# Research Papers — 2026-02 · bundle page 111 of 210 > Full-text markdown of papers #5501–5550 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/111 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/110.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/112.md) ### Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization Authors: Yihang Yao, Zhepeng Cen, Haohong Lin, Shiqi Liu, Zuxin Liu, Jiacheng Zhu, Zhang-Wei Hong, Laixi Shi, Ding Zhao Published: 2026-02-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.11351v2 Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric applications. Agentic reinforcement learning (RL) has recently emerged as a promising solution for training such agents in multi-turn settings, allowing them to learn long-horizon decision-making strategies. However, existing pipelines face a critical challenge in balancing task performance with user engagement, as passive agents cannot efficiently adapt to users' intentions while overuse of human feedback increases the burden on users, which forms a Pareto Frontier between these two objectives. To push forward this frontier, we propose Behavior Agentic Optimization (BAO), an agentic RL framework that enhances and regularizes inter-turn behaviors to improve information-gathering capabilities and suppress inefficient or redundant interactions with users. We evaluate BAO on multiple tasks from the UserRL benchmark suite and demonstrate that it substantially outperforms proactive agentic RL baselines in terms of both higher task performance and lower user efforts, while achieving comparable or even superior performance to commercial LLM agents, highlighting its effectiveness for training proactive, user-centric LLM agents in complex multi-turn scenarios. Our website: https://proactive-agentic-rl.github.io/. --- ### Structured Hybrid Mechanistic Models for Robust Estimation of Time-Dependent Intervention Outcomes Authors: Tomer Meir, Ori Linial, Danny Eytan, Uri Shalit Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11350v1 Estimating intervention effects in dynamical systems is crucial for outcome optimization. In medicine, such interventions arise in physiological regulation (e.g., cardiovascular system under fluid administration) and pharmacokinetics, among others. Propofol administration is an anesthetic intervention, where the challenge is to estimate the optimal dose required to achieve a target brain concentration for anesthesia, given patient characteristics, while avoiding under- or over-dosing. The pharmacokinetic state is characterized by drug concentrations across tissues, and its dynamics are governed by prior states, patient covariates, drug clearance, and drug administration. While data-driven models can capture complex dynamics, they often fail in out-of-distribution (OOD) regimes. Mechanistic models on the other hand are typically robust, but might be oversimplified. We propose a hybrid mechanistic-data-driven approach to estimate time-dependent intervention outcomes. Our approach decomposes the dynamical system's transition operator into parametric and nonparametric components, further distinguishing between intervention-related and unrelated dynamics. This structure leverages mechanistic anchors while learning residual patterns from data. For scenarios where mechanistic parameters are unknown, we introduce a two-stage procedure: first, pre-training an encoder on simulated data, and subsequently learning corrections from observed data. Two regimes with incomplete mechanistic knowledge are considered: periodic pendulum and Propofol bolus injections. Results demonstrate that our hybrid approach outperforms purely data-driven and mechanistic approaches, particularly OOD. This work highlights the potential of hybrid mechanistic-data-driven models for robust intervention optimization in complex, real-world dynamical systems. --- ### ArtContext: Contextualizing Artworks with Open-Access Art History Articles and Wikidata Knowledge through a LoRA-Tuned CLIP Model Authors: Samuel Waugh, Stuart James Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11349v1 Many Art History articles discuss artworks in general as well as specific parts of works, such as layout, iconography, or material culture. However, when viewing an artwork, it is not trivial to identify what different articles have said about the piece. Therefore, we propose ArtContext, a pipeline for taking a corpus of Open-Access Art History articles and Wikidata Knowledge and annotating Artworks with this information. We do this using a novel corpus collection pipeline, then learn a bespoke CLIP model adapted using Low-Rank Adaptation (LoRA) to make it domain-specific. We show that the new model, PaintingCLIP, which is weakly supervised by the collected corpus, outperforms CLIP and provides context for a given artwork. The proposed pipeline is generalisable and can be readily applied to numerous humanities areas. --- ### AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition Authors: Ruipeng Wang, Yuxin Chen, Yukai Wang, Chang Wu, Junfeng Fang, Xiaodong Cai, Qi Gu, Hui Su, An Zhang, Xiang Wang, Xunliang Cai, Tat-Seng Chua Published: 2026-02-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.11348v2 Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in complex and imperfect environments. This discrepancy largely arises because prevailing training and evaluation paradigms are typically built on idealized assumptions, overlooking the inherent stochasticity and noise present in real-world interactions. To bridge this gap, we introduce AgentNoiseBench, a framework for systematically evaluating the robustness of agentic models under noisy environments. We first conduct an in-depth analysis of biases and uncertainties in real-world scenarios and categorize environmental noise into two primary types: user-noise and tool-noise. Building on this analysis, we develop an automated pipeline that injects controllable noise into existing agent-centric benchmarks while preserving task solvability. Leveraging this pipeline, we perform extensive evaluations across a wide range of models with diverse architectures and parameter scales. Our results reveal consistent performance variations under different noise conditions, highlighting the sensitivity of current agentic models to realistic environmental perturbations. --- ### Divide and Learn: Multi-Objective Combinatorial Optimization at Scale Authors: Esha Singh, Dongxia Wu, Chien-Yi Yang, Tajana Rosing, Rose Yu, Yi-An Ma Published: 2026-02-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.11346v1 Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theoretical guarantees. We reformulate it as an online learning problem over a decomposed decision space, solving position-wise bandit subproblems via adaptive expert-guided sequential construction. This formulation admits regret bounds of $O(d\sqrt{T \log T})$ depending on subproblem dimensionality \(d\) rather than combinatorial space size. On standard benchmarks, our method achieves 80--98\% of specialized solvers performance while achieving two to three orders of magnitude improvement in sample and computational efficiency over Bayesian optimization methods. On real-world hardware-software co-design for AI accelerators with expensive simulations, we outperform competing methods under fixed evaluation budgets. The advantage grows with problem scale and objective count, establishing bandit optimization over decomposed decision spaces as a principled alternative to surrogate modeling or offline training for multi-objective optimization. --- ### Situated, Dynamic, and Subjective: Envisioning the Design of Theory-of-Mind-Enabled Everyday AI with Industry Practitioners Authors: Qiaosi Wang, Jini Kim, Avanita Sharma, Alicia, Lee, Jodi Forlizzi, Hong Shen Published: 2026-02-11 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.11342v1 Theory of Mind (ToM) -- the ability to infer what others are thinking (e.g., intentions) from observable cues -- is traditionally considered fundamental to human social interactions. This has sparked growing efforts in building and benchmarking AI's ToM capability, yet little is known about how such capability could translate into the design and experience of everyday user-facing AI products and services. We conducted 13 co-design sessions with 26 U.S.-based AI practitioners to envision, reflect, and distill design recommendations for ToM-enabled everyday AI products and services that are both future-looking and grounded in the realities of AI design and development practices. Analysis revealed three interrelated design recommendations: ToM-enabled AI should 1) be situated in the social context that shape users' mental states, 2) be responsive to the dynamic nature of mental states, and 3) be attuned to subjective individual differences. We surface design tensions within each recommendation that reveal a broader gap between practitioners' envisioned futures of ToM-enabled AI and the realities of current AI design and development practices. These findings point toward the need to move beyond static, inference-driven approach to ToM and toward designing ToM as a pervasive capability that supports continuous human-AI interaction loops. --- ### Bi-Level Prompt Optimization for Multimodal LLM-as-a-Judge Authors: Bo Pan, Xuan Kan, Kaitai Zhang, Yan Yan, Shunwen Tan, Zihao He, Zixin Ding, Junjie Wu, Liang Zhao Published: 2026-02-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.11340v1 Large language models (LLMs) have become widely adopted as automated judges for evaluating AI-generated content. Despite their success, aligning LLM-based evaluations with human judgments remains challenging. While supervised fine-tuning on human-labeled data can improve alignment, it is costly and inflexible, requiring new training for each task or dataset. Recent progress in auto prompt optimization (APO) offers a more efficient alternative by automatically improving the instructions that guide LLM judges. However, existing APO methods primarily target text-only evaluations and remain underexplored in multimodal settings. In this work, we study auto prompt optimization for multimodal LLM-as-a-judge, particularly for evaluating AI-generated images. We identify a key bottleneck: multimodal models can only process a limited number of visual examples due to context window constraints, which hinders effective trial-and-error prompt refinement. To overcome this, we propose BLPO, a bi-level prompt optimization framework that converts images into textual representations while preserving evaluation-relevant visual cues. Our bi-level optimization approach jointly refines the judge prompt and the I2T prompt to maintain fidelity under limited context budgets. Experiments on four datasets and three LLM judges demonstrate the effectiveness of our method. --- ### Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content Authors: Evgeney Bogatyrev, Khaled Abud, Ivan Molodetskikh, Nikita Alutis, Dmitriy Vatolin Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11339v2 Recent advancements in real-time super-resolution have enabled higher-quality video streaming, yet existing methods struggle with the unique challenges of compressed video content. Commonly used datasets do not accurately reflect the characteristics of streaming media, limiting the relevance of current benchmarks. To address this gap, we introduce a comprehensive dataset - StreamSR - sourced from YouTube, covering a wide range of video genres and resolutions representative of real-world streaming scenarios. We benchmark 11 state-of-the-art real-time super-resolution models to evaluate their performance for the streaming use-case. Furthermore, we propose EfRLFN, an efficient real-time model that integrates Efficient Channel Attention and a hyperbolic tangent activation function - a novel design choice in the context of real-time super-resolution. We extensively optimized the architecture to maximize efficiency and designed a composite loss function that improves training convergence. EfRLFN combines the strengths of existing architectures while improving both visual quality and runtime performance. Finally, we show that fine-tuning other models on our dataset results in significant performance gains that generalize well across various standard benchmarks. We made the dataset, the code, and the benchmark available at https://github.com/EvgeneyBogatyrev/EfRLFN. --- ### MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation Authors: Yejin Kim, Wilbert Pumacay, Omar Rayyan, Max Argus, Winson Han, Eli VanderBilt, Jordi Salvador, Abhay Deshpande, Rose Hendrix, Snehal Jauhri, Shuo Liu, Nur Muhammad Mahi Shafiullah et al. Published: 2026-02-11 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.11337v2 Deploying robots at scale demands robustness to the long tail of everyday situations. The countless variations in scene layout, object geometry, and task specifications that characterize real environments are vast and underrepresented in existing robot benchmarks. Measuring this level of generalization requires infrastructure at a scale and diversity that physical evaluation alone cannot provide. We introduce MolmoSpaces, a fully open ecosystem to support large-scale benchmarking of robot policies. MolmoSpaces consists of over 230k diverse indoor environments, ranging from handcrafted household scenes to procedurally generated multiroom houses, populated with 130k richly annotated object assets, including 48k manipulable objects with 42M stable grasps. Crucially, these environments are simulator-agnostic, supporting popular options such as MuJoCo, Isaac, and ManiSkill. The ecosystem supports the full spectrum of embodied tasks: static and mobile manipulation, navigation, and multiroom long-horizon tasks requiring coordinated perception, planning, and interaction across entire indoor environments. We also design MolmoSpaces-Bench, a benchmark suite of 8 tasks in which robots interact with our diverse scenes and richly annotated objects. Our experiments show MolmoSpaces-Bench exhibits strong sim-to-real correlation (R = 0.96, \r{ho} = 0.98), confirm newer and stronger zero-shot policies outperform earlier versions in our benchmarks, and identify key sensitivities to prompt phrasing, initial joint positions, and camera occlusion. Through MolmoSpaces and its open-source assets and tooling, we provide a foundation for scalable data generation, policy training, and benchmark creation for robot learning research. --- ### Traffic Flow Reconstruction from Limited Collected Data Authors: Nail Baloul, Amaury Hayat, Thibault Liard, Pierre Lissy Published: 2026-02-11 Categories: math.DS, cs.LG arXiv: https://arxiv.org/abs/2602.11336v1 We propose an efficient method for reconstructing traffic density with low penetration rate of probe vehicles. Specifically, we rely on measuring only the initial and final positions of a small number of cars which are generated using microscopic dynamical systems. We then implement a machine learning algorithm from scratch to reconstruct the approximate traffic density. This approach leverages learning techniques to improve the accuracy of density reconstruction despite constraints in available data. For the sake of consistency, we will prove that, if only using data from dynamical systems, the approximate density predicted by our learned-based model converges to a well-known macroscopic traffic flow model when the number of vehicles approaches infinity. --- ### Cross-Fitting-Free Debiased Machine Learning with Multiway Dependence Authors: Kaicheng Chen, Harold D. Chiang Published: 2026-02-11 Categories: econ.EM, stat.ML arXiv: https://arxiv.org/abs/2602.11333v5 This paper develops an asymptotic theory for two-step debiased machine learning (DML) estimators in generalised method of moments (GMM) models with general multiway clustered dependence, without relying on cross-fitting. While cross-fitting is commonly employed, it can be statistically inefficient and computationally burdensome when first-stage learners are complex and the effective sample size is governed by the number of independent clusters. We show that valid inference can be achieved without sample splitting by combining orthogonal moments with a localisation-based empirical process approach, allowing for an arbitrary number of clustering dimensions. The resulting debiased GMM estimators are shown to be asymptotically linear and asymptotically normal under multiway clustered dependence. A central technical contribution of the paper is the derivation of novel global and local maximal inequalities for empirical processes indexed by general classes of functions for separately exchangeable arrays, which underpin our theoretical arguments and are of independent interest. Python and R packages are available for implementing the proposed procedures. --- ### Cross-Fitting-Free Debiased Machine Learning with Multiway Dependence Authors: Kaicheng Chen, Harold D. Chiang Published: 2026-02-11 Categories: econ.EM, stat.ML arXiv: https://arxiv.org/abs/2602.11333v2 This paper develops an asymptotic theory for two-step debiased machine learning (DML) estimators in generalised method of moments (GMM) models with general multiway clustered dependence, without relying on cross-fitting. While cross-fitting is commonly employed, it can be statistically inefficient and computationally burdensome when first-stage learners are complex and the effective sample size is governed by the number of independent clusters. We show that valid inference can be achieved without sample splitting by combining Neyman-orthogonal moment conditions with a localisation-based empirical process approach, allowing for an arbitrary number of clustering dimensions. The resulting debiased GMM estimators are shown to be asymptotically linear and asymptotically normal under multiway clustered dependence. A central technical contribution of the paper is the derivation of novel global and local maximal inequalities for general classes of functions of sums of separately exchangeable arrays, which underpin our theoretical arguments and are of independent interest. --- ### Sample-Free Safety Assessment of Neural Network Controllers via Taylor Methods Authors: Adam Evans, Roberto Armellin Published: 2026-02-11 Categories: eess.SY, cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.11332v1 In recent years, artificial neural networks have been increasingly studied as feedback controllers for guidance problems. While effective in complex scenarios, they lack the verification guarantees found in classical guidance policies. Their black-box nature creates significant concerns regarding trustworthiness, limiting their adoption in safety-critical spaceflight applications. This work addresses this gap by developing a method to assess the safety of a trained neural network feedback controller via automatic domain splitting and polynomial bounding. The methodology involves embedding the trained neural network into the system's dynamical equations, rendering the closed-loop system autonomous. The system flow is then approximated by high-order Taylor polynomials, which are subsequently manipulated to construct polynomial maps that project state uncertainties onto an event manifold. Automatic domain splitting ensures the polynomials are accurate over their relevant subdomains, whilst also allowing an extensive state-space to be analysed efficiently. Utilising polynomial bounding techniques, the resulting event values may be rigorously constrained and analysed within individual subdomains, thereby establishing bounds on the range of possible closed-loop outcomes from using such neural network controllers and supporting safety assessment and informed operational decision-making in real-world missions. --- ### Evaluating Alignment of Behavioral Dispositions in LLMs Authors: Amir Taubenfeld, Zorik Gekhman, Lior Nezry, Omri Feldman, Natalie Harris, Shashir Reddy, Romina Stella, Ariel Goldstein, Marian Croak, Yossi Matias, Amir Feder Published: 2026-02-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11328v1 As LLMs integrate into our daily lives, understanding their behavior becomes essential. In this work, we focus on behavioral dispositions$-$the underlying tendencies that shape responses in social contexts$-$and introduce a framework to study how closely the dispositions expressed by LLMs align with those of humans. Our approach is grounded in established psychological questionnaires but adapts them for LLMs by transforming human self-report statements into Situational Judgment Tests (SJTs). These SJTs assess behavior by eliciting natural recommendations in realistic user-assistant scenarios. We generate 2,500 SJTs, each validated by three human annotators, and collect preferred actions from 10 annotators per SJT, from a large pool of 550 participants. In a comprehensive study involving 25 LLMs, we find that models often do not reflect the distribution of human preferences: (1) in scenarios with low human consensus, LLMs consistently exhibit overconfidence in a single response; (2) when human consensus is high, smaller models deviate significantly, and even some frontier models do not reflect the consensus in 15-20% of cases; (3) traits can exhibit cross-LLM patterns, e.g., LLMs may encourage emotion expression in contexts where human consensus favors composure. Lastly, mapping psychometric statements directly to behavioral scenarios presents a unique opportunity to evaluate the predictive validity of self-reports, revealing considerable gaps between LLMs' stated values and their revealed behavior. --- ### Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP Authors: Zeynab Anbiaee, Mahdi Rabbani, Mansur Mirani, Gunjan Piya, Igor Opushnyev, Ali Ghorbani, Sajjad Dadkhah Published: 2026-02-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.11327v2 The rapid development of the AI agent communication protocols, including the Model Context Protocol (MCP), Agent2Agent (A2A), Agora, and Agent Network Protocol (ANP), is reshaping how AI agents communicate with tools, services, and each other. While these protocols support scalable multi-agent interaction and cross-organizational interoperability, their security principles remain understudied, and standardized threat modeling is limited; no protocol-centric risk assessment framework has been established yet. This paper presents a systematic security analysis of four emerging AI agent communication protocols. First, we develop a structured threat modeling analysis that examines protocol architectures, trust assumptions, interaction patterns, and lifecycle behaviors to identify protocol-specific and cross-protocol risk surfaces. Second, we introduce a qualitative risk assessment framework that identifies twelve protocol-level risks and evaluates security posture across the creation, operation, and update phases through systematic assessment of likelihood, impact, and overall protocol risk, with implications for secure deployment and future standardization. Third, we provide a measurement-driven case study on MCP that formalizes the risk of missing mandatory validation/attestation for executable components as a falsifiable security claim by quantifying wrong-provider tool execution under multi-server composition across representative resolver policies. Collectively, our results highlight key design-induced risk surfaces and provide actionable guidance for secure deployment and future standardization of agent communication ecosystems. --- ### Amortised and provably-robust simulation-based inference Authors: Ayush Bharti, Charita Dellaporta, Yuga Hikida, François-Xavier Briol Published: 2026-02-11 Categories: stat.ML, cs.LG, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2602.11325v2 Complex simulator-based models are now routinely used to perform inference across the sciences and engineering, but existing inference methods are often unable to account for outliers and other extreme values in data which occur due to faulty measurement instruments or human error. In this paper, we introduce a novel approach to simulation-based inference grounded in generalised Bayesian inference and a neural approximation of a weighted score-matching loss. This leads to a method that is both amortised and provably robust to outliers, a combination not achieved by existing approaches. Furthermore, through a carefully chosen conditional density model, we demonstrate that inference can be further simplified and performed without the need for Markov chain Monte Carlo sampling, thereby offering significant computational advantages, with complexity that is only a small fraction of that of current state-of-the-art approaches. --- ### MDE-VIO: Enhancing Visual-Inertial Odometry Using Learned Depth Priors Authors: Arda Alniak, Sinan Kalkan, Mustafa Mert Ankarali, Afsar Saranli, Abdullah Aydin Alatan Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11323v2 Traditional monocular Visual-Inertial Odometry (VIO) systems struggle in low-texture environments where sparse visual features are insufficient for accurate pose estimation. To address this, dense Monocular Depth Estimation (MDE) has been widely explored as a complementary information source. While recent Vision Transformer (ViT) based complex foundational models offer dense, geometrically consistent depth, their computational demands typically preclude them from real-time edge deployment. Our work bridges this gap by integrating learned depth priors directly into the VINS-Mono optimization backend. We propose a novel framework that enforces affine-invariant depth consistency and pairwise ordinal constraints, explicitly filtering unstable artifacts via variance-based gating. This approach strictly adheres to the computational limits of edge devices while robustly recovering metric scale. Extensive experiments on the TartanGround and M3ED datasets demonstrate that our method prevents divergence in challenging scenarios and delivers significant accuracy gains, reducing Absolute Trajectory Error (ATE) by up to 28.3%. Code will be made available. --- ### MDE-VIO: Enhancing Visual-Inertial Odometry Using Learned Depth Priors Authors: Arda Alniak, Sinan Kalkan, Mustafa Mert Ankarali, Afsar Saranli, Abdullah Aydin Alatan Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11323v1 Traditional monocular Visual-Inertial Odometry (VIO) systems struggle in low-texture environments where sparse visual features are insufficient for accurate pose estimation. To address this, dense Monocular Depth Estimation (MDE) has been widely explored as a complementary information source. While recent Vision Transformer (ViT) based complex foundational models offer dense, geometrically consistent depth, their computational demands typically preclude them from real-time edge deployment. Our work bridges this gap by integrating learned depth priors directly into the VINS-Mono optimization backend. We propose a novel framework that enforces affine-invariant depth consistency and pairwise ordinal constraints, explicitly filtering unstable artifacts via variance-based gating. This approach strictly adheres to the computational limits of edge devices while robustly recovering metric scale. Extensive experiments on the TartanGround and M3ED datasets demonstrate that our method prevents divergence in challenging scenarios and delivers significant accuracy gains, reducing Absolute Trajectory Error (ATE) by up to 28.3%. Code will be made available. --- ### Predictive Associative Memory: Retrieval Beyond Similarity Through Temporal Co-occurrence Authors: Jason Dury Published: 2026-02-11 Categories: cs.LG, cs.AI, cs.IR, cs.NE arXiv: https://arxiv.org/abs/2602.11322v1 Current approaches to memory in neural systems rely on similarity-based retrieval: given a query, find the most representationally similar stored state. This assumption -- that useful memories are similar memories -- fails to capture a fundamental property of biological memory: association through temporal co-occurrence. We propose Predictive Associative Memory (PAM), an architecture in which a JEPA-style predictor, trained on temporal co-occurrence within a continuous experience stream, learns to navigate the associative structure of an embedding space. We introduce an Inward JEPA that operates over stored experience (predicting associatively reachable past states) as the complement to the standard Outward JEPA that operates over incoming sensory data (predicting future states). We evaluate PAM as an associative recall system -- testing faithfulness of recall for experienced associations -- rather than as a retrieval system evaluated on generalisation to unseen associations. On a synthetic benchmark, the predictor's top retrieval is a true temporal associate 97% of the time (Association Precision@1 = 0.970); it achieves cross-boundary Recall@20 = 0.421 where cosine similarity scores zero; and it separates experienced-together from never-experienced-together states with a discrimination AUC of 0.916 (cosine: 0.789). Even restricted to cross-room pairs where embedding similarity is uninformative, the predictor achieves AUC = 0.849 (cosine: 0.503, chance). A temporal shuffle control confirms the signal is genuine temporal co-occurrence structure, not embedding geometry: shuffling collapses cross-boundary recall by 90%, replicated across training seeds. All results are stable across seeds (SD < 0.006) and query selections (SD $\leq$ 0.012). --- ### Efficient Analysis of the Distilled Neural Tangent Kernel Authors: Jamie Mahowald, Brian Bell, Alex Ho, Michael Geyer Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11320v2 Neural tangent kernel (NTK) methods are computationally limited by the need to evaluate large Jacobians across many data points. Existing approaches reduce this cost primarily through projecting and sketching the Jacobian. We show that NTK computation can also be reduced by compressing the data dimension itself using NTK-tuned dataset distillation. We demonstrate that the neural tangent space spanned by the input data can be induced by dataset distillation, yielding a 20-100$\times$ reduction in required Jacobian calculations. We further show that per-class NTK matrices have low effective rank that is preserved by this reduction. Building on these insights, we propose the distilled neural tangent kernel (DNTK), which combines NTK-tuned dataset distillation with state-of-the-art projection methods to reduce up NTK computational complexity by up to five orders of magnitude while preserving kernel structure and predictive performance. --- ### The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotation Authors: Sheza Munir, Benjamin Mah, Krisha Kalsi, Shivani Kapania, Julian Posada, Edith Law, Ding Wang, Syed Ishtiaque Ahmed Published: 2026-02-11 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2602.11318v3 In machine learning, "ground truth" refers to the assumed correct labels used to train and evaluate models. However, the foundational "ground truth" paradigm rests on a positivistic fallacy that treats human disagreement as technical noise rather than a vital sociotechnical signal. This systematic literature review analyzes research published between 2020 and 2025 across seven premier venues: ACL, AIES, CHI, CSCW, EAAMO, FAccT, and NeurIPS, investigating the mechanisms in data annotation practices that facilitate this "consensus trap". Our reflexive thematic analysis of 346 papers reveals that systemic failures in positional legibility, combined with the recent architectural shift toward human-as-verifier models, specifically the reliance on model-mediated annotations, introduce deep-seated anchoring bias and effectively remove human voices from the loop. We further demonstrate how geographic hegemony imposes Western norms as universal benchmarks, often enforced by the performative alignment of precarious data workers who prioritize requester compliance over honest subjectivity to avoid economic penalties. Critiquing the "noisy sensor" fallacy, where statistical models misdiagnose pluralism as error, we argue for reclaiming disagreement as a high-fidelity signal essential for building culturally competent models. To address these systemic tensions, we propose a roadmap for pluralistic annotation infrastructures that shift the objective from discovering a singular "right" answer to mapping the diversity of human experience. --- ### Selective Prior Synchronization via SYNC Loss Authors: Ishan Mishra, Jiajie Li, Deepak Mishra, Jinjun Xiong Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11316v1 Prediction under uncertainty is a critical requirement for the deep neural network to succeed responsibly. This paper focuses on selective prediction, which allows DNNs to make informed decisions about when to predict or abstain based on the uncertainty level of their predictions. Current methods are either ad-hoc such as SelectiveNet, focusing on how to modify the network architecture or objective function, or post-hoc such as softmax response, achieving selective prediction through analyzing the model's probabilistic outputs. We observe that post-hoc methods implicitly generate uncertainty information, termed the selective prior, which has traditionally been used only during inference. We argue that the selective prior provided by the selection mechanism is equally vital during the training stage. Therefore, we propose the SYNC loss which introduces a novel integration of ad-hoc and post-hoc method. Specifically, our approach incorporates the softmax response into the training process of SelectiveNet, enhancing its selective prediction capabilities by examining the selective prior. Evaluated across various datasets, including CIFAR-100, ImageNet-100, and Stanford Cars, our method not only enhances the model's generalization capabilities but also surpasses previous works in selective prediction performance, and sets new benchmarks for state-of-the-art performance. --- ### Advancing Digital Twin Generation Through a Novel Simulation Framework and Quantitative Benchmarking Authors: Jacob Rubinstein, Avi Donaty, Don Engel Published: 2026-02-11 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.11314v1 The generation of 3D models from real-world objects has often been accomplished through photogrammetry, i.e., by taking 2D photos from a variety of perspectives and then triangulating matched point-based features to create a textured mesh. Many design choices exist within this framework for the generation of digital twins, and differences between such approaches are largely judged qualitatively. Here, we present and test a novel pipeline for generating synthetic images from high-quality 3D models and programmatically generated camera poses. This enables a wide variety of repeatable, quantifiable experiments which can compare ground-truth knowledge of virtual camera parameters and of virtual objects against the reconstructed estimations of those perspectives and subjects. --- ### Hierarchical Testing of a Hybrid Machine Learning-Physics Global Atmosphere Model Authors: Ziming Chen, L. Ruby Leung, Wenyu Zhou, Jian Lu, Sandro W. Lubis, Ye Liu, Chuan-Chieh Chang, Bryce E. Harrop, Ya Wang, Mingshi Yang, Gan Zhang, Yun Qian Published: 2026-02-11 Categories: physics.ao-ph, cs.LG, physics.geo-ph arXiv: https://arxiv.org/abs/2602.11313v1 Machine learning (ML)-based models have demonstrated high skill and computational efficiency, often outperforming conventional physics-based models in weather and subseasonal predictions. While prior studies have assessed their fidelity in capturing synoptic-scale atmospheric dynamics, their performance across timescales and under out-of-distribution forcing, such as +3K or +4K uniform-warming forcings, and the sources of biases remain elusive, to establish the model reliability for Earth science. Here, we design three sets of experiments targeting synoptic-scale phenomena, interannual variability, and out-of-distribution uniform-warming forcings. We evaluate the Neural General Circulation Model (NeuralGCM), a hybrid model integrating a dynamical core with ML-based component, against observations and physics-based Earth system models (ESMs). At the synoptic scale, NeuralGCM captures the evolution and propagation of extratropical cyclones with performance comparable to ESMs. At the interannual scale, when forced by El Niño-Southern Oscillation sea surface temperature (SST) anomalies, NeuralGCM successfully reproduces associated teleconnection patterns but exhibits deficiencies in capturing nonlinear response. Under out-of-distribution uniform-warming forcings, NeuralGCM simulates similar responses in global-average temperature and precipitation and reproduces large-scale tropospheric circulation features similar to those in ESMs. Notable weaknesses include overestimating the tracks and spatial extent of extratropical cyclones, biases in the teleconnected wave train triggered by tropical SST anomalies, and differences in upper-level warming and stratospheric circulation responses to SST warming compared to physics-based ESMs. The causes of these weaknesses were explored. --- ### Are Aligned Large Language Models Still Misaligned? Authors: Usman Naseem, Gautam Siddharth Kashyap, Rafiq Ali, Ebad Shabbir, Sushant Kumar Ray, Abdullah Mohammad, Agrima Seth Published: 2026-02-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11305v1 Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a real-world query. Existing misalignment benchmarks-such as INSECURE CODE (safety-centric), VALUEACTIONLENS (value-centric), and CULTURALHERITAGE (culture centric)-rely on evaluating misalignment along individual dimensions, preventing simultaneous evaluation. To address this gap, we introduce Mis-Align Bench, a unified benchmark for analyzing misalignment across safety, value, and cultural dimensions. First we constructs SAVACU, an English misaligned-aligned dataset of 382,424 samples spanning 112 domains (or labels), by reclassifying prompts from the LLM-PROMPT-DATASET via taxonomy into 14 safety domains, 56 value domains, and 42 cultural domains using Mistral-7B-Instruct-v0.3, and expanding low-resource domains via Llama-3.1-8B-Instruct with SimHash-based fingerprint to avoid deduplication. Furthermore, we pairs prompts with misaligned and aligned responses via two-stage rejection sampling to enforce quality. Second we benchmarks general-purpose, fine-tuned, and open-weight LLMs, enabling systematic evaluation of misalignment under three dimensions. Empirically, single-dimension models achieve high Coverage (upto 97.6%) but incur False Failure Rate >50% and lower Alignment Score (63%-66%) under joint conditions. --- ### CryptoAnalystBench: Failures in Multi-Tool Long-Form LLM Analysis Authors: Anushri Eswaran, Oleg Golev, Darshan Tank, Sidhant Rahi, Himanshu Tyagi Published: 2026-02-11 Categories: cs.IR, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.11304v1 Modern analyst agents must reason over complex, high token inputs, including dozens of retrieved documents, tool outputs, and time sensitive data. While prior work has produced tool calling benchmarks and examined factuality in knowledge augmented systems, relatively little work studies their intersection: settings where LLMs must integrate large volumes of dynamic, structured and unstructured multi tool outputs. We investigate LLM failure modes in this regime using crypto as a representative high data density domain. We introduce (1) CryptoAnalystBench, an analyst aligned benchmark of 198 production crypto and DeFi queries spanning 11 categories; (2) an agentic harness equipped with relevant crypto and DeFi tools to generate responses across multiple frontier LLMs; and (3) an evaluation pipeline with citation verification and an LLM as a judge rubric spanning four user defined success dimensions: relevance, temporal relevance, depth, and data consistency. Using human annotation, we develop a taxonomy of seven higher order error types that are not reliably captured by factuality checks or LLM based quality scoring. We find that these failures persist even in state of the art systems and can compromise high stakes decisions. Based on this taxonomy, we refine the judge rubric to better capture these errors. While the judge does not align with human annotators on precise scoring across rubric iterations, it reliably identifies critical failure modes, enabling scalable feedback for developers and researchers studying analyst style agents. We release CryptoAnalystBench with annotated queries, the evaluation pipeline, judge rubrics, and the error taxonomy, and outline mitigation strategies and open challenges in evaluating long form, multi tool augmented systems. --- ### The PBSAI Governance Ecosystem: A Multi-Agent AI Reference Architecture for Securing Enterprise AI Estates Authors: John M. Willis Published: 2026-02-11 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.11301v1 Enterprises are rapidly deploying large language models, retrieval augmented generation pipelines, and tool using agents into production, often on shared high performance computing clusters and cloud accelerator platforms that also support defensive analytics. These systems increasingly function not as isolated models but as AI estates: socio technical systems spanning models, agents, data pipelines, security tooling, human workflows, and hyperscale infrastructure. Existing governance and security frameworks, including the NIST AI Risk Management Framework and systems security engineering guidance, articulate principles and risk functions but do not provide implementable architectures for multi agent, AI enabled cyber defense. This paper introduces the Practitioners Blueprint for Secure AI (PBSAI) Governance Ecosystem, a multi agent reference architecture for securing enterprise and hyperscale AI estates. PBSAI organizes responsibilities into a twelve domain taxonomy and defines bounded agent families that mediate between tools and policy through shared context envelopes and structured output contracts. The architecture assumes baseline enterprise security capabilities and encodes key systems security techniques, including analytic monitoring, coordinated defense, and adaptive response. A lightweight formal model of agents, context envelopes, and ecosystem level invariants clarifies the traceability, provenance, and human in the loop guarantees enforced across domains. We demonstrate alignment with NIST AI RMF functions and illustrate application in enterprise SOC and hyperscale defensive environments. PBSAI is proposed as a structured, evidence centric foundation for open ecosystem development and future empirical validation. --- ### Voxtral Realtime Authors: Mistral-AI, :, Alexander H. Liu, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume Lample, Jean-Malo Delignon, Khyathi Raghavi Chandu, Patrick von Platen, Pavankumar Reddy Muddireddy, Rohin Arora et al. Published: 2026-02-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.11298v3 We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adapt offline models through chunking or sliding windows, Voxtral Realtime is trained end-to-end for streaming, with explicit alignment between audio and text streams. Our architecture builds on the Delayed Streams Modeling framework, introducing a new causal audio encoder and Ada RMS-Norm for improved delay conditioning. We scale pretraining to a large-scale dataset spanning 13 languages. At a delay of 480ms, Voxtral Realtime achieves performance on par with Whisper, the most widely deployed offline transcription system. We release the model weights under the Apache 2.0 license. --- ### On Decision-Valued Maps and Representational Dependence Authors: Gil Raitses Published: 2026-02-11 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2602.11295v1 A computational engine applied to different representations of the same data can produce different discrete outcomes, with some representations preserving the result and others changing it entirely. A decision-valued map records which representations preserve the outcome and which change it, associating each member of a declared representation family with the discrete result it produces. This paper formalizes decision-valued maps and describes DecisionDB, an infrastructure that logs, replays and audits these relationships using identifiers computed from content and artifacts stored in write-once form. Deterministic replay recovers each recorded decision identifier exactly from stored artifacts, with all three identifying fields matching their persisted values. The contribution partitions representation space into persistence regions and boundaries, and treats decision reuse as a mechanically checkable condition. --- ### HiFloat4 Format for Language Model Inference Authors: Yuanyong Luo, Jing Huang, Yu Cheng, Ziwei Yu, Kaihua Tang, Xinda Ma, Xin Wang, Anping Tong, Guipeng Hu, Yun Xu, Mehran Taghian, Peng Wu et al. Published: 2026-02-11 Categories: cs.LG, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2602.11287v2 This paper introduces HiFloat4 (HiF4), a block floating-point data format tailored for deep learning. Each HiF4 unit packs 64 4-bit elements with 32 bits of shared scaling metadata, averaging 4.5 bits per value. The metadata specifies a three-level scaling hierarchy, capturing inter- and intra-group dynamic range while improving the utilization of the representational space. In addition, the large 64-element group size enables matrix multiplications to be executed in a highly fixed-point manner, significantly reducing hardware area and power consumption. To evaluate the proposed format, we conducted inference experiments on several language models, including LLaMA, Qwen, Mistral, DeepSeek-V3.1 and LongCat. Results show that HiF4 achieves higher average accuracy than the state-of-the-art NVFP4 format across multiple models and diverse downstream tasks. --- ### DeepRed: an architecture for redshift estimation Authors: Alessandro Meroni, Nicolò Oreste Pinciroli Vago, Piero Fraternali Published: 2026-02-11 Categories: astro-ph.IM, cs.AI, cs.LG, gr-qc arXiv: https://arxiv.org/abs/2602.11281v1 Estimating redshift is a central task in astrophysics, but its measurement is costly and time-consuming. In addition, current image-based methods are often validated on homogeneous datasets. The development and comparison of networks able generalize across different morphologies, ranging from galaxies to gravitationally-lensed transients, and observational conditions, remain an open challenge. This work proposes DeepRed, a deep learning pipeline that demonstrates how modern computer vision architectures, including ResNet, EfficientNet, Swin Transformer, and MLP-Mixer, can estimate redshifts from images of galaxies, gravitational lenses, and gravitationally-lensed supernovae. We compare these architectures and their ensemble to both neural networks (A1, A3, NetZ, and PhotoZ) and a feature-based method (HOG+SVR) on simulated (DeepGraviLens) and real (KiDS, SDSS) datasets. Our approach achieves state-of-the-art results on all datasets. On DeepGraviLens, DeepRed achieves a significant improvement in the Normalized Mean Absolute Deviation compared to the best baseline (PhotoZ): 55% on DES-deep (using EfficientNet), 51% on DES-wide (Ensemble), 52% on DESI-DOT (Ensemble), and 46% on LSST-wide (Ensemble). On real observations from the KiDS survey, the pipeline outperforms the best baseline (NetZ), improving NMAD by 16% on a general test set without high-probability lenses (Ensemble) and 27% on high-probability lenses (Ensemble). For non-lensed galaxies in the SDSS dataset, the MLP-Mixer architecture achieves a 5% improvement over the best baselines (A3 and NetZ). SHAP shows that the models correctly focus on the objects of interest with over 95% localization accuracy on high-quality images, validating the reliability of the predictions. These findings suggest that deep learning is a scalable, robust, and interpretable solution for redshift estimation in large-scale surveys. --- ### Unlearnable phases of matter Authors: Tarun Advaith Kumar, Yijian Zou, Amir-Reza Negari, Roger G. Melko, Timothy H. Hsieh Published: 2026-02-11 Categories: cond-mat.dis-nn, cs.LG, quant-ph arXiv: https://arxiv.org/abs/2602.11262v2 We identify fundamental limitations in machine learning by demonstrating that non-trivial mixed-state phases of matter are computationally hard to learn. Focusing on unsupervised learning of distributions, we show that autoregressive neural networks fail to learn global properties of distributions characterized by locally indistinguishable (LI) states. We demonstrate that conditional mutual information (CMI) is a useful diagnostic for LI: we show that for classical distributions, long-range CMI of a state implies a spatially LI partner. By introducing a restricted statistical query model, we prove that nontrivial phases with long-range CMI, such as strong-to-weak spontaneous symmetry breaking phases, are hard to learn. We validate our claims by using recurrent, convolutional, and Transformer neural networks to learn the syndrome and physical distributions of toric/surface code under bit flip noise. Our findings suggest hardness of learning as a diagnostic tool for detecting mixed-state phases and transitions and error-correction thresholds, and they suggest CMI and more generally ``non-local Gibbsness'' as metrics for how hard a distribution is to learn. --- ### Peak + Accumulation: A Proxy-Level Scoring Formula for Multi-Turn LLM Attack Detection Authors: J Alex Corll Published: 2026-02-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.11247v2 Multi-turn prompt injection attacks distribute malicious intent across multiple conversation turns, exploiting the assumption that each turn is evaluated independently. While single-turn detection has been extensively studied, no published formula exists for aggregating per-turn pattern scores into a conversation-level risk score at the proxy layer -- without invoking an LLM. We identify a fundamental flaw in the intuitive weighted-average approach: it converges to the per-turn score regardless of turn count, meaning a 20-turn persistent attack scores identically to a single suspicious turn. Drawing on analogies from change-point detection (CUSUM), Bayesian belief updating, and security risk-based alerting, we propose peak + accumulation scoring -- a formula combining peak single-turn risk, persistence ratio, and category diversity. Evaluated on 10,654 multi-turn conversations -- 588 attacks sourced from WildJailbreak adversarial prompts and 10,066 benign conversations from WildChat -- the formula achieves 90.8% recall at 1.20% false positive rate with an F1 of 85.9%. A sensitivity analysis over the persistence parameter reveals a phase transition at rho ~ 0.4, where recall jumps 12 percentage points with negligible FPR increase. We release the scoring algorithm, pattern library, and evaluation harness as open source. --- ### How Many Features Can a Language Model Store Under the Linear Representation Hypothesis? Authors: Nikhil Garg, Jon Kleinberg, Kenny Peng Published: 2026-02-11 Categories: cs.LG, cs.AI, cs.CL, cs.IT, math.CO arXiv: https://arxiv.org/abs/2602.11246v1 We introduce a mathematical framework for the linear representation hypothesis (LRH), which asserts that intermediate layers of language models store features linearly. We separate the hypothesis into two claims: linear representation (features are linearly embedded in neuron activations) and linear accessibility (features can be linearly decoded). We then ask: How many neurons $d$ suffice to both linearly represent and linearly access $m$ features? Classical results in compressed sensing imply that for $k$-sparse inputs, $d = O(k\log (m/k))$ suffices if we allow non-linear decoding algorithms (Candes and Tao, 2006; Candes et al., 2006; Donoho, 2006). However, the additional requirement of linear decoding takes the problem out of the classical compressed sensing, into linear compressed sensing. Our main theoretical result establishes nearly-matching upper and lower bounds for linear compressed sensing. We prove that $d = Ω_ε(\frac{k^2}{\log k}\log (m/k))$ is required while $d = O_ε(k^2\log m)$ suffices. The lower bound establishes a quantitative gap between classical and linear compressed setting, illustrating how linear accessibility is a meaningfully stronger hypothesis than linear representation alone. The upper bound confirms that neurons can store an exponential number of features under the LRH, giving theoretical evidence for the "superposition hypothesis" (Elhage et al., 2022). The upper bound proof uses standard random constructions of matrices with approximately orthogonal columns. The lower bound proof uses rank bounds for near-identity matrices (Alon, 2003) together with Turán's theorem (bounding the number of edges in clique-free graphs). We also show how our results do and do not constrain the geometry of feature representations and extend our results to allow decoders with an activation function and bias. --- ### Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models Authors: Sethuraman T, Savya Khosla, Aditi Tiwari, Vidya Ganesh, Rakshana Jayaprakash, Aditya Jain, Vignesh Srinivasakumar, Onkar Kishor Susladkar, Srinidhi Sunkara, Aditya Shanmugham, Rakesh Vaideeswaran, Abbaas Alif Mohamed Nishar et al. Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11244v2 Video-Language Models (VidLMs) achieve strong benchmark scores, yet these scores often hide whether models use the video at all. We show that VidLM failures follow two pathways: some visual signals are never reliably encoded, while others are encoded but overridden by model priors. We introduce REVEAL, a diagnostic stress-test benchmark for quantifying when and why VidLMs under-use visual evidence. REVEAL contains five controlled probes: camera-motion sensitivity, cross-frame integration, video sycophancy, language-only shortcuts, and temporal expectation bias. Together, they test whether models encode basic video signals, combine evidence across frames, and preserve visual evidence against user assertions, language cues, and learned event expectations. Across 12 VidLMs we find systematic failures along both pathways, with most models falling below chance on the binary and six-way probes that humans solve at 78--100% accuracy. Under assertive prompts, a model's output distribution becomes nearly invariant to whether it is shown a real video or random noise, making visual evidence effectively causally inert. We further carry out mechanistic probes to identify where these failures arise in the model pipeline and why visual evidence is lost. REVEAL provides a scalable, human-verified framework for moving beyond aggregate scores toward structured, reproducible evaluation of multimodal reliability. --- ### Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models Authors: Sethuraman T, Savya Khosla, Aditi Tiwari, Vidya Ganesh, Rakshana Jayaprakash, Aditya Jain, Vignesh Srinivasakumar, Onkar Kishor Susladkar, Srinidhi Sunkara, Aditya Shanmugham, Rakesh Vaideeswaran, Abbaas Alif Mohamed Nishar et al. Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11244v1 This work investigates a fundamental question: Do Video-Language Models (VidLMs) robustly account for video content, temporal sequence, and motion? Our investigation shows that, surprisingly, they often do not. We introduce REVEAL{}, a diagnostic benchmark that probes fundamental weaknesses of contemporary VidLMs through five controlled stress tests; assessing temporal expectation bias, reliance on language-only shortcuts, video sycophancy, camera motion sensitivity, and robustness to spatiotemporal occlusion. We test leading open- and closed-source VidLMs and find that these models confidently describe reversed scenes as forward, answer questions while neglecting video content, agree with false claims, struggle with basic camera motion, and fail to aggregate temporal information amidst simple spatiotemporal masking. Humans, on the other hand, succeed at these tasks with ease. Alongside our benchmark, we provide a data pipeline that automatically generates diagnostic examples for our stress tests, enabling broader and more scalable evaluation. We will release our benchmark and code to support future research. --- ### Evaluating Memory Structure in LLM Agents Authors: Alina Shutova, Alexandra Olenina, Ivan Vinogradov, Anton Sinitsin Published: 2026-02-11 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.11243v3 Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augment reasoning. As researchers create more complex memory architectures, it becomes increasingly difficult to analyze their capabilities and guide future memory designs. Most long-term memory benchmarks focus on simple fact retention, multi-hop recall, and time-based changes. While undoubtedly important, these capabilities can often be achieved with simple retrieval-augmented LLMs and do not test complex memory hierarchies. To bridge this gap, we propose StructMemEval - a benchmark that tests the agent's ability to organize its long-term memory, not just factual recall. We gather a suite of tasks that humans solve by organizing their knowledge in a specific structure: transaction ledgers, to-do lists, trees and others. Our initial experiments show that simple retrieval-augmented LLMs struggle with these tasks, whereas memory agents can reliably solve them if prompted how to organize their memory. However, we also find that modern LLMs do not always recognize the memory structure when not prompted to do so. This highlights an important direction for future improvements in both LLM training and memory frameworks. --- ### Evaluating Memory Structure in LLM Agents Authors: Alina Shutova, Alexandra Olenina, Ivan Vinogradov, Anton Sinitsin Published: 2026-02-11 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.11243v2 Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augment reasoning. As researchers create more complex memory architectures, it becomes increasingly difficult to analyze their capabilities and guide future memory designs. Most long-term memory benchmarks focus on simple fact retention, multi-hop recall, and time-based changes. While undoubtedly important, these capabilities can often be achieved with simple retrieval-augmented LLMs and do not test complex memory hierarchies. To bridge this gap, we propose StructMemEval - a benchmark that tests the agent's ability to organize its long-term memory, not just factual recall. We gather a suite of tasks that humans solve by organizing their knowledge in a specific structure: transaction ledgers, to-do lists, trees and others. Our initial experiments show that simple retrieval-augmented LLMs struggle with these tasks, whereas memory agents can reliably solve them if prompted how to organize their memory. However, we also find that modern LLMs do not always recognize the memory structure when not prompted to do so. This highlights an important direction for future improvements in both LLM training and memory frameworks. --- ### ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems Authors: Yitong Wang, Yue Yao Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11242v1 We present ReTracing, a multi-agent embodied performance art that adopts an archaeological approach to examine how artificial intelligence shapes, constrains, and produces bodily movement. Drawing from science-fiction novels, the project extracts sentences that describe human-machine interaction. We use large language models (LLMs) to generate paired prompts "what to do" and "what not to do" for each excerpt. A diffusion-based text-to-video model transforms these prompts into choreographic guides for a human performer and motor commands for a quadruped robot. Both agents enact the actions on a mirrored floor, captured by multi-camera motion tracking and reconstructed into 3D point clouds and motion trails, forming a digital archive of motion traces. Through this process, ReTracing serves as a novel approach to reveal how generative systems encode socio-cultural biases through choreographed movements. Through an immersive interplay of AI, human, and robot, ReTracing confronts a critical question of our time: What does it mean to be human among AIs that also move, think, and leave traces behind? --- ### Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration Authors: Jinghan He, Junfeng Fang, Feng Xiong, Zijun Yao, Fei Shen, Haiyun Guo, Jinqiao Wang, Tat-Seng Chua Published: 2026-02-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.11241v1 Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passive interaction with static image collections, resulting in strong dependence on initial datasets and inefficient learning. Without the ability to actively seek visual data tailored to their evolving capabilities, agents waste computational effort on samples that are either trivial or beyond their current skill level. To address these limitations, we propose Active-Zero, a framework that shifts from passive interaction to active exploration of visual environments. Active-Zero employs three co-evolving agents: a Searcher that retrieves images from open-world repositories based on the model's capability frontier, a Questioner that synthesizes calibrated reasoning tasks, and a Solver refined through accuracy rewards. This closed loop enables self-scaffolding auto-curricula where the model autonomously constructs its learning trajectory. On Qwen2.5-VL-7B-Instruct across 12 benchmarks, Active-Zero achieves 53.97 average accuracy on reasoning tasks (5.7% improvement) and 59.77 on general understanding (3.9% improvement), consistently outperforming existing self-play baselines. These results highlight active exploration as a key ingredient for scalable and adaptive self-evolving vision-language systems. --- ### Toward Reliable Tea Leaf Disease Diagnosis Using Deep Learning Model: Enhancing Robustness With Explainable AI and Adversarial Training Authors: Samanta Ghosh, Jannatul Adan Mahi, Shayan Abrar, Md Parvez Mia, Asaduzzaman Rayhan, Abdul Awal Yasir, Asaduzzaman Hridoy Published: 2026-02-11 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.11239v1 Tea is a valuable asset for the economy of Bangladesh. So, tea cultivation plays an important role to boost the economy. These valuable plants are vulnerable to various kinds of leaf infections which may cause less production and low quality. It is not so easy to detect these diseases manually. It may take time and there could be some errors in the detection.Therefore, the purpose of the study is to develop an automated deep learning model for tea leaf disease classification based on the teaLeafBD dataset so that anyone can detect the diseases more easily and efficiently. There are 5,278 high-resolution images in this dataset. The images are classified into seven categories. Six of them represents various diseases and the rest one represents healthy leaves. The proposed pipeline contains data preprocessing, data splitting, adversarial training, augmentation, model training, evaluation, and comprehension made possible with Explainable AI strategies. DenseNet201 and EfficientNetB3 were employed to perform the classification task. To prepare the model more robustly, we applied adversarial training so it can operate effectively even with noisy or disturbed inputs. In addition, Grad-CAM visualization was executed to analyze the model's predictions by identifying the most influential regions of each image. Our experimental outcomes revealed that EfficientNetB3 achieved the highest classification accuracy of 93%, while DenseNet201 reached 91%. The outcomes prove that the effectiveness of the proposed approach can accurately detect tea leaf diseases and provide a practical solution for advanced agricultural management. --- ### SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation Authors: Beichen Guo, Zhiyuan Wen, Jia Gu, Haochen Shi, Jian Wang, Senzhang Wang, Haoyang Li, Ruosong Yang, Shuaiqi Liu Published: 2026-02-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11238v2 Automatic Survey Generation (ASG) aims to produce comprehensive literature surveys by retrieving, organizing, and synthesizing academic papers. Despite rapid progress in specialized ASG frameworks and Deep Research agents, existing evaluations largely center on Computer Science or rely on generic criteria, leaving it unclear whether current systems satisfy the survey standards of diverse disciplines. We introduce SurveyLens, the first discipline-aware ASG benchmark. SurveyLens comprises SurveyLens-1k, a curated dataset of 1,000 human-written surveys across 10 disciplines, and a dual-lens framework that combines discipline-aware rubric scoring with reference-based alignment to human-written surveys. Evaluating 11 state-of-the-art systems across vanilla LLMs, ASG systems, and Deep Research agents, we find that Deep Research agents are the only paradigm robust across all 10 disciplines, ASG systems lead on structural planning, and all paradigms remain weak on reference quality, providing practical guidance for discipline-specific tool selection and future ASG design. --- ### AI-Driven Clinical Decision Support System for Enhanced Diabetes Diagnosis and Management Authors: Mujeeb Ur Rehman, Imran Rehan, Sohail Khalid Published: 2026-02-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.11237v1 Identifying type 2 diabetes mellitus can be challenging, particularly for primary care physicians. Clinical decision support systems incorporating artificial intelligence (AI-CDSS) can assist medical professionals in diagnosing type 2 diabetes with high accuracy. This study aimed to assess an AI-CDSS specifically developed for the diagnosis of type 2 diabetes by employing a hybrid approach that integrates expert-driven insights with machine learning techniques. The AI-CDSS was developed (training dataset: n = 650) and tested (test dataset: n = 648) using a dataset of 1298 patients with and without type 2 diabetes. To generate predictions, the algorithm utilized key features such as body mass index, plasma fasting glucose, and hemoglobin A1C. Furthermore, a clinical pilot study involving 105 patients was conducted to assess the diagnostic accuracy of the system in comparison to non-endocrinology specialists. The AI-CDSS showed a high degree of accuracy, with 99.8% accuracy in predicting diabetes, 99.3% in predicting prediabetes, 99.2% in identifying at-risk individuals, and 98.8% in predicting no diabetes. The test dataset revealed a 98.8% agreement between endocrinology specialists and the AI-CDSS. Type 2 diabetes was identified in 45% of 105 individuals in the pilot study. Compared with diabetes specialists, the AI-CDSS scored a 98.5% concordance rate, greatly exceeding that of nonendocrinology specialists, who had an 85% agreement rate. These findings indicate that the AI-CDSS has the potential to be a useful tool for accurately identifying type 2 diabetes, especially in situations in which diabetes specialists are not readily available. --- ### ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning Authors: Yandan Yang, Shuang Zeng, Tong Lin, Xinyuan Chang, Dekang Qi, Junjin Xiao, Haoyun Liu, Ronghan Chen, Yuzhi Chen, Dongjie Huo, Feng Xiong, Xing Wei et al. Published: 2026-02-11 Categories: cs.CV, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2602.11236v2 Building general-purpose embodied agents across diverse hardware remains a central challenge in robotics, often framed as the ''one-brain, many-forms'' paradigm. Progress is hindered by fragmented data, inconsistent representations, and misaligned training objectives. We present ABot-M0, a framework that builds a systematic data curation pipeline while jointly optimizing model architecture and training strategies, enabling end-to-end transformation of heterogeneous raw data into unified, efficient representations. From six public datasets, we clean, standardize, and balance samples to construct UniACT-dataset, a large-scale dataset with over 6 million trajectories and 9,500 hours of data, covering diverse robot morphologies and task scenarios. Unified pre-training improves knowledge transfer and generalization across platforms and tasks, supporting general-purpose embodied intelligence. To improve action prediction efficiency and stability, we propose the Action Manifold Hypothesis: effective robot actions lie not in the full high-dimensional space but on a low-dimensional, smooth manifold governed by physical laws and task constraints. Based on this, we introduce Action Manifold Learning (AML), which uses a DiT backbone to predict clean, continuous action sequences directly. This shifts learning from denoising to projection onto feasible manifolds, improving decoding speed and policy stability. ABot-M0 supports modular perception via a dual-stream mechanism that integrates VLM semantics with geometric priors and multi-view inputs from plug-and-play 3D modules such as VGGT and Qwen-Image-Edit, enhancing spatial understanding without modifying the backbone and mitigating standard VLM limitations in 3D reasoning. Experiments show components operate independently with additive benefits. We will release all code and pipelines for reproducibility and future research. --- ### Learning Glioblastoma Tumor Heterogeneity Using Brain Inspired Topological Neural Networks Authors: Ankita Paul, Wenyi Wang Published: 2026-02-11 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2602.11234v1 Accurate prognosis for Glioblastoma (GBM) using deep learning (DL) is hindered by extreme spatial and structural heterogeneity. Moreover, inconsistent MRI acquisition protocols across institutions hinder generalizability of models. Conventional transformer and DL pipelines often fail to capture the multi-scale morphological diversity such as fragmented necrotic cores, infiltrating margins, and disjoint enhancing components leading to scanner-specific artifacts and poor cross-site prognosis. We propose TopoGBM, a learning framework designed to capture heterogeneity-preserved, scanner-robust representations from multi-parametric 3D MRI. Central to our approach is a 3D convolutional autoencoder regularized by a topological regularization that preserves the complex, non-Euclidean invariants of the tumor's manifold within a compressed latent space. By enforcing these topological priors, TopoGBM explicitly models the high-variance structural signatures characteristic of aggressive GBM. Evaluated across heterogeneous cohorts (UPENN, UCSF, RHUH) and external validation on TCGA, TopoGBM achieves better performance (C-index 0.67 test, 0.58 validation), outperforming baselines that degrade under domain shift. Mechanistic interpretability analysis reveals that reconstruction residuals are highly localized to pathologically heterogeneous zones, with tumor-restricted and healthy tissue error significantly low (Test: 0.03, Validation: 0.09). Furthermore, occlusion-based attribution localizes approximately 50% of the prognostic signal to the tumor and the diverse peritumoral microenvironment advocating clinical reliability of the unsupervised learning method. Our findings demonstrate that incorporating topological priors enables the learning of morphology-faithful embeddings that capture tumor heterogeneity while maintaining cross-institutional robustness. --- ### Latent Generative Solvers for Generalizable Long-Term Physics Simulation Authors: Zituo Chen, Sili Deng Published: 2026-02-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.11229v3 Reliable physics simulation demands two capabilities that today's neural PDE solvers do not deliver together: generalization across heterogeneous PDE families, and stability under long autoregressive rollouts. Deterministic operators accumulate error geometrically, while existing probabilistic solvers are confined to a single PDE family or short horizons. We close this gap with the \textbf{Latent Generative Solver} (LGS), three coupled components: (i) a Physics VAE (PhyVAE) compressing twelve PDE families into a shared latent manifold; (ii) a Pyramidal Flow-Forcing Transformer (PFlowFT) that generates the next latent by flow matching, conditioned on a per-trajectory context updated on the model's own predictions; and (iii) input noising during training, for which we derive a sufficient-condition contraction bound explaining the observed long-horizon stability. Pretrained on a 2.5\,M-trajectory, 16-system corpus at $128^2$, LGS matches the strongest deterministic baseline at one step, wins on 15/16 systems at both 5- and 10-step rollout, cuts 20-step L2RE from $56.1\%$ to $\mathbf{30.2\%}$, and uses $\mathbf{13}$--$\mathbf{77\times}$ less recurrent dynamics-step compute. It also adapts efficiently to a $256^2$ Kolmogorov flow held out from the pretraining corpus, dropping 1-step L2RE from $0.398$ to $0.129$ in five finetune epochs against U-AFNO's $0.653{\to}0.343$. These empirical claims are limited to the evaluated 2D regular-grid systems and discrete horizons. --- ### Latent Generative Solvers for Generalizable Long-Term Physics Simulation Authors: Zituo Chen, Sili Deng Published: 2026-02-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.11229v2 Reliable physics simulation demands two capabilities that today's neural PDE solvers do not deliver together: generalization across heterogeneous PDE families, and stability under long autoregressive rollouts. Deterministic operators accumulate error geometrically, while existing probabilistic solvers are confined to a single PDE family or short horizons. We close this gap with the \textbf{Latent Generative Solver} (LGS), three coupled components: (i) a Physics VAE (PhyVAE) compressing twelve PDE families into a shared latent manifold; (ii) a Pyramidal Flow-Forcing Transformer (PFlowFT) that generates the next latent by flow matching, conditioned on a per-trajectory context updated on the model's own predictions; and (iii) input noising during training, for which we derive a sufficient-condition contraction bound explaining the observed long-horizon stability. Pretrained on a 2.5\,M-trajectory, 16-system corpus at $128^2$, LGS matches the strongest deterministic baseline at one step, wins on 15/16 systems at both 5- and 10-step rollout, cuts 20-step L2RE from $56.1\%$ to $\mathbf{30.2\%}$, and uses $\mathbf{13}$--$\mathbf{77\times}$ less recurrent dynamics-step compute. It also adapts efficiently to a $256^2$ Kolmogorov flow held out from the pretraining corpus, dropping 1-step L2RE from $0.398$ to $0.129$ in five finetune epochs against U-AFNO's $0.653{\to}0.343$. --- ### Generative AI-Driven Phase Control for RIS-Aided Cell-Free Massive MIMO Systems Authors: Kalpesh K. Patel, Malay Chakraborty, Ekant Sharma, Sandeep Kumar Singh Published: 2026-02-11 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2602.11226v1 This work investigates a generative artificial intelligence (GenAI) model to optimize the reconfigurable intelligent surface (RIS) phase shifts in RIS-aided cell-free massive multiple-input multiple-output (mMIMO) systems under practical constraints, including imperfect channel state information (CSI) and spatial correlation. We propose two GenAI based approaches, generative conditional diffusion model (GCDM) and generative conditional diffusion implicit model (GCDIM), leveraging the diffusion model conditioned on dynamic CSI to maximize the sum spectral efficiency (SE) of the system. To benchmark performance, we compare the proposed GenAI based approaches against an expert algorithm, traditionally known for achieving near-optimal solutions at the cost of computational efficiency. The simulation results demonstrate that GCDM matches the sum SE achieved by the expert algorithm while significantly reducing the computational overhead. Furthermore, GCDIM achieves a comparable sum SE with an additional $98\%$ reduction in computation time, underscoring its potential for efficient phase optimization in RIS-aided cell-free mMIMO systems. --- ### Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation Authors: Hubert M. Pysklo, Artem Zhuravel, Patrick D. Watson Published: 2026-02-11 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2602.11224v3 We present Agent-Diff, a novel benchmarking framework for evaluating agentic Large Language Models (LLMs) on real-world productivity software API tasks via code execution. Agentic LLM performance varies due to differences in models, external tool access, prompt structures, and agentic frameworks. Benchmarks must make fundamental trade-offs between a sandboxed approach that controls for variation in software environments and more ecologically valid approaches employing real services. Agent-Diff attempts to capture the desirable features of both of these approaches by including access to the real API interfaces for software services while sandboxing the environment in which calls are made, processed, and evaluated. This approach relies on two key innovations. The first is a novel state-diff contract, which separates process from outcome - rather than fuzzy trace or parameter matching, we define task success as whether the expected change in environment state was achieved. The second is a novel sandbox built on containerized replicas of enterprise APIs, allowing all models to interact with the same service interfaces through code execution. This enables controlled evaluation against a common set of state-diff contracts while preserving the structure of real-world API interaction. Using the Agent-Diff framework, we provide benchmarks for nine LLMs across 224 tasks utilizing enterprise software workflows. In addition, we evaluate the robustness of the framework with ablation experiments to assess the contribution of access to API documentation on benchmark performance. Code and data: https://github.com/agent-diff-bench/agent-diff. --- ### The Automatic Verification of Image-Text Claims (AVerImaTeC) Shared Task Authors: Rui Cao, Zhenyun Deng, Yulong Chen, Michael Schlichtkrull, Andreas Vlachos Published: 2026-02-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11221v2 The Automatic Verification of Image-Text Claims (AVerImaTeC) shared task aims to advance system development for retrieving evidence and verifying real-world image-text claims. Participants were allowed to either employ external knowledge sources, such as web search engines, or leverage the curated knowledge store provided by the organizers. System performance was evaluated using the AVerImaTeC score, defined as a conditional verdict accuracy in which a verdict is considered correct only when the associated evidence score exceeds a predefined threshold. The shared task attracted 14 submissions during the development phase and 6 submissions during the testing phase. All participating systems in the testing phase outperformed the baseline provided. The winning team, HUMANE, achieved an AVerImaTeC score of 0.5455. This paper provides a detailed description of the shared task, presents the complete evaluation results, and discusses key insights and lessons learned. ---