# Research Papers — 2026-10 · bundle page 123 of 156 > Full-text markdown of papers #6101–6150 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/123 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/122.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/124.md) ### NeuroCBIR: A Fast and Accurate Image Retrieval System for Whole-Brain and Region-Specific MRI Authors: Felix Nieto-del-Amor, Jingru Fu, J. -Sebastian Muehlboeck, Eric Westman, Daniel Ferreira, Rodrigo Moreno Published: 2026-10-05 Categories: cs.CV, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2610.06502v1 Content-based image retrieval (CBIR) in neuroimaging enables the identification of structurally similar brain scans, supporting diagnosis, prognosis, and treatment planning; however, existing methods are often limited to small datasets, single brain regions, or coarse class labels, thereby restricting their clinical utility and generalizability. Here, we present NeuroCBIR, a framework for fast and flexible retrieval of both whole-brain and region-specific 3D T1w MRI scans. A total of 103 cortical and subcortical regions are extracted to enable both whole-brain and region-level queries. NeuroCBIR leverages latent representations learned by a variational autoencoder (VAE) combined with contrastive learning, producing scan-specific embeddings that capture anatomical patterns. These embeddings were evaluated for subject re-identification, zero-shot age prediction, and zero-shot multi-class pathology stratification. Re-identification performance was high across both whole-brain and brain-region levels (mean average precision across the top-5 retrieved images (mAP@5) >= 98.4%), with robust generalization across datasets and acquisition conditions. While NeuroCBIR is not trained for age prediction or pathology stratification, zero-shot evaluations for these two tasks demonstrate that the embeddings encode meaningful information for downstream tasks. Embedding extraction on a 4-core CPU required approximately 18.7 s per scan, whereas similarity search was effectively instantaneous (less than 0.01 s). NeuroCBIR is publicly available for brain MRI with more than 26,000 precomputed T1w MRI embeddings. It supports reproducible research, region-specific flexibility, and clinically meaningful personalized diagnostic support. The software is available at https://github.com/minnelab/NeuroCBIR. --- ### You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue Authors: Junle Chen, Wei Chen, Zhengjun Huang, Zhoujin Tian, Yuxuan Liu, Kai Wang, Rui Chen, Xiaofang Zhou Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06496v1 When a large language model handles a multi-turn task and a user proposes a change but ultimately rejects it, the model should continue as if nothing changed. We find a surprising failure: merely mentioning a rejected change can derail task execution, even when the user's final intent remains unchanged. To systematically study language model behavior under evolving user intent, we introduce Intent-Eval, a controlled benchmark spanning tool actions, code, databases, and mathematics. Across diverse tasks, models are vulnerable to both rejected proposals and superseded requirements, consistent with mentioned-as-in-effect confusion: conversational content is treated as active requirements even after it has been rejected or replaced. Accuracy degradation can deepen or persist as interaction continues, highlighting the need to distinguish what has been mentioned from what remains in effect. Building on this insight, we propose Intent-OPSD, a decision-conditioned on-policy self-distillation framework with Teacher and Student initialized from the same model. The frozen Teacher provides active-intent supervision from the complete task matching the user's decision, training the Student on the full dialogue to follow active requirements reflecting user intent. --- ### Topology-Informed Prompt-Conditioned Universal Segmentation of Uterine Structures from Ultrasound and MRI Authors: Yongheng Sun, Yuexi Gu, Jingwen Sun, Maureen Kohi, Mingxia Liu Published: 2026-10-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.06494v1 Multi-structure segmentation of the uterus is important for computer-assisted screening, diagnosis, and treatment planning of uterine diseases, where ultrasound and MRI provide complementary clinical information. However, developing a unified model across these modalities is challenging due to their substantially different image appearances, anatomical contexts, spatial resolutions, and label spaces. Moreover, existing datasets often define different segmentation targets, making joint learning challenging and potentially leading to negative transfer across heterogeneous tasks. To this end, we propose a Topology-informed Prompt-conditioned Universal Segmentation (TPUS) framework for segmenting multiple uterine structures across ultrasound and MRI. TPUS introduces a graph-based multi-dataset backbone comprising modality-specific stems and a modality-shared graph-based encoder-decoder to support modality-sensitive input adaptation, structural feature reasoning, and joint representation learning across heterogeneous uterine segmentation tasks. In addition, TPUS uses task-aware class prompts to condition the segmentation process for different datasets and label spaces, a dynamic convolutional adaptation module to generate task-specific output responses, and a topology-informed loss to encourage anatomically consistent predictions. Experiments on a uterine ultrasound dataset and a T2-weighted uterine myoma MRI dataset demonstrate that TPUS achieves Dice scores of 0.898 and 0.693 on the two held-out test sets, respectively, outperforming several generic and universal segmentation baselines. Source code can be accessed at https://github.com/YonghengSun1997/TPUS. --- ### polyview: A Python package for multi-view machine learning Authors: Gwendal Debaussart-Joniec, Argyris Kalogeratos Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06491v1 Multi-view learning jointly exploits multiple complementary representations of the same data and has become increasingly important in machine learning. However, the Python ecosystem lacks actively maintained, unified tooling for end-to-end multi-view workflows. In this paper, we present polyview, a Python package that provides tools for multi-view embedding, clustering, fusion, and view augmentation, as well as for handling incomplete views, all compatible with scikit-learn. The library offers a unified interface for composing heterogeneous multi-view workflows, including seamless transitions between multi-view and single-view stages. It is built around a core set of classes and utilities that enable composition of different methods and straightforward implementation of new ones. We illustrate the package on five real multi-view datasets and compare its components based on canonical correlation analysis with those of two established libraries. polyview aims to be both a practical toolkit for benchmarking and prototyping multi-view methods and a foundation for future research and development in this area. --- ### GPlaceRL: An Open-Source Graph Reinforcement Learning Framework for Detailed Placement Authors: Pavlos Stoikos, Foteini Oikonomou, Christos Poulos, Maria Pantazi-Kypriou, Athanasios Tziouvaras, Christos Anagnostopoulos, Georgios Karakonstantis, George Floros Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06489v1 Reinforcement learning (RL) has emerged as a promising approach for placement optimization, particularly when combined with graph neural networks (GNNs) that capture circuit connectivity. However, most learning-based placement approaches focus on floorplanning, macro placement, or global placement, while detailed placement refinement remains relatively unexplored. In this paper, we present GPlaceRL, an open-source graph reinforcement learning framework for detailed placement refinement. GPlaceRL represents legalized placements as graphs and provides a modular environment for studying graph encoders, policy architectures, reward formulations, and local placement actions. To demonstrate the capabilities of GPlaceRL, we conduct a systematic evaluation of proximal policy optimization (PPO) policies with graph attention network (GAT) encoders in a per-design optimization setting. Across five placement benchmarks, the best greedy evaluation results achieve HPWL improvements ranging from $3.27\%$ to $32.87\%$. The results highlight the importance of compact GAT architectures and flexible local action spaces for placement optimization. Overall, GPlaceRL provides a reproducible and extensible framework for systematic research on RL-based detailed placement refinement. --- ### FairProp: Fair Node Representation Learning via Differentiable Propagation Layers Authors: Emmanouil Kariotakis, Aritra Konar Published: 2026-10-05 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2610.06484v1 Graph neural networks (GNNs) are the standard tool for node representation learning and are increasingly used in high-stakes settings. Their message-passing backbone, however, can amplify topological bias, raising fairness concerns. We study group fairness at the level of downstream predictions for node classification, link prediction, and node regression, and bound the demographic parity gap for an arbitrary number of sensitive groups. Our node classification bound is provably no looser than the closest prior result. For link prediction, ours is the first bound on the parity gap of the deployed sigmoid-activated prediction rather than a pre-activation proxy, and for node regression we provide the first such bound. Across all three tasks, the analysis identifies two distinct sources of bias: the separation between group means and the within-group covariance of the final representations. Building on this insight, we embed fairness into propagation itself by augmenting the convex smoothing problem underlying APPNP with a convex group-mean constraint and a within-group covariance regularizer. Unfolding projected gradient descent on this problem yields FairProp, whose layers pair a propagation step with a closed-form projection and which provably converges linearly to the unique fair optimum. Experiments on three tasks show that FairProp, even with exact group-mean equalization alone, provides a strong inductive bias that achieves excellent fairness-utility trade-offs against strong baselines. --- ### AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation Authors: Jiaqi Xue, Yanjun Wang, Xiangci Li, Lingbo Mo, Aritra Sengupta, Shweta Garg, Murali Krishna Ramanathan, Myeongsoo Kim Published: 2026-10-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.06481v1 As AI agents increasingly tackle complex repository-level coding tasks, distributing work across multiple agents is a natural way to scale beyond the capabilities of a single agent. To coordinate their interdependent work, these agents share findings and agree on interfaces between modules. However, exchanged information often serves only as context, leaving individual agents to interpret it and incorporate it into subsequent work. Consequently, shared findings may go unused and deviations from interface agreements may go undetected, undermining the reliability and efficiency of collaboration. This motivates moving part of the coordination responsibility from individual agents to the execution harness. To make shared information actionable during execution, we introduce the Artifact-Exclusive Communication Protocol (AECP). AECP requires agents to communicate exclusively through structured artifacts and specifies how the harness processes them. The harness supplies findings when agents access relevant code, screens implementations for mismatches with recorded interface commitments, and requires affected agents to revisit revised agreements. These coordination steps become part of harness execution rather than actions that agents must initiate from prior messages. Across Doc2Repo, NL2Repo, and CodeProjectEval, using closed- and open-source models including Opus-4.8 and DeepSeek-V4-Flash, AECP improves average test pass rate by 28.2% and reduces average wall time by 16.5% relative to an agent team using free-form inter-agent messages. Artifact-exclusive communication also blocks the relay of malicious instructions between agents, reducing how often they reach other agents from 95% to 0% and how often those agents act on them from 40% to 0%. --- ### Behavior-Preserving KV Cache Compression Authors: Doo Hwan Hwang, Junyoung Jang, Junho Na, Hosung Lim, Kee-Eung Kim Published: 2026-10-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.06479v1 KV caches are a major bottleneck in long-context inference and long-form generation with large language models. Existing training-free eviction policies largely rely on proxy importance signals, such as attention mass, to decide which past tokens to retain. We argue that cache compression should instead preserve the predictive behavior of the full-cache model, retaining entries whose removal would substantially change the model's output distribution. We propose Behavior-Preserving KV Cache Compression, a training-free framework that scores candidate evictions by estimating the compressed-cache logits induced by their removal and evaluating the resulting KL to the full-cache next-token distribution. Using pre-eviction forward statistics, the method avoids running separate masked forward passes for each candidate. Across diverse architectures and both prefill-time and generation-time compression, our method delivers substantial gains in downstream task quality over lightweight attention-based heuristics at matched retained-KV budgets, with the largest gains under aggressive compression. It achieves these gains with additional compression-time computation while retaining an end-to-end speedup over full-cache inference in our evaluated settings. --- ### MaRO-GS: Mask-Robust Object-Centric Gaussian Splatting from Inconsistent Multi-view Masks Authors: Eunji Kim, Gahyeon Kim, Gianella Cravioto, Dong-hun Lee, Chaewon Moon, Chae-yeong Song, Sang-hyo Park Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06472v1 We address the challenge of accurate 3D object reconstruction from multi-view images in Gaussian Splatting. Existing object-level 3DGS methods reconstruct the entire scene rather than directly optimizing the target object, even when only the target object is needed, which incurs substantial computational overhead. They also rely on 2D segmentation masks to associate Gaussians with objects, but these masks are often inconsistent across views. Such inconsistencies corrupt Gaussian optimization and produce incorrectly supervised Gaussians that degrade object reconstruction fidelity. To overcome these limitations, we propose MaRO-GS, a 3DGS framework that directly optimizes target-object Gaussians from object-masked multi-view images and remains robust to inconsistent supervision. For reliable supervision, mask-reliability view filtering excludes unreliable views. Object-supported Gaussian density control suppresses Gaussians irrelevant to the target object and prevents background densification, while Silhouette-aligned Object Loss maintains object-focused optimization. Extensive experiments across diverse datasets demonstrate that MaRO-GS improves PSNR, segmentation accuracy, and computational efficiency, with the largest PSNR gain of 2.05 dB on the small-object LERF-Mask dataset. --- ### Odyssey: A Closed-Loop Benchmark for Long-Horizon Real-World Driving with Explicit Navigation Routes Authors: Jungho Kim, Hongjae Shin, Seunghoon Yu, Heecheol Yoo, Myeongjun Kim, Jiyong Oh, Donghyuk Kwak, Seunghyeop Nam, Haesung Oh, Hyunju Kim, Hyungchan Cho, Jaehyun Park et al. Published: 2026-10-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.06469v1 Closed-loop evaluation of end-to-end driving requires continuous rollouts that reveal how earlier decisions affect subsequent driving. However, existing benchmarks evaluate only short segments and fail to capture later consequences. Ambiguous directional commands also obscure the intended navigation objective. We introduce Odyssey, a closed-loop benchmark for long-horizon driving comprising 100 scenarios, each reconstructed from a 100-second nuPlan driving log to preserve the context of navigation maneuvers and traffic interactions. To provide a consistent navigation objective, Odyssey replaces directional commands with explicit standard-definition (SD) map routes that specify which roads to follow, while sensor-based planning determines local driving actions. Throughout these rollouts, diffusion-based refinement of 3DGS-rendered images reduces rendering artifacts along the ego trajectory. To assess how effectively planners follow these routes and prepare for upcoming maneuvers, we introduce SD Route Compliance and Pre-Lane Change Score. These assessments are complemented by RouteDS, which extends the Driving Score with penalties for SD-route deviations and failed lane preparation. We adapt state-of-the-art planners, including vision-language-action (VLA) models, and evaluate their navigation performance using these metrics. Odyssey highlights open questions in route representation and integration for E2E driving. Benchmark code and adapted baselines will be released publicly. --- ### Latent Flow Matching for Molecular Graph Generation Authors: Mathis Goupillon, Roman Bresson, Konstantinos Divriotis, Michalis Vazirgiannis Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06468v1 Modern graph generative models typically operate directly in the discrete graph space, explicitly generating node and edge variables, which can become costly as graphs grow. In this paper, we perform generation explicitly on latent representations of entire graphs obtained from a pretrained Variational Autoencoder with high reconstruction fidelity. The generated representations, obtained through flow matching, are then decoded only at the final step. Across molecular benchmarks of increasing size, our approach achieves strong validity and FCD while offering a favorable quality-efficiency trade-off compared with state-of-the-art explicit graph generative models. One of the main advantages of this formulation is that the graph representation only needs to be learned once, after which the same one can be reused across multiple generative objectives without retraining. We demonstrate generation guided by molecular properties and further introduce validity-aware generation though a classifier learned directly in latent space. All code will be made available upon acceptance. --- ### A Physics-Guided Transformer Framework for Electromigration Analysis in Multi-Segment Interconnects Authors: Pavlos Stoikos, Anuj Pathania, George Floros Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06464v1 As technology scales to smaller nodes, increasing current densities make electromigration (EM) one of the dominant reliability challenges in on-chip interconnects. Accurate transient stress analysis is needed to identify wires susceptible to EM degradation, but applying physics-based solvers across many interconnects remains computationally expensive. This paper proposes a physics-guided transformer framework for fast EM stress prediction in multi-segment interconnect lines. The framework converts each line into geometry- and DC-aware segment tokens and uses transformer attention to capture line-level context. A lightweight query decoder then predicts stress at selected locations and time instants. The model is trained with an objective that combines normalized supervised regression, linewise relative-$L_2$ loss, and physics-guided continuity and terminal-flux terms. Experiments on IBM power grid benchmarks show that the proposed model achieves relative-$L_2$ error below 8\% and reaches up to 2459.68$\times$ speedup compared with the matrix exponential~solver. --- ### AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy Authors: Shouju Wang, Haopeng Zhang Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06454v1 The rapid advancement of LLM agents has enabled systems to autonomously perform complex tasks through external tools, but their growing access to personal data introduces significant privacy risks. Existing benchmarks primarily evaluate LLM agent privacy through simulated trajectories and outcome-based metrics, limiting their ability to capture privacy risks arising during multi-step agent execution. In this work, we introduce AgentPrivArena, a framework for evaluating privacy risks in realistic LLM agent workflows. AgentPrivArena integrates authentic MCP tools and self-hosted services within a reproducible execution environment. We further propose trajectory-level privacy metrics that quantify unnecessary information access beyond final response leakage. Building on this framework, we introduce AgentPrivAudit, a runtime auditing approach for monitoring privacy violations during agent execution. Extensive experiments on state-of-the-art LLM agents reveal substantial privacy risks overlooked by existing evaluation paradigms, highlighting the importance of trajectory-level auditing for trustworthy agent deployment. --- ### Normality Constraint Learning: Adapting Foundation Models for Time Series Anomaly Detection Authors: Xiaohui Zhou, Yijie Wang, Hongzuo Xu, Weixuan Liang, Guansong Pang Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06453v1 Time Series Foundation Models (TSFMs) achieve strong generalization by learning to reconstruct or forecast broad temporal patterns from large-scale time series during pre-training. Yet this strength can become a weakness for anomaly detection: TSFMs may model rare anomalous patterns as effectively as normal ones, allowing anomalies to be accurately reconstructed or forecasted and thus diminishing their reconstruction/forecasting error-based anomaly scores. This paper proposes $\underline{\textbf{N}}$$\textbf{ormality}$ $\underline{\textbf{C}}$$\textbf{onstraint}$ $\underline{\textbf{L}}$$\textbf{earning}$ ($\textbf{NCL}$), a lightweight plug-and-play framework that adapts pre-trained TSFMs for accurate anomaly detection without modifying their pre-trained parameters. Our key insight is to constrain the broad pattern space of TSFMs to the normal structure of a target time series, preventing their broad modeling capability from obscuring abnormal deviations. Specifically, NCL constructs a compact normality subspace from a few normal patch features and adaptively steers each patch feature toward normality within this subspace, guided by contrastive constraints that form compact and discriminative normality manifolds. The calibrated features are aggregated to reinforce normal components and fused with the original TSFM output, amplifying the discrepancy between normal and abnormal observations for the reconstruction/forecasting error-based anomaly scoring. Extensive experiments across diverse TSFM families and benchmarks show that NCL consistently improves anomaly detection performance, providing a generalizable framework for adapting TSFMs to anomaly detection. --- ### Multimodal Safety Evaluation Should Measure Controllability Beyond Classification Authors: Junhyeong Park, Hanwool Lee, DongGeon Lee, Dasol Choi, Yejin Son, Haon Park, Youngjae Yu Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06452v1 VLM safety is commonly evaluated through input- and output-level classification. Such classification is necessary, but it does not reveal whether a safety state is accessible or controllable inside the model. We argue that multimodal safety evaluation should therefore report a \emph{controllability profile} alongside behavioral classification, separating representation-level detectability, cross-modal specificity, intervention sensitivity, and benign-preserving selectivity. Using implicit toxicity as a stress case, we instantiate this profile on LlavaGuard and Qwen3.5 with sparse feature decompositions. LlavaGuard admits localized handles with a narrow benign-preserving intervention range and modest downstream safety gains, whereas Qwen3.5 supports strong representation-level readout but no comparable selective-control regime under the tested operators. These results show that internal readout and controllability can diverge. Future multimodal safety benchmarks should therefore report not only behavioral safety metrics, but also whether safety-relevant internal signals can be intervention-tested and controlled within a validated operating range. --- ### EMG-FM-Bench: A Comprehensive Benchmark for Foundation Model Transfer and Adaptation on Electromyography Authors: Tianhao Wu, Jiawei Yu, Xiangdong Hu, Xu Wu, Hongyu Wu, Sidharth Anupkrishnan, Amirmohammad Radmehr, Yi Chen Liu, Phuc Nguyen, Yi Wu, Jian Liu Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06450v2 Foundation models (FMs) are increasingly being developed for general time series and physiological signals, yet their transferability to downstream physiological tasks remains poorly understood. This question is particularly challenging for electromyography (EMG), where signal distributions vary substantially across users, sensing configurations, acquisition hardware, and downstream tasks. We introduce EMG-FM-Bench, a systematic benchmark for studying foundation-model transfer and adaptation on EMG. EMG-FM-Bench unifies 20 public datasets with over 1 million EMG segments and evaluates nine pretrained foundation models across four questions: how pretrained models perform when frozen or fully fine-tuned, how much pretraining helps compared with training the same model from scratch, how well models generalize to new users with limited labeled data, and how performance changes across different EMG tasks. Across the benchmark, linear probing provides useful information about pretrained representations, but full fine-tuning can substantially change downstream EMG performance. Comparing each pretrained model with the same model trained from scratch shows that the benefit of pretraining varies substantially across models and is not universal. Performance decreases when models are evaluated on new users, while five-shot adaptation improves macro-F1 in 70.2% of evaluated model-dataset combinations but recovers only part of the lost performance. Model performance is highly consistent between upper- and lower-limb classification and remains strongly correlated with continuous EMG-to-text decoding. Together, these results provide a systematic view of when pretrained time-series models transfer effectively to EMG and how their performance depends on fine-tuning, user variation, and downstream task. --- ### Time-series Foundation Models for Predictive Control: The Role of Excitation Authors: Mazen Amria, Jasper Hoffmann, Philipp Bordne, Anna Rothenhäusler, Lilli Frison, Harald Taxt Walnum, Sebastien Gros, Joschka Bödecker Published: 2026-10-05 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2610.06447v1 Deploying model predictive control (MPC) requires constructing or identifying a predictive model for each target system. Time-series foundation models (TSFMs) offer an attractive option thanks to strong zero-shot forecasting capabilities across systems. However, low forecast error does not guarantee that a TSFM captures the system's response to the alternative actions considered by the controller. We study this gap using residential heat-pump control as a test bed, measuring the agreement between predicted and ground-truth effects of control interventions. Importantly, we find that TSFMs can recover the system's input-response relationship when the context contains sufficient independent control excitation. Common fine-tuning pipelines and feature smoothing reduce, but do not eliminate, the need for in-context excitation. Our results indicate that current TSFMs used for predictive control require sufficiently informative control variation in the inference context. Initial closed-loop results show promise for shorter context windows. --- ### The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning Authors: Jakub Macina, Manu Kapur, Mrinmaya Sachan Published: 2026-10-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.06446v1 Large language models (LLMs) trained to answer questions are natively poor at teaching. Reinforcement Learning (RL) against a simulated student is a promising approach to improve their pedagogy, but existing RL-trained tutors reward the student's success on the tutored problem with the tutor's words still in context. The reward is then easiest to raise by telling the student the answer, and a tuned penalty is needed to reduce telling. Drawing on learning sciences, we introduce a masked near-transfer post-test: the student is tested on an unseen variant of the tutored problem with the tutor's utterances masked, so the reward can rise only through what the student wrote in its own turns. This discourages cognitive offloading by the student and allows the continuous penalty to be replaced by two binary reward gates (factual correctness of tutor response, no solution handover). A leave-one-out ablation shows that the learning-gain reward on its own does not separate teaching from telling: the gates reduce solution handover while the near-transfer post-test improves out-of-domain transfer. Using these reward designs we develop Eduardo, a multi-turn RL recipe for training LLM tutors, and use it to train 4B, 9B, 14B and 27B models from two distinct LLM architectures. Our post-trained Eduardo-27B model matches Gemini-3.1-Pro on MathTutorBench and Claude Opus 4.8 on TutorMoments at 2.4-6.2x fewer thinking tokens than frontier models, which matters for interactive tutoring. Without being named in the reward, the model more than doubles its use of the push-for-justification teacher move while support fading (e.g., assigning independent work), whose payoff lies beyond a single-problem dialog episode, is trained out. We open-source our training environment, an 8,671-problem near-transfer dataset, and trained models for further development. --- ### Choosing an energy-efficient software architecture for building system diagnostic support Authors: Roxane Koitz-Hristov, Franz Wotawa Published: 2026-10-05 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2610.06444v1 Around 30\% of global energy expenditure can be attributed to the building sector, where a large portion of energy-consumption could be avoided by repairing existing faults. Fault detection and diagnosis (FDD) software addresses this issue; however, its creation and operation also have an environmental impact. The magnitude of this impact is influenced by the diagnosis architecture, as different architectures and methods have different energy demands. Yet, simply considering the energy consumed by the software itself is not sufficient to assess its overall environmental impact, since the diagnostic performance, e.g., number of detected faults or number of faults missed, also contributes to its ecological footprint. In this paper, we propose an energy-consumption model that considers FDD performance and energy spend directly by the diagnosis software. In an initial experiment, we compare several FDD architecture families, i.e., rule-based, model-based, classical machine learning, and large-language-model-based, in simulation using performance and energy-consumption values collected from prior literature. The results show that considering the computational energy and accuracy of FDD can change the relative benefit of the different approaches. Computationally efficient machine learning methods, such as random forest, provide the largest net savings on smaller buildings, whereas more resource-intensive approaches, such as fine-tuned large language models, become advantageous as building size increases. Our findings suggest that overall energy efficiency depends not only on the computational demand of the FDD software, but also on its diagnostic performance and the scale of the building. --- ### ARO: Aligned Representation learning for multi-Omics data Authors: Amogh Singh, Yash Shah, Chiara D'Ercoli, Arash Mehrjou, Patrick Schwab, Timothy Jones, Pietro Liò Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06443v1 The high cost of functional molecular assays, and prevalence of missing modalities and unmatched samples in computational biology, create significant barriers to comprehensive multi-omic profiling, essential for capturing and reasoning over molecules, cells, tissues, and organisms. This work proposes a model that learns meaningful representations from multi-omics cancer data supporting the reconstruction of missing and unpaired modalities. Contrary to increasingly complex, larger models, e.g. Foundation Models (FMs), ARO prioritizes practical applicability in limited or incomplete data settings. ARO optimally reconstructs missing modalities (MSE of $0.15$ on the validation and test data in the Unmasked settings), with its learned latent embeddings enabling a downstream cancer classification task. Our findings indicate that analyzing diverse molecular layers as a single integrated system offers a reliable and cost-efficient approach, reducing dependence on large-scale experimental testing, while still supporting multi-omic exploration in limited data settings. --- ### Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models Authors: Subramanyam Sahoo, Justin Shenk Published: 2026-10-05 Categories: cs.LG, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2610.06439v1 What happens when a legal AI model learns to look like a lawyer instead of reasoning like one? We fine tune Qwen3-8B with Group Relative Policy Optimisation (GRPO) against a proxy built from three surface features: citation count, legalese density, and response length. The model does not learn to reason more effectively. It learns to withhold commitment. Across 16 yes or no legal reasoning tasks from LegalBench (N=320), overall accuracy collapses from 0.500 (chance) to 0.072 (McNemar p < 10^-36), driven entirely by the rate of properly formatted answers falling from 0.900 to 0.109. The model stops committing to answers. Yet when it does commit, accuracy rises from 0.556 to 0.657, showing that the collapse is not a failure of capability but a strategic response: the model has learned that verbose responses packed with citations but empty of a direct answer score higher than terse correct ones. We term this the Saul Goodman effect, a policy that becomes maximally lawyerly while becoming maximally noncommittal, and prove formally that it is the optimal response to any surface feature proxy that attaches no penalty to abstention. We further show that 89.3% of citations produced after training are structurally implausible hallucinations, many of them subtly corrupted names of real landmark cases, constructed in effect to survive a casual read and fail under scrutiny. To detect this failure mode before deployment, we introduce three diagnostic tools: the Confidence Theater Score (CTS), the Citation Plausibility Rate (CPR), and the Regret Gap (RG). In a domain where a confidently wrong answer can constitute malpractice, the broader lesson is direct: a reward function that measures how legal a response looks will produce a model that is maximally photogenic and minimally useful. --- ### HeuFouFT: Task-Guided Metaheuristic Coordinate Search for Fourier Fine-Tuning Authors: Ruiheng Wang, Yubo Hou, Yakun Zhu, Tianle Shen, Tao Wan, Zengchang Qin Published: 2026-10-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.06437v1 We introduce Heuristic-Guided Fourier Fine-Tuning (HeuFouFT), a task-guided framework for selecting trainable frequency coordinates in Fourier fine-tuning. Existing uniform and Gaussian band-pass schemes allocate a limited spectral budget through fixed, task-agnostic rules. HeuFouFT instead searches for coordinates using downstream performance. A coarse intensity map from lightweight block-level probes initializes three metaheuristic optimizers: Genetic Algorithm with Simulated Annealing (GA-SA), Particle Swarm Optimization (PSO), and Cuckoo Search (CS). During search, a Random Forest filters each population so that only the top 30% of candidates proceed to proxy fine-tuning. On E2E with GPT-2-Medium, all three variants outperform random-uniform FourierFT, Gaussian band-pass FourierFT, and LoRA across five metrics. PSO further outperforms LoCA, the best-performing baseline, on four metrics while using 37.6% fewer trainable spectral coefficients. Once coordinates are selected, HeuFouFT requires only 15--18% FLOPs of Full FT. These results show that task-guided search allocates limited spectral capacity more effectively than fixed sampling. Our code is publicly available. --- ### KESurv: A Kernel Ensemble Method for Patient-Specific Survival Prediction Authors: Rahul Goswami Published: 2026-10-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.06434v1 Predicting patient-specific survival functions is crucial for clinicians in making informed decisions about patient care and treatment strategies. Among the various models available, the Survival Forest has demonstrated significant effectiveness in numerous scenarios. In this work, we propose an ensemble method that leverages the strengths of the Survival Forest as the master model, complemented by several base models. This ensemble incorporates the Beran estimator, a type of kernel estimator, to enhance predictions of patient-specific survival curves. We evaluated the performance of our proposed model using four distinct healthcare datasets. The results highlight the superiority of our ensemble method over baseline models in both calibration and ranking across most datasets. The findings suggest that our approach offers a more accurate and reliable estimation of patient-specific survival functions, providing a valuable tool for clinical decision-making. --- ### Valid Stopping in Adaptive Generator-Verifier Loops Authors: Mahmoud Hegazy, Michael I. Jordan, Aymeric Dieuleveut Published: 2026-10-05 Categories: stat.ML, cs.AI, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2610.06432v1 Numerous agentic workflows are based on a generator-verifier loop: a generator proposes candidates, a cheap verifier scores them, and the workflow terminates when a proposal is verified as good enough. The verifier typically proxies a more costly ground-truth oracle, and as the generator searches adaptively against it, false acceptances may accumulate. Proposals can pass the proxy but fail under the costlier ground-truth check. We study when to stop these loops while controlling the false discovery rate of the accepted proposals. Our construction introduces tools of independent interest in distribution-free statistical testing and conformal risk control, including analysis of $e$-values constructed through index betting and a novel conformal risk control procedure for non-monotone losses. We validate the approach in synthetic settings and on a protein-design benchmark. --- ### Do Speech Representations Preserve Regional Accent Across Read and Spontaneous Speech? Authors: Paula A. Perez-Toro, Tomas Arias-Vergara, Annette Schwarz, Abner Hernandez, Andreas Horr, Cornelia Kristen, Andreas Maier Published: 2026-10-05 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2610.06430v1 Regional accent cues can be captured under matched conditions, but it remains unclear whether they persist between read and spontaneous speech. We study RVG1, with 500 German speakers from nine regions, comparing ten speech representations on regional classification and continuous geolocation under matched conditions and speaker-independent read--spontaneous transfer. Whisper performs best under matched conditions, reaching 0.489 nine-way UAR and 148 km median geolocation error, but drops to 0.11/0.18 UAR across transfer directions and 363 km geolocation error. Self-supervised models show a similar degradation, whereas speaker embeddings are less discriminative in-domain but more robust under transfer. This contrast is consistent across classification and geolocation. Across representations, robustness is associated with how little a representation shifts between styles (style-invariance), for which crossstyle speaker retrieval is an interpretable proxy. Age, sex, sentence-overlap, and duration controls do not account for the gap, although channel characteristics contribute. These results show that strong matched-condition performance does not indicate robust regional information. --- ### SoK: Semantic Decision Engines in Network Control Loops Authors: Delong Li, Chen Li, Xu Wang, Haochen Gong, Rui Lang, Guangsheng Yu Published: 2026-10-05 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2610.06425v1 A semantic decision engine such as Jev can return a valid answer and still miss a network deadline, select an infeasible action or leave the service unverified. We systematize 139 paper families by decision interface, execution path and check ownership. Fifty families claim that their engine fits a control loop or time budget, but only four support the claim with matched measurement. Across all 139, four report deadline attainment. The gap concentrates where the decision has no deterministic computation step. Those 72 families make 22 of the claims, none supported, and name a coverage owner in only two. Bounded tests under one event model show that each gap can reverse an admission verdict. A decision that meets a 10 s budget for every isolated request meets it for none once decisions queue ahead of replayed execution times. The same engine passes one coverage check and fails another. We derive a minimum reporting record, design rules and a research agenda for admitting decision engines to control loops. --- ### Toward Reliable Infant Pose Estimation: A Training-Dynamics Approach to Noisy Annotation Detection Authors: Emanuele Cardinale, Sara Moccia, Alessandro Cacciatore, Lucia Migliorelli Published: 2026-10-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.06423v1 Spontaneous movement analysis in preterm infants relies increasingly on markerless pose estimation (PE) to derive clinically relevant motion biomarkers directly from video recordings. Training accurate infant PE models requires large sets of manually annotated keypoints, and human annotation is inherently prone to error. Noisy keypoints (i.e., keypoints mislocalized with respect to their true anatomical position) are especially problematic in this clinical setting, since they can propagate as artificial artifacts into the reconstructed joint trajectories. Building on the small-loss hypothesis and training-dynamics-based sample selection established in the noisy-label learning literature, we propose a novel framework for detecting noisy keypoint annotations. A hybrid convolutional-attention model is trained to predict the anatomical category of each keypoint from its spatial coordinates and local visual features; the resulting cross-entropy training dynamics are then used to derive per-keypoint descriptors, which are partitioned into clean and noisy subsets via unsupervised clustering. We validate the approach on NeoPose, a newly collected dataset of 65 hospitalized preterm infants, under two realistic noise scenarios (random positional perturbation and left-right swapping) across multiple noise levels. Results show that the proposed approach achieves an F1-score of up to 91.9% in noisy-keypoint detection. The framework further generalizes to the heterogeneous COCO benchmark, where filtering CE-detected noisy keypoints from the training set also yields measurable improvements (up to 7.4 AP points) in downstream pose estimation accuracy at moderate-to-high noise levels. --- ### On the Comparison of Optimizers for Imbalanced Learning Authors: Cl{é}ment Lezane, Fran{\c c}ois Bachoc, J{é}r{ô}me Bolte, Jean-Michel Loubes Published: 2026-10-05 Categories: stat.ML arXiv: https://arxiv.org/abs/2610.06421v1 Data imbalance is pervasive in machine learning, from rare words and anomalies to underrepresented patterns in heterogeneous or cross-tabulated data. We study idealized optimizers geometries in continuous time to model small-step training in deep learning. We assume that the source of imbalance is unobserved: the optimizer has only access to the aggregate training loss ignoring the exact contributions of the majority and minority groups. In this setting, we characterize a region where majority losses are optimized regardless of the admissible minority structure. We derive explicit equations of this zone and bounds on the time needed to leave it. These bounds exhibit a milder dependence on minority amplitude for sign, spectral, and Newton descent than for Euclidean gradient descent. Experiments with AdamW and Muon suggest similar advantages over SGD across language, tabular, and image tasks. --- ### Efficient Secure Federated Learning via Information-Theoretically Secure Key Distribution: A Medical Imaging Case Study Authors: Ivan Donà, Hans H. Brunner, Álvaro Troyano Olivas, Chi-Hang Fred Fung, Momtchil Peev, Giovanni Iacca Published: 2026-10-05 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2610.06420v1 Federated Learning (FL) enables collaborative training of models across institutions without centralizing sensitive data, making it well-suited for privacy-concerned applications, such as medical imaging. To protect FL model updates during secure aggregation, additive masking is commonly employed. However, its underlying classical key establishment is only computationally secure. On the other hand, physics-based Information-Theoretically Secure (ITS) key exchange introduces practical constraints: finite key generation rates and time-limited storage severely limit throughput and sustained training of uncompressed models. In this work, we address this bottleneck by developing an FL framework that integrates frozen backbones, knowledge distillation, and quantization. These techniques reduce communication payload and, consequently, key material consumption. Moving beyond simulation, we benchmark this framework on a real physics-based key distribution testbed involving a chest X-ray classification application. Our results show that key usage can be reduced by $\sim$35$\times$ while maintaining predictive accuracy. This prevents buffer depletion and key expiration, enabling sustainable FL training under physical key generation constraints. --- ### Training-Free Transformer Merging via Sequential Local Operator Alignment Authors: Akansh Maurya, Ya-Wei Eileen Lin, Stefanie Jegelka, Sebastian U Stich, Rotem Mulayoff Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06415v1 Training-free model merging aims to combine multiple fine-tuned models into a single model without further optimization on labeled data. Yet, in transformers, independently merging individual layers can affect a shared attention computation because the query-key and value-output operators depend on composed matrices, overlooking the functional structure. Moreover, when merging earlier components, downstream components receive different activations than they do in the original model, thus, the merged and original execution paths no longer match. In this paper, we introduce Sequential Local Operator Alignment, a training-free method that merges transformers along the execution path of the partially merged model. Our method uses calibration data to estimate the local behavior of each functional component, aligns operators sequentially under the intermediate activation of the partially merged model, and subsequently factorizes the merged operators back into valid transformer parameters. We empirically show that this sequential step reduces error accumulation across layers. Furthermore, the proposed operator factorization step enables rank expansion, providing a principled mechanism for increasing multi-task capacity. We demonstrate that our approach generalizes across modalities, model scales, and varying numbers of tasks, from CLIP and RoBERTa to billion-parameter LLMs, and further extends naturally to the merging of LoRA-fine-tuned models. The results indicate improvements over strong merging baselines without requiring rank expansion, while optional expansion provides a further accuracy-inference-cost trade-off. Project link: https://akansh12.github.io/SLOA-Merge/ --- ### SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs Authors: Rafael Teixeira Sousa, Vinícius Paulo Lopes de Oliveira, Elisa Ayumi Masasi de Oliveira, Luiza Martins de Freitas Cintra, Fernanda Bufon Färber, Igor Dias Aguiar, Julia Yasmim de Almeida Nobre, Arlindo Rodrigues Galvão Filho Published: 2026-10-05 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.06413v1 Thinking-enabled vision-language models (VLMs) report ever-higher accuracy on spatial benchmarks, yet final-answer scores cannot reveal whether a correct prediction reflects faithful spatial reasoning or a linguistic shortcut. We introduce SpatialChain, a dataset of 28,350 training and 899 test examples pairing spatially-oriented GQA questions with scene-graph-grounded reasoning chains, retained only when the generated answer matches the symbolic ground truth, and a two-axis evaluation combining objective chain-overlap metrics with a scene-graph-aware LLM judge that scores faithfulness and completeness independently of the final answer. Applied to nine thinking-enabled VLMs, the protocol surfaces three findings invisible to standard accuracy: (i) four of nine models achieve $\geq$79% VQA accuracy while exhibiting shortcut rates above 39%, i.e., correct answers whose reasoning the judge marks as unfaithful; (ii) chain quality significantly predicts answer correctness for seven of nine models, but the two exceptions (Claude Sonnet 4.6, InternVL3.5-8B) reveal qualitatively distinct failure modes, terse output vs. verbose-decorative reasoning, that benchmark accuracy alone conflates; (iii) SFT on SpatialChain improves Qwen3-VL-8B by +6.2 pp in-domain and reduces its shortcut rate to 22%, while a stylistic specialization effect on external benchmarks motivates replay-augmented training as mitigation. The faithfulness judge is validated against 198 human-annotated items, where judge-human agreement matches human-human agreement, and against a second judge from a different provider, which preserves the model ranking ($ρ$ = 0.88). Data, generation scripts, and evaluation code are released at https://github.com/spatialchain/SpatialChainBenchmark. --- ### From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery? Authors: Pierre Llompart, Levent Guner, Helen Lai, Alessandro Tibo, Yijie Xu Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06411v2 Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We developed MAGI, an open modular agent that authors objectives, launches and monitors optimization, interprets structure--activity relationships, and revises its strategy accordingly. MAGI generates molecules either directly through the LLM or by delegating to REINVENT 4, with scoring services interchangeable behind a common contract. We tested it across nine retrospective lead-optimization campaigns from three pharmaceutical companies, replayed under fixed temporal cutoffs. Both routes produced valid structures: LLM proposals stayed closer to local chemistry and reached comparable or higher primary activity in fewer operations, whereas REINVENT explored broader chemical space. Whether a campaign met its objective depended on the predictive models, not on the generation route: attainment followed model accuracy on the chemistry proposed, dropping once that chemistry moved outside the model's applicability domain. Separately, a blinded evaluation asked whether the MAGI's output could pass as expert work: chemists were not able to discriminate agentic proposals from held-out compounds, and judged the SAR reasoning broadly plausible yet incomplete. Together, these results position MAGI as a coordination layer pluggable into existing computational chemistry workflows. The ceiling on real projects, however, remains currently set by scorer applicability rather than by tool orchestration. --- ### FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials Authors: Viktor Zaverkin, Payman Goodarzi, Sergey V. Sukhomlinov, Davit Hovhannisyan, Roland Aydin, Martin H. Müser, Mathias Niepert Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06409v1 Machine-learned interatomic potentials extend atomistic simulations beyond the length- and timescales accessible to electronic-structure methods. However, the computational cost of equivariant architectures limits the local correlations they can represent in practice and therefore their achievable accuracy. Here we introduce FlashCart, which makes higher-order correlations affordable by combining generated GPU kernels with an architecture that recursively builds equivariant features and compresses them to a fixed width at each step. We express tensor products in independent Cartesian components and symbolically simplify them and their derivatives, producing fused kernels that often outperform optimized spherical counterparts. We then show that increasing correlation order improves accuracy more efficiently than increasing width, depth, or tensor rank. On SPICE-MACE-OFF, FlashCart models advance the measured accuracy-efficiency frontier: a model with $5.6$ million parameters achieves lower energy and force errors and $10\times$ faster inference than a transformer with $189$ million parameters. --- ### What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents Authors: Zhongxiang Sun, Jiahao Yan, Hongkang Zhao, Haojie Ding, Boheng Zhang, Fan Yang, Xiao Zhang, Jun Xu Published: 2026-10-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.06406v1 As agents take on long-horizon tasks, users shift from making individual decisions to overseeing autonomous execution. Yet the volume of agent activity and the fragmentation of supporting evidence make it difficult to determine which decisions warrant user verification. We study monitors that identify consequential decisions and locate evidence to help users assess their implications. We introduce AgentMonBench, a software-engineering benchmark comprising three subsets that cover two complementary dimensions: alignment between requirements and behavior, and awareness of consequential autonomous decisions for verification. To support these judgments, we propose the Evidence-Grounded Behavior Graph (EBG), a training-free method that groups source-linked evidence into behaviors and organizes their relationships into a graph. EBG presents task-oriented views of this graph to help monitors interpret behavior in context. Experiments across eight models show that EBG improves decision identification and evidence localization in most settings compared with direct access to the original context. Further experiments show that EBG's evidence-localization gains persist across input scales and hyperparameter settings, while real-world applications illustrate its practical value for human oversight. --- ### Quantifying the Stability of Multi-Step Reasoning via Error Amplification Authors: Dongyue Li, Ziniu Zhang, Minxuan Duan, Hongyang R. Zhang Published: 2026-10-05 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2610.06404v1 We consider the stability of multi-step reasoning processes, which have extensive applications in language models, including chain-of-thought and algorithmic reasoning. While longer sequences of reasoning can improve a model's generation capability at test time, the errors due to intermediate reasoning steps can accumulate in autoregressive generation, and thus grow substantially at the end. In this paper, we ask: What are the key factors determining the stability of multi-step reasoning? First, we show an inference error bound governed by the product of spectral norms of the Jacobians taken through the input space across generation steps. This product can be viewed as an error amplification factor, which could scale exponentially with the number of reasoning steps, serving as a quantitative measure of reasoning stability. Second, we analyze this measure in transformer models trained to predict simple tasks like linear and quadratic functions. We theoretically prove that the transformer model converges to a solution where the stability measure decays, thus yielding nearly zero inference loss over (arbitrarily) long steps. Finally, the stability analysis leads to several algorithmic implications for controlling the stability, through (i) chain-of-thought length compression that reduces the sensitivity of each step, and (ii) quantization-aware training that regularizes the input Jacobian norms. We validate the proposed algorithms by fine-tuning language models on graph-algorithmic reasoning tasks and symbolic state-tracking tasks. Across seven evaluations, our algorithms improve over baseline comparisons by 3.5% on average, and by 8.2% for longer-length inputs. Ablation analysis validates that the stability measure is drastically reduced by 3-8$\times$, confirming the regularization effect on the spectral norms of the (input space) Jacobians. --- ### RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents Authors: Mohamed Dhouib, Clement Elliker, Alexi Canesse, Maël Jenny, Lucas-Andrei Thil, Mahammed El Sharkawy, Sonia Vanier, Elie Bursztein Published: 2026-10-05 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.06401v2 Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities. We show that training-based defenses induce substantial drift in the model's output distribution, altering its behavior even in benign settings and providing a potential mechanism for utility degradation. We further identify a failure mode of these defenses: On benign tool-use tasks, the model refrains from a step needed to finish an authorized task, particularly when that step is indicated by a tool output. To address these limitations, we introduce RAISED (Robust Attack Invariance through Self-Distillation), a training framework that combines self-generation and self-distillation. The model first generates its own tool-use scenarios, with an emphasis on cases where task completion requires acting on legitimate guidance from tool outputs. Then, through self-distillation, the student is trained to match the teacher's clean-context behavior on both clean and injected variants of the same trajectory. RAISED substantially reduces the attack success rate of prompt injections in tool responses while, unlike prior training-based defenses, preserving utility on both agentic and general-purpose benchmarks. --- ### Visual Swarm Navigation via Deep Reinforcement Learning and Evolutionary Hybrid Design Authors: Álvaro Díez, Fidel Aznar Published: 2026-10-05 Categories: cs.RO, cs.MA, cs.NE arXiv: https://arxiv.org/abs/2610.06400v1 Swarm robotics presents a robust and cost-effective paradigm for advanced automation in complex, dynamic environments, such as those encountered in search and rescue or environmental monitoring. A fundamental challenge for this field is the data-driven design of decentralized controllers capable of generating emergent collective behaviors. This paper proposes a novel, AI-driven hybrid methodology for the automatic synthesis of swarm robotic controllers for autonomous visual navigation. This approach synergistically combines multi-agent reinforcement learning with neuro-evolutionary strategies, specifically leveraging implementations of the cross-entropy method and the covariance matrix adaptation evolution strategy to optimize a pre-trained individual navigation policy. The underlying deep architecture is engineered for low-cost, resource-constrained platforms, utilizing a compact neural network that relies exclusively on monocular camera imagery. This vision-based design emphasizes computational and energy efficiency, a critical requirement for practical swarm deployments. Experiments, performed in a high-fidelity physics simulator, demonstrate that the resulting controllers enable robust and scalable collective exploration of diverse indoor environments. The controller trained using our cross-entropy method achieves superior exploration coverage, visiting 36.20% more regions compared to the covariance matrix adaptation evolution strategy. Critically, our best vision-based policy achieves exploration performance statistically comparable to traditional methods relying on more expensive distance sensors, while delivering a significant 31.40% average reduction in energy consumption. These findings validate an effective and economically viable autonomous control system, establishing a path for deploying highly efficient collective intelligence in real-world engineering applications. --- ### CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs Authors: Jiahui Kang, Bifan Wei, Lingling Zhang, Tianwen Jiang, Qiuyong Xiao, Jihong Zhang, Jun Liu Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06399v1 Despite significant progress in visual tasks by Multimodal Large Language Models (MLLMs), geometric diagram understanding remains challenging due to the presence of sparse visual cues and ambiguous symbol-primitive associations. MLLMs may therefore rely on textual priors, producing interpretations that conflict with visual evidence. We introduce the training-free Criticality-Driven Visual Intervention Framework (CVIF), an inference-time method that localizes critical layers and executes visual interventions during the transition from evidence aggregation to semantic decoding. At these layers, a Geometry-Constrained Local Relation Reconstruction (GCLR) module selects and weights vertex-centered visual evidence, while an Adaptive Visual Steering Operator (AVSO) redistributes attention mass toward the selected tokens. Experiments on PGPS9K and PGDP5K show that CVIF raises Overall F1 from 77.85 to 85.58 and from 75.23 to 82.84, respectively, establishing a novel inference-time visual intervention paradigm. --- ### Learning Pareto Stationary Fronts via Single-Pass Backpropagation Authors: Elina Rojin Celik, Marcos Medeiros Raimundo, Isabel Valera Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06397v1 We propose MOSEL (Multi-Objective Stackelberg Efficient Learning), a framework for a posteriori multi-objective optimization (MOO) in deep neural networks that recovers a full front of Pareto stationary solutions at the computational cost of standard single-objective training. MOSEL reformulates the problem as a bilevel optimization problem that leverages network modularity to decouple representation learning from objective-preference alignment. Casting the bilevel optimization problem as a Stackelberg game enables solving the original a posteriori MOO problem in a single forward-backward pass. As a result, MOSEL matches the time and memory efficiency of standard single-objective training while enabling scalable Pareto stationary front learning. Empirically, MOSEL uncovers diverse and optimal Pareto frontiers in strongly conflicting settings (e.g., fairness-accuracy). Remarkably, even in weakly conflicting regimes such as multi-task learning, it consistently converges to solutions closer to the utopia point, outperforming both standard single-objective training and specialized multi-task learning methods. These results highlight the broader potential of a posteriori MOO learning as a pathway to efficiently learn more diverse and robust representations, ultimately improving generalization. --- ### Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction Detection Authors: Zhaolin Cai, Huiyu Duan, Liu Yang, Yanjun Qin, Bo Ai, Wei Chen, Xiongkuo Min, Guangtao Zhai Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06394v1 Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform strongly but rely on task-specific training. Recent multimodal large language models (MLLMs) offer a promising route to training-free HOI detection through their broad visual-semantic knowledge and versatile perceptual and reasoning capabilities. However, existing approaches largely invoke these capabilities through loosely coordinated inference stages. This fragmented execution restricts the role of interaction hypotheses in guiding visual exploration, leaving key participants overlooked and local ambiguities unresolved. Furthermore, propagating early semantic assumptions through subsequent visual grounding and relation prediction induces self-reinforcing semantic circularity. To resolve these challenges, we propose HarnessHOI, a training-free framework that transforms passive MLLM inference into an active interaction-centric harness. Specifically, we introduce an interaction-guided perception mechanism that projects emerging interaction hypotheses back into the visual space to discover missing participants and refine ambiguous evidence through targeted observation. Furthermore, a relation-agnostic geometric adjudication module reconciles multi-source evidence to establish a unified spatial basis for grounded interaction reasoning across multiple actions and semantic roles. Extensive experiments on HICO-DET and V-COCO demonstrate that HarnessHOI achieves state-of-the-art performance among training-free methods, confirming the effectiveness of the proposed harness for complex interaction understanding. Code will be released upon publication. --- ### Multi-Task Partially Supervised Learning for Super-Resolution and Semantic Segmentation on Earth Observation data Authors: Hoàng-Ân Lê, Minh-Tan Pham, Solange Lemai-Chenevier, Daniel Greslou Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06389v1 Super-resolution and semantic segmentation are known to benefit one another, especially in the Earth observation context. However, learning both tasks in a joint model often requires both task annotations, which is impractical and expensive. In this paper, we study the multi-task partially supervised learning paradigm for both tasks, where each example is assumed to have only a single-task annotation. To that end, we examine two multi-task architectural variations, the sequential and shared variants, and then propose a hybrid variant and a re-projection loss to benefit from the shared representation and enforce image quality of super-resolution when training with semantic segmentation. Experiments show favorable results compared to the SOTA sequential variant. Source code will be published at https://github.com/lhoangan/munera. --- ### Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models Authors: Joe Dwyer Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06387v2 Large language models (LLMs) have achieved substantial performance gains through increases in model size, training data, and computational resources. However, traditional scaling approaches produce diminishing returns, rising financial and environmental costs, and barriers to participation for researchers operating outside large industrial laboratories. This review examines the evolution of LLM scaling theory from empirical scaling laws to compute-optimal training, with particular emphasis on parameter efficiency, token utilization, data efficiency, and resource-constrained environments. Foundational work on scaling laws is synthesized alongside later research on compute-optimal training, data pruning, efficient architectures, quantization, low-rank adaptation, and edge-oriented optimization. The literature indicates a shift from scale maximization toward more deliberate allocation of parameters, tokens, compute, and hardware resources. At the same time, important empirical, theoretical, and methodological gaps remain regarding whether scaling principles established on enterprise-grade infrastructure generalize to smaller models and constrained computing environments. This review organizes these developments into a unified framework for resource-efficient LLM training and argues that future progress should evaluate efficiency not solely through model performance, but through the relationship among performance, parameter count, computational cost, token allocation, and hardware constraints. --- ### Steering by Influence: Curvature Aware Data Weighting for Activation Steering Authors: James A. E. Dixon, Stephen J. Roberts, Francesco Quinzan Published: 2026-10-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.06383v1 Inference-time steering offers cheap, fine-grained control over a language model's outputs by estimating a concept's representation in activation space and shifting activations towards it. Existing methods build these representations from activation averages over contrastive datasets. These averages incorporate unrelated concepts and noise, and are dominated by a few tokens, meaning the activation transport encodes token-level rather than thematic concepts. In this work, we steer towards examples that most express a concept thematically, rather than towards an expectation over all. We identify these examples using influence functions, which estimate how much each data point contributes to a model's representation of a concept. Unlike simple model activation similarity, they incorporate the curvature of the model's loss landscape, allowing them to capture concept-relevant relationships beyond superficial token-level similarity. We then propose influence-weighted activation transport, which uses optimal transport to steer activations of non-concept text towards those of concept text, weighting concept examples by their influence scores. We evaluate on toxicity suppression (Jigsaw), object-based concept induction (OneSec) and truthfulness induction (TruthfulQA), outperforming existing activation-transport baselines. We track capability after steering using perplexity and MMLU accuracy, finding that our method improves steering while largely preserving model quality. We further show that influence functions capture concept-relevant information that activation-based methods miss with the two approaches ranking data points significantly differently. Together, these results demonstrate the value of curvature-aware influence information for activation steering. --- ### MTOR: Generalizable AI-Generated Video Detection with Multimodal Semantics and Temporal Over-Regularity Authors: Hang Wang, Chao Shen, Lei Zhang, Zhi-Qi Cheng Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06378v1 The rapid evolution of video generation has narrowed the perceptual gap between authentic and synthetic videos, making generalizable AI-generated video detection increasingly challenging. Existing detectors predominantly rely on visual representations, leaving caption-derived textual semantics underexplored. Meanwhile, temporal regularity in fine-grained visual representations has received limited attention. We find that caption-derived textual representations provide complementary discriminative cues to global visual representations. Our analysis further reveals that AI-generated videos exhibit stronger temporal persistence and lower temporal variability, a pattern we term temporal over-regularity (TOR). Based on these findings, we propose MTOR with a multimodal branch and a TOR component. The multimodal branch integrates global visual and caption-derived textual representations, while the TOR component models temporal over-regularity at three levels: coarse inter-frame continuity, fine-grained token correspondence, and frame-to-video stability. Extensive evaluations on five benchmarks covering 46 generator variants demonstrate state-of-the-art overall performance against 16 representative baselines, while robustness experiments confirm strong resilience to twelve real-world video perturbations. Code and models will be released at https://github.com/hwang-cs-ime/MTOR. --- ### Environmental sensor readings in two crop disease image datasets identify the session in which each image was taken Authors: Sungwoo Kang Published: 2026-10-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.06369v1 Integrating environmental sensor data with leaf imagery is widely reported to boost crop disease classification accuracy. In this work, we reveal that these reported gains are often artifacts of dataset construction: because a single sensor reading is shared across many images collected in a single session (one farm on one date), multimodal networks can predict disease simply by memorizing session identities. Analyzing two widely used Korean datasets, the Crop Disease Diagnosis (CDD) benchmark and an AI Hub pest/disease dataset, we demonstrate that nearly all images share sensor values, with 91.9% of CDD test images having exact sensor duplicates in the training set. Remarkably, an image-free classifier given only timestamps matches or exceeds sensor-driven predictions across all seven evaluated crops, and matches the published macro-F1 of a state-of-the-art CDD fusion model. These results indicate that performance gains on standard random splits cannot be disentangled from session leakage. We propose that multimodal crop studies must evaluate on session-held-out splits and report performance against sensor-free date-time baselines to ensure genuine generalization. --- ### Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning Authors: Boyue Caroline Hu, Kaivalya Ahir, Ronghao Ni, Limin Jia Published: 2026-10-05 Categories: cs.CR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2610.06366v1 Large Language Models (LLMs) are increasingly deployed for automated software vulnerability analysis. Binary classification alone is insufficient; practitioners need explanations to triage bugs and engineer patches. Standard practice relies on Chain-of-Thought (CoT) prompting, but free-form reasoning allows models to obscure logical leaps, hallucinated execution steps, and internal inconsistencies behind plausible prose. Our manual audit reveals that approximately 60% of correct vulnerability verdicts are accompanied by fabricated or unverifiable claims, and free-form explanations allow reasoning errors to evade LLM-as-a-judge evaluation. We present Vulnerability Explanation Reasoning Auditor (VERA), an automated framework for auditing LLM vulnerability reasoning. Rather than accepting free-form text, VERA asks models to output a Structured Reasoning Record (SRR) encoding tracked pointers, memory operations, and state transitions in machine-readable fields. A multi-stage judge audits each SRR against eight reasoning failure modes using deterministic checks, with LLM calls reserved for semantic interpretation. The standardized SRR schema also enables automated mutation testing to benchmark judges at scale without human annotation. Our evaluation shows reasoning flaws occur in correct verdicts just as frequently as incorrect ones, and VERA exposes 87% of reasoning errors that free-form LLM-as-judge systematically miss. --- ### Multimodal Deep Survival Analysis for Sinkhole Susceptibility Authors: Lucas Yuan, Minhee Kim, Zihan Li, Chunli Dai, Sanduni S. Disanayaka Mudiyanselage, Ming Ye, Kani Fu Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06365v1 Sinkholes are a widespread geohazard in karst terrain. In Florida, soluble carbonate bedrock, shallow groundwater, and intense rainfall combine to make subsidence both common and spatially heterogeneous. Predicting where and when sinkholes will occur is difficult for two reasons. First, locations without reported sinkholes cannot be directly labeled or sampled as true negative locations. Second, the potential factors governing sinkhole risk span heterogeneous data modalities and therefore require careful integration within a unified modeling framework. We address both problems with our proposed model, a multimodal Cox proportional hazards framework for sinkhole susceptibility. Our contributions are threefold. First, we extend the proportional-hazards formulation to heterogeneous multimodal input through modality-specific encoders and a cross-modal fusion layer. Second, we treat unreported locations as right-censored rather than negative, avoiding hard-negative labeling and yielding continuous, time-aware susceptibility from the predicted survival function. Third, a statewide Florida case study with spatially blocked validation and ablation studies quantifies the benefit of multimodal integration. A Florida case study demonstrates that the proposed method effectively ranks sinkhole risk and produces a statewide susceptibility map that captures spatial variations in sinkhole occurrence. --- ### Capability-Driven Self-Evolution of Agent Memory Authors: Yaoqi Chen, Yuru Feng, Qianxi Zhang, Baotong Lu, Jianan Lu, Zhirui Wang, Shusen Xu, Zewen Jin, Zengzhong Li, Cheng Li, Qi Chen Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06361v1 Memory self-evolution uses task feedback to iteratively improve executable memory programs that store and retrieve information from past interactions. Existing approaches typically adopt holistic evolution, deriving revision directions from mixed feedback and judging progress by overall performance. This can obscure optimization directions and hide capability-specific gains offset by regressions elsewhere, leaving promising directions underexplored. We introduce capability-driven evolution, which extends search guidance from overall performance to individual capability dimensions, preserving promising revisions and expanding exploration beyond the boundaries of holistic evolution. We propose PrisMem, which uses dependency-aware capability selection to prioritize targets with potential cross-capability benefits and history-guided diagnosis to refine capability specialists. Trace-guided integration compares evaluated programs on paired differential cases, using their behavioral differences to consolidate complementary gains into a unified memory program. Experiments show that PrisMem outperforms the strongest baselines by 10.54 and 7.83 percentage points on BEAM-1M and LongMemEval-M, respectively, demonstrating its effectiveness on million-token histories. --- ### Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering Authors: Aditya Tanna, Abhishek Jindal Published: 2026-10-05 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.06360v1 Reinforcement learning post-training for language models relies on two reward designs: human preferences (RLHF, DPO) and binary verifiers (RLVR). Clinical question answering fits neither. Near-correct answers differ by a single substituted entity, and no executable check decides clinical correctness. We instantiate a soft verifier from a maintained controlled vocabulary: UMLS Concept Unique Identifier overlap (via scispaCy, set-level F1) gives a graded, externally specified reward computed without a model in the loop. We combine it inside GRPO with an entropy-normalised LLM judge, which covers the safety and evidence axes overlap cannot see, and a small consistency penalty on padding and repetition that keeps early-training samples scorable. This three-term composite improves over SFT on Phi-3-mini (3.8B) over MedQA by 2.9% on EM (0.700 vs 0.680) and 39% on Token-F1 (0.202 vs 0.145); on Llama-3.2-3B the corresponding gains are 14% on EM and 35% on Token-F1. We report Token-F1 as the primary metric because it credits partially-correct clinical content that EM discards at this open-generation scale. Main-table results are means over 3 seeds with standard deviations below 0.005. The method transfers to PubMedQA, where training on the PubMedQA train set with the same composite reward improves Token-F1 over SFT by 22% on Phi-3-mini and 17% on Llama-3.2-3B without retuning. A reward ablation on Phi-3, varying the judge-ontology split at a fixed consistency weight, attributes 3 EM points to the ontology term, the contribution that catches entity substitutions the judge cannot. Three negative findings constrain the design: DPO under random negatives underperforms SFT for strong-prior models but helps the weakest-prior one; PPO under a sparse neural reward diverges; GRPO with KL-in-loss collapses at 7B. --- ### A Flexible and Generic Approach for Explainable Landscape Analysis and the pyXla Toolbox Authors: Tony Ombaso, Anna S. Bosman, Arnaud Liefooghe, Katherine M. Malan, Sébastien Verel Published: 2026-10-05 Categories: cs.NE, cs.MS arXiv: https://arxiv.org/abs/2610.06359v1 Landscape analysis has been successfully applied to understand complex optimisation problems, gain insights into algorithm behaviour, and automate algorithm selection and configuration. Although many landscape analysis techniques have been developed over the last decades, it remains difficult for researchers and practitioners to decide which approaches are appropriate and to implement them in practice. Some tools are available, but these are either restricted to particular problem domains (e.g., unconstrained black-box continuous optimisation), or are limited in what they model and measure. In addition, output from landscape analysis is often not easily interpretable, especially when computed landscape features do not correspond with aspects of problems that practitioners are familiar with. In this paper, we introduce a principled approach for explainable landscape analysis (XLA) with an associated Python package called pyXla. The approach is generic in that it applies to problems with different representations (continuous or combinatorial), with single or multiple objectives, with or without constraints. The extent of analysis provided by the XLA framework depends on the data available, with richer analysis offered as additional information is provided by the user. We demonstrate the explainable output produced by pyXla on a selection of hand-crafted problems with diverse landscape characteristics. ---