all 18 scenes across two robots pass the joint visual check; mean four-view Depth MAE against reference depth estimates is 0.0808 m, mean Lab $ΔE_{76}$ is 8.01, and mean grayscale SSIM is 0.7338. In real-robot experiments, the aggregate task success rate reaches 80% of the simulation task success rate, indicating substantial retention of simulated performance on hardware. Code and reconstructed scene data will be made publicly available. --- ### Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies Authors: Yihan Li, Yating Feng, Shengjiu Sun, Jianing Chen, Hao Ren, Bowen Yang, Weisheng Xu, Qiwei Wu, Hui Cheng, Renjing Xu Published: 2026-10-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.10479v1 A simulation of a real robot workspace must preserve task-relevant interactions, while policies developed in it must operate on observations available to the real robot. Yet scene reconstruction and policy development are often treated separately. We present Agentic Real-to-Sim-to-Real (Agentic RSR), a framework that links scene reconstruction, policy development, and real-robot execution through the same manipulation task. Given a workspace video, a task description, and a known robot model, an agent recovers metric scale, iteratively refines the scene using visual feedback, and checks task-relevant interactions in MuJoCo. A coding agent then develops an executable policy, progressing from privileged object poses to visual observations and randomized simulation. The policy can interleave multiple observations and actions within one invocation, while the agent uses execution feedback to continue, retry, or revise its approach. A shared task-level interface carries the policy and accumulated experience to the real robot, where fresh observations and safety checks guide execution. Across 18 reconstructed scenes involving two robots, the mean four-view Depth MAE against reference depth estimates is 0.1057 m, the mean Lab $ΔE_{76}$ is 11.04, and the mean grayscale SSIM is 0.6990. In real-robot experiments, the aggregate task success rate reaches 80% of the simulation task success rate, indicating substantial retention of simulated performance on hardware. Code and reconstructed scene data will be made publicly available. --- ### Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models Authors: Tan Yu, Alexander Bukharin, Khushi Bhardwaj, Jennifer Williams, Zirui Liu, Jonathan Lingjie Li, Soumye Singhal, Joseph Jennings, Sanjeev Satheesh, Yash Jain, Ashish Vaswani, Venkat Krishna Srinivasan et al. Published: 2026-10-07 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.10478v1 How can we predict which base checkpoint is worth an expensive round of agentic post-training? End-to-end pass@$K$ tests whether successful behavior already appears in a base model's distribution, but it is a poor fit for agentic coding: many base checkpoints cannot reliably produce the well-formed tool invocation required to complete a task end-to-end. Single-shot or short-horizon tasks avoid these tool-calling failures by collapsing a multi-step interaction into a fixed prompt and a single patch, but they sidestep the core capability we care about: maintaining coherent state over many tool-using steps as the repository evolves. To bridge this gap, we treat successful post-trained agent trajectories as a lookahead signal of base-model potential. Replaying each trajectory and rerunning tests after every code-changing step identifies the decisive step: the first step whose cumulative patch flips the repository from failing to passing, certifying that the recorded action solves the task given the prior context. Motivated by a coverage principle for agentic traces, we build three screens at this step that do not require a base checkpoint to drive the harness from a cold start: (i) Decisive-Action BPB (bits per byte) measures the probability mass on the certified action, (ii) Patch MCQ tests the checkpoint's choice between that action and alternatives rejected by the same verifier, and (iii) prefix-conditioned pass@$K$ evaluates support for functionally-correct generations and credits any continuation that the tests accept. Across ten pairs of public base and post-trained models, all three screens rank the cohort in close agreement with post-trained SWE-bench Verified pass@$1$. As our methods need only a benchmark's successful trajectories and its verifier, they can be applied to turn future agentic coding benchmarks into base-model evaluations. --- ### Label-free cell counting and viability prediction with brightfield imaging and deep learning Authors: Amir Reza Vazifeh, Christian Zeigler, Sornanathan Meyyappan, Richard Jeske, Jason W. Fleischer Published: 2026-10-07 Categories: cs.CV, q-bio.CB arXiv: https://arxiv.org/abs/2610.10473v1 Cell viability assessment is a core requirement in cell culture systems, with critical applications in biopharmaceutical manufacturing and drug development. Conventionally, it is measured by adding membrane-impermeable dyes to a sample (a process called staining), which allows compromised cell membranes to be distinguished from intact ones. However, staining has several limitations: (a) chemical agents can perturb normal cellular processes of the cells being measured, (b) it is often ambiguous to assign viability to individual cells whose membrane integrity is only partially compromised. (c) photobleaching can undermine measurement accuracy over time when using fluorescent stains, and (d) staining cannot be performed in situ or in real time. Here, we show that (1) stained cells captured under brightfield imaging contain sufficient information to distinguish live and dead cells, and (2) cells captured under unstained brightfield imaging exhibit similar image features to their stained counterparts, enabling models trained on stained cells to generalize to unstained ones. We then report the development and validation of ViabiLens, an AI-assisted software for label-free cell viability analysis. The ViabiLens combines a cell detection model for localizing individual cells with a convolutional neural network (CNN) classifier for live/dead prediction, paired with an interactive UMAP-based viewer for visualizing and exploring individual cells across the sample. Evaluated on Chinese Hamster Ovary (CHO) cells spanning a wide range of viability conditions, ViabiLens achieves a mean absolute error of 2.68\% on unstained samples against fluorescence-based reference measurements. We also release a benchmark dataset for label-free cell viability analysis to facilitate future research, available at https://amirrezavazifeh.github.io/ViabiLens-Project-Page/. --- ### A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents Authors: Ali Asaria, Deep Gandhi, Tony Salomone Published: 2026-10-07 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2610.10468v1 Deployments of research agents are moving to populations of thousands that share one pool of compute, while most current systems organize one project at a time or leave the population unorganized. We argue that such a population will acquire an organization whether or not its designers provide one, so designers should provide it explicitly, and that the multi-agent systems community holds the tools to do so. We propose a society of agents, a population of persistent agents under explicit institutions, and develop it for science as a society of researchers built on six principles. Principal investigators compete for compute through requests for proposals, independent review, and grants; a human governor, the mayor, allocates resources and assigns no tasks. In a running society of ten thousand researchers, asked only to improve the pretraining of language models, one lab reported a way to reach the same quality with about 30% less compute, a result the labs that tested it do not yet agree on. We close with six open problems for the agents community. --- ### How assigned AI use before class shapes active student engagement in class Authors: Dan J. Wang, Neelam Modi Jain, Vanessa Burbano, Jorge Guzman, Daniel Keum, Soomi Kim, Bruce Kogut, Nataliya Wright Published: 2026-10-07 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2610.10463v1 AI learning tools are rapidly entering classrooms, but evidence about whether they help students learn is mixed and rests mostly on test scores. Comparatively less research addresses whether the use of AI changes students' live learning behaviors in class. Here, we report the results of a preregistered field experiment with 759 MBA students enrolled in ten sections of a course, in which each student was randomly assigned two of ten class sessions to prepare for with a purpose-built voice-based AI discussion partner. After two uses of the AI discussion partner, students made about 31% more voluntary contributions in each later class session. Students who used the AI discussion partner more also reported greater comfort speaking up and greater perceived learning, but not greater focus or motivation. These findings suggest that repeated practice with a voice-based AI partner can meaningfully increase students' engagement in class discussion, enhancing a critical intermediate learning outcome. --- ### FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding Authors: Lipeng Zhuang, Shiyu Fan, Yingdong Ru, Zhuo He, Florent P. Audonnet, Paul Henderson, Gerardo Aragon Camarasa Published: 2026-10-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.10462v1 We present FoldBack, a self-correcting masked generative policy for long-horizon garment folding. Existing long-trajectory policies may continue after a missed or slipped grasp even when the garment has not reached the intended configuration. We structure FoldBack's recovery mechanisms around three inference-time decisions: when to refine and verify, how to roll back, and where and how to retry. FoldBack aligns refinement and grasp verification with pick-and-place events, returns the robot to a retryable pre-grasp configuration while preserving successful grasps, and selectively regenerates the failed segment and selected future actions while avoiding previous failed grasp locations. To our knowledge, FoldBack is the first editable full-trajectory policy to unify these decisions, enabling failed interactions to be detected, undone, and repaired before execution continues, without recovery demonstrations or base-policy retraining. Across 33 real garments from six categories, FoldBack achieves 75.2% final folding success and 0.837 final-mask IoU, versus 45.7% and 0.689 for the strongest prior baseline. --- ### Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts Authors: Hejian Sang, Zhengze Zhou, Shayan Mohajer Hamidi, Xiaomin Li, Rohit Jain, Alborz Geramifard Published: 2026-10-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.10460v1 Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt domain and their signals form a single target; in routed-domain distillation, prompts from different domains are assigned to the corresponding specialist. Both settings usually transfer each teacher's endpoint policy, which mixes what post-training changed with preferences inherited from the teacher's base. We introduce $Δ$-MOPD, which transfers each teacher's teacher-minus-base logit shift re-anchored at the student's frozen initialization, and compare it with endpoint supervision in both settings while holding teacher selection fixed. We first expose the mechanism that impedes endpoint transfer: inherited base pull can exceed the post-training shift. Removing it reduces the teacher-term norm ratio and target--student KL. Across our experiments, the results suggest that shift targets are particularly useful when teacher signals are combined at a state. With three composed teachers, $Δ$-MOPD exceeds endpoint composition by $4.11$ Math and $1.95$ five-benchmark points; with two, it matches endpoint accuracy. Under phased routing, it achieves higher mean performance in both phase orders and reduces the observed order gap from $10.50$ to $6.42$ points. Under interleaved routing, where each update involves one teacher, the two targets perform comparably. The phased results provide supporting evidence that the benefit may extend to signals accumulated across training phases. Target construction is thus an independent design axis in MOPD, complementary to teacher selection. --- ### NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling Authors: Ting-Yu Dai, Takuya Kurihana, Wing Yee Au, Hon Yung Wong Published: 2026-10-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10459v2 Demand-side flexibility i.e. forecasting, shifting, and curtailing residential energy loads, depends on thermal models trusted across millions of heterogeneous buildings. Existing tools force a hard tradeoff: high-fidelity physics simulators such as EnergyPlus are accurate but sequential and require per-building calibration, while purely data-driven sequence models scale but abandon the physical structure that makes their predictions trustworthy. We introduce NeuralBES (Building Energy Simulation), a differentiable emulator that resolves this tradeoff by parameterizing a resistance--capacitance (RC) based thermal model with a shared neural encoder: static building metadata such as floor area, vintage, and HVAC type is mapped to physically bounded capacitances, conductances, and equipment coefficients, which become the coefficients of a scalar linear recurrence solved via a log-space parallel scan, and a predictor--corrector loop closes the thermostat--temperature nonlinearity while preserving full-horizon gradient flow. Trained on the ResStock dataset across three climate zones, NeuralBES handles heterogeneous building archetypes, vintages, and climate zones within a single trained encoder, while black-box baselines produce statistically plausible but physically inconsistent trajectories. On the annual full-year rollout, NeuralBES is the only data-conditioned model that is simultaneously physics-valid and accurate to within 4 MAPE points of the strongest raw-error baseline, while operating at roughly an order of magnitude fewer parameters than the transformer and recurrent baselines; among physics-valid baselines at parameter parity it more than halves the MAPE of the grey-box RC alternative. --- ### NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling Authors: Ting-Yu Dai, Takuya Kurihana, Wing Yee Au, Hon Yung Wong Published: 2026-10-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10459v1 Demand-side flexibility i.e. forecasting, shifting, and curtailing residential energy loads, depends on thermal models trusted across millions of heterogeneous buildings. Existing tools force a hard tradeoff: high-fidelity physics simulators such as EnergyPlus are accurate but sequential and require per-building calibration, while purely data-driven sequence models scale but abandon the physical structure that makes their predictions trustworthy. We introduce NeuralBES (Building Energy Simulation), a differentiable emulator that resolves this tradeoff by parameterizing a resistance--capacitance (RC) based thermal model with a shared neural encoder: static building metadata such as floor area, vintage, and HVAC type is mapped to physically bounded capacitances, conductances, and equipment coefficients, which become the coefficients of a scalar linear recurrence solved via a log-space parallel scan, and a predictor--corrector loop closes the thermostat--temperature nonlinearity while preserving full-horizon gradient flow. Trained on the ResStock dataset across three climate zones, NeuralBES handles heterogeneous building archetypes, vintages, and climate zones within a single trained encoder, while black-box baselines produce statistically plausible but physically inconsistent trajectories. On the annual full-year rollout, NeuralBES is the only data-conditioned model that is simultaneously physics-valid and accurate to within 4 MAPE points of the strongest raw-error baseline, while operating at roughly an order of magnitude fewer parameters than the transformer and recurrent baselines; among physics-valid baselines at parameter parity it more than halves the MAPE of the grey-box RC alternative. --- ### MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration Authors: Yuxiang Xiong, Ruiyan Wang, Wenqiang Wang, Teng Hu, Songhang Shen, Bohao Feng, Hongqian Deng, Ran Yi Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10457v1 Diffusion Transformers (DiTs) achieve remarkable performance in video synthesis, but their iterative denoising process suffers from high inference latency. To address this, caching has emerged as an effective acceleration strategy by capitalizing on inter-step redundancy during denoising. Existing dynamic caching methods typically estimate the error that cache reuse would introduce at each denoising step (step error) to guide cache decisions, whereas our concern is how much quality loss cache reuse would cause in the final generated video (terminal error). We show that step error does not directly correspond to terminal error and that latent information helps capture their relationship, thereby informing cache decisions. Moreover, existing threshold-based methods cannot provide precise speedup control, making it difficult to meet practical requirements for user-specified acceleration targets. To address these limitations, we introduce MORCA, a cache scheduling framework trained through offline-to-online reinforcement learning to make latent-aware reuse/recompute decisions under user-specified acceleration targets. Extensive experiments on different video generation models across multiple target acceleration ratios demonstrate that MORCA achieves better generation fidelity than state-of-the-art caching methods under comparable computational budgets. Code is available at https://github.com/x10ngyx/MORCA. --- ### PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs Authors: Linghao Meng, Feng He, Xuan Yang, Junyuan Mao, Pinze Ren, Deqing Mu, Hesen Yang, Qiankun Li Published: 2026-10-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.10455v2 Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent reasoning. Existing studies of post-hallucination reasoning (PHR) mainly characterize changes in final outcomes and aggregate reasoning dynamics, leaving how models resolve hallucinated premises at the response level insufficiently understood. In this work, we introduce PHRBench, a controlled benchmark for behaviorally structured PHR across four domains and 18 large language models. PHRBench characterizes each reasoning trajectory independently of final-answer correctness through Hallucination Compliance, Hallucination Avoidance, and Heuristic Correction, and defines an insightful trajectory as successful correction that ultimately reaches the correct answer. Across 4820 controlled instances, we find that successful recovery remains relatively rare and is associated with more frequent belief updates along the reasoning trajectory. We further find that properties of the hallucinated prompt contain substantial predictive signal for successful recovery, with a lightweight predictor achieving an AUROC of 0.847. These findings provide a behavioral view of post-hallucination reasoning, characterizing how LLMs resolve erroneous context and when successful recovery is likely to occur. --- ### PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs Authors: Linghao Meng, Feng He, Xuan Yang, Junyuan Mao, Pinze Ren, Deqing Mu, Hesen Yang, Qiankun Li Published: 2026-10-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.10455v1 Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent reasoning. Existing studies of post-hallucination reasoning (PHR) mainly characterize changes in final outcomes and aggregate reasoning dynamics, leaving how models resolve hallucinated premises at the response level insufficiently understood. In this work, we introduce PHRBench, a controlled benchmark for behaviorally structured PHR across four domains and 18 large language models. PHRBench characterizes each reasoning trajectory independently of final-answer correctness through Hallucination Compliance, Hallucination Avoidance, and Heuristic Correction, and defines an insightful trajectory as successful correction that ultimately reaches the correct answer. Across 4820 controlled instances, we find that successful recovery remains relatively rare and is associated with more frequent belief updates along the reasoning trajectory. We further find that properties of the hallucinated prompt contain substantial predictive signal for successful recovery, with a lightweight predictor achieving an AUROC of 0.847. These findings provide a behavioral view of post-hallucination reasoning, characterizing how LLMs resolve erroneous context and when successful recovery is likely to occur. --- ### MemoCare: An Interactive Multimodal Mobile System for Automated Cognitive Screening Authors: Duy-Cat Can, Mau Minh Phuc Le, Tuan-Khoa Hoang, Hai-Dang Nguyen, Trung-Hieu Do, Dang Minh Ly, Minh-Duc Nguyen, Nghia TT Hoang, Linh-Trung Nguyen, Huy-Hieu Pham, Huong Ha, Binh T. Nguyen et al. Published: 2026-10-07 Categories: cs.MM, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2610.10448v1 MemoCare is an interactive mobile system for automated multimodal cognitive screening. A React Native application combines spoken responses, temporal and spatial orientation, touchscreen actions, and visuoconstruction in complete English and Vietnamese workflows. Speech is transcribed by Google Speech-to-Text and scored locally with deterministic task-specific natural language processing rules; GPS coordinates are resolved by the MemoCare spatial module before answer matching; touch tasks are scored from interaction events; and the drawing task uses a three-model convolutional neural network consensus with separate visual interpretation. Software tests pass 151/151 predefined cases across speech/language, spatial-answer, and touch-interaction scoring, while spatial regression passes 48/48 four-country coordinate-resolution cases. For the drawing module, validation-selected ShuffleNetV2 x1.5 achieved 91.33% mean balanced accuracy and 78.87% exact three-criterion accuracy on a locked 71-image test set. Four clinician co-authors additionally inspected the end-to-end workflow, yielding a pooled median rating of 4/5 across eight criteria, with item-level medians ranging from 3 to 4.5. At MMM, attendees can directly try a shortened multimodal screening workflow and inspect automatic item-level and total scoring. --- ### A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching Authors: Randy Ardywibowo, Arnav Dalal, Jiantao Jiao Published: 2026-10-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.10447v1 Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and costly to generate. On-Policy Distillation (OPD) offers an attractive alternative by providing dense token-level supervision from a stronger teacher along the student's own generations. Self-distillation methods further remove the need for a separate teacher model by conditioning the same policy on privileged information to serve as its own teacher. However, privileged conditioning alone does not guarantee that the resulting distillation update improves the student. Indeed, privileged information can lead the teacher to solve tasks through shortcuts unavailable to the student, producing supervision poorly matched to the student's current behavior. Consequently, even a higher-performing teacher can provide guidance that degrades student performance. To address this, we analyze how the choice of privileged teacher affects the student's update. We derive a necessary and sufficient condition for the teacher's local distillation update to be a positive multiple of the student's reward gradient. Our analysis suggests that the teacher should not only perform well on the task, but also provide guidance suited to the student's current capabilities. This characterization motivates a practical teacher-training surrogate that combines outcome rewards with token-level Kullback-Leibler (KL) regularization toward the student. Based on this result, we propose Joint On-Policy Learning and Teaching (JOLT), which jointly trains a single policy in two roles: a privileged teacher using a KL-regularized objective, and an unprivileged student using dense on-policy distillation. Across mathematical reasoning, coding, tool use, and terminal use, JOLT improves training efficiency and performance, with further gains from student rewards. --- ### RunningTab: Direct Workspace Interaction with Environment-Side Tabs Authors: Jinheon Baek, Soyeong Jeong, Yumin Choi, Dongsu Han, Sung Ju Hwang Published: 2026-10-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.10444v1 Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over. Through direct corpus interaction, an agent can search and read any of those files from a terminal with no indexing, and producing a deliverable from many of them in this way is what we call direct workspace interaction (DWI). Reaching the files, however, is only half the task: nothing keeps track of what the task asks for, what has been read, and what was listed but never opened, all of which slip through the context window without leaving a trace, so an agent may extract a figure and still deliver a report without it. To address this, we present RunningTab, a framework that equips direct workspace interaction with an environment-side tab: a per-task record of what the task still owes, kept by the environment alongside the agent. Specifically, the agent adds its requirements, while the environment records every file read as an excerpt with its provenance and every listed but unopened file as a candidate; the agent can then see each requirement beside its best-matching excerpts and top unopened candidates, resolve it against matching content or set it aside with a reason, and, should it try to finish with requirements still open, receive them in a finish check. We validate RunningTab on three benchmarks with three LLMs, where it consistently outperforms plain DWI and baselines that keep the record in the model, while its tab usually holds the values a deliverable needs once seen. --- ### Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control Authors: Yinan Huang, Shitij Govil, Bo Dai, Pan Li Published: 2026-10-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10440v1 Many scientific forecasting tasks require updating a distribution over future trajectories as new observations arrive. Conventional diffusion and flow models generate each forecast from Gaussian noise, often at the cost of many sampling steps. Warm-start methods reuse earlier predictions to reduce this cost, but their models are not trained to perform the forecast update itself, which can compromise quality under few-step sampling. In this work, we introduce Seq-Flow, a conditional flow model whose ODE transports samples from the previous forecast distribution to the updated one. Because successive forecasts often differ only modestly, this transport starts from an informative distribution and can produce accurate updates with few flow evaluations. Recursive reuse also creates a challenge: errors in one forecast become errors in the initial states of subsequent flows. We address this with self-rollout training, in which a moving average copy of the model generates forecasts that initialize later training updates. Unlike self-forcing methods, which reuse generated outputs as conditioning context, Seq-Flow reuses them as the source of the next flow. Experiments On particle-accelerator beam spill forecasting show Seq-Flow reduces CRPS by 65% under a few-NFE sampling budget, while remaining competitive with strong baselines on fluid-dynamics forecasting tasks. Although trained on self-rollouts of at most four updates, Seq-Flow remains accurate over more than 400 consecutive updates. Our code is available at https://github.com/Graph-COM/Seq-Flow. --- ### ECHO: Embodied Camera Observations of Human Object Carrying Authors: Xuefei Sun, Lorin Achey, Kali Hamilton, Alberto Speranzon, Gregory Grebe, Yonatan Bisk, Christoffer Heckman Published: 2026-10-07 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.10438v1 Embodied and assistive agents must do more than recognize objects: they must reason about where an object belongs given the layout of an environment and the habits of the people who live in it. Progress on this problem has been limited, in part because no dedicated benchmark or dataset exists to define and evaluate it. Existing RGB-D scan datasets reconstruct static rooms without human activity, while human-object-interaction datasets capture motion without a navigable, fully reconstructed scene or a ground-truth notion of an object's natural destination. We introduce contextual object placement as a benchmark task: predicting an object's destination during an observed object-carrying episode. To support this task, we present Embodied Camera observations of Human Object carrying (ECHO), a large-scale synthetic dataset that pairs dense RGB-D scans of indoor scenes with recordings of an embodied human carrying everyday objects to context-appropriate destinations. ECHO is the first publicly available dataset to combine reconstructed scenes, human activity, natural language, and contextual-placement annotations. It comprises 3,805 human-annotated episodes across 159 floors of 115 HM3D scenes, involving 198 distinct objects. Each floor includes a complete RGB-D scan with human-annotated room labels and a surface list. Each episode provides synchronized RGB-D encounter clips; 6-DoF camera, human, and object trajectories; start and destination surfaces; an action caption; and a human-written context: a single sentence describing the inhabitant's routine that implies the destination without naming it. We evaluate contextual object placement using input-masked probes and an end-to-end baseline. Results show that no single input modality is sufficient, highlighting the need to jointly reason over scene structure, human activity, and contextual knowledge. --- ### Q-Learning with Scalar Adjoint Matching Authors: Yonghoon Dong, Minsung Yoon, Jaehyuk Kim, Jungwoo Park, Changyeon Kim, Jinwoo Shin Published: 2026-10-07 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2610.10437v1 Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-tuning a flow policy against a learned value function is not trivial, because the policy generates its action over many flow steps. Adjoint matching offers a principled way to update the flow model itself by propagating value information from the final action back to each flow step, but it requires a vector--Jacobian product through the policy at every step, a cost that grows with the number of flow steps and the policy size. We observe that the batch-averaged velocity Jacobian of pretrained flow policies concentrates on its diagonal. Motivated by this finding, we derive a closed-form scalar adjoint that scales the value gradient at the final action by the flow time, eliminating the per-step vector--Jacobian products. We further find that controlling the critic's value at policy-generated actions is particularly important under the scalar adjoint. Based on these findings, we propose Q-learning with Scalar Adjoint Matching (SQAM), which combines the scalar adjoint with a value penalty at those actions. SQAM's gains concentrate on the four hardest OGBench domains, where its success rate exceeds that of the strongest baseline in each domain by 18 to 35 percentage points. To test whether SQAM extends to large pretrained policies, we also fine-tune a vision-language-action policy on a real bimanual robot. SQAM improves over supervised fine-tuning on all three tasks. --- ### Detecting Adversarial Images through Response Profiles of Vision-Language Models Authors: Arash Vashagh, Roozbeh Razavi-Far Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10436v1 Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity patterns seemingly plausible. We investigate whether we can identify adversarial inputs based on the broader way an image interacts with a collection of general semantic prompts. Our detector summarizes these responses using category-level statistics, relationships among prompts, deviations from clean reference distributions, and stability under weak image transformations, producing a compact response profile that is classified by a lightweight model while the VLM remains fixed. We evaluate the approach on multiple public image datasets, several CLIP-style visual backbones, and a range of gradient-based, optimization-based, automated, and spatial attacks. The detector achieves strong discrimination in attack-specific settings and retains substantial performance when evaluated on attacks not seen during training. Under a controlled detector-specific protocol, the response-profile representation outperforms the evaluated embedding-geometry baselines. Additional analyses show that the feature groups provide complementary information and that the method remains effective under variations in the prompt configuration. We also examine inference cost and performance against detector-aware adaptive attacks. Overall, the results indicate that response patterns across semantic prompts provide a useful complementary signal for adversarial image detection in frozen VLMs. --- ### Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields Authors: Peng Liu, Shaoxiang Qin, Theodore Potsis, Lili Ji, Dingyang Geng, Liangzhu Leon Wang Published: 2026-10-07 Categories: physics.flu-dyn, cs.CE, cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2610.10430v1 Rapid and accurate prediction of urban wind and temperature fields is important for urban microclimate design and climate adaptation. Large-eddy simulation (LES) effectively resolves these instantaneous fields, but its application is limited in iterative design of urban microclimate applications due to high computational cost. Existing regressive data-driven models offers quick outputs, but they produce only deterministic point predictions that inherently fail to represent turbulent stochasticity. This paper adopts a novel generative framework of Conditional Flow Matching (CFM) that uses building geometry and mean flow as guidance to generate plausible three-dimensional instantaneous velocity and temperature fields for urban microclimate in seconds. To overcome the GPU memory bottleneck of pixel space 3D generation, the model operates in parallel on overlapping pixel space through a shared-noise initialization that preserves high spatial continuity of flow structure across the entire domain. Against reference LES data, the CFM surrogate can rapidly and accurately restore the first-order statistics with Normalized Root Mean Square Error (NRMSE) of 2.99% for wind and 1.77% for temperature, second-order turbulence metrics with NRMSE of 7.17% for wind and 8.84% for temperature, turbulent kinetic energy with NRMSE of 7%, probability density function and vertical profiles in representative locations. Wind engineering application of local gust prediction demonstrate that the speed and accuracy of CFM, supporting the use of generative AI for making turbulence-aware resilient urban design and climate adaptation more computationally feasible. --- ### SGF+: Decoupling Gradient Flows for Autoregressive Video Generation Authors: Zihan Su, Junhao Zhuang, Yaowei Li, Siwen Lu, Haoran Li, Lingen Li, Haoyu Wu, Weiyang Jin, Songchun Zhang, Haoyang Huang, Chun Yuan, Zeyue Xue et al. Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10429v2 Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that their gradients exhibit distinct patterns and systematic negative alignment, hindering the joint optimization of visual quality and temporal consistency. We introduce Self Gradient Forcing Plus (SGF+), which assigns separate parameters to context writing and denoising while preserving their interaction through causal attention. Both roles are jointly optimized using the original generation objective without auxiliary losses, with context writing supervised through its contribution to future predictions. This simple change improves visual quality and long-horizon consistency over the evaluated baselines in both framewise and chunkwise generation, without additional video training data or a longer training horizon. Trained on only 5s rollouts, SGF+ supports continuous generation for up to 24 hours without long-video fine-tuning. These results highlight role-specific parameterization as an effective design principle for high-quality autoregressive video generation and native long-horizon extrapolation. --- ### SGF+: Decoupling Gradient Flows for Autoregressive Video Generation Authors: Zihan Su, Junhao Zhuang, Yaowei Li, Siwen Lu, Haoran Li, Lingen Li, Haoyu Wu, Weiyang Jin, Songchun Zhang, Haoyang Huang, Chun Yuan, Zeyue Xue et al. Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10429v1 Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that their gradients exhibit distinct patterns and systematic negative alignment, hindering the joint optimization of visual quality and temporal consistency. We introduce Self Gradient Forcing Plus (SGF+), which assigns separate parameters to context writing and denoising while preserving their interaction through causal attention. Both roles are jointly optimized using the original generation objective without auxiliary losses, with context writing supervised through its contribution to future predictions. This simple change improves visual quality and long-horizon consistency over the evaluated baselines in both framewise and chunkwise generation, without additional video training data or a longer training horizon. Trained on only 5s rollouts, SGF+ supports continuous generation for up to 24 hours without long-video fine-tuning. These results highlight role-specific parameterization as an effective design principle for high-quality autoregressive video generation and native long-horizon extrapolation. --- ### Derivative Gaussian Processes on a Two-Direction Budget Authors: Hyunseok Seung, Matthias Katzfuss Published: 2026-10-07 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.10428v1 Gradient observations promise more accurate Gaussian process (GP) surrogates, but the cost of incorporating them has long stood in the way of realizing that promise. We propose a derivative GP with a budget of just two directions per observed gradient. One direction focuses on each gradient's direct contribution to target prediction, while the other aggregates its indirect contributions through correlations with the conditioning function values. Within a Vecchia approximation, where each prediction conditions on $m$ nearby inputs in $d$ dimensions, this construction represents their $md$ gradient coordinates using at most $2m$ directional derivatives, giving $\mathcal{O}(m^3)$ dense factorization cost per prediction target. For general conditioning sets, we bound the posterior approximation error relative to using full gradients and characterize when the error is small or the approximation is exact. In simulations, our method matches the accuracy of a leading exact gradient-reduction method at equal conditioning set size. Because its cost grows much more slowly with that size, it can use conditioning sets well beyond the memory limit of the exact method, reaching lower prediction error with a small fraction of the time and memory. Notably, our method can exploit gradient observations while requiring less computation time or memory than function-only GP baselines. --- ### CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution Authors: Jixuan Chen, Jiaxin Zhang, Qinyuan Ye, Yada Pruksachatkun, Haoxiang Zhang, Jingming Zhuo, Yifan Zhang, Yutong Dai, Juntao Tan, Xiangyu Peng, Silvio Savarese, Zeyuan Chen et al. Published: 2026-10-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.10426v1 Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery. Existing harness-model co-evolution approaches improve both components, yet often treat trajectories produced during harness search as an undifferentiated replay buffer. This practice overlooks that a trajectory's value for model training depends on the harness under which it was generated. To systematically analyze this interface, we establish an alternating co-evolution framework that decouples harness search and policy training through component-wise promotion decisions. Within this framework, we introduce CoTrace, a harness-aware data recipe that explicitly governs trajectory routing, provenance matching, and curriculum refresh. Under CoTrace, recurring execution failures guide harness synthesis, while policy training is strictly conditioned on verified rollouts matched to the adopted runtime for supervised fine-tuning (SFT) or fresh online interactions for reinforcement learning (RL). On the Tmax promotion split, CoTrace advances Qwen3.5-9B from 78 to 88 solved tasks under supervised fine-tuning while an online reinforcement variant reaches 90. Specifically, a compact harness-matched corpus produces steady model gains at substantially lower compute than much larger corpora pooled across sibling harnesses. Furthermore, evaluations on Terminal-Bench 2.1 and SWE-bench Lite show that out-of-distribution transfer depends fundamentally on harness compatibility, where maintaining consistency between training and evaluation runtimes prevents procedural execution breakdowns observed under foreign scaffolds. --- ### GraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural Networks Authors: Arash Vashagh, Roozbeh Razavi-Far Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10423v1 Adversarial example detectors are often tied to the classifier backbone they were trained on, limiting reuse when the protected model is replaced or upgraded. Directly transferring such detectors across backbones is challenging because different networks generally produce incompatible internal representations. We propose GraphRectify, a graph-based framework for transferring adversarial image detectors across classifier backbones. GraphRectify learns a structured representation of intermediate classifier features and adapts representations from a new backbone to the detector learned on the original model, enabling detector reuse. We evaluate GraphRectify across multiple datasets, backbone architectures, and adversarial attacks, including detector-aware adaptive attacks that jointly target the classifier and detector. Across the complete evaluation matrix, GraphRectify achieves higher aggregate ROC-AUC than training a detector from scratch on the new backbone and the evaluated transfer ablations. The gains are particularly strong for transfers between different backbone families and when sufficient data are available. In contrast, training from scratch remains competitive in the most data-limited settings. These results show that adversarial detection knowledge can transfer effectively across heterogeneous classifier architectures rather than being relearned whenever the protected backbone changes. --- ### Which Rollout Taught It That? BehaviorTrace and the Limits of Training-Data Attribution in Online RL Authors: Amit Nautiyal Published: 2026-10-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.10422v1 When reinforcement learning teaches a language model a new behavior, can we find the training rollouts that taught it? And when an attribution method says it can, how do we know the answer is real? We study both questions on online RL fine-tuning with GRPO, using a planted behavior with a known cause. We release BehaviorTrace, an open evaluation harness that combines full-gradient sketching, the planted-behavior setup, and controls for gradient magnitude, fluency, headroom, and variation across seeds and generation draws. Across three seeds on Qwen2.5-1.5B, much of the apparent attribution signal comes from confounds. A control that ranks training steps by gradient size alone, with no behavior target, reaches 4.2 to 4.5 times chance and matches or beats the best targeted estimator on two of three seeds. At saturated checkpoints, model fluency predicts the behavior label at least as well as every gradient method we compared it with. Once fluency is controlled, the per-rollout results change from seed to seed and from one generation draw to the next, so a single run cannot settle the question. One signal does hold on all three seeds. The gradient of the trigger tokens aligns with a target built where the behavior actually occurs. We turn these findings into a checklist for evaluating attribution in RL. We test existing estimators, including GAS (renormalized TracInCP) and a TRAK-style estimator, and do not propose a new one. --- ### Steerspeech: Activation Steering For Emotion Control In Generated Speech Authors: Afsara Benazir, Darius Pétermann, Felix Xiaozhu Lin, Salar Rahili Published: 2026-10-07 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2610.10415v1 Pretrained text-to-speech (TTS) models can generate expressive speech, but reliable inference-time emotion control remains challenging: prompts and reference audio offer coarse, inconsistent control, whereas specialized conditioning and model adaptation require costly training. We present SteerSpeech, a lightweight activation-steering framework that controls emotion by injecting steering vectors into hidden activations. For each target emotion we train a lightweight low-rank transform, using a multi-expert objective that encourages monotonic emotion control while preserving speaker identity and linguistic content, constraining steering drift, and keeping the TTS backbone frozen. To optimize through discrete speech tokens, we introduce a two-pass generation-and-replay pipeline using a straight-through estimator to backpropagate expert supervision through sampled tokens. At inference, a target-emotion steering direction is optimized with its respective transform and injected into the base TTS model. Objective and subjective evaluations with Qwen3-TTS across seen, unseen, and accented speakers show stronger continuous emotion control with limited speaker and content degradation. SteerSpeech achieves 1.08x-7.12x baseline target-emotion scores and for a representative emotion subjectively, it receives 78.1%-96.8% intensity preference and 1.43x-1.46x speaker-identity preservation at high steering strengths. --- ### Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds Authors: Yunxiao Zhao, Changxiao Cai Published: 2026-10-07 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2610.10411v1 Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model verifies in parallel. Parallel and semi-autoregressive (semi- AR) drafters improve drafting efficiency by proposing an entire block in a single forward pass, but training them raises a new difficulty: the draft distribution for a given position depends on where the decoding round starts, and where rounds start depends on how many tokens earlier rounds accepted. Existing training objectives typically rely on block-local surrogates that ignore this cross-round coupling, and therefore do not directly optimize the global decoding efficiency. In this work, we develop a theoretical framework for training and evaluating these drafters by representing speculative decoding as a Markov reward process. This formulation yields the Expected Decoding Rounds (EDR) objective, which weights local rejection costs by state occupancies and exactly equals the expected number of decoding rounds. Unlike prior surrogate objectives, EDR introduces no auxiliary hyperparameters. We then derive an exact temporal-difference gradient that supports unbiased stochastic optimization from target-model rollouts. The same framework also yields an exact offline evaluator for round counts, enabling paired drafter comparisons on shared target rollouts without running speculative decoding. Finetuning two state-of-the- art drafters, DSpark and DFly, with EDR consistently improves mean accepted length and outperforms existing training objectives across nine benchmarks spanning math reasoning, code generation, and chat. --- ### RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments Authors: Zhiqin Yang, Chenxin Li, Xiaomeng Hu, Yibin Liu, Weidong Huang, Jiankai Sun, Haitao Li, Zijian Wu, Yuzhi Huang, Fanding Huang, Hanwen Sun, Jiashun Liu et al. Published: 2026-10-07 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2610.10409v1 General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we introduce RobotWorld, a challenging simulation testbed for robot use: turning instructions and observations into physical task execution through robot interfaces. Its 84 tasks span manipulation, mobile manipulation, locomotion, driving, and aerial control, with explicit interaction budgets and executable success checks. By analysing task outcomes alongside execution traces, we identify both the capabilities that transfer and the gaps that prevent reliable completion. Furthermore, we find that current agents can construct sophisticated perception and control workflows, including image segmentation, camera calibration, spatial estimation, and dynamics-based computation. These capabilities, however, do not consistently compose into successful behaviour: agents lose task-relevant object states despite reaching commanded poses, fail to correct ineffective actions, recover too late, or mistake unfinished tasks for completion. This uneven transfer also differs across models: Astra succeeds more often on spatial and constrained-contact goals, whereas Opus 5.5 succeeds more often on continuous-balance and timed-interaction goals. By linking these outcomes to execution behaviour, RobotWorld provides both a rigorous proving ground and an empirical account of the remaining capability gaps, thereby establishing concrete targets for training and designing more reliable physical-world agents. --- ### Rubix: Global Correspondence-Free Point Set Alignment through Assignment Geometry Authors: Subhransu S. Bhattacharjee, Dylan Campbell, Rahul Shome Published: 2026-10-07 Categories: cs.CV, cs.CG, cs.LG, cs.RO, math.OC arXiv: https://arxiv.org/abs/2610.10408v1 Procrustes-Wasserstein alignment jointly estimates a matching and rotation without supplied correspondences, but alternating minimization can stop at suboptimal solutions. Rubix solves the equally weighted planar problem globally under squared Euclidean loss. Each matching $σ$ of two centered $n$-point sets defines a complex correlation $z_σ=\sum_i\bar x_i y_{σ(i)}$. Their convex hull is the permutation polygon: supporting vertices give optimal matchings at fixed rotations, and the farthest vertex gives the global alignment. We prove the sharp bound of $n(n-1)$ vertices for $n\ge2$, answering Rote's rotation-assignment open problem. In exact arithmetic, assignment queries recover the polygon in $\mathcal O(n^5)$ operations. Assignment-based bounds extend the approach to three-dimensional rotations and partial matching at a supplied translation through branch-and-bound. On timed MPEG-7 shape pairs, Rubix attains every numerical reference value in 12 ms on average, 50 times faster than a rotation grid at the same accuracy. Its distances improve gravity-aligned matching of real 3D scans, shape retrieval and noisy crystal classification over alternating minimization. --- ### SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions Authors: Yizhen Xie, Mengyang Liu Published: 2026-10-07 Categories: cs.AI, cs.LG, q-fin.PM, q-fin.TR arXiv: https://arxiv.org/abs/2610.10407v1 As option markets grow and AI advances, agentic systems for option trading are gaining increasing attention. Language-model-based agents can reason over contextual information such as news, but option trading presents a particularly challenging decision problem: a single stock can have thousands of contracts, and the agent must decide both which contracts to trade and how to combine them. Existing approaches often sidestep this complexity by restricting the policy to a fixed strategy structure, such as a straddle, limiting their ability to switch strategies as market conditions change. We present SOTA (Stock Options Trading Agents), an agentic trading framework for structured option-strategy selection. SOTA abstracts the large option universe into strategy-level decisions while deterministic resolvers handle portfolio implementation. We develop SOTA by post-training Qwen3.8-27B with supervised fine-tuning followed by reinforcement learning. SOTA is evaluated on options on nine large-cap U.S. equities and SPY against rule-based and machine-learning strategy selectors in the same trading environment. Over a six-month out-of-sample period, SOTA earns an 18.3% total return with a Sharpe ratio of 1.60 and a maximum drawdown of 8.96%. We also document an asymmetric role of news: news improves frontier-teacher trajectories, but retaining news during reinforcement learning reduces out-of-sample return from 18.3% to -2.7%. --- ### Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language Models Authors: Maverick Morales, Tomáš Dominik, Vermut Gao, Katrina Shirey, Paulius Rimkevičius, Aaron Schurger, Uri Maoz Published: 2026-10-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.10405v2 Monitoring the chain-of-thought of reasoning artificial intelligence (AI) models remains a key approach to detecting deception and other forms of misbehavior in such models. However, semantic chain-of-thought monitoring depends on reasoning traces being legible and sufficiently faithful to the underlying computations that produced the model's behavior, not to mention accessible. Moreover, there is increasing evidence that chain-of-thought outputs may soon become illegible or unfaithful, if they even remain accessible. Based on cognitive load theory, we investigate a lower-bandwidth signal--the number of reasoning tokens generated--which does not require access to the content of the reasoning trace. Three reasoning-capable large language models answered 210 multiple-choice questions--across analytic, descriptive, and normative reasoning types as well as moral and non-moral domains--under system prompts instructing them to respond truthfully, falsely, or without regard for truth. Across all three models, truth-directed responses elicited fewer reasoning tokens than both lie-directed and truth-indifferent responses. In addition, in one model, untruthful instructions increased the likelihood of reasoning at all. These findings show that explicitly prompted untruthful response policies can produce robust group-level differences in test-time reasoning-token use. While not yet establishing reasoning-token count as a detector of spontaneous deception or general misalignment, our results are a proof of concept that it can serve as a simple, content-independent black-box candidate signal for differentiating untruthful from truthful model behavior when raw reasoning traces are unavailable or unreliable. Future work should test instance-level detection rates, out-of-distribution generalization, learned deceptive policies, hidden objectives, and robustness under adversarial pressure. --- ### Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language Models Authors: Maverick Morales, Tomáš Dominik, Vermut Gao, Katrina Shirey, Paulius Rimkevičius, Aaron Schurger, Uri Maoz Published: 2026-10-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.10405v1 Monitoring the chain-of-thought of reasoning artificial intelligence (AI) models remains a key approach to detecting deception and other forms of misbehavior in such models. However, semantic chain-of-thought monitoring depends on reasoning traces being legible and sufficiently faithful to the underlying computations that produced the model's behavior, not to mention accessible. Moreover, there is increasing evidence that chain-of-thought outputs may soon become illegible or unfaithful, if they even remain accessible. Based on cognitive load theory, we investigate a lower-bandwidth signal -- the number of reasoning tokens generated -- which does not require access to the content of the reasoning trace. Three reasoning-capable large language models answered 210 multiple-choice questions -- across analytic, descriptive, and normative reasoning types as well as moral and non-moral domains -- under system prompts instructing them to respond truthfully, falsely, or without regard for truth. Across all three models, truth-directed responding elicited fewer reasoning tokens than both lie-directed and truth-indifferent responding. These findings show that explicitly prompted untruthful response policies can produce robust group-level differences in test-time reasoning-token use. While not yet establishing reasoning-token count as a detector of spontaneous deception or general misalignment, our results are a proof of concept that it can serve as a simple, content-independent candidate signal for differentiating untruthful from truthful model behavior when raw reasoning traces are unavailable or unreliable. Future work should test instance-level detection rates, out-of-distribution generalization, learned deceptive policies, hidden objectives, and robustness under adversarial pressure. --- ### Self-correction Optimization for Interleaved Multimodal Generation Authors: Xin You, Zhiwei Ning, Zukai Chen, Minghui Zhang, Xuanke Shi, Hanxiao Zhang, Jingsong Liu, Jie Yang, Quan Wang, Yun Gu Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10400v1 Multimodal large language models (MLLMs) have made significant progress in visual understanding and generation. However, generating interleaved image--text content remains challenging, as it requires tightly integrated multimodal understanding and generation capabilities. Although existing MLLMs provide promising solutions, most rely on additional training with augmented data, which is computationally expensive and remains limited in preserving visual subjects, temporal consistency, and physical plausibility. In this work, we propose self-correction optimization (SCO), an effective training-free method for consistent interleaved generation. SCO treats the classifier-free guidance update as a reference and performs minimal self-correction under two complementary constraints, including new-event and state-preserving constraints. Specifically, the new-event constraint promotes temporal consistency across image--text sequences, while the state-preserving constraint maintains the coherence of visual subjects throughout subsequent generation steps. Experiments on challenging interleaved multimodal generation benchmarks demonstrate significant improvements in temporal coherence and visual-subject preservation. Furthermore, SCO can be extended to video generation and improves the modeling of physically grounded processes, including robot manipulation and long-horizon handcrafting. --- ### Cross-Domain Pretraining for Steady-State Neural CFD Surrogates Authors: Anthony Zhou, Amir Barati Farimani, Shirley Ho, Rudy Morel Published: 2026-10-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10398v1 Neural surrogates for computational fluid dynamics (CFD) have the potential to greatly enhance engineering innovation through accelerating simulation. However, the primary limitation for neural surrogates is the lack of generalization to geometries and applications beyond the training set, which is significant given the diversity of engineering scenarios. Currently, this is addressed by generating a new dataset for a specific application; however, this requires running costly numerical solvers. In this work, we take a step toward addressing this by studying neural surrogates trained across different geometries, boundary conditions, and fidelities. We find that cross-domain pretraining improves zero- and few-shot performance on held-out datasets relative to both training from scratch and transferring from domain-specific experts. In particular, finetuning a pretrained, cross-domain model can achieve 2-3x lower errors at the same sample size and use 8x fewer samples to achieve the same error, compared to training from scratch. This benefit is architecture agnostic and improves with model size and pretraining dataset diversity. Furthermore, we study how and why cross-domain pretraining works in CFD surrogates, and find that simply pooling steady-state datasets is both sufficient and effective. Given the high cost of generating CFD data, leveraging existing datasets through cross-domain pretraining will likely be a valuable strategy as future surrogates expand to tackle new problems and use cases. --- ### Gaussian Density Splatting Network Authors: Miao Shang, Yabin Wang, Xiaopeng Hong Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10396v2 This paper proposes a novel crowd counting approach, the Gaussian Density Splatting Network (GDSNet). Unlike methods that rely on conventional, grid-based density maps and are sensitive to spatial resolution, GDSNet represents a crowd as a superposition of continuous 2D Gaussian primitives. Our approach is built upon two key contributions. First, a control-point-based fitting mechanism is introduced to structure the prediction of Gaussian parameters. A set of control points is adaptively allocated to define local regions, from which features are pooled to regress each primitive's parameters. Second, we adapt a differentiable Gaussian Splatting framework to the counting task by parameterizing each primitive with geometric parameters and a scalar density mass. This formulation allows the network to be trained end-to-end via spatial matching of differentiably rendered density maps, naturally providing both local density supervision and global count optimization. Extensive evaluations on four standard benchmarks show GDSNet consistently outperforms the state of the art. The code is available at https://github.com/infinite0522/GDSNet-Gaussian-Density-Splatting-Network. --- ### Gaussian Density Splatting Network Authors: Miao Shang, Yabin Wang, Xiaopeng Hong Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10396v1 This paper proposes a novel crowd counting approach, the Gaussian Density Splatting Network (GDSNet). Unlike methods that rely on conventional, grid-based density maps and are sensitive to spatial resolution, GDSNet represents a crowd as a superposition of continuous 2D Gaussian primitives. Our approach is built upon two key contributions. First, we introduce a control-point-based fitting mechanism to structure the prediction of the Gaussian parameters. We design a method to allocate a set of control points that define local regions, from which features are pooled to regress each primitive's parameters. Second, we adapt a differentiable Gaussian Splatting framework to the counting task by parameterizing each primitive with geometric parameters and a scalar density mass. This formulation allows the network to be trained end-to-end via spatial matching of differentiably rendered density maps, naturally providing both local density supervision and global count optimization. Extensive evaluations on four standard benchmarks show GDSNet consistently outperforms the state of the art. --- ### Executing Causal Structure Learning with Linear-Attention Transformers Authors: Amartya Roy, Sayar Karmakar Published: 2026-10-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10395v1 Transformers can execute algorithms on data given in their input. We ask whether they can do the same for causal discovery. We study a standard continuous method that repeatedly updates a candidate causal graph while enforcing acyclicity. We explicitly construct a fixed-weight transformer whose forward pass exactly reproduces one update of this method, so repeated blocks reproduce its optimization trajectory. The transformer carries the current graph and the algorithm's multiplier between updates. We show that retaining the multiplier is essential for exact execution, since different multiplier values can lead to different next updates. We also give conditions under which, within a fixed stage, the number of updates needed to reach a target accuracy can be computed in advance and rounding errors stay bounded as depth grows. Experiments show that the constructed block agrees with a reference update to floating-point precision, while arithmetic replay on synthetic data and seven published benchmark network topologies inherits the reference solver's successes and failures. This separates accurate algorithm execution from accurate causal recovery. In contrast, the ordinary attention models tested under our training budgets do not reliably execute the update or transfer to larger graphs. Whether gradient training can learn an executor in the architecture class of the construction remains open. --- ### Kernel Autoresearch for Open-Ended Model Discovery Authors: Richard Cornelius Suwandi, Feng Yin, Kevin Murphy Published: 2026-10-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10394v1 Kernels encode the inductive bias of a wide range of machine learning models, yet automated kernel design faces a fundamental dilemma. A fixed grammar of base kernels and operators guarantees validity but limits the search to structures expressible by those building blocks. Conversely, unrestricted programs remove this limitation but no longer guarantee validity. In our stress tests, 22-58% of LLM-generated kernels that pass numerical checks on random inputs fail when evaluated at different scales or dimensions. We propose Kernel Autoresearch (Kernaut), which treats kernel design as open-ended model discovery. Coding agents write kernels as programs, while construction contracts ensure that every accepted kernel is valid. A quality-diversity archive retains high-performing kernels with distinct behaviors, and novelty screening steers agents toward functionally new candidates. Our experiments demonstrate that the discovered kernels encode reusable inductive biases that generalize to unseen tasks. On held-out black-box optimization families, a discovered kernel outperforms a meta-learned deep kernel trained on the same episodes. Furthermore, kernels discovered from ten enzyme-kinetic rate laws achieve lower error than tuned ARD and deep kernel baselines on five unseen mechanisms. The discovered kernels are also interpretable programs that human researchers can refine: a human-refined version of one further reduces the held-out predictive error by 5.7% and optimization regret by 7.8%. --- ### Safe Meta-Policy Design with Risk Control Authors: Wenbin Zhou, Michael Lingzhi Li, Shixiang Zhu Published: 2026-10-07 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2610.10393v1 Models can be retrained as new data arrive, but deploying every new version risks replacing a good policy with a worse one. We study how to plan policy updates (i.e., meta-policy) before future candidates are trained, balancing the benefits of improvement against the risk of performance regression. Our offline meta-policy maximizes expected cumulative value subject to a budget on the expected number of updates that perform worse than the policies they replace. We estimate the value and risk of possible switches from historical learning trajectories, represent an update schedule as a path in a directed acyclic graph, and select a schedule using dynamic programming. A leading-order analysis identifies the signal-to-noise ratio of policy improvement as a key driver of update frequency, waiting times, and risk allocation: clearer improvements support earlier, more frequent updates, while noisier improvements call for longer waits or greater risk expenditure. Their asymptotic rates also reveal a diminishing marginal cost of achieving greater safety over time. Experiments on synthetic and clinical trial data illustrate the performance--risk tradeoff and compare our method with alternative baselines. --- ### MOTIP2: Spatial Priors for End-to-End Multi-Object Tracking Authors: Benoît Roussel, Damien Bouet, Liming Chen, Pierre Perrault Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10391v1 End-to-end multi-object trackers have narrowed the gap with classical tracking-by-detection on association-difficult benchmarks. Yet they still make spatially implausible errors no classical tracker would, such as assigning one identity to objects on opposite sides of the frame. A model could learn to avoid them, but tracking annotations are scarce, so we encode spatial priors explicitly instead, while keeping inference fully end-to-end with no post-hoc association. We propose three spatial priors, at the data, loss, and representation stages. Spatial ID Switches bias trajectory permutations toward spatially overlapping objects, reducing the mismatch between training and inference confusions. Spatial ID Loss scales each identity's penalty by its box distance, so a distant switch costs more than a nearby one. Spatial Anchor gives each track token its frame position, an explicit spatial cue for attention. We instantiate the three priors in MOTIP2, a tracker adapted from MOTIP and built on the real-time DEIM detection transformer. Trained without extra data, its main model, MOTIP2-L, sets a new state of the art: 73.4 HOTA on DanceTrack, 76.0 on SportsMOT, and 71.1 IDF1 on PersonPath22. MOTIP2 is a family of models spanning the speed-accuracy trade-off: a lighter model, MOTIP2-S, matches the original MOTIP at over 3x the speed, and MOTIP2-X reaches 74.8 HOTA on DanceTrack. --- ### Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving Authors: Xingtai Gui, Yucheng Zhou, Dongqian Guo, Jiahao Gong, Feiyang Tan, Jianbing Shen Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.10390v1 Vision-language-action~(VLA) models have emerged as a promising paradigm for autonomous driving. However, existing VLA models still suffer from a fundamental mismatch: driving actions require precise 3D geometric cues, while visual-language understanding and reasoning are largely conducted in a 2D semantic space. In this paper, we propose GeoCoTDrive, an explicit geometric chain-of-thought framework that grounds geometry in a planning-oriented manner. GeoCoTDrive follows a think with 2D first, drive with dedicated 3D priors paradigm. It first grounds 2D regions corresponding to decision-critical cues, and then retrieves localized 3D priors by sampling features from a geometric foundation model within the grounded regions. These localized geometric features are interleaved into the autoregressive context to support the trajectory generation. To supervise this process, we introduce planning-relevant grounding, a new region-level grounding task that focuses on local spatial cues directly affecting ego planning decisions, and construct the PlanningGrounding dataset to endow VLAs with planning-oriented grounding capability. Experiments across multiple end-to-end autonomous driving benchmarks show that GeoCoTDrive consistently improves safety-critical planning performance, demonstrating the effectiveness of the explicit geometric chain-of-thought process for VLA-based planning. --- ### RoboQuest: Generalist Physical Agents that Search, Inspect and Test Authors: Liu Renhang, Navonil Majumder, Tej Deep Pala, Soujanya Poria Published: 2026-10-07 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.10388v1 Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, successful operation in an unfamiliar environment may require an agent to seek task-relevant information through interaction when it is absent from the observations: it may need to determine where a relevant object is, inspect an unobserved property, or discover the effect of an unfamiliar tool. We thus introduce RoboQuest, a benchmark for goal-directed embodied exploration, where agents must actively acquire task-relevant information through physical interaction, use the resulting evidence to adapt subsequent actions, and autonomously decide when to commit to task completion. RoboQuest comprises ten mobile manipulation tasks centered on three forms of uncertainty: search, manipulation-based inspection, and interactive testing. We evaluate five frontier multimodal agents through a common visuomotor interface, as well as a $π_{0.5}$ policy fine-tuned on the full-episode demonstrations we release. The best agent succeeds in only 23\% of the episodes, and the fine-tuned policy almost never succeeds. Isolated tests of the execution skills the tasks are built from, with the hidden information supplied, show that the agents can carry out most of the required actions, and our failure analysis attributes only a minority of the failures to execution. Our failure analysis further finds that the agents often stop exploring too early as they make decisions before observing the required evidence for task completion. We also find that agents rarely prevent or repair the disturbances caused by their exploration. Moreover, learning by trial and error remains difficult for most models. --- ### OrBIT: Structure-Guided Embedding Compression Authors: Yunied Puig, Amit Kumar Jaiswal Published: 2026-10-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10385v1 Embedding tables are among the largest components of modern language models. Most compression methods fix a coding geometry such as coordinate blocks, low-rank subspaces, or unrestricted codebooks, and optimize within it. We instead ask whether the coding geometry can itself be discovered. We introduce \emph{OrBIT}, a structure-guided embedding compression framework that learns reusable local geometry from orbit dynamics and uses it to constrain a small set of shared codewords. The global reconstruction residual then decides where the fixed coding budget is spent, while redundant overlapping charts let local errors compensate one another after gluing. Our theory shows how tight-chart geometry controls distortion, how the global residual directs sequential allocation, and how data-geometry-guided refinement improves the codec. The resulting orbit machinery is compiled away, leaving a compact decoder in which the learned structure governs what is stored, where capacity is allocated, and how local information is assembled globally. Across four LLM embedding tables, OrBIT achieves $37.9\times$ compression on GPT-2 and over $23\times$ on each 7B table relative to 16-bit storage, while delivering competitive rate-distortion performance against established quantization and low-rank baselines. --- ### Boosting and the Expressive Power of Simple Weak Learners via the $γ$-VC Dimension Authors: Arthur da Cunha, Kasper Green Larsen, Liang-Yu Zou Published: 2026-10-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10383v1 Boosting converts weak hypotheses with a small edge over random guessing into highly accurate predictors, but the expressive power of the resulting classifier can depend strongly on the structure of the base class. We study this phenomenon through the $γ$-VC dimension introduced by Alon et al. (STOC 2021). Our first result shows that this parameter characterizes the sample complexity for weak-to-strong learning up to a constant factor scaling in $γ$. We then sharpen the general relationship between the classic VC dimension and the $γ$-VC dimension. Finally, we also give improved upper and lower bounds on the $γ$-VC dimension for the fundamental concept classes of decision stumps and axis-parallel rectangles in $\mathbb{R}^d$. ---