# Research Papers — 2026-09 · bundle page 187 of 266 > Full-text markdown of papers #9301–9350 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/187 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/186.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/188.md) ### AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization Authors: Ji Liu, Saptarshi Majumder, Yiqing Huang, Wenwen Ouyang, Umang Pandey, Zeping Li, Chushi Chen, Zihao An, Puyuan Yang, Zekai Li, Sina Rafati, Ziqiong Liu et al. Published: 2026-09-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.12471v1 We introduce AMDKernelVault, an open HIP and Triton kernel corpus and training framework for recent AMD CDNA GPUs. Existing LLM-based kernel agents are largely CUDA/NVIDIA-centric and often depend on repeated frontier-LLM calls for generation, reflection, and optimization. To address this gap, we develop HIPKernelGen and TritonKernelGen, agent-driven pipelines that transform PyTorch references into HIP or Triton kernels, compile and validate candidates under ROCm, and latency-profile them on AMD hardware. The corpus contains 62,153 execution-verified HIP kernel samples, 2,377 production-grounded ROCm Libraries QA entries, and 39,893 Triton kernels. We further train Qwen3-8B with supervised fine-tuning and execution-aware reinforcement learning as a demonstration of the corpus's utility. Under fixed evaluation budgets, it achieves the highest correctness among the compared models on PyTorch-to-HIP (34.0% Pass@1), TritonBench-G (33.2% Corr@3), and ROCmBench (41.94% Corr@3), but does not uniformly lead compilation or speed metrics. The corpus and documentation are available at https://huggingface.co/datasets/amd/AIG-Datasets, and the associated training and kernel-generation code is available at https://github.com/AMD-AGI/hip_kernel_llm_lab. --- ### A Differentially Private Federated Proximal Optimization Framework for Customer Churn Prediction in Heterogeneous Federated Telecom Networks Authors: Joydeb Kumar Sana, Subrata Chakraborty, M M Manjurul Islam Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.12470v1 Customer churn is one of the major issues in the telecommunication industry. To predict customer churn, conventional centralized machine learning approaches have been widely used. This centralized approach requires customer data to be stored in a central repository, which raises privacy concerns and may violate data protection regulations. Federated learning addresses this problem by allowing multiple telecom operators to collaboratively train a global model without transferring their raw customer data. However, real-world customer data are often heterogeneous (non-IID), which may negatively affect the performance of standard federated learning. Trained models can also suffer from privacy attacks. To address those issues, we propose a Differentially Private (DP) based Federated Proximal optimization (FedProx) framework. All experiments were performed on two publicly available telecom churn datasets. We trained Federated Averaging (FedAvg), DP-FedAvg, FedProx, and the proposed DP-FedProx framework. For baseline comparison, we also used several centralized and local models. To evaluate the models, we employed seven widely used evaluation metrics. The experimental results show that the FedProx based models consistently outperform the FedAvg based models. Compared with the best centralized model, the proposed DP-FedProx framework achieves competitive prediction performance with only a small reduction in accuracy while providing privacy guarantees. To explain our model, we conducted SHAP analysis which shows that DP-FedProx method priorities revenue group features. These results indicate that the proposed DP-FedProx framework provides a practical balance between prediction performance and data privacy protection. --- ### Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up Authors: Preeti Saraswat, Divya Neelagiri, Anil Yadav Published: 2026-09-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.12469v1 False wake-up activations remain a persistent challenge in conversational AI. Speech phonetically similar to a device's wake word can produce a syntactically valid and semantically coherent ASR transcript that the assistant incorrectly executes. Most existing systems make a single intent decision in isolation, without a mechanism to learn from recurring errors over time or adapt to individual users through personalized learning. We introduce the Feedback-Driven Adaptive Self-Correcting Inference Layer (ASCIL), a complementary post-ASR correction framework that re-evaluates wake-up intent before response generation by fusing acoustic embeddings, linguistic cues, device context, and patterns from past misclassifications. ASCIL interprets implicit signals, including hesitation, disengagement, and silence, and explicit signals, including cancellation and repetition, as automatically inferred, noisy behavioral indicators of potential misclassification. These signals drive online pattern updates without manual annotation, whereas the intentional/unintentional reference labels used for offline evaluation are human-annotated. It generalizes from prior errors, applies corrective adjustments at inference time, and continuously updates in parallel with natural-language execution. Evaluated on a proprietary dataset of 3,667 interactions with human-annotated intentional/unintentional reference labels spanning 14 acoustic and contextual conditions, ASCIL achieves 54.27% relative error reduction on a session-disjoint subset constructed from baseline failures, and up to 24.39% relative error reduction at threshold 0.90 on the issue-tagged evaluation slice. These gains are achieved while improving intentional acceptance rates, with a median added latency below 60 ms in the reported benchmark. --- ### Beyond Vector Similarity: Hierarchical Context-Aware Graph RAG vs Standard RAG in Enterprise Code Migration Authors: Nilesh Jaiswal, Aniket Agrawal, Arjit Shukla, Divya Malhotra, Saurabh Garg, Suchit Puri, Suddhasatwa Bhaumik Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12464v1 As enterprises modernize legacy monolithic systems to microservices, Large Language Models (LLMs) are heavily utilized for automated code translation. However, traditional vector-based Retrieval-Augmented Generation (Standard RAG) struggles to capture topological relationships. It fetches isolated chunks that sever inheritance chains, leading to high compilation failure rates. This paper introduces a Hierarchical Context-Resident Graph (HCRG) methodology to resolve these limitations. Our pipeline uses tree-sitter for Abstract Syntax Tree (AST) extraction, maps architectural edges into a Google Cloud Spanner Property Graph, and serializes this structure into a Gemini Context Cache for topological, parent-first code translation. We shift evaluation from naive text-overlap to a custom 7-metric Software Engineering framework. Traditional metrics like CodeBLEU (which scored 91% for both methods) effectively masked Standard RAG's structural failures behind syntactically plausible but broken code. Empirically, Graph RAG decisively mitigates dependency loss: API hallucination rates dropped from 56.4% to 16.2%, Dependency Resolution Quality improved from 34.8% to 65.9%, and Parent-Child Consistency rose from 26.7% to 45.5%. However, Graph RAG introduces specific trade-offs. The dense global context causes defensive over-engineering by the LLM, reducing Cyclomatic Complexity Consistency from 71.6% to 46.7%, and slightly degrades Docstring Preservation (67.0% to 61.0%). Ultimately, while trading code complexity for reduced hallucinations, Graph RAG provides a substantially more viable, architecturally sound path for automated enterprise codebase modernization. --- ### Linear Exponential Quadratic Gaussian Covariance Steering Authors: Chiran B. Cherian, Yasemin Isik, Abhishek Halder Published: 2026-09-11 Categories: math.OC, cs.AI, cs.LG, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2609.12463v1 We formulate and analyze the linear exponential quadratic Gaussian (LEQG) covariance steering problem in continuous time over a given deadline (finite time horizon). The solution for this problem can be seen as a risk-sensitive Schrödinger bridge between Gaussian endpoints in the linear quadratic setting. Unlike the risk-neutral case, the LEQG covariance steering controller--still a linear state feedback--can no longer be written in closed form. We show that the optimal controller is parameterized by a symmetric matrix solving an algebraic equation that encodes the implicit dependence on the risk-sensitivity parameter. We explain how the structure of this optimal controller significantly generalizes the existing results for the risk-neutral case. Building on these results, for the matched noise and input channel case, we prove the existence-uniqueness of solution for the LEQG covariance steering problem in the neighborhood of the known risk-neutral optimal solution. We give an illustrative numerical example. --- ### EvoRS: On-Policy Self-Evolution of Reward Systems for Open-Ended Reinforcement Learning Authors: Weiyuan Li, Aili Chen, Xintao Wang, Yikai Zhang, Qingqing Dong, Jinghan Xu, Hongru Hou, Wenxuan Zhao, Chengkun Lang, Jun Gao, Yuanli Guo, Hongcheng Guo et al. Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12459v1 Open-ended reinforcement learning often relies on rubric-based rewards for tasks without directly verifiable answers. Yet the policy and reward system form a dynamic feedback loop: as the policy optimizes the current reward, an initially useful reward system may become unreliable due to reward hacking or reduced response discriminability. The reward system should therefore evolve rather than remain fixed during training. Existing dynamic-rubric methods adapt evaluation criteria, but reward failures can also arise from scoring mechanisms or signal composition. We introduce EvoRS, a self-evolving RL framework that evolves the reward system from on-policy experience, representing it as an executable Reward-DAG. Specifically, an agentic designer updates this system from on-policy rollouts and reward traces to maintain train-time reliability. Across writing and roleplay, EvoRS achieves the best quality under all three judges, outperforming the policy by \(2.107\) and \(4.767\) points, respectively, while reducing reward hacking and coverage failures and preserving reward informativeness. Ablations confirm that a comprehensive fixed reward system cannot remain reliable in open-ended tasks and must evolve throughout training. --- ### SAGE-Loop: Reliable Closed-Loop LLM-Driven AutoML with Trial-and-Correction and Adaptive Ensembling Authors: Junquan Gu, Shibo Cui, Xiangfeng Luo, Hang Yu Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.12455v1 Automated machine learning (AutoML) is reshaping data-driven science and industrial practice, and as large language models are introduced into AutoML, pipeline reliability becomes as important as automation efficiency. However, existing AutoML still struggles to realize instant feedback and adaptive optimization during execution, so once a run drifts into a suboptimal or failed state, it lacks a process-level correction mechanism. The fundamental pathology lies in its one-way pipeline: intermediate failures are typically terminated or bypassed, while fixed paradigms often strengthen model generation but leave ensemble decisions static, weakening both execution reliability and the controlled use of structural diversity. This indicates that LLM-driven AutoML needs a closed-loop ability for trial-correction-improvement together with evidence-based use of model diversity. To this end, we propose SAGE-Loop, a reliable closed-loop, self-adaptive, LLM-driven AutoML framework that performs multi-round generation and validation for trial-and-repair, and adaptively selects ensemble strategies in both supervised and unsupervised tasks, thereby unifying how to generate with how to use models. Across 20 public datasets, SAGE-Loop consistently improves performance and stability on classification, regression, and clustering tasks. Additional results further show its ability to recover from execution failures and maintain robust pipeline behavior. --- ### Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images Authors: Juzheng Miao, Yuchen Yuan, Cheng Chen, Pheng-Ann Heng Published: 2026-09-11 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.12454v1 Vision-Language Models such as CLIP enable effective few-shot medical anomaly detection (AD) via strong image-text semantic alignment. However, their globally contrastive pretraining lacks explicit spatial supervision, limiting precise lesion localization. In contrast, Vision Foundation Models (VFMs) such as DINO learn spatially coherent patch representations via self-distillation and local-to-global consistency, better capturing fine-grained anatomical structures. Leveraging this complementarity, we propose Spatial-FAD, a spatial-aware few-shot medical AD framework that improves lesion localization by combining VFM spatial priors with CLIP semantics. Specifically, we introduce a VFM-enhanced adapter that injects a structural affinity prior derived from DINO into CLIP features. This structure-guided refinement encourages visual embeddings to better adhere to lesion boundaries while maintaining semantic alignment. To address the loss of spatial detail from patchification and the limited input resolution of CLIP, we adopt a sliding-window aggregation strategy. This generates high-resolution, spatially dense embeddings to further enhance localization granularity. Moreover, we introduce a prototype-enhanced support memory scheme to efficiently exploit the few-shot support set. This module stores compact prototypes for normal and abnormal patterns, reducing memory costs while boosting performance by fusing patch-to-prototype and image-text similarities. Extensive experiments on three benchmark datasets, including Liver CT, Retinal OCT, and Brain MRI, demonstrate that Spatial-FAD significantly outperforms state-of-the-art methods, especially in lesion segmentation. Notably, in the 4-shot scenario, our method achieves an average improvement of over 11.4% in Dice score and 1.8% in AUC. Code is available at: https://github.com/JuzhengMiao/Spatial-FAD. --- ### GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs Authors: Ahmed Sohair Khan, Estrid He, Chenglong Ma, Monica Wachowicz, Elham Naghizade Published: 2026-09-11 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2609.12448v1 Sensitive attributes such as age, income, and occupation can be inferred from user-generated content by aggregating indirect cues across many ordinary posts. LLM-based profilers can perform this aggregation automatically and with high accuracy, which makes large-scale personal attribute inference a major privacy threat. Existing LLM-based profilers, however, offer limited insight into which specific posts, concepts, and relationships made an inference possible, which is key to targeted privacy mitigation, i.e., redacting or rewriting only the few posts that actually leak an attribute, rather than perturbing entire histories. We introduce GraphProfiler, an auditable LLM-based profiler that represents each user's post history as a source-linked personal knowledge graph where nodes and edges trace back to the originating post and resolves attribute predictions to cited graph records and source texts. GraphProfiler reaches 86.7% attack success rate on the eight-attribute SynthPAI benchmark, within two points of strong text-only baselines, and 84.6% on PANDORA, while citing supporting evidence for over 98% of predictions. Our controlled ablation experiments provide evidence that the cited posts contribute to attack success, as removing them reduces the attack success rate substantially more than removing an equal number of random posts. --- ### Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf Authors: Yu-Yu Yang, Ti-Rong Wu, Hung Guei, Hsing-Yu Chen, I-Chen Wu Published: 2026-09-11 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.12446v1 Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We propose a belief-shift evaluation benchmark in Werewolf for analyzing communication skills through belief updating. Using LLM-played games, we annotate suspicion and accusation messages and measure how an observing village-side model's beliefs change after each message. We evaluate 40 open-weight LLM configurations on 1,224 annotated messages. Our results show that larger models better distinguish true wolves from villagers based on game history, but accusations still strongly influence their beliefs. Models become more suspicious of the accused target and less suspicious of the accuser, especially when the accuser is trusted, even if the accuser is wolf-aligned. Larger models better resist accusations from accusers they already distrust. Overall, our findings suggest that current open-weight LLMs up to 120B parameters still struggle to integrate accusation content with source trust in strategic communication. Our benchmark and code are available at https://rlg.iis.sinica.edu.tw/papers/werewolf-accusation-benchmark. --- ### Exact Community Recovery in Bipartite Networks Authors: Huan Qing Published: 2026-09-11 Categories: cs.SI, math.ST, stat.ML arXiv: https://arxiv.org/abs/2609.12445v1 Community detection in bipartite networks is a fundamental problem in modern data analysis, with applications in recommendation systems, biological networks, and social network analysis. Unlike conventional unipartite graphs, bipartite networks consist of two distinct types of nodes with edges only connecting across types, so recovering latent communities requires estimating labels on the two node types. The stochastic co-blockmodel is a classical probabilistic framework for such networks, yet theoretical guarantees for exact community recovery in this setting remain limited, especially when the number of communities grows, the community sizes are unbalanced, or the degrees are heterogeneous. In this work, we prove that a simple spectral clustering algorithm based on the diagonal-deleted Gram matrix achieves exact recovery with high probability under mild conditions on sparsity, community balance, and the number of clusters. We further extend the result to the degree-corrected stochastic co-blockmodel, where each node carries its own degree heterogeneity parameter, and show that a row-normalized version of the same algorithm maintains the exact recovery guarantee. Extensive experiments validate our theoretical findings. --- ### Diverse Minds, Divided Networks? Personality Composition, Polarization, and Collective Intelligence in LLM-Based Social Simulations Authors: Raad Bin Tareaf Published: 2026-09-11 Categories: physics.soc-ph, cs.CL arXiv: https://arxiv.org/abs/2609.12444v1 Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two are rarely measured in the same system. It is therefore difficult to say whether a society's personality composition shapes both, or whether reducing polarization costs collective competence. We present TraitMix, an experimental design in which the Big Five composition of a simulated social network, both trait levels and trait heterogeneity, is a controlled experimental variable, and in which polarization and collective performance are measured in the same runs. Across 991 simulations of hundred-agent societies, spanning six contested topics and six language models, trait heterogeneity has the largest measured effects, acting in opposite directions on two faces of polarization: varied societies hold more dispersed opinions while being less segregated into camps, so homogeneous societies are not moderate but consensual echo chambers. Trait effects are not additive, as Agreeableness determines the sign of Openness, an interaction that replicates across models although the primary model's estimate is influence-driven. Contrary to the trade-off the study was designed to measure, no polarization measure predicts poorer collective performance, and cross-cutting interaction is the only one of four whose association with collective accuracy survives partialling on the aggregation identity. We report ablations removing two potential measurement circularities, an induction gate applied to every model, and the measures that failed them. --- ### 3D Digital Twin Visualization of Multiclass GRF-Based Gait Disorder Classification Authors: Nayoung Son, Minwoo Shin Published: 2026-09-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.12442v1 Automated gait analysis requires accurate classification and interpretable outputs. We propose an integrated framework for classifying healthy gait and multiple musculoskeletal impairment groups using bilateral ground reaction force (GRF) and center-of-pressure (COP) signals. The signals were normalized over the stance phase and standardized using training-set statistics. The model achieved a validation accuracy of 99.00\% and a test accuracy of 90.07\% under a session-level split. Class-specific $ε$-LRP identified positive and negative contributions across both sides, multiple signal components, and different stance phases. Separately, the processed GRF signals and model predictions were synchronized within a Blender-based 3D visualization, enabling sample-level inspection of gait trials and classification results. The proposed framework integrates classification, explainability, and 3D visualization to improve model transparency. The source code is available in the following repository: https://github.com/nyoico/grf-gait-3d-visualization.git --- ### IMPLY: Physically Anchored Consistency for World-Model Rollouts Authors: Aman Mehta, Riya Baviskar Published: 2026-09-11 Categories: cs.RO, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.12441v1 A world model asked what happens if an object is pushed at several speeds produces several futures. If the model has the object in mind, those futures agree about it: each implies the same mass and friction. The consistency checks now used to vet world-action models ask whether a model's futures agree with each other, and none of them knows any physics. We show that this is not enough, and what to do instead. IMPLY reads the physics each rollout implies by inverting a simulator and scores a set of rollouts by how well one object explains all of them, anchored to two calibration pushes the model has observed. In a controlled setting, self-consistency gives a perfect score to a model that ignores the object and always predicts a typical push; anchoring exposes it (AUROC 0.70 versus 1.00). On a real model, V-JEPA 2-AC adapted to the scene, the same thing happens. Given its own calibration pushes the model tracks the object (per-object correlation with the truth 0.91); given another object's, it does not (0.05). Self-consistency cannot tell these apart, preferring the right evidence on 52% of objects, chance level, while anchored disagreement prefers it on 73% and correlates 0.92-0.99 with the rollouts' error. Used to choose among candidate rollout sets, it comes within 0.003 of an oracle that sees the truth. A model that has internalised the wrong object is exactly as self-consistent as one that has internalised the right one; consistency has to be anchored to evidence. --- ### Debiasing as a Measurement Intervention: Calibrated Ties and Resolution Loss in LLM-as-a-Judge Evaluation Authors: Liang Zhao, Yong Wang, Jiangzhe Chen Published: 2026-09-11 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2609.12439v1 LLM-as-a-judge protocols are commonly debiased by instructing judges to ignore presentation cues such as citation formatting, source labels, and evidence-display style. We show that this intervention can suppress bias while damaging the resolution of the measurement instrument. We introduce TraceJudgeBench, a diagnostic benchmark for auditing citation-like artifacts in RAG and agent-workflow evaluation, covering content-equivalent pairs, citation ablations, correctness conflicts, human-validated soft and moderate quality gaps, prompt-strength ladders, decoupled judging, and a controlled workflow-ranking probe. Across GPT-5.5, Claude Sonnet 4.6, and DeepSeek V4-Flash, stronger anti-citation prompts reduce worse-cited wins from up to 50.5% to 0%; yet some operating points already convert validated moderate-gap decisions into Tie before the strict stress-test endpoint, while correctness-conflict accuracy remains at or above 93.0%. A second, 50-pair FinQA moderate-gap construction reproduces the qualitative frontier, and open-weight Qwen2.5-14B-Instruct-AWQ and Gemma-3-12B-IT runs reproduce the central HotpotQA frontier. TRACE-style decoupling recovers 96.5-100.0% better-plain resolution across the reported settings. Human validation separates three meanings of Tie: correct equivalence Tie, calibrated soft-boundary Tie, and resolution-destroying Tie on validated quality gaps. We frame debiasing as a measurement intervention whose bias suppression, resolution retention, Tie cost, and protocol cost must be reported jointly. The supplementary artifact contains benchmark splits, prompts, raw judge outputs, validation summaries, and analysis. --- ### Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing? Authors: Qiaomu Li, Qiuyuan Zhang, Nong Ming Published: 2026-09-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.12437v1 Adaptive RAG often uses retrieval-time signals to decide whether another retrieval, reranking, or multimodal step should run. We ask whether these signals add routing value once the query itself is already known. Across document, audio, and video RAG, we compare matched query-only and query+retrieval routers while holding the optional actions, router family, training procedure, and evaluation fixed. On the held-out final evaluation, adding the tested retrieval signals does not produce a reliable routing improvement over the query-only baseline. Some retrieval signals are associated with whether a later step will help, but that predictability does not consistently lead to bet- ter RUN/SKIP decisions. The main lesson is therefore methodological: retrieval-state features should not be credited with routing value unless they improve over a matched query-only control. Our results do not show that routing or retrieval state is generally useless; they show that the incremental value of retrieval signals must be demonstrated rather than assumed. --- ### LifeFuse-Mem: Lifecycle-Aware State Fusion Against Temporary Overwriting for Long-Term Memory Authors: Hanyu Zhao, Yuqian Feng, Zhenyu Song, Yuanchao Cheng, Yance Jiao, Tengfei Pan, Li Du Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12436v1 Long-running LLM agents require memory mechanisms that maintain coherent internal states across interactions. We study a lifecycle-labeled memory setting in which write episodes provide lifecycle metadata during training, and phase-aware readout is used during evaluation. This setting reflects the need to distinguish information that should remain influential across future interactions from information that should affect only the current context. A mismatch between these lifecycles can cause temporary information to overwrite durable knowledge, leading to behavioral drift in persistent agents. Within this setting, we introduce \textbf{LifeFuse-Mem}, a lifecycle-aware neural memory framework that separates information according to its temporal commitment. LifeFuse-Mem uses dedicated memory components and lifecycle-aware updates to allow stable and transient knowledge to evolve locally without converting temporary context into durable state. On the controlled anti-overwrite benchmark, LifeFuse-Mem improves acquisition-controlled retention and reduces temporary overwrite; on two public long-memory benchmarks, it remains broadly competitive. These results suggest that explicit lifecycle signals can help diagnose and mitigate overwrite in compact online memory. --- ### Observation-Anchored Selective Assimilation for Longitudinal Tumor-State Proxy Forecasting in Post-Treatment Glioma Authors: Yeonjae Jung, Minwoo Shin Published: 2026-09-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.12435v1 Post-treatment MRI in patients with glioma provides serial observations for updating patient-specific tumor-state proxy estimates, but variable appearances and trajectories complicate forecasting. We formulate forecasting as an observation-aware digital-twin update in which an intermediate observation anchors the patient-specific state. Among 203 patients and 594 follow-up time points, a predefined no-new-treatment criterion retained 120 of 236 candidate triplets, split into 81/24/15 training/validation/test triplets at the patient level. Each time point was represented by a continuous voxel-wise tumor-state proxy map in (0,1) derived from MRI lesion labels. A SegMamba-based single-step forecaster predicted update proposals from multimodal source-state tensors. Observation-Anchored Selective Assimilation (OASA) retained the observed intermediate proxy as the state anchor and selectively applied updates through a validation-selected tiered case-level rule and voxel-wise soft gate. We compared initial-scan forecasting, rollout without assimilation, latest-observation persistence, direct prediction, OASA, OASA + calibration, and morphological dilation. Checkpoints, OASA rules, and calibration thresholds were selected using validation data only. Across three seeds on 15 held-out test triplets, OASA maintained Dice at $τ$ = 0.2 comparable to persistence (0.6071 $\pm$ 0.0025 vs. 0.6070) while yielding numerically higher Dice at $τ$ = 0.5 (0.4269 $\pm$ 0.0079 vs. 0.3981), with a small RMSE increase. Calibration increased Dice at $τ$ = 0.2 to 0.6178 $\pm$ 0.0025, increased false-positive (FP) support (11,836$\rightarrow$18,663), and reduced false-negative (FN) support (22,107$\rightarrow$17,536). This reflects near-threshold support calibration rather than improved biological predictive capability. Code is publicly available at https://github.com/jsudg436/longitudinal-proxy-forecasting. --- ### An End-to-End Automated Pipeline for Controllable Crack Data Synthesis Authors: Conghui Li, Muxin Pu, Chern Hong Lim, Weiyao Lin, Xin Wang Published: 2026-09-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.12431v2 Vision-based crack inspection depends on segmentation networks whose reliability depends on the quantity, diversity and label quality of their training data. Pixel-level annotations are costly, and crack images of specific structures are scarce. Generative augmentation can supply additional data, but existing methods address isolated steps. They reuse annotated masks, offer limited control over crack geometry, and adopt the conditioning mask as the label without checking it. This paper presents an end-to-end pipeline that produces labelled crack data without manual annotation and assesses the reliability of these data and of the detectors trained on them. Procedurally sampled Bézier skeletons with guaranteed geometric properties are converted into crack masks by a generative adversarial network (GAN). A dual-ControlNet Stable Diffusion model renders the masks as crack images, either on text-described surfaces or on user-provided backgrounds. An ensemble of segmentation networks trained on real images combines its agreement with the inherited label and its internal disagreement into a pixel-wise label confidence. This confidence weights the training loss instead of removing samples with a threshold. The trained detectors are evaluated with image-space probability of detection (POD) and calibration analyses. On CRACK500 and CrackTree200, the pipeline improves five segmentation networks over conventional, diffusion-based and flow-matching-based augmentation, and on CRACK500 confidence weighting yields a higher accuracy than threshold filtering at every tested threshold. On CRACK500, the crack width that U-Net detects with 90\% probability at 95\% confidence decreases from 8.0 to 4.3 pixels, and the expected calibration error decreases from 14.2\% to 9.6\%. --- ### Granularity-Adaptive Credit Assignment for Long-Horizon LLM Agent Reinforcement Learning Authors: Taoran Liang, Yang Liu, Shang Luo, Yingguang Yang, Rongrong Zhang, Yingzong Min, Yulin Huang, Jianshen Zhang, Yongzhi Qi, Kefu Xu, Congjing Ran, Bin Chong Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.12424v1 Reinforcement learning is now the standard way to train large language model agents on long-horizon tasks, where dozens of interdependent actions precede a single sparse reward. Critic-free, group-relative methods such as GRPO suit this regime, but they broadcast one trajectory-level scalar to every step and cannot say which decision drove the outcome. GiGPO recovers a step-level signal by grouping time steps that share an anchor state, yet it merges the step- and episode-level estimates under one fixed weight, spending the same resolution on a pivotal branching decision as on a routine, near-deterministic transition. We argue that the right resolution is state-dependent, and propose GACA, a critic-free estimator whose granularity follows an uncertainty-based criticality proxy. GACA scores every step by the negative log-likelihood its own rollout already records, then blends the two advantages with a per-step weight that grows with that score, so the gradient places more weight on the fine-grained signal at above-average NLL and on the episode-level signal below it. We derive an exact risk decomposition for the implemented mixture and show that sufficiently small modulation improves on fixed mixing under positive directional alignment. A separate conditional result bounds local action-value variation using expected NLL, while an error-projection analysis characterizes when mixing adds value beyond scalar uncertainty reweighting. On ALFWorld and WebShop, GACA improves task success over GRPO and GiGPO at both 1.5B and 7B scales. --- ### Hierarchical Belief Modeling for Zero-Shot Opponent Adaptation in Partially Observable Multi-Agent Navigation Authors: Kowei Shih, Lu Cheng, Zeyu Wang, Yeyun Xu, Kejian Tong Published: 2026-09-11 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.12422v1 Lux AI Season 3 requires agents to act under partial observability, randomized episode level dynamics, and a best of five match structure that rewards both tactical execution and fast adaptation. We present HORIZON, a hierarchical agent that combines symmetry aware spatial perception, dual memory belief tracking, relic centric graph attention, information gain driven exploration, and an opponent conditioned policy mixture. HORIZON separates short horizon control from cross match meta reasoning, while auxiliary belief and world model objectives stabilize learning. Trained with PPO in a large scale JAX simulator, the resulting agent explicitly infers hidden game parameters and opponent style. Experiments show consistent gains in match win rate, episode win rate, adaptation gain, and league rating over strong recurrent and feed forward baselines. --- ### Inference for Newton Methods with Accelerated Sketch-and-Project via Random Scaling Authors: Xinchen Du, Elizaveta Rebrova, Michał Dereziński, Sen Na Published: 2026-09-11 Categories: stat.ML, cs.LG, math.NA, math.OC, math.ST arXiv: https://arxiv.org/abs/2609.12421v1 We study an online sketched Newton method that approximates the Newton direction at each step via a state-of-the-art sketching solver, called the generalized accelerated sketch-and-project solver (GAS), thereby mitigating the computational bottleneck of classical second-order methods. The GAS solver improves upon vanilla, unaccelerated sketch-and-project solvers by achieving accelerated convergence through Nesterov momentum updates, and accommodates a flexible projection metric whose proper choice further reduces computational cost. Building on this design, we establish asymptotic normality of the averaged sketched Newton iterates and characterize their limiting covariance matrix. The resulting covariance recovers that of the unaccelerated sketched Newton method under a specific choice of acceleration parameters, converges more rapidly (in the number of sketching steps) to the minimax-optimal covariance in general, and is smaller than that of the last iterate produced by the accelerated method. Finally, we strengthen these results by establishing a functional central limit theorem for the Newton iterates, which allows us to bypass explicit covariance estimation and develop an online inference procedure based on random scaling. Specifically, we construct a pivotal test statistic by appropriately rescaling the averaged iterates, so that its limiting distribution is free of any unknown parameters, enabling asymptotically valid online inference. Numerical experiments demonstrate superior performance of the proposed inference procedure. --- ### MInTRL: Off-policy Intervention can boost On-policy RL Authors: Mingyu Chen, Yefan Tao, Gerald Friedland, Xuezhou Zhang, Chris Kong Published: 2026-09-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.12419v1 Reinforcement learning with verifiable rewards is typically performed on-policy, keeping training data close to the current policy but limiting learning to trajectories that the policy can discover itself. Off-policy methods such as supervised fine-tuning, on the other hand, can leverage external knowledge beyond the base model's capabilities, but may suffer from large distribution shift. The key challenge is thus to expand exploration without sacrificing learnability. In this work, we introduce Minimal Intervention Reinforcement Learning (MInTRL), which expands the exploration frontier through sparse, local interventions in otherwise on-policy rollouts. During generation, a judge-intervention policy periodically reviews the current policy's output, replaces erroneous suffixes with short corrections, and immediately returns control to the policy. During training, MInTRL adopts a sequence-level advantage-regression objective that eliminates the need for importance sampling. We show that sparse, local interventions can substantially improve coverage beyond finite-budget on-policy sampling while preserving the overall on-policy nature of the resulting trajectories. Across math and code benchmarks, MInTRL consistently outperforms standard on-policy and off-policy baselines. Ablations show that MInTRL remains effective with self-intervention and across different judge policies, while performance peaks at moderate intervention intensity, highlighting the importance of intervening minimally. These results establish minimal intervention as an effective paradigm for enhancing on-policy RL. --- ### RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search Authors: Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang Published: 2026-09-11 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.12418v1 Neural architecture search (NAS) evaluates candidate networks, but fully training enough architectures to rank an entire space is expensive. Zero-cost proxies score architectures at initialization, yet their ranking quality varies across search spaces. Learned predictors reduce evaluation cost but typically require fully trained labels or partial-training features for individual candidates. We introduce $\textbf{RiPPLE}$, $\underline{\textbf{R}}$anking v$\underline{\textbf{i}}$a $\underline{\textbf{P}}$refix-$\underline{\textbf{P}}$ropagated $\underline{\textbf{L}}$abel $\underline{\textbf{E}}$xtrapolation, which treats partial training as a source of labels for a small coverage set of anchors. RiPPLE trains these anchors to an early prefix, extrapolates their learning curves to surrogate labels, and propagates the labels over label-free architecture features. The early-training signal remains a label on the anchors rather than a per-candidate feature. Feature, readout, and encoding rules are selected without held-out accuracy and reused across search spaces. We evaluate the method on twelve benchmark cells from four search-space families and on the larger DARTS space. The results examine ranking quality, label efficiency, architecture selection, and the roles of readout, coverage, and propagation. RiPPLE provides a whole-space ranking from a fractional anchor-training budget, with comparisons interpreted under their respective evaluation and cost protocols. --- ### Spectral Consistency-Guided Multiview Point Cloud Registration for Low-Overlap Scenes Authors: Tianyu Li, Yanghong Lin, Shudong Zhou, Kui Yang, Jingru Zhang, Li Fang, Wei Yao Published: 2026-09-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.12417v1 Multiview point cloud registration is particularly challenging in low-overlap scenes, where reliable correspondences are limited and incorrect pairwise transformations can affect global pose estimation. In addition, registering all scan pairs is computationally expensive because many pairs provide weak geometric information. To address these problems, we propose GMPCR, a non-learning-based spectral consistency-guided framework for efficient and robust multiview point cloud registration. GMPCR builds a refined second-order compatibility structure from initial correspondences and uses its dominant spectral response to evaluate both correspondence reliability and scan-pair confidence. This allows unreliable correspondences to be filtered and informative scan pairs to be selected before relative transformation estimation, leading to a sparse pose graph and reduced pairwise registration cost. For each retained scan pair, maximal-clique-based hypothesis generation is used to estimate reliable relative transformations. The resulting pose graph is further refined by an adaptive history-aware synchronization scheme, in which the effect of residual history is adjusted according to changes in the global rotation residual. A recovery mechanism also allows down-weighted edges to regain confidence when their global consistency improves. Experiments on 3DMatch, 3DLoMatch, ScanNet, and ETH demonstrate the effectiveness of GMPCR. It achieves registration recalls of 97.2% and 89.6% on 3DMatch and 3DLoMatch, respectively, while maintaining competitive performance on ScanNet and ETH. The results show that GMPCR provides a favorable balance among registration accuracy, robustness to low overlap, and computational efficiency. The code is publicly available at https://github.com/swccj/gmpcr. --- ### SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration Authors: Md Jueal Mia, Yanzhao Wu, Selcuk Uluagac, M. Hadi Amini Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12413v1 Large language models (LLMs) are rapidly evolving from conversational assistants into agentic AI systems that reason, plan, invoke tools, maintain persistent memory, communicate with other agents, and execute multi-step tasks. At the same time, modern models exhibit substantially stronger native safety alignment than earlier generations on which many jailbreak attacks and defenses were originally studied. This shift raises a fundamental question: \textit{which established jailbreak-security findings remain valid in the era of modern LLMs and agentic AI?} We address this question through a Systematization of Knowledge (SoK) that reframes jailbreak security around the full agentic execution pipeline. We develop unified taxonomies of attacks and defenses spanning user interaction, planning and reasoning, memory, tool use, and inter-agent communication, and introduce a security--utility--efficiency evaluation framework that separates native harmful-prompt safety, adversarial jailbreak robustness, and agent-level security outcomes. We further conduct a controlled empirical study of representative attacks and defenses within a common agentic framework. Our results reveal three important gaps. First, strong native alignment does not imply robustness to adversarial jailbreaks. Second, defense effectiveness is highly model-, attack-, and component-dependent and can come at substantial cost in over-refusal, utility, and latency. Third, low final-response attack success can mask severe intermediate compromise: planning, memory, and tool interactions may remain unsafe even when the final response is successfully filtered. These findings motivate a shift from response-centric jailbreak defense toward cross-layer, execution-aware security that protects agent state, component transitions, and external actions while preserving practical utility and efficiency. --- ### HoliBench: A Cross-Platform Benchmarking and Deployment Toolkit for Foundation Models in CPS-IoT Applications Authors: Inesh Chakrabarti, Zejun Xiong, Pragya Sharma, Mani Srivastava Published: 2026-09-11 Categories: cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2609.12412v1 Foundation models, including large language models, vision-language models, and time-series foundation models, are increasingly deployed on embedded and edge platforms for CPS and IoT applications, where energy, latency, and memory are as critical as task accuracy. Existing benchmarking tools evaluate model capability in isolation, reporting accuracy assuming sufficient compute, while hardware profiling tools remain platform-specific and mutually incompatible. As a result, users lack a unified workflow for making deployment decisions across heterogeneous devices. We present HoliBench, a modular benchmarking and deployment toolkit that jointly characterizes accuracy, latency, and energy across platforms from single-board computers to GPU servers. Its platform abstraction layer calibrates cross-device measurement, and the toolkit supports multiple model modalities, inference engines, concurrencies, and existing evaluation harnesses. An interactive interface exposes constraint-aware configuration selection over a design space that is profiled once and reused across studies. Using HoliBench, we characterize 20 models across 7 device types, 3 quantization levels, 8 inference backends, and over 30 tasks, surfacing tradeoffs that existing tools miss: quantization reduces latency only on hardware with low-precision support, accuracy gains show diminishing returns relative to energy, and for autoregressive workloads, average inference power is approximately constant across output lengths. We further find that single-model profiles compose under sequential co-resident execution. In a multi-model CPS deployment, standalone profiles predict combined-pipeline latency and power within 1.2% and 2.5%, enabling deployment exploration without exhaustively profiling every pipeline configuration. We release HoliBench as open-source infrastructure for deployment-aware evaluation of foundation models. --- ### DERA: Detached Edge-Residual Adaptation for Prohibited item Detection Authors: Yonathan Michael, Mohamad Alansari, Mohammed Bennamoun, Dwarikanath Mahapatra, Andreas Henschel, Naoufel Werghi Published: 2026-09-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.12411v1 Prohibited-item detection in X-ray imagery remains challenging due to object superposition, weak texture, and material clutter which obscure both semantic appearance and object boundaries. We propose \textbf{DERA}, a \textbf{D}etached \textbf{E}dge-\textbf{R}esidual \textbf{A}daptation framework for prohibited item detection under X-ray imagery. DERA combines hierarchical visual features with a parallel pixel-difference edge pyramid and learns an object-specific boundary prior from training-time contours of the instance masks. The detached prior gates edge-sensitive features, which are injected into the early visual stages through residual heads. This staged design preserves the foundation detector at the start of adaptation, isolates boundary supervision from semantic feature learning, and restricts the final adaptation stage to only \(14.7\)K trainable parameters. Evaluated on PIDray, CLCXray, and STCray, DERA improves the baseline by \textbf{3.1}, \textbf{1.6}, and \textbf{2.4} AP points, respectively. --- ### A Multimodal Explainable Deep Learning Framework for Alzheimer's Disease Diagnosis using 3D Magnetic Resonance Imaging and Clinical Data Authors: Yusuf Brima, Marcellin Atemkeng, Lakshmana Rao Namamula, Antoine Vacavant Published: 2026-09-11 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2609.12410v1 Dementia is a major and growing global health burden, with Alzheimer's disease (AD) accounting for most cases. Timely and accurate diagnosis is central to managing this burden and increasingly depends on integrating complementary clinical and imaging information. Multimodal deep learning can combine these modalities for AD diagnosis, but how its explanations behave across modalities, fusion strategies, and cohorts remains unclear. We developed an explainable multimodal framework pairing a 3D CNN encoder for T1-weighted MRI with a feedforward network for harmonized clinical and demographic data, comparing varied model setups on three-way and pairwise diagnostic tasks using 6,479 internal records from the ADNI and 1,703 independent records from the OASIS-3. On ADNI, the tabular-only model achieved the highest three-class AUC-ROC of 0.879 and best discriminated cognitively normal (CN) versus mild cognitive impairment (MCI; 0.903), while cross-attention performed best for MCI versus AD (0.861); CN versus AD was highly discriminative overall. On OASIS-3, the vision-only model performed best (three-class AUC-ROC 0.910); CN versus MCI remained difficult, and no fusion strategy consistently outperformed single modalities across tasks and cohorts. SHAP and Integrated Gradients identified the MMSE as the dominant tabular feature in both cohorts, with global feature rankings agreeing strongly in ADNI ($ρ=0.94$) and OASIS-3 ($ρ=0.96$); CAM-based explanations, however, changed with model configuration and cohort. These findings show that multimodal performance and explanations are task, modality, fusion, and cohort-dependent: a dominant cognitive signal persisted across cohorts, but feature contributions and CAM explanations did not, underscoring the need to evaluate explainability under cohort shift rather than as a stable, intrinsic property. --- ### OphBiWSSD: Scaling Temporal Action Localization in Ophthalmic Surgeries with Bidirectional Weight-tied State Space Duality Authors: Yang Liu, Qionghong Ma, Joongwon Chae, Lihui Luo, Yibing Shen, Yulin Zhuo, Yingting Zhu, Jiashu Chang, Xiaoyun Zhong, Dongmei Yu, Peter E. Lobie, Peiwu Qin et al. Published: 2026-09-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.12409v1 High-frequency surgical maneuvers in ophthalmology necessitate high-fidelity temporal modeling, yet characterizing long-range procedural dependencies remains computationally prohibitive for attention-based architectures. Existing models often require aggressive temporal downsampling, which compromises the detection of fine-grained action boundaries and instrument-tissue interactions. To address these scalability constraints, we present OphBiWSSD, a framework that reformulates surgical temporal action localization leveraging Bidirectional State Space Duality. By employing a weight-tied selective scan mechanism that incorporates both preceding and succeeding surgical contexts, our approach facilitates the global synthesis of non-causal temporal cues with linear complexity. This streamlined architecture is well-suited to capture the bidirectional dependencies present in ophthalmic workflows, effectively bridging the gap between local boundary precision and long-range procedural context without incurring the quadratic memory overhead of traditional Transformers. Extensive experiments on the OphNet benchmark demonstrate that OphBiWSSD achieves state-of-the-art temporal localization performance, with mean Average Precisions of 44.42% on phases and 43.08% on operations, surpassing the baselines by 6.80% and 6.66%, respectively. Empirical validation indicates that our approach ensures precise temporal localization and offers a computationally viable pathway for deploying surgical intelligence systems in clinical environments. The code is publicly available at https://github.com/yo3nglau/OphBiWSSD. --- ### GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes Authors: Yu Xie, Bangshu Xiong, Zhibo Rao, Rui Gan, Chongxuan Liu, Zechu Ouyang Published: 2026-09-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.12408v1 Hazardous-freight operations at petrochemical logistics nodes are safety-critical for intelligent transportation systems, yet existing vision benchmarks rarely address procedural compliance under realistic deployment constraints. In large infrastructure networks, cameras often operate under sparse round-robin polling, so transfer status must be inferred from incomplete observations and localized evidence. We present GSO-Net, a large-scale benchmark for visual understanding of standard operating procedures (SOPs) in petrochemical unloading scenarios. To our knowledge, GSO-Net is the first public benchmark dataset dedicated to visual SOP understanding in petrochemical hazardous-freight transfer scenarios. It contains over 50,000 independently sampled frames from 64 real expressway petrochemical logistics nodes and adopts an SOP-derived hierarchy linking 9 macroscopic procedural steps with 15 microscopic operational states. Two tasks are defined: joint detection of microscopic states and macroscopic steps as the core benchmark, and frame-level step classification as a diagnostic reference. Experiments with lightweight, transformer-based, open-vocabulary, and holistic models reveal a clear gap between object perception and transfer-stage understanding. Current models remain weak on contact-level state grounding, transient step recognition, and stage consistency, especially under sparse polling, tiny critical targets, and long-tailed operational evidence. GSO-Net provides a practical benchmark for fine-grained state perception and vision-based safety monitoring in hazardous freight transportation. The dataset is publicly available at https://github.com/yuxieHarrison/GSO-Net --- ### VRL-Bench: Benchmarking agents on computer control tasks under finite trial budgets Authors: Yu Bai, Yukai Miao, Dawei Wang, Li Chen, Yanyu Ren, Yuqian Shi, Dan Li, Ying Xiong, Chengqiu Tan, Run Zhou, Li Li Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12404v1 Learning from trial and error is a promising way to improve language agents on complex tasks such as computer control. Reflexion introduced verbal reinforcement learning, which turns failed trials into text that guides later attempts without updating model parameters. We introduce VRL-Bench, a harness for fair evaluation of trial-and-error learning under finite trial budgets. Across three models on MiniWoB and WebShop, we evaluate updates from several prominent verbal-memory methods spanning Reflexion and later work: each improves observed success over memory-free retry in some settings but reduces it in others. Replay experiments show that using reflection can reduce success rates, revealing a trade-off between exploiting experience and continued exploration. We propose VEX$^2$, a verbal exploration--exploitation scheduler that uses a language model to jointly select policies and allocate the remaining trial budget. VEX$^2$ is the only evaluated update to achieve positive observed success-rate gains over retry in all six settings. --- ### Beyond ID Embeddings: Process-Grounded Language Modeling for Cognitive Diagnosis Authors: Minghang Liu, Yuanzhuo Wang, Qiang Qiu, Huawei Shen, Xueqi Cheng Published: 2026-09-11 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.12403v1 Cognitive Diagnosis Models (CDMs) play a pivotal role in personalized online learning. Traditional CDMs rely on discrete, ID-based embeddings to represent students, exercises, and concepts. This paradigm diverges from the nature of learner cognition, where knowledge is not stored and retrieved as isolated symbols. As a result, CDMs suffer from semantic limitations when new exercises or concepts appear. In this paper, we propose a Process-aware Language Cognitive Diagnosis (PLCD) framework that uses language-derived structures as cognitive priors and response records to calibrate student posterior states. PLCD leverages large language models (LLMs) to construct concept schemas and cognitive process graphs, and uses target-conditioned semantic memory to retrieve historical responses that are relevant to each target exercise. A process-grounded Language-to-Cognition Mapper with DA-MoE experts and process-level contrastive learning then maps the textual evidence into a unified cognitive space. Experimental results show that PLCD not only outperforms traditional baselines in predicting student performance but also exhibits strong cognitive transfer capabilities. These results connect the computational power of LLMs with the psychometric goal of measuring latent knowledge states, suggesting that structured language priors calibrated by response records can improve cold-start robustness and cognitive grounding. --- ### Decentralized Evolution of Hexapod Gaits with Independent Leg Controllers Authors: Gary B. Parker, John Asaro, Jim O'Connor Published: 2026-09-11 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.12400v1 This paper presents a novel approach to hexapod locomotion by evolving each leg's gait independently through a decentralized evolutionary algorithm. Using the Webots simulator and the Mantis hexapod robot, we optimize individual leg controllers without centralized coordination, allowing emergent behaviors to drive the development of efficient, coordinated locomotion. Our decentralized method is benchmarked against cooperative coevolution, demonstrating improved efficacy in generating stable and adaptive gaits while showing interesting emergent coordination. By enabling independent evolution of leg controllers, this method reduces the complexity of gait optimization and highlights the potential of decentralized strategies for scalable and adaptive robotic systems. --- ### OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation Authors: Xiangrui Yang, Cheng Peng, Yunfeng Zhao, Liang Zeng, Ao Hu, Jiawei Yang, Shengzhe Wang, Jingshan Lv, Xiao Liang, Chen Yang, Jiaqiang Liu, Yiming Qiu Published: 2026-09-11 Categories: cs.AI, cs.DC, cs.IR arXiv: https://arxiv.org/abs/2609.12399v1 Generative recommendation (GR) relies on large-beam decoding to generate hundreds of candidate items, creating a new scaling challenge for recurrent linear attention. Existing linear attention serving systems either materialize a full recurrent state for every beam or repeatedly replay shared history, incurring substantial memory and traffic overhead. To address this, we present OneLA, a linear-attention decoding framework that exploits the shared prompt and short divergent suffixes of GR workloads. Specifically, OneLA represents all beam states using a single shared prompt-derived state and compact, append-only records of their divergent transitions. Using this representation, OneLA computes only the state information required at each decoding step, without reconstructing a full recurrent state for every beam. Furthermore, OneLA uses a lightweight ancestry index to track the transition records that make up each beam's history, allowing beams to be updated without moving or copying existing records. A fused GPU kernel further reuses the shared state across beams. Our analysis shows that OneLA achieves 1.54-2.46x end-to-end decode speedups while substantially reducing recurrent-state memory use and data movement. --- ### Niching Agents in The Core Authors: Gary B. Parker, Jim O'Connor, John Asaro Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12398v1 The Core is a unique competitive co-evolution algorithm that allows agents to evolve autonomous control without utilizing a traditional fitness function. The agents evolve via local interactions through tournament selection, crossover, and mutation, producing offspring by evolving better controllers. Previous works have shown The Core's ability to evolve agents capable of combat and navigation in the Xpilot video game. This research expands upon that premise by niching agents to specific subsets of the original environment The Core was tested in. Our results demonstrate the niched agents capacity for success over agents niched to the entire system and agents niched to different sub-environments. --- ### UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation Authors: Danning Zhang, Yijing Lin, Shuhan Zhuang, Mengqi Huang, Shaojin Wu, Shancheng Fang, Zhendong Mao Published: 2026-09-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.12397v2 Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years. Despite the rapid advancement of generative models, their evaluation remains largely lagging. Existing methods, whether embedding-based or Multi-modal Large Language Model (MLLM)-based, evaluate alignment with each modal condition in isolation, which contradicts the simultaneous condition alignment objective of multi-modal image generation, leading to poor consistency with human judgments. To address this challenge, we propose UFO, the first unified framework for omni-condition alignment simultaneous evaluation. Specifically, UFO introduces a novel Atomized Chain-of-Evaluation paradigm, i.e., it first decomposes omni-condition alignment into a sequential chain of fine-grained, disentangled Atomic Evaluation Units (AEUs), categorizes them into distinct modality-relevance classes, and then employs general or dedicated functional calls for accurate verification of different AEU types. Experimental results demonstrate that UFO achieves the highest correlation with human evaluation preferences, delivering an average improvement of 15.25%. Furthermore, we present UFO-Bench, a dedicated benchmark designed to holistically evaluate the performance of existing customization models under the diverse mutual interactions of textual and visual conditions. --- ### Is Gaussian Splatting Becoming Neural Again? A Taxonomy and Controlled Study of Learned Parameterization Authors: YuanHang Wang, Xin Cao, Yi Zhang Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12395v1 Three-dimensional Gaussian Splatting (3DGS) combines explicit primitives with efficient rasterization, yet recent systems increasingly use neural networks to generate or share Gaussian parameters. We characterize this trend along five axes: attribute decoding, spatial sharing, view-conditioned decoding, topology generation, and amortized inference. An analysis of 19 representative methods shows that these choices address different limitations and cannot be reduced to a binary neural label. We also isolate three forms of neural parameterization in a controlled mip-NeRF 360 study. Sharing appearance and opacity improves reconstruction quality, while decoding geometric structure offers no further gain. The evidence favors selective neuralization: shared functions help when they capture reusable correlations without sacrificing the local geometric freedom of explicit splats. --- ### BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents Authors: Tong Ye, Kunyang Han, Guozhi Wang, Longqiang Luo, Zhifeng Ding, Yongxiang Zhang, Xiaolei Shen, Yuxuan Zhang, Zhuping Zhang, Tao Xu, Yue Pan, Yucheng Zhao et al. Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12394v3 Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent gaps. Sandbox training produces a distribution mismatch with production environments; expensive real-device failures remain underutilized; and fixed benchmarks saturate, losing the power to guide iteration. We present BlueLM-GUI, a 35B-A3B mobile GUI agent built as a real-device-centric flywheel that closes these gaps through three principles. Every Sample Matters: a dual-track pipeline with Heterogeneous Triple-System Consensus evaluation and an Error Correction \& Derivation Module salvages every trajectory into usable supervision. Every Rollout Is Real: a three-stage recipe---continual pre-training, supervised fine-tuning, and agentic reinforcement learning on hundreds of real phones---grounds every rollout in real production environments, so the capability the model learns transfers directly to deployment. Every Query Evolves: a quota-driven benchmark methodology with three orthogonal axes enables precise attribution and allows the benchmark to be systematically upgraded as the model improves. BlueLM-GUI achieves 87.4 on MobileGUI-VBench, surpassing the best closed-source model by 5.1 points, and 84.9 on AndroidWorld, the best result among open-source models and competitive with closed-source models. These results demonstrate that grounding model training and iterative improvement in both real devices and the three Every principles yields strong, robust, and transferable mobile GUI capability. --- ### RF-VoID: Towards Bandwidth-Efficient Exterior Tile Void Detection via Narrowband Radio-Frequency Representation Learning Authors: Xinyan Chen, Ruiqin Ma, Shunsuke Shoda, Changyu Zhou, Ryo Natsuaki, Akira Hirose, Jianfei Yang, Li Yi Published: 2026-09-11 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2609.12388v1 Hidden debonding behind exterior ceramic tiles is a falling-tile hazard, and millimeter-wave radar offers a non-contact way to find it. Conventional interpretation first reconstructs a range profile, so its reliability is bounded by the available bandwidth, yet bandwidth is what sets the cost, the acquisition time, and the regulatory footprint of a deployed system. This work asks whether that bandwidth can be traded for computation. A 4-40 GHz stepped-frequency system scans twelve exterior-wall specimens containing 0.5-1.0 mm air voids at different depths and interfaces, and the bandwidth dependence of A-scan, B-scan, and C-scan interpretation is analyzed to establish the resolution bound. RF-VoID is then proposed, which decides directly on the narrowband complex response: the sub-band is kept in its measured frequency order with amplitude and phase alongside the in-phase and quadrature channels, a dual-branch encoder reads it along the physical frequency axis using relative position encoding and a distance-dependent locality bias, and an inspection-oriented objective handles the class imbalance and the asymmetric error cost of facade screening. Under a mixed-sample protocol the method attains 98.61% accuracy and a 95.84% F1-score with 0.5 GHz of bandwidth, a seventy-two-fold reduction relative to the full sweep, without range-profile reconstruction, deconvolution, or depth-slice selection; on specimens held out entirely from training it remains the strongest of the compared models, with a mean macro F1-score of 62.12% at 0.5 GHz that rises to 68.57% at 1 GHz. --- ### Split Conformal Prediction with Label-Shift-Adjusted Bayesian Scores Authors: Hyeonsu Lee, Juyeon Kim, Erkhembayar Jadamba, Seungjin Choi, Hyunjin Shin Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.12386v1 Conformal prediction provides distribution-free uncertainty quantification under exchangeability. However, this assumption is violated by label shift, where the marginal distribution of labels changes while the conditional distribution of inputs given labels remains stable. Under such shifts, standard conformal procedures no longer maintain their intended coverage behavior. Existing approaches address this via importance weighting. They pair the reweighting with residual-based nonconformity scores that ignore predictive uncertainty. The resulting intervals have uniform width. Bayesian conformal methods produce adaptive intervals by leveraging predictive distributions. They evaluate conformity under the source predictive, which is misaligned with the target domain under label shift. We propose the \emph{Label-Shift-Adjusted Bayesian Score} (LSA score), a nonconformity score derived from a posterior predictive tilting identity. This identity shows that the target predictive is an importance-weighted transformation of the source predictive. We use it to derive a direct correction to the Bayesian score. We evaluate the method on molecular property prediction under controlled label shift. The LSA score consistently yields shorter intervals than residual-based and source-based Bayesian scores. Coverage in the target domain remains comparable. Under stronger shift, all methods incur some coverage loss due to pseudo-label-based density-ratio estimation. The LSA score is defined for any source predictive with a tractable log-density. We instantiate it with Bayesian Ridge Regression, where the correction admits a closed form. --- ### Representation-based Masked Diffusion Model Authors: Yangrong Hu, Ding Huang, Xueyu Zhou, Jian Huang Published: 2026-09-11 Categories: cs.CL, stat.ML arXiv: https://arxiv.org/abs/2609.12382v1 Masked Diffusion Models (MDMs) have emerged as a compelling paradigm for language modeling, offering the capability for efficient parallel text generation. However, existing parallel sampling methods typically update multiple masked tokens independently and ignore the complex mutual dependencies among the masked tokens. This independent updating mechanism lacks global coordination and might lead to incoherent outputs. To address this limitation, we propose Representation-based Masked Diffusion Model (RMDM), a framework that leverages the text representation to explicitly encode global semantics and help to parallel update tokens more precisely. Specifically, we first encode text into a continuous semantic space using a pretrained encoder and learn an invertible transformation that normalizes the representation distribution to a Gaussian prior, facilitating efficient sampling during generation. Conditioned on this latent semantic representation, we train a masked diffusion model to learn the conditional text distribution, where the representation serves as global semantic guidance to coordinate parallel token updates and faithfully approximate the target distribution. Empirical results demonstrate that RMDM significantly improves generation quality, particularly in aggressive few-step sampling regimes. --- ### Context-Aware Causal Gaze Forecasting for Human-Vehicle Interaction During In-Cabin Tracking Dropouts Authors: Shabnam Shabani, Ghazal Farhani Published: 2026-09-11 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2609.12374v1 Dashboard-mounted gaze trackers often lose sight of the driver's eyes during large head rotations, including shoulder checks, mirror glances, and intersection scanning. These maneuvers occur when information about the driver's visual attention is most useful. Offline gap-filling methods may reconstruct a missing interval using observations from both sides, but an online driver-monitoring system cannot rely on measurements that have not yet occurred. We therefore formulate causal gaze recovery: forecasting unavailable gaze at time t without target-tracker gaze at t or later. We introduce the Causal Context-Gated Forecaster (CCGF), which encodes a 60-frame pre-dropout history of gaze and head pose and combines it with DINOv3 scene features. A learned reliability gate controls the contribution of the history and scene representations as the dropout progresses. We evaluate two scene conditions: Live, in which the scene representation continues to update during tracker loss, and Frozen, in which the final pre-dropout representation is used throughout the missing interval. We evaluate CCGF on 2,047 eligible, naturally occurring GazeSense head\_lost events drawn from 10.5 h of naturalistic driving by ten drivers. Across all recordings, head\_lost accounts for 8.5 percent of GazeSense recording time. Synchronized gaze coordinates from a head-mounted Neon tracker provide supervision and evaluation targets but are never used as model inputs. Under leave-one-driver-out evaluation, CCGF achieves a mean per-driver median error of 175.7 px (10.5 deg) with Live scene updates, a 33 percent reduction relative to history-only causal forecasting. With Frozen scene input, the error increases to 210.8 px (12.9 deg), indicating that scene observations acquired during the dropout provide useful predictive information. We will release the dataset, evaluation protocol, and causal baselines. --- ### Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue Authors: Youyuan Zhang, Siyuan Li, Fangming Liu, Jing Li Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.12373v1 Persona drift remains a central challenge for personalized language models, as user profiles evolve over long interactions rather than remain permanently fixed. Models must therefore revise persistent persona states when preferences genuinely change, while avoiding updates driven by transient, ambiguous, or unresolved observations. We propose CORE, which separates turn-local evidence from persistent persona-state revision and selectively updates grounded user preferences through uncertainty-aware belief revision. We also introduce PERSIST, a held-out post-anchor benchmark for persona-state robustness under sequential interaction stress, covering ambiguity, conflict, and controlled social influence. Across ALOE, PersonaChat, and PERSIST, CORE improves personalized alignment and robustness, with complementary gains in normalized closed-slot state fidelity. Human evaluation and mechanistic controls further support explicit update control beyond stronger generation or persistent memory alone. --- ### Membership Inference via Pairwise Likelihood Ratios Authors: Shengjie Niu, Zebin Yun, Yeheng Ge, Jian Huang Published: 2026-09-11 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.12367v1 Membership inference attacks (MIAs) are the standard tool for auditing the privacy risks of machine learning models. Given a query point, an MIA aims to determine whether that point was used to train the target model. In practice, such inference must rely on the statistical signals exposed by the model's outputs, such as confidence scores, logits, and intermediate feature representations. However, existing methods often fail to efficiently summarize and combine these statistical signals. To address this limitation, we propose Pairwise Likelihood MIA (PL-MIA), a unified method that combines a Gaussian likelihood-ratio (GLR) statistic with population calibration and the Cauchy combination test. We characterize theoretically how the GLR retains variance-contraction signals and establish conditions under which population calibration and Cauchy combination improve attack power. We obtain $p$-values from pairwise comparisons between the query point and reference points not used for training, and aggregate these continuous signals using the Cauchy combination test. This preserves the evidence strength that is discarded when each pairwise comparison is reduced to a binary vote. Extensive experiments demonstrate that PL-MIA outperforms strong baselines, improving the true positive rate (TPR) by over 25\% in the critical low-false-positive regime, corroborating our theoretical findings. These results demonstrate how statistical principles can turn noisy model outputs into more powerful, calibrated, and reproducible evidence for membership privacy auditing. --- ### ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge Authors: Shreyas Krishnan, Serina Chang, Abhishek Nagaraj Published: 2026-09-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.12366v1 We present ORQA, a method for testing occupation-level knowledge in large language models. Prior methods either map abstract LLM skills to occupations via task definitions or utilize expert knowledge which is difficult to obtain at scale and expensive. ORQA complements both of these methods by connecting O*NET occupations to trusted occupation-specific websites (such as regulatory agencies, licensing bodies, professional organizations, and government publications) and converting these into source-traceable question-answer pairs. A combination of an automated pipeline and human review produces a set of high quality questions about occupations. The question set created via our method covers 116 occupations from all 21 major groups in the SOC, with 480 questions sourced from 187 different websites. Each question is designed to probe a real-world skill question that is relevant to the occupation in question. We test 15 state-of-the-art frontier and open-weight models via this method. Claude Opus 4.6, GPT-5.4 and Claude Sonnet 4.6 all perform the best at approximately 58-62% while smaller open-weight models achieve approximately 33-41% performance. Performance varies significantly across occupations. Healthcare-related occupations achieve the highest performance (78%) while Office and Administrative Support achieve approximately 40%. Performance on individual occupations (e.g. Sheet Metal Workers and Fish and Game Wardens) is essentially zero. We also find that open-ended questions and weighting by wage bill do not significantly affect the ranking of models on this benchmark. We believe that leveraging existing trusted occupation-specific information to test LLM knowledge in professional domains may be a scalable and useful method for evaluating occupation-level AI performance in the future. Results and data are available at orqabench.org. --- ### Certified AI Triage of ICU Alarms Authors: Mohammed Sameer Syed, Rozhin Yasaei Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.12365v1 In the VTaC benchmark 71% of ventricular-tachycardia alarms are false, but silencing a real one can delay recognition of a dangerous arrhythmia. We reframe alarm reduction as three-way triage (retain, suppress, or defer) and bound the decision this analysis treats as harmful: among suppressed alarms, the fraction that were genuine stays below a user-set budget with 95% confidence, under i.i.d. event sampling. Alarms sharing a waveform record are dependent, so the clustered analysis is a sensitivity check. On the official split a 5% budget certifies in all three seeds, suppressing 74.8% of false alarms while silencing 1.5% of genuine ones, at AUROC 0.953 and Challenge Score 83.33, numerically comparable to the strongest of the eleven published systems. Our central finding measures what multiplicity costs: the correction charges for every candidate, so a finer grid can certify strictly less. Under held-out calibration the 885-cell grid we declared certifies 1 of 15 fold-runs, while choosing the grid on a separate selection partition certifies 8. We project the calibration volume each budget needs, making an uncertifiable budget a design parameter. Finally, adding a learned reliability dimension to the policy grid did not sharpen the certified frontier. --- ### LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations Authors: Majd Alafrange, Samuel Friedman, John Kitonyo, Sana Tonekaboni, Mahnaz Maddah Published: 2026-09-11 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2609.12364v1 Latent embeddings have become a central data abstraction in modern machine learning, especially in biomedicine, where foundation models are increasingly used to encode multimodal data like clinical text, medical images, omics, and physiological signals. However, the utility and value of these representations depends on understanding their quality, structure, and the information they encode. Existing analysis workflows for evaluating representations remain fragmented across custom scripts, isolated metrics, and most importantly lack multimodal analysis, limiting accessibility and reproducibility. We present LatentVerse, a representation analysis resource that combines a web-based visual analytics platform for accessible, report-driven exploration with a command-line interface for scalable technical workflows. LatentVerse unifies diagnostics for various representation quality metrics and extends to multimodal settings by decomposing embeddings into shared and modality-specific components. We evaluate LatentVerse through controlled unimodal and multimodal simulations, discovery-oriented analyses on real biomedical embeddings, and a user study across diverse use cases. By supporting thorough and interpretable evaluation of latent spaces, LatentVerse makes foundation model representations more understandable in biomedical and data science applications. --- ### When Connected Does Not Mean Similar: Charting the Homophily Boundary of SNAP-KG for Streaming Entity Integration Authors: Jui-Chien Lin, Oshani Seneviratne Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.12356v1 SNAP-KG is a framework for assigning newly arriving entities to semantic communities in a growing knowledge graph (KG) using only their raw features, with no graph access and no retraining at inference time. It was evaluated on five multi-view benchmarks and a 2.4M-node OGB-WikiKG2 KG. In each of these datasets, at least one graph view is homophilous, meaning that connected nodes usually belong to the same class, and SNAP-KG performs well on all of them. This paper asks what happens outside that setting. We extend the evaluation to three heterophilous graphs (Texas, Wisconsin, Chameleon) and measure the edge homophily of every view. When no homophilous view is available, clustering quality drops sharply for both SNAP-KG and the transductive baselines used in its original evaluation. What decides this is the homophily of the relation, not the number of relations. Multi-view fusion still helps, but only when at least one homophilous relation provides a reliable foundation. The homophily assumption is therefore shared by the whole method family, not specific to SNAP-KG. We argue that heterophilous multi-view clustering is a separate research problem, outside the scope of this work. As future work, we outline how a heterophily-aware teacher could be distilled into SNAP-KG's projector to serve both homophilous and heterophilous KGs. --- ### CueMem: Cue-Guided Context Reconstruction for Long-Term Conversational Memory Authors: Changjian Wang, Rongzhen Li, Weili Guan, Shuming Shi, Quan Lu, Ning Jiang Published: 2026-09-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.12354v1 Long-term conversational agents must answer user queries by recalling information from extended dialogue histories, yet directly using the full history is costly and often unreliable, while compressed memory units may lose fine-grained evidence needed for question answering. Motivated by the reconstructive view of autobiographical memory, we propose CueMem, a cue-guided framework that treats extracted memory records as retrieval cues rather than self-contained evidence and reconstructs query-relevant dialogue context from their source turns. During memory construction, CueMem extracts fine-grained memory cues from dialogue turns and links each cue to its source turn. At query time, it retrieves query-relevant cues, maps them to source-turn anchors, and expands from these anchors over a turn graph that captures temporal proximity and semantic relatedness, reconstructing a compact evidence context from the original dialogue for LLM answer generation. Experiments on LoCoMo and LongMemEval show that CueMem consistently outperforms representative long-term memory baselines. Further analyses show that graph-based context reconstruction helps recover supporting dialogue evidence while reducing query-time input tokens and latency compared with the full-history LLM setting. These results highlight retrieval cues as an effective alternative to self-contained memory evidence for long-term conversational question answering. ---