# Research Papers — 2026-03 · bundle page 176 of 243

> Full-text markdown of papers #8751–8800 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-03/page/176
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/175.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/177.md)

### Training Language Models via Neural Cellular Automata

Authors: Dan Lee, Seungwook Han, Akarsh Kumar, Pulkit Agrawal
Published: 2026-03-09
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.10055v1

Pre-training is crucial for large language models (LLMs), as it is when most representations and capabilities are acquired. However, natural language pre-training has problems: high-quality text is finite, it contains human biases, and it entangles knowledge with reasoning. This raises a fundamental question: is natural language the only path to intelligence? We propose using neural cellular automata (NCA) to generate synthetic, non-linguistic data for pre-pre-training LLMs--training on synthetic-then-natural language. NCA data exhibits rich spatiotemporal structure and statistics resembling natural language while being controllable and cheap to generate at scale. We find that pre-pre-training on only 164M NCA tokens improves downstream language modeling by up to 6% and accelerates convergence by up to 1.6x. Surprisingly, this even outperforms pre-pre-training on 1.6B tokens of natural language from Common Crawl with more compute. These gains also transfer to reasoning benchmarks, including GSM8K, HumanEval, and BigBench-Lite. Investigating what drives transfer, we find that attention layers are the most transferable, and that optimal NCA complexity varies by domain: code benefits from simpler dynamics, while math and web text favor more complex ones. These results enable systematic tuning of the synthetic distribution to target domains. More broadly, our work opens a path toward more efficient models with fully synthetic pre-training.

---

### Quantization of Ricci Curvature in Information Geometry

Authors: Carlos C. Rodriguez
Published: 2026-03-09
Categories: cs.IT, cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2603.10054v1

In 2004, while studying the information geometry of binary Bayesian networks (bitnets), the author conjectured that the volume-averaged Ricci scalar <R> computed with respect to the Fisher information metric is universally quantized to positive half-integers: <R> in (1/2)Z. This paper resolves the conjecture after 20 years. We prove it for tree-structured and complete-graph bitnets via a universal Beta function cancellation mechanism, and disprove it in general by exhibiting explicit loop counterexamples. We extend the program to Gaussian DAG networks, where a sign dichotomy holds: discrete bitnets have positive curvature, while Gaussian networks form solvable Lie groups with negative curvature.

---

### Cluster-Aware Attention-Based Deep Reinforcement Learning for Pickup and Delivery Problems

Authors: Wentao Wang, Lifeng Han, Guangyu Zou
Published: 2026-03-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.10053v1

The Pickup and Delivery Problem (PDP) is a fundamental and challenging variant of the Vehicle Routing Problem, characterized by tightly coupled pickup--delivery pairs, precedence constraints, and spatial layouts that often exhibit clustering. Existing deep reinforcement learning (DRL) approaches either model all nodes on a flat graph, relying on implicit learning to enforce constraints, or achieve strong performance through inference-time collaborative search at the cost of substantial latency. In this paper, we propose \emph{CAADRL} (Cluster-Aware Attention-based Deep Reinforcement Learning), a DRL framework that explicitly exploits the multi-scale structure of PDP instances via cluster-aware encoding and hierarchical decoding. The encoder builds on a Transformer and combines global self-attention with intra-cluster attention over depot, pickup, and delivery nodes, producing embeddings that are both globally informative and locally role-aware. Based on these embeddings, we introduce a Dynamic Dual-Decoder with a learnable gate that balances intra-cluster routing and inter-cluster transitions at each step. The policy is trained end-to-end with a POMO-style policy gradient scheme using multiple symmetric rollouts per instance. Experiments on synthetic clustered and uniform PDP benchmarks show that CAADRL matches or improves upon strong state-of-the-art baselines on clustered instances and remains highly competitive on uniform instances, particularly as problem size increases. Crucially, our method achieves these results with substantially lower inference time than neural collaborative-search baselines, suggesting that explicitly modeling cluster structure provides an effective and efficient inductive bias for neural PDP solvers.

---

### OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies

Authors: Yunzhou Song, Long Le, Yong-Hyun Park, Jie Wang, Junyao Shi, Lingjie Liu, Jiatao Gu, Eric Eaton, Dinesh Jayaraman, Kostas Daniilidis
Published: 2026-03-09
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2603.10052v1

Vision-language-action(VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks. However, they demonstrate limited performance on more complex tasks, such as those requiring complex spatial or semantic understanding, manipulation in clutter, or precise manipulation. We propose OMNIGUIDE, a flexible framework that improves VLA performance on such tasks by leveraging arbitrary sources of guidance, such as 3D foundation models, semantic-reasoning VLMs, and human pose models. We show how many kinds of guidance can be naturally expressed as differentiable energy functions with task-specific attractors and repellers located in 3D space, that influence the sampling of VLA actions. In this way, OMNIGUIDE enables guidance sources with complementary task-relevant strengths to improve a VLA model's performance on challenging tasks. Extensive experiments in both simulation and real-world environments, across diverse sources of guidance, demonstrate that OMNIGUIDE enhances the performance of state-of-the-art generalist policies (e.g., $π_{0.5}$, GR00T N1.6) significantly across success and safety rates. Critically, our unified framework matches or surpasses the performance of prior methods designed to incorporate specific sources of guidance into VLA policies. Project Page: $\href{https://omniguide.github.io/}{this \; url}$

---

### Where Do Flow Semantics Reside? A Protocol-Native Tabular Pretraining Paradigm for Encrypted Traffic Classification

Authors: Sizhe Huang, Zitong Li, Shujie Yang
Published: 2026-03-09
Categories: cs.NI, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2603.10051v2

Self-supervised masked modeling shows promise for encrypted traffic classification by masking and reconstructing raw bytes. Yet recent work reveals these methods fail to reduce reliance on labeled data despite costly pretraining: under frozen encoder evaluation, accuracy drops from greater than 0.9 to less than 0.47. We argue the root cause is inductive bias mismatch: flattening traffic into byte sequences destroys protocol-defined semantics. We identify three specific issues: 1) field unpredictability, random fields like ip.id are unlearnable yet treated as reconstruction targets; 2) embedding confusion, semantically distinct fields collapse into a unified embedding space; 3) metadata loss, capture-time metadata essential for temporal analysis is discarded. To address this, we propose a protocol-native paradigm that treats protocol-defined field semantics as architectural priors, reformulating the task to align with the data's intrinsic tabular modality rather than incrementally adapting sequence-based architectures. Instantiating this paradigm, we introduce FlowSem-MAE, a tabular masked autoencoder built on Flow Semantic Units (FSUs). It features predictability-guided filtering that focuses on learnable FSUs, FSU-specific embeddings to preserve field boundaries, and dual-axis attention to capture intra-packet and temporal patterns. FlowSem-MAE significantly outperforms state-of-the-art across datasets. With only half labeled data, it outperforms most existing methods trained on full data.

---

### InFusionLayer: a CFA-based ensemble tool to generate new classifiers for learning and modeling

Authors: Eric Roginek, Jingyan Xu, D. Frank. Hsu
Published: 2026-03-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.10049v1

Ensemble learning is a well established body of methods for machine learning to enhance predictive performance by combining multiple algorithms/models. Combinatorial Fusion Analysis (CFA) has provided method and practice for combining multiple scoring systems, using rank-score characteristic (RSC) function and cognitive diversity (CD), including ensemble method and model fusion. However, there is no general-purpose Python tool available that incorporate these techniques. In this paper we introduce \texttt{InFusionLayer}, a machine learning architecture inspired by CFA at the system fusion level that uses a moderate set of base models to optimize unsupervised and supervised learning multiclassification problems. We demonstrate \texttt{InFusionLayer}'s ease of use for PyTorch, TensorFlow, and Scikit-learn workflows by validating its performance on various computer vision datasets. Our results highlight the practical advantages of incorporating distinctive features of RSC function and CD, paving the way for more sophisticated ensemble learning applications in machine learning. We open-sourced our code to encourage continuing development and community accessibility to leverage CFA on github: https://github.com/ewroginek/Infusion

---

### Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation

Authors: Jianlong Chen, Zhiming Zhou
Published: 2026-03-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.10048v1

Sharpness-Aware Minimization (SAM) enhances generalization by minimizing the maximum training loss within a predefined neighborhood around the parameters. However, its practical implementation approximates this as gradient ascent(s) followed by applying the gradient at the ascent point to update the current parameters. This practice can be justified as approximately optimizing the objective by neglecting the (full) derivative of the ascent point with respect to the current parameters. Nevertheless, a direct and intuitive understanding of why using the gradient at the ascent point to update the current parameters works superiorly is still lacking. Our work bridges this gap by proposing a novel and intuitive interpretation. We show that the gradient at the single-step ascent point, \uline{when applied to the current parameters}, provides a better approximation of the direction from the current parameters toward the maximum within the local neighborhood than the local gradient. This improved approximation thereby enables a more direct escape from the maximum within the local neighborhood. Nevertheless, our analysis further reveals two issues. First, the approximation by the gradient at the single-step ascent point is often inaccurate. Second, the approximation quality may degrade as the number of ascent steps increases. To address these limitations, we propose in this paper eXplicit Sharpness-Aware Minimization (XSAM). It tackles the first by explicitly estimating the direction of the maximum during training, while addressing the second by crafting a search space that effectively leverages the gradient information at the multi-step ascent point. XSAM features a unified formulation that applies to both single-step and multi-step settings and only incurs negligible computational overhead. Extensive experiments demonstrate the consistent superiority of XSAM against existing counterparts.

---

### PlayWorld: Learning Robot World Models from Autonomous Play

Authors: Tenny Yin, Zhiting Mei, Zhonghe Zheng, Miyu Yamane, David Wang, Jade Sceats, Samuel M. Bateman, Lihan Zha, Apurva Badithela, Ola Shorinwa, Anirudha Majumdar
Published: 2026-03-09
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.09030v3

Action-conditioned video models offer a promising path to building general-purpose robot simulators that can improve directly from data. Yet, despite training on large-scale robot datasets, current state-of-the-art video models still struggle to predict physically consistent robot-object interactions that are crucial in robotic manipulation. To close this gap, we present PlayWorld, a simple, scalable, and fully autonomous pipeline for training high-fidelity video world simulators from interaction experience. In contrast to prior approaches that rely on success-biased human demonstrations, PlayWorld is the first system capable of learning entirely from unsupervised robot self-play, enabling naturally scalable data collection while capturing complex, long-tailed physical interactions essential for modeling realistic object dynamics. Experiments across diverse manipulation tasks show that PlayWorld generates high-quality, physically consistent predictions for contact-rich interactions that are not captured by world models trained on human-collected data. We further demonstrate the versatility of PlayWorld in enabling fine-grained failure prediction and policy evaluation, with up to 40% improvements over human-collected data. Finally, we demonstrate how PlayWorld enables reinforcement learning in the world model, improving policy performance by 65% in success rates when deployed in the real world.

---

### Automating Detection and Root-Cause Analysis of Flaky Tests in Quantum Software

Authors: Janakan Sivaloganathan, Ainaz Jamshidi, Andriy Miranskyy, Lei Zhang
Published: 2026-03-09
Categories: cs.SE, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2603.09029v1

Like classical software, quantum software systems rely on automated testing. However, their inherently probabilistic outputs make them susceptible to quantum flakiness -- tests that pass or fail inconsistently without code changes. Such quantum flaky tests can mask real defects and reduce developer productivity, yet systematic tooling for their detection and diagnosis remains limited. This paper presents an automated pipeline to detect flaky-test-related issues and pull requests in quantum software repositories and to support the identification of their root causes. We aim to expand an existing quantum flaky test dataset and evaluate the capability of Large Language Models (LLMs) for flakiness classification and root-cause identification. Building on a prior manual analysis of 14 quantum software repositories, we automate the discovery of additional flaky test cases using LLMs and cosine similarity. We further evaluate a variety of LLMs from OpenAI GPT, Meta LLaMA, Google Gemini, and Anthropic Claude suites for classifying flakiness and identifying root causes from issue descriptions and code context. Classification performance is assessed using standard performance metrics, including F1-score. Using our pipeline, we identify 25 previously unknown flaky tests, increasing the original dataset size by 54%. The best-performing model, Google Gemini, achieves an F1-score of 0.9420 for flakiness detection and 0.9643 for root-cause identification, demonstrating that LLMs can provide practical support for triaging flaky reports and understanding their underlying causes in quantum software. The expanded dataset and automated pipeline provide reusable artifacts for the quantum software engineering community. Future work will focus on improving detection robustness and exploring automated repair of quantum flaky tests.

---

### When to Retrain after Drift: A Data-Only Test of Post-Drift Data Size Sufficiency

Authors: Ren Fujiwara, Yasuko Matsubara, Yasushi Sakurai
Published: 2026-03-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.09024v2

Sudden concept drift makes previously trained predictors unreliable, yet deciding when to retrain and what post-drift data size is sufficient is rarely addressed. We propose CALIPER - a detector- and model-agnostic, data-only test that estimates the post-drift data size required for stable retraining. CALIPER exploits state dependence in streams generated by dynamical systems: we run a single-pass weighted local regression over the post-drift window and track a one-step proxy error as a function of a locality parameter $θ$. When an effective sample size gate is satisfied, a monotonically non-increasing trend in this error with increasing a locality parameter indicates that the data size is sufficiently informative for retraining. We also provide a theoretical analysis of our method, and we show that the algorithm has a low per-update time and memory. Across datasets from four heterogeneous domains, three learner families, and two detectors, CALIPER consistently matches or exceeds the best fixed data size for retraining while incurring negligible overhead and often outperforming incremental updates. CALIPER closes the gap between drift detection and data-sufficient adaptation in streaming learning.

---

### The Missing Memory Hierarchy: Demand Paging for LLM Context Windows

Authors: Tony Mason
Published: 2026-03-09
Categories: cs.OS, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.09023v1

The context window of a large language model is not memory. It is L1 cache: a small, fast, expensive resource that the field treats as the entire memory system. There is no L2, no virtual memory, no paging. Every tool definition, every system prompt, and every stale tool result occupies context for the lifetime of the session. The result is measurable: across 857 production sessions and 4.45 million effective input tokens, 21.8% is structural waste. We present Pichay, a demand paging system for LLM context windows. Implemented as a transparent proxy between client and inference API, Pichay interposes on the message stream to evict stale content, detect page faults when the model re-requests evicted material, and pin working-set pages identified by fault history. In offline replay across 1.4 million simulated evictions, the fault rate is 0.0254%. In live production deployment over 681turns, the system reduces context consumption by up to 93% (5,038KB to 339KB); under extreme sustained pressure, the system remains operational but exhibits the expected thrashing pathology, with repeated fault-in of evicted content. The key observation is that the problems the field faces, such as context limits, attention degradation, cost scaling, lost state across sessions, are virtual memory problems wearing different clothes. The solutions exist: working set theory (Denning, 1968), demand paging, fault-driven replacement policies, and memory hierarchies with multiple eviction-managed levels. We describe the architecture of a full memory hierarchy for LLM systems (L1 through persistent storage), report on the first three levels deployed in production use (L1 eviction, L2 fault-driven pinning, L3 model-initiated conversation compaction), and identify cross-session memory as the remaining frontier.

---

### MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

Authors: Yunfei Xie, Kevin Wang, Bobby Cheng, Jianzhu Yao, Zhizhou Sha, Alexander Duffy, Yihan Xi, Hongyuan Mei, Cheston Tan, Chen Wei, Pramod Viswanath, Zhangyang Wang
Published: 2026-03-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.09022v2

Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates and makes rankings unreliable across repeated tournaments. Prompt choice worsens this further by producing different effective policies. We address both instability and underperformance with MEMO (Memory-augmented MOdel context optimization), a self-play framework that optimizes inference-time context by coupling retention and exploration. Retention maintains a persistent memory bank that stores structured insights from self-play trajectories and injects them as priors during later play. Exploration runs tournament-style prompt evolution with uncertainty-aware selection via TrueSkill, and uses prioritized replay to revisit rare and decisive states. Across five text-based games, MEMO raises mean win rate from 25.1% to 49.5% for GPT-4o-mini and from 20.9% to 44.3% for Qwen-2.5-7B-Instruct, using $2,000$ self-play games per task. Run-to-run variance also drops, giving more stable rankings across prompt variations. These results suggest that multi-agent LLM game performance and robustness have substantial room for improvement through context optimization. MEMO achieves the largest gains in negotiation and imperfect-information games, while RL remains more effective in perfect-information settings. All code is open-source and available here: https://github.com/openverse-ai/MEMO

---

### AI Phenomenology for Understanding Human-AI Experiences Across Eras

Authors: Bhada Yun, Evgenia Taranova, Dana Feng, Renn Su, April Yi Wang
Published: 2026-03-09
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.09020v1

There is no 'ordinary' when it comes to AI. The human-AI experience is extraordinarily complex and specific to each person, yet dominant measures such as usability scales and engagement metrics flatten away nuance. We argue for AI phenomenology: a research stance that asks "How did it feel?" beyond the standard questions of "How well did it perform?" when interacting with AI systems. AI phenomenology acts as a paradigm for bidirectional human-AI alignment as it foregrounds users' first-person perceptions and interpretations of AI systems over time. We motivate AI phenomenology as a framework that captures how alignment is experienced, negotiated, and updated between users and AI systems. Tracing a lineage from Husserl through postphenomenology to Actor-Network Theory, and grounding our argument in three studies-two longitudinal studies with "Day", an AI companion, and a multi-method study of agentic AI in software engineering-we contribute a set of replicable methodological toolkits for conducting AI phenomenology research: instruments for capturing lived experience across personal and professional contexts, three design concepts (translucent design, agency-aware value alignment, temporal co-evolution tracking), and a concrete research agenda. We offer this toolkit not as a new paradigm but as a practical scaffold that researchers can adapt as AI systems-and the humans who live alongside them-continue to co-evolve.

---

### Meissa: Multi-modal Medical Agentic Intelligence

Authors: Yixiong Chen, Xinyi Bai, Yue Pan, Zongwei Zhou, Alan Yuille
Published: 2026-03-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.09018v1

Multi-modal large language models (MM-LLMs) have shown strong performance in medical image understanding and clinical reasoning. Recent medical agent systems extend them with tool use and multi-agent collaboration, enabling complex decision-making. However, these systems rely almost entirely on frontier models (e.g., GPT), whose API-based deployment incurs high cost, high latency, and privacy risks that conflict with on-premise clinical requirements. We present Meissa, a lightweight 4B-parameter medical MM-LLM that brings agentic capability offline. Instead of imitating static answers, Meissa learns both when to engage external interaction (strategy selection) and how to execute multi-step interaction (strategy execution) by distilling structured trajectories from frontier models. Specifically, we propose: (1) Unified trajectory modeling: trajectories (reasoning and action traces) are represented within a single state-action-observation formalism, allowing one model to generalize across heterogeneous medical environments. (2) Three-tier stratified supervision: the model's own errors trigger progressive escalation from direct reasoning to tool-augmented and multi-agent interaction, explicitly learning difficulty-aware strategy selection. (3) Prospective-retrospective supervision: pairing exploratory forward traces with hindsight-rationalized execution traces enables stable learning of effective interaction policies. Trained on 40K curated trajectories, Meissa matches or exceeds proprietary frontier agents in 10 of 16 evaluation settings across 13 medical benchmarks spanning radiology, pathology, and clinical reasoning. Using over 25x fewer parameters than typical frontier models like Gemini-3, Meissa operates fully offline with 22x lower end-to-end latency compared to API-based deployment. Data, models, and environments are released at https://github.com/Schuture/Meissa.

---

### An accurate flatness measure to estimate the generalization performance of CNN models

Authors: Rahman Taleghani, Maryam Mohammadi, Francesco Marchetti
Published: 2026-03-09
Categories: cs.LG, cs.CV, cs.NE
arXiv: https://arxiv.org/abs/2603.09016v1

Flatness measures based on the spectrum or the trace of the Hessian of the loss are widely used as proxies for the generalization ability of deep networks. However, most existing definitions are either tailored to fully connected architectures, relying on stochastic estimators of the Hessian trace, or ignore the specific geometric structure of modern Convolutional Neural Networks (CNNs). In this work, we develop a flatness measure that is both exact and architecturally faithful for a broad and practically relevant class of CNNs. We first derive a closed-form expression for the trace of the Hessian of the cross-entropy loss with respect to convolutional kernels in networks that use global average pooling followed by a linear classifier. Building on this result, we then specialize the notion of relative flatness to convolutional layers and obtain a parameterization-aware flatness measure that properly accounts for the scaling symmetries and filter interactions induced by convolution and pooling. Finally, we empirically investigate the proposed measure on families of CNNs trained on standard image-classification benchmarks. The results obtained suggest that the proposed measure can serve as a robust tool to assess and compare the generalization performance of CNN models, and to guide the design of architecture and training choices in practice.

---

### The Coupling Within: Flow Matching via Distilled Normalizing Flows

Authors: David Berthelot, Tianrong Chen, Jiatao Gu, Marco Cuturi, Laurent Dinh, Bhavik Chandna, Michal Klein, Josh Susskind, Shuangfei Zhai
Published: 2026-03-09
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.09014v1

Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration steps. A crucial ingredient in flow training is the choice of coupling measure for sampling noise/data pairs that define the flow matching (FM) regression loss. While FM training defaults usually to independent coupling, recent works show that adaptive couplings informed by noise/data distributions (e.g., via optimal transport, OT) improve both model training and inference. We radicalize this insight by shifting the paradigm: rather than computing adaptive couplings directly, we use distilled couplings from a different, pretrained model capable of placing noise and data spaces in bijection -- a property intrinsic to normalizing flows (NF) through their maximum likelihood and invertibility requirements. Leveraging recent advances in NF image generation via auto-regressive (AR) blocks, we propose Normalized Flow Matching (NFM), a new method that distills the quasi-deterministic coupling of pretrained NF models to train student flow models. These students achieve the best of both worlds: significantly outperforming flow models trained with independent or even OT couplings, while also improving on the teacher AR-NF model.

---

### Improving through Interaction: Searching Behavioral Representation Spaces with CMA-ES-IG

Authors: Nathaniel Dennler, Zhonghao Shi, Yiran Tao, Andreea Bobu, Stefanos Nikolaidis, Maja Matarić
Published: 2026-03-09
Categories: cs.RO, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2603.09011v1

Robots that interact with humans must adapt to individual users' preferences to operate effectively in human-centered environments. An intuitive and effective technique to learn non-expert users' preferences is through rankings of robot behaviors, e.g., trajectories, gestures, or voices. Existing techniques primarily focus on generating queries that optimize preference learning outcomes, such as sample efficiency or final preference estimation accuracy. However, the focus on outcome overlooks key user expectations in the process of providing these rankings, which can negatively impact users' adoption of robotic systems. This work proposes the Covariance Matrix Adaptation Evolution Strategies with Information Gain (CMA-ES-IG) algorithm. CMA-ES-IG explicitly incorporates user experience considerations into the preference learning process by suggesting perceptually distinct and informative trajectories for users to rank. We demonstrate these benefits through both simulated studies and real-robot experiments. CMA-ES-IG, compared to state-of-the-art alternatives, (1) scales more effectively to higher-dimensional preference spaces, (2) maintains computational tractability for high-dimensional problems, (3) is robust to noisy or inconsistent user feedback, and (4) is preferred by non-expert users in identifying their preferred robot behaviors. This project's code is available at github.com/interaction-lab/CMA-ES-IG

---

### Statistical Inference via Generative Models: Flow Matching and Causal Inference

Authors: Shinto Eguchi
Published: 2026-03-09
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.09009v1

Generative AI has achieved remarkable empirical success, but from the perspective of statistics it often remains opaque: its predictions may be accurate, yet the underlying mechanism is difficult to interpret, analyze, and trust. This book reinterprets generative AI in the language of statistics, using flow matching as a central example. The key idea is that generative models should be understood not merely as devices for producing plausible data, but as methods for the nonparametric learning of high-dimensional probability distributions. From this viewpoint, missing-data imputation becomes principled sampling from learned conditional distributions, counterfactual analysis becomes the estimation of intervention distributions, and distributional dynamics become statistically analyzable objects. Mathematically, flow matching represents distributional deformation through the continuity equation and a time-dependent velocity field, thereby extending score matching from the learning of static score fields to the learning of transport paths themselves. Building on this foundation, the book develops a statistical framework in which generative models are used to estimate nuisance components while inferential validity is maintained through orthogonalization and cross-fitting in the spirit of double/debiased machine learning. Applications to survival analysis, censoring, missingness, and causal inference show how generative models can be integrated into statistical inference for structured high-dimensional problems.

---

### Gender Fairness in Audio Deepfake Detection: Performance and Disparity Analysis

Authors: Aishwarya Fursule, Shruti Kshirsagar, Anderson R. Avila
Published: 2026-03-09
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2603.09007v2

Audio deepfake detection aims to detect real human voices from those generated by Artificial Intelligence (AI) and has emerged as a significant problem in the field of voice biometrics systems. With the ever-improving quality of synthetic voice, the probability of such a voice being exploited for illicit practices like identity thest and impersonation increases. Although significant progress has been made in the field of Audio Deepfake Detection in recent times, the issue of gender bias remains underexplored and in its nascent stage In this paper, we have attempted a thorough analysis of gender dependent performance and fairness in audio deepfake detection models. We have used the ASVspoof 5 dataset and train a ResNet-18 classifier and evaluate detection performance across four different audio features, and compared the performance with baseline AASIST model. Beyond conventional metrics such as Equal Error Rate (EER %), we incorporated five established fairness metrics to quantify gender disparities in the model. Our results show that even when the overall EER difference between genders appears low, fairness-aware evaluation reveals disparities in error distribution that are obscured by aggregate performance measures. These findings demonstrate that reliance on standard metrics is unreliable, whereas fairness metrics provide critical insights into demographic-specific failure modes. This work highlights the importance of fairness-aware evaluation for developing a more equitable, robust, and trustworthy audio deepfake detection system.

---

### Security Considerations for Multi-agent Systems

Authors: Tam Nguyen, Moses Ndebugre, Dheeraj Arremsetty
Published: 2026-03-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.09002v2

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct security vulnerabilities from those documented for singular AI models. Existing security and governance frameworks were not designed for these emerging attack surfaces. This study systematically characterizes the threat landscape of MAS and quantitatively evaluates 16 security frameworks for AI against it. A four-phase methodology is proposed: constructing a deep technical knowledge base of production multi-agent architectures; conducting generative AI-assisted threat modeling scoped to MAS cybersecurity risks and validated by domain experts; structuring survey plans at individual-threat granularity; and scoring each framework on a three-point scale against the cybersecurity risks. The risks were organized into 193 distinct main threat items across nine risk categories. The expected minimal average score is 2. No reviewed framework achieves majority coverage of any single category. Non-Determinism (mean score 1.231 across all 16 frameworks) and Data Leakage (1.340) are the most under-addressed domains. The OWASP Agentic Security Initiative leads overall at 65.3\% coverage and in the design phase; the CDAO Generative AI Responsible AI Toolkit leads in development and operational coverage. These results provide the first empirical cross-framework comparison for MAS security and offer evidence-based guidance for framework selection. Please check back for information on the published journal version.

---

### Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning

Authors: Juming Xiong, Kevin Guo, Congning Ni, Weixin Liu, Chao Yan, Katherine Brown, Avinash Baidya, Xiang Gao, Bradley Malin, Zhijun Yin
Published: 2026-03-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.08999v4

Large language models (LLMs) can achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet they often generate unnecessarily long reasoning paths that incur high inference cost. Self-consistency-based approaches push accuracy higher still, but they require sampling and aggregating multiple reasoning trajectories, leading to substantial computational overhead. In this paper, we introduce a confidence-aware selective sampling framework that, at inference time, analyzes a single reasoning trajectory to adaptively determine whether to rely on that trajectory alone or trigger multi-path sampling. The framework uses trajectory-level numeric features and sentence-level linguistic features extracted from reasoning states to guide selective multi-path reasoning. We train it on MedQA and evaluate it in-domain on MedQA and under calibration-only transfer on MathQA, MedMCQA, and MMLU, without further fine-tuning. Experimental results show that the proposed framework maintains comparable performance to full and efficient multi-path reasoning baselines, with accuracy changes of $-0.41 \pm 0.58$ and $-0.31 \pm 0.58$ percentage points, respectively, while reducing token usage by $71.7 \pm 5.0%$ and $36.6 \pm 9.1%$. These findings demonstrate that reasoning trajectories contain rich signals for uncertainty estimation, enabling a simple, transferable mechanism to balance accuracy and efficiency in LLM reasoning.

---

### Diffusion-Based Authentication of Copy Detection Patterns: A Multimodal Framework with Printer Signature Conditioning

Authors: Bolutife Atoki, Iuliia Tkachenko, Bertrand Kerautret, Carlos Crispim-Junior
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08998v1

Counterfeiting affects diverse industries, including pharmaceuticals, electronics, and food, posing serious health and economic risks. Printable unclonable codes, such as Copy Detection Patterns (CDPs), are widely used as an anti-counterfeiting measure and are applied to products and packaging. However, the increasing availability of high-resolution printing and scanning devices, along with advances in generative deep learning, undermines traditional authentication systems, which often fail to distinguish high-quality counterfeits from genuine prints. In this work, we propose a diffusion-based authentication framework that jointly leverages the original binary template, the printed CDP, and a representation of printer identity that captures relevant semantic information. Formulating authentication as multi-class printer classification over printer signatures lets our model capture fine-grained, device-specific features via spatial and textual conditioning. We extend ControlNet by repurposing the denoising process for class-conditioned noise prediction, enabling effective printer classification. On the Indigo 1 x 1 Base dataset, our method outperforms traditional similarity metrics and prior deep learning approaches. Results show the framework generalises to counterfeit types unseen during training.

---

### SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training

Authors: Jingxing Li, Yongjae Lee, Deliang Fan
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08997v2

3D Gaussian Splatting (3DGS) achieves real-time novel-view synthesis by optimizing millions of anisotropic Gaussians, yet its training remains expensive, with the backward pass dominating runtime in the post-densification refinement phase. We observe substantial update redundancy in this phase: many sampled views have near-plateaued losses and provide diminishing gradient benefits, but standard training still runs full backpropagation. We propose SkipGS with a novel view-adaptive backward gating mechanism for efficient post-densification training. SkipGS always performs the forward pass to update per-view loss statistics, and selectively skips backward passes when the sampled view's loss is consistent with its recent per-view baseline, while enforcing a minimum backward budget for stable optimization. On Mip-NeRF 360, compared to 3DGS, SkipGS reduces end-to-end training time by 23.1%, driven by a 42.0% reduction in post-densification time, with comparable reconstruction quality. Because it only changes when to backpropagate without modifying the renderer, representation, or loss, SkipGS is plug-and-play and compatible with other complementary efficiency strategies, enabling additive speedups. Code is available at https://github.com/ASU-ESIC-FAN-Lab/SkipGS.

---

### Arbiter: Detecting Interference in LLM Agent System Prompts

Authors: Tony Mason
Published: 2026-03-09
Categories: cs.SE, cs.AI, cs.CR, cs.PL
arXiv: https://arxiv.org/abs/2603.08993v1

System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to conventional software. We present Arbiter, a framework combining formal evaluation rules with multi-model LLM scouring to detect interference patterns in system prompts. Applied to three major coding agent system prompts: Claude Code (Anthropic), Codex CLI (OpenAI), and Gemini CLI (Google), we identify 152 findings across the undirected scouring phase and 21 hand-labeled interference patterns in directed analysis of one vendor. We show that prompt architecture (monolithic, flat, modular) strongly correlates with observed failure class but not with severity, and that multi-model evaluation discovers categorically different vulnerability classes than single-model analysis. One scourer finding was structural data loss in Gemini CLI's memory system was consistent with an issue filed and patched by Google, which addressed the symptom without addressing the schema-level root cause identified by the scourer. Total cost of cross-vendor analysis: \$0.27 USD.

---

### Automated Thematic Analysis for Clinical Qualitative Data: Iterative Codebook Refinement with Full Provenance

Authors: Seungjun Yi, Joakim Nguyen, Huimin Xu, Terence Lim, Joseph Skrovan, Mehak Beri, Hitakshi Modi, Andrew Well, Carlos M. Mery, Yan Zhang, Mia K. Markey, Ying Ding
Published: 2026-03-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.08989v1

Thematic analysis (TA) is widely used in health research to extract patterns from patient interviews, yet manual TA faces challenges in scalability and reproducibility. LLM-based automation can help, but existing approaches produce codebooks with limited generalizability and lack analytic auditability. We present an automated TA framework combining iterative codebook refinement with full provenance tracking. Evaluated on five corpora spanning clinical interviews, social media, and public transcripts, the framework achieves the highest composite quality score on four of five datasets compared to six baselines. Iterative refinement yields statistically significant improvements on four datasets with large effect sizes, driven by gains in code reusability and distributional consistency while preserving descriptive quality. On two clinical corpora (pediatric cardiology), generated themes align with expert-annotated themes.

---

### MAPLE: Elevating Medical Reasoning from Statistical Consensus to Process-Led Alignment

Authors: Kailong Fan, Anqi Pu, Yichen Wu, Wanhua Li, Yicong Li, Hanspeter Pfister, Huafeng Liu, Xiang Li, Quanzheng Li, Ning Guo
Published: 2026-03-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.08987v1

Recent advances in medical large language models have explored Test-Time Reinforcement Learning (TTRL) to enhance reasoning. However, standard TTRL often relies on majority voting (MV) as a heuristic supervision signal, which can be unreliable in complex medical scenarios where the most frequent reasoning path is not necessarily the clinically correct one. In this work, we propose a novel and unified training paradigm that integrates medical process reward models with TTRL to bridge the gap between test-time scaling (TTS) and parametric model optimization. Specifically, we advance the TTRL framework by replacing the conventional MV with a fine-grained, expert-aligned supervision paradigm using Med-RPM. This integration ensures that reinforcement learning is guided by medical correctness rather than mere consensus, effectively distilling search-based intelligence into the model's parametric memory. Extensive evaluations on four different benchmarks have demonstrated that our developed method consistently and significantly outperforms current TTRL and standalone PRM selection. Our findings establish that transitioning from stochastic heuristics to structured, step-wise rewards is essential for developing reliable and scalable medical AI systems

---

### SurgCalib: Gaussian Splatting-Based Hand-Eye Calibration for Robot-Assisted Minimally Invasive Surgery

Authors: Zijian Wu, Shuojue Yang, Yu Chung Lee, Eitan Prisman, Yueming Jin, Septimiu E. Salcudean
Published: 2026-03-09
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2603.08983v1

We present a Gaussian Splatting-based framework for hand-eye calibration of the da Vinci surgical robot. In a vision-guided robotic system, accurate estimation of the rigid transformation between the robot base and the camera frame is essential for reliable closed-loop control. For cable-driven surgical robots, this task faces unique challenges. The encoders of surgical instruments often produce inaccurate proprioceptive measurements due to cable stretch and backlash. Conventional hand-eye calibration approaches typically rely on known fiducial patterns and solve the AX = XB formulation. While effective, introducing additional markers into the operating room (OR) environment can violate sterility protocols and disrupt surgical workflows. In this study, we propose SurgCalib, an automatic, markerless framework that has the potential to be used in the OR. SurgCalib first initializes the pose of the surgical instrument using raw kinematic measurements and subsequently refines this pose through a two-phase optimization procedure under the RCM constraint within a Gaussian Splatting-based differentiable rendering pipeline. We evaluate the proposed method on the public dVRK benchmark, SurgPose. The results demonstrate average 2D tool-tip reprojection errors of 12.24 px (2.06 mm) and 11.33 px (1.9 mm), and 3D tool-tip Euclidean distance errors of 5.98 mm and 4.75 mm, for the left and right instruments, respectively.

---

### SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

Authors: Xuanyi Zhou, Qiuyang Mang, Shuo Yang, Haocheng Xi, Jintao Zhang, Huanzhi Mao, Joseph E. Gonzalez, Kurt Keutzer, Ion Stoica, Alvin Cheung
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08982v2

Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost by computing only a subset of attention blocks. However, prior methods often either drop the remaining blocks, which incurs information loss, or rely on learned predictors to approximate them, introducing training overhead and potential output distribution shifting. In this paper, we show that the missing contributions can be recovered without training: after semantic clustering, keys and values within each block exhibit strong similarity and can be well summarized by a small set of cluster centroids. Based on this observation, we introduce SVG-EAR, a parameter-free linear compensation branch that uses the centroid to approximate skipped blocks and recover their contributions. While centroid compensation is accurate for most blocks, it can fail on a small subset. Standard sparsification typically selects blocks by attention scores, which indicate where the model places its attention mass, but not where the approximation error would be largest. SVG-EAR therefore performs error-aware routing: a lightweight probe estimates the compensation error for each block, and we compute exactly the blocks with the highest error-to-cost ratio while compensating for skipped blocks. We provide theoretical guarantees that relate attention reconstruction error to clustering quality, and empirically show that SVG-EAR improves the quality-efficiency trade-off and increases throughput at the same generation fidelity on video diffusion tasks. Overall, SVG-EAR establishes a clear Pareto frontier over prior approaches, achieving up to 1.77$\times$ and 1.93$\times$ speedups while maintaining PSNRs of up to 29.759 and 31.043 on Wan2.2 and HunyuanVideo, respectively.

---

### Data-driven robust Markov decision processes on Borel spaces: performance guarantees via an axiomatic approach

Authors: Sivaramakrishnan Ramani
Published: 2026-03-09
Categories: math.OC, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.08979v1

We consider Markov decision processes (MDPs) with unknown disturbance distribution and address this problem using the robust Markov decision process (RMDP) approach. We construct the empirical distribution of the unknown disturbance distribution and characterize our ambiguity set of distributions as the sublevel set of a nonnegative distance function from the empirical distribution. By connecting the weak convergence of distributions to convergence with respect to the distance function, we prove that the robust optimal value function and the out-of-sample value function converge to the true optimal value function with increasing sample-sizes. We establish that, for finite sample-sizes, the robust optimal value function serves as a high probability upper bound on the out-of-sample value function. We also obtain probabilistic convergence rates, sample complexity bounds, and out-of-distribution performance bounds. The finite sample performance guarantees rely on the distance function satisfying a certain concentration type inequality. Several well-studied distances in the literature meet the requirements imposed on the distance function. We also analyze the data-driven properties of empirical MDPs and demonstrate that, unlike our data-driven RMDPs, empirical MDPs fail to satisfy some of the finite sample performance guarantees.

---

### MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence

Authors: Federico Giannini, Emanuele Della Valle
Published: 2026-03-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.08972v1

Internet of Things (IoT) Analytics often involves applying machine learning (ML) models on data streams. In such scenarios, traditional ML paradigms face obstacles related to continuous learning while dealing with concept drifts, temporal dependence, and avoiding forgetting. Moreover, in IoT, different edge devices build up a network. When learning models on those devices, connecting them could be useful in improving performance and reusing others' knowledge. This work proposes Mutual Assisted Learning, a learning paradigm grounded on Vygotsky's popular Sociocultural Theory of Cognitive Development. Each device is autonomous and does not need a central orchestrator. Whenever it degrades its performance due to a concept drift, it asks for assistance from others and decides whether their knowledge is useful for solving the new problem. This way, the number of connections is drastically reduced compared to the classical Federated Learning approaches, where the devices communicate at each training round. Every device is equipped with a Continuous Progressive Neural Network (cPNN) to handle the dynamic nature of data streams. We call this implementation Mutual Assisted cPNN (MAcPNN). To implement it, we allow cPNNs for single data point predictions and apply quantization to reduce the memory footprint. Experimental results prove the effectiveness of MAcPNN in boosting performance on synthetic and real data streams.

---

### Can You Hear, Localize, and Segment Continually? An Exemplar-Free Continual Learning Benchmark for Audio-Visual Segmentation

Authors: Siddeshwar Raghavan, Gautham Vinod, Bruce Coburn, Fengqing Zhu
Published: 2026-03-09
Categories: cs.CV, eess.AS
arXiv: https://arxiv.org/abs/2603.08967v1

Audio-Visual Segmentation (AVS) aims to produce pixel-level masks of sound producing objects in videos, by jointly learning from audio and visual signals. However, real-world environments are inherently dynamic, causing audio and visual distributions to evolve over time, which challenge existing AVS systems that assume static training settings. To address this gap, we introduce the first exemplar-free continual learning benchmark for Audio-Visual Segmentation, comprising four learning protocols across single-source and multi-source AVS datasets. We further propose a strong baseline, ATLAS, which uses audio-guided pre-fusion conditioning to modulate visual feature channels via projected audio context before cross-modal attention. Finally, we mitigate catastrophic forgetting by introducing Low-Rank Anchoring (LRA), which stabilizes adapted weights based on loss sensitivity. Extensive experiments demonstrate competitive performance across diverse continual scenarios, establishing a foundation for lifelong audio-visual perception. Code is available at${}^{*}$\footnote{Paper under review} - \hyperlink{https://gitlab.com/viper-purdue/atlas}{https://gitlab.com/viper-purdue/atlas} \keywords{Continual Learning \and Audio-Visual Segmentation \and Multi-Modal Learning}

---

### Semantic Level of Detail for Knowledge Graphs: Discovering Abstraction Boundaries via Spectral Heat Diffusion

Authors: Edward Izgorodin
Published: 2026-03-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.08965v2

Graph-structured knowledge systems -- from knowledge graphs to GraphRAG pipelines -- organize information into hierarchical communities, yet lack a principled mechanism for continuous resolution control: where do the qualitative boundaries between abstraction levels lie, and how should an agent navigate them? Current approaches rely on discrete community detection with manually tuned resolution parameters (e.g., Leiden $γ$), offering no continuous zoom and no formal guarantees. We introduce Semantic Level of Detail (SLoD), a framework that addresses both problems by defining a continuous zoom operator via heat kernel diffusion on a graph Laplacian whose kNN structure is induced by a Poincare-ball embedding. We prove hierarchical coherence in the tree limit (exact tree with Sarkar embedding), with bounded approximation error, and demonstrate consistent boundary-detection behaviour on noisy hierarchies; spectral gaps in the graph Laplacian then induce emergent scale boundaries -- scales where the representation undergoes qualitative transitions -- detectable without manual resolution tuning. On synthetic hierarchies (HSBM, 1024 nodes), spectral clustering at the BoundaryScan-detected scale recovers planted levels, with macro ARI saturating at 1.00 in the high-SNR regime (50-seed median) and meso ARI reaching 0.89 (0.86, 0.92) at r=200. On the full WordNet noun hierarchy (82K synsets), using 100 stratified leaf queries, detected boundaries align with true taxonomic depth ($τ= 0.79$), demonstrating meaningful abstraction-level discovery in real-world knowledge graphs without resolution-parameter tuning. The composite weights, MAD threshold, and kNN-parameter rule ($k = \max(10, \min(\lfloor\sqrt{N}\rfloor, 50))$) use defaults that transferred unchanged between HSBM and WordNet; their behaviour on graphs with implicit or qualitatively different hierarchical structure is open.

---

### The FABRIC Strategy for Verifying Neural Feedback Systems

Authors: Samuel I. Akinwande, Sydney M. Katz, Mykel J. Kochenderfer, Clark Barrett
Published: 2026-03-09
Categories: cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2603.08964v2

Forward reachability analysis is a dominant approach for verifying reach-avoid specifications in neural feedback systems, i.e., dynamical systems controlled by neural networks, and a number of directions have been proposed and studied. In contrast, far less attention has been given to backward reachability analysis for these systems, in part because of the limited scalability of known techniques. In this work, we begin to address this gap by introducing new algorithms for computing both over- and underapproximations of backward reachable sets for nonlinear neural feedback systems. We also describe and implement an integration of these backward reachability techniques with existing ones for forward analysis. We call the resulting algorithm Forward and Backward Reachability Integration for Certification (FaBRIC). We evaluate our algorithms on a representative set of benchmarks and show that they significantly outperform the prior state of the art.

---

### Estimation of heterogeneous principal effects under principal ignorability

Authors: Rui Zhang, Charles R. Doss, Jared D. Huling
Published: 2026-03-09
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2603.08963v1

We study estimation and inference for heterogeneous principal causal effects with binary treatments and binary intermediate variables. Principal causal effects are subgroup effects within strata defined by potential values of an intermediate variable, including effects among compliers. We propose a framework for estimating and forming pointwise confidence intervals for heterogeneous principal causal effects under the principal ignorability assumption. Several estimators are developed, and their robustness properties are characterized: one estimator is doubly robust, whereas the other two attain intermediate robustness between double and triple robustness; in contrast, principal causal effects can be estimated in a triply robust manner only. We establish large-sample theory under nonparametric smoothness conditions and analyze the bias contributions of each approach, providing insight into performance beyond the smooth setting, including in high-dimensional regimes. Camden Coalition hotspotting randomized trial are used to illustrate the methods by estimating heterogeneous complier effects.

---

### The $qs$ Inequality: Quantifying the Double Penalty of Mixture-of-Experts at Inference

Authors: Vignesh Adhinarayanan, Nuwan Jayasena
Published: 2026-03-09
Categories: cs.LG, cs.AR, cs.DC, cs.PF
arXiv: https://arxiv.org/abs/2603.08960v1

Mixture-of-Experts (MoE) models deliver high quality at low training FLOPs, but this efficiency often vanishes at inference. We identify a double penalty that structurally disadvantages MoE architectures during decoding: first, expert routing fragments microbatches and reduces weight reuse; second, massive resident expert pools reduce high-bandwidth memory (HBM) headroom for the KV cache. This phenomenon, formalized as reuse fragmentation, pushes feed-forward networks (FFNs) into a bandwidth-bound regime, especially at long context lengths. We introduce the $qs$ inequality, a predictive criterion that identifies when MoE is structurally disadvantaged relative to a quality-matched dense model. This criterion unifies sparsity ($s$), the fraction of parameters activated per token, and the quality-equivalence factor ($q$), the size multiplier required for a dense model to match MoE performance. Our evaluation across frontier models including DeepSeek-V3, Qwen3-235B, Grok-1, and Switch-C demonstrates that this fragmentation is a general architectural phenomenon. For DeepSeek-V3 at 128k context, this results in a 4.5x throughput advantage for a quality-matched dense baseline. Crucially, massive architectures like Switch-C can become infeasible on cluster sizes where a quality-matched dense model remains viable. Our results suggest that training-time FLOP efficiency is an incomplete proxy for inference-time performance in long-context serving. They also indicate that MoE may be best viewed as a training-time optimization, with distillation into dense models as a possible path toward inference-efficient deployment.

---

### Automated Tensor-Relational Decomposition for Large-Scale Sparse Tensor Computation

Authors: Yuxin Tang, Zhiyuan Xin, Zhimin Ding, Xinyu Yao, Daniel Bourgeois, Tirthak Patel, Chris Jermaine
Published: 2026-03-09
Categories: cs.MS, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2603.08957v1

A \emph{tensor-relational} computation is a relational computation where individual tuples carry vectors, matrices, or higher-dimensional arrays. An advantage of tensor-relational computation is that the overall computation can be executed on top of a relational system, inheriting the system's ability to automatically handle very large inputs with high levels of sparsity while high-performance kernels (such as optimized matrix-matrix multiplication codes) can be used to perform most of the underlying mathematical operations. In this paper, we introduce upper-case-lower-case \texttt{EinSum}, which is a tensor-relational version of the classical Einstein Summation Notation. We study how to automatically rewrite a computation in Einstein Notation into upper-case-lower-case \texttt{EinSum} so that computationally intensive components are executed using efficient numerical kernels, while sparsity is managed relationally.

---

### A Survey of Reinforcement Learning For Economics

Authors: Pranjal Rawat
Published: 2026-03-09
Categories: econ.GN, cs.LG
arXiv: https://arxiv.org/abs/2603.08956v6

This survey (re)introduces reinforcement learning methods to economists. The curse of dimensionality limits how far exact dynamic programming can be effectively applied, forcing us to rely on suitably "small" problems or our ability to convert "big" problems into smaller ones. While this reduction has been sufficient for many classical applications, a growing class of economic models resists such reduction. Reinforcement learning algorithms offer a natural, sample-based extension of dynamic programming, extending tractability to problems with high-dimensional states, continuous actions, and strategic interactions. I review the theory connecting classical planning to modern learning algorithms and demonstrate their mechanics through simulated examples in pricing, inventory control, strategic games, and preference elicitation. I also examine the practical vulnerabilities of these algorithms, noting their brittleness, sample inefficiency, sensitivity to hyperparameters, and the absence of global convergence guarantees outside of tabular settings. The successes of reinforcement learning remain strictly bounded by these constraints, as well as a reliance on accurate simulators. When guided by economic structure, reinforcement learning provides a remarkably flexible framework. It stands as an imperfect, but promising, addition to the computational economist's toolkit. A companion survey (Rust and Rawat, 2026b) covers the inverse problem of inferring preferences from observed behavior. All simulation code is publicly available.

---

### A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations

Authors: Joshua Castillo, Ravi Mukkamala
Published: 2026-03-09
Categories: cs.AI, cs.CL, cs.DC, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2603.08954v1

The first 72 hours of a missing-person investigation are critical for successful recovery. Guardian is an end-to-end system designed to support missing-child investigation and early search planning. This paper presents the Guardian LLM Pipeline, a multi-model system in which LLMs are used for intelligent information extraction and processing related to missing-person search operations. The pipeline coordinates end-to-end execution across task-specialized LLM models and invokes a consensus LLM engine that compares multiple model outputs and resolves disagreements. The pipeline is further strengthened by QLoRA-based fine-tuning, using curated datasets. The presented design aligns with prior work on weak supervision and LLM-assisted annotation, emphasizing conservative, auditable use of LLMs as structured extractors and labelers rather than unconstrained end-to-end decision makers.

---

### Towards Reliable Simulation-based Inference

Authors: Arnaud Delaunoy
Published: 2026-03-09
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.08947v1

Scientific knowledge expands by observing the world, hypothesizing some theories about it, and testing them against collected data. When those theories take the form of statistical models, statistical analyses are involved in the process of testing and refining scientific hypotheses. In this thesis, we focus on statistical models that take the form of scientific simulators and provide background about how machine learning can be used for statistical analyses in this context. The first part of this thesis is about showing empirically that performing statistical analyses with machine learning involves a degree of approximation. Specifically, all statistical analyses involve a level of uncertainty in the conclusions drawn, and we show that approximations can lead to overconfident conclusions. We draw caution regarding such overconfident conclusions and introduce a criterion to diagnose overconfident approximations. In the second part, we introduce balancing, a way to regularize machine learning models to reduce overconfidence and favor calibrated or underconfident approximations. Balancing is first introduced for neural ratio estimation algorithms and then extended to other algorithms. Intuition about why balancing leads to less overconfident solutions is provided, and it is shown empirically that balanced algorithms are often either close to calibrated or underconfident. The third part shows that Bayesian neural networks can also be used to mitigate the overconfidence of approximations. Unlike balancing, no regularization is required, and this solution can then work with few training samples and, hence, computationally expensive simulators. To that end, a new Bayesian neural network prior tailored for simulation-based inference is developed, and empirical results show a reduction in overconfidence compared to similar solutions without Bayesian neural networks.

---

### Kernel Debiased Plug-in Estimation based on the Universal Least Favorable Submodel

Authors: Haiyi Chen, Yang Liu, Ivana Malenica
Published: 2026-03-09
Categories: math.ST, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.08945v1

We propose ULFS-KDPE, a kernel debiased plug-in estimator based on the universal least favorable submodel, for estimating pathwise differentiable parameters in nonparametric models. The method constructs a data-adaptive debiasing flow in a reproducing kernel Hilbert space (RKHS), producing a plug-in estimator that achieves semiparametric efficiency without requiring explicit derivation or evaluation of efficient influence functions. We place ULFS-KDPE on a rigorous functional-analytic foundation by formulating the universal least favorable update as a nonlinear ordinary differential equation on probability densities. We establish existence, uniqueness, stability, and finite-time convergence of the empirical score along the induced flow. Under standard regularity conditions, the resulting estimator is regular, asymptotically linear, and attains the semiparametric efficiency bound simultaneously for a broad class of pathwise differentiable parameters. The method admits a computationally tractable implementation based on finite-dimensional kernel representations and principled stopping criteria. In finite samples, the combination of solving a rich collection of score equations with RKHS-based smoothing and avoidance of direct influence-function evaluation leads to improved numerical stability. Simulation studies illustrate the method and support the theoretical results.

---

### BiCLIP: Domain Canonicalization via Structured Geometric Transformation

Authors: Pranav Mantini, Shishir K. Shah
Published: 2026-03-09
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.08942v2

Recent advances in vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities, yet adapting these models to specialized domains remains a significant challenge. Building on recent theoretical insights suggesting that independently trained VLMs are related by a canonical transformation, we extend this understanding to the concept of domains. We hypothesize that image features across disparate domains are related by a canonicalized geometric transformation that can be recovered using a small set of anchors. Few-shot classification provides a natural setting for this alignment, as the limited labeled samples serve as the anchors required to estimate this transformation. Motivated by this hypothesis, we introduce BiCLIP, a framework that applies a targeted transformation to multimodal features to enhance cross-modal alignment. Our approach is characterized by its extreme simplicity and low parameter footprint. Extensive evaluations across 11 standard benchmarks, including EuroSAT, DTD, and FGVCAircraft, demonstrate that BiCLIP consistently achieves state-of-the-art results. Furthermore, we provide empirical verification of existing geometric findings by analyzing the orthogonality and angular distribution of the learned transformations, confirming that structured alignment is the key to robust domain adaptation. Code is available at https://github.com/QuantitativeImagingLaboratory/BilinearCLIP

---

### AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem

Authors: Rui Liu, Tao Zhe, Dongjie Wang, Zijun Yao, Kunpeng Liu, Yanjie Fu, Huan Liu, Jian Pei
Published: 2026-03-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.08938v2

The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as OpenClaw demonstrate that Large Language Model (LLM)-based agents can autonomously operate local computing environments, orchestrate workflows, and integrate external tools. However, within the current paradigm, these agents remain conventional applications running on legacy operating systems originally designed for Graphical User Interfaces (GUIs) or Command Line Interfaces (CLIs). This architectural mismatch leads to fragmented interaction models, poorly structured permission management (often described as "Shadow AI"), and severe context fragmentation. This paper proposes a new paradigm: a Personal Agent Operating System (AgentOS). In AgentOS, traditional GUI desktops are replaced by a Natural User Interface (NUI) centered on a unified natural language or voice portal. The system core becomes an Agent Kernel that interprets user intent, decomposes tasks, and coordinates multiple agents, while traditional applications evolve into modular Skills-as-Modules enabling users to compose software through natural language rules. We argue that realizing AgentOS fundamentally becomes a Knowledge Discovery and Data Mining (KDD) problem. The Agent Kernel must operate as a real-time engine for intent mining and knowledge discovery. Viewed through this lens, the operating system becomes a continuous data mining pipeline involving sequential pattern mining for workflow automation, recommender systems for skill retrieval, and dynamically evolving personal knowledge graphs. These challenges define a new research agenda for the KDD community in building the next generation of intelligent computing systems.

---

### VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs

Authors: Hezhao Zhang, Huang-Cheng Chou, Shrikanth Narayanan, Thomas Hain
Published: 2026-03-09
Categories: cs.SD, cs.AI, cs.CL, cs.MM, eess.AS
arXiv: https://arxiv.org/abs/2603.08936v1

Speech Large Language Models (LLMs) show great promise for speech emotion recognition (SER) via generative interfaces. However, shifting from closed-set classification to open text generation introduces zero-shot stochasticity, making evaluation highly sensitive to prompts. Additionally, conventional speech LLMs benchmarks overlook the inherent ambiguity of human emotion. Hence, we present VoxEmo, a comprehensive SER benchmark encompassing 35 emotion corpora across 15 languages for Speech LLMs. VoxEmo provides a standardized toolkit featuring varying prompt complexities, from direct classification to paralinguistic reasoning. To reflect real-world perception/application, we introduce a distribution-aware soft-label protocol and a prompt-ensemble strategy that emulates annotator disagreement. Experiments reveal that while zero-shot speech LLMs trail supervised baselines in hard-label accuracy, they uniquely align with human subjective distributions.

---

### PathoScribe: Transforming Pathology Data into a Living Library with a Unified LLM-Driven Framework for Semantic Retrieval and Clinical Integration

Authors: Abdul Rehman Akbar, Samuel Wales-McGrath, Alejadro Levya, Lina Gokhale, Rajendra Singh, Wei Chen, Anil Parwani, Muhammad Khalid Khan Niazi
Published: 2026-03-09
Categories: cs.CV, cs.AI, cs.CL, cs.DL, cs.IR
arXiv: https://arxiv.org/abs/2603.08935v2

Pathology underpins modern diagnosis and cancer care, yet its most valuable asset, the accumulated experience encoded in millions of narrative reports, remains largely inaccessible. Although institutions are rapidly digitizing pathology workflows, storing data without effective mechanisms for retrieval and reasoning risks transforming archives into a passive data repository, where institutional knowledge exists but cannot meaningfully inform patient care. True progress requires not only digitization, but the ability for pathologists to interrogate prior similar cases in real time while evaluating a new diagnostic dilemma. We present PathoScribe, a unified retrieval-augmented large language model (LLM) framework designed to transform static pathology archives into a searchable, reasoning-enabled living library. PathoScribe enables natural language case exploration, automated cohort construction, clinical question answering, immunohistochemistry (IHC) panel recommendation, and prompt-controlled report transformation within a single architecture. Evaluated on 70,000 multi-institutional surgical pathology reports, PathoScribe achieved perfect Recall@10 for natural language case retrieval and demonstrated high-quality retrieval-grounded reasoning (mean reviewer score 4.56/5). Critically, the system operationalized automated cohort construction from free-text eligibility criteria, assembling research-ready cohorts in minutes (mean 9.2 minutes) with 91.3% agreement to human reviewers and no eligible cases incorrectly excluded, representing orders-of-magnitude reductions in time and cost compared to traditional manual chart review. This work establishes a scalable foundation for converting digital pathology archives from passive storage systems into active clinical intelligence platforms.

---

### Interpretable Markov-Based Spatiotemporal Risk Surfaces for Missing-Child Search Planning with Reinforcement Learning and LLM-Based Quality Assurance

Authors: Joshua Castillo, Ravi Mukkamala
Published: 2026-03-09
Categories: cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2603.08933v1

The first 72 hours of a missing-child investigation are critical for successful recovery. However, law enforcement agencies often face fragmented, unstructured data and a lack of dynamic, geospatial predictive tools. Our system, Guardian, provides an end-to-end decision-support system for missing-child investigation and early search planning. It converts heterogeneous, unstructured case documents into a schema-aligned spatiotemporal representation, enriches cases with geocoding and transportation context, and provides probabilistic search products spanning 0-72 hours. In this paper, we present an overview of Guardian as well as a detailed description of a three-layer predictive component of the system. The first layer is a Markov chain, a sparse, interpretable model with transitions incorporating road accessibility costs, seclusion preferences, and corridor bias with separate day/night parameterizations. The Markov chain's output prediction distributions are then transformed into operationally useful search plans by the second layer's reinforcement learning. Finally, the third layer's LLM performs post hoc validation of layer 2 search plans prior to their release. Using a synthetic but realistic case study, we report quantitative outputs across 24/48/72-hour horizons and analyze sensitivity, failure modes, and tradeoffs. Results show that the proposed predictive system with the three-layer architecture produces interpretable priors for zone optimization and human review.

---

### Optimizing Reinforcement Learning Training over Digital Twin Enabled Multi-fidelity Networks

Authors: Hanzhi Yu, Hasan Farooq, Julien Forgeat, Shruti Bothe, Kristijonas Cyras, Md Moin Uddin Chowdhury, Mingzhe Chen
Published: 2026-03-09
Categories: cs.NI, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2603.08931v1

In this paper, we investigate a novel digital network twin (DNT) assisted deep learning (DL) model training framework. In particular, we consider a physical network where a base station (BS) uses several antennas to serve multiple mobile users, and a DNT that is a virtual representation of the physical network. The BS must adjust its antenna tilt angles to optimize the data rates of all users. Due to user mobility, the BS may not be able to accurately track network dynamics such as wireless channels and user mobilities. Hence, a reinforcement learning (RL) approach is used to dynamically adjust the antenna tilt angles. To train the RL, we can use data collected from the physical network and the DNT. The data collected from the physical network is more accurate but incurs more communication overhead compared to the data collected from the DNT. Therefore, it is necessary to determine the ratio of data collected from the physical network and the DNT to improve the training of the RL model. We formulate this problem as an optimization problem whose goal is to jointly optimize the tilt angle adjustment policy and the data collection strategy, aiming to maximize the data rates of all users while constraining the time delay introduced by collecting data from the physical network. To solve this problem, we propose a hierarchical RL framework that integrates robust adversarial loss and proximal policy optimization (PPO). Simulation results show that our proposed method reduces the physical network data collection delay by up to 28.01% and 1x compared to a hierarchical RL that uses vanilla PPO as the first level RL, and the baseline that uses robust-RL at the first level and selects the data collection ratio randomly.

---

### Using Vision Language Foundation Models to Generate Plant Simulation Configurations via In-Context Learning

Authors: Heesup Yun, Isaac Kazuo Uyehara, Earl Ranario, Lars Lundqvist, Christine H. Diepenbrock, Brian N. Bailey, J. Mason Earles
Published: 2026-03-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.08930v2

This paper introduces a benchmark for evaluating whether vision-language models (VLMs) can generate plant simulation configurations from imagery using in-context learning. We study this benchmark for cowpea plot reconstruction for plant simulations, where the VLM needs to generate structured JSON configurations that include field and plant information. Open-source multimodal models from Gemma 4 and Qwen3.5 families are evaluated on a synthetic cowpea dataset with known JSON ground truth and on a real drone orthophoto dataset with field-collected JSON. Five in-context learning methods are used, from format restriction instruction to few-shot image examples with auxiliary grounding information. The results show that VLMs can generate valid JSON outputs, can generally estimate days after planting (DAP), plant counts, plant locations, sun angles, and leaf chlorophyll content, and can render approximate simulations of cowpea plots. Error metrics fluctuate across model families and often remain worse than dataset baselines, particularly when VLMs' pretrained knowledge dominates over weak visual evidence. These results position image-to-simulation JSON generation as a promising but currently challenging task, and establish a benchmark for studying how multimodal reasoning, prompt design, and the sim-to-real domain gap affect plant phenotyping tasks.

---

### Using Vision Language Foundation Models to Generate Plant Simulation Configurations via In-Context Learning

Authors: Heesup Yun, Isaac Kazuo Uyehara, Earl Ranario, Lars Lundqvist, Christine H. Diepenbrock, Brian N. Bailey, J. Mason Earles
Published: 2026-03-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.08930v1

This paper introduces a synthetic benchmark to evaluate the performance of vision language models (VLMs) in generating plant simulation configurations for digital twins. While functional-structural plant models (FSPMs) are useful tools for simulating biophysical processes in agricultural environments, their high complexity and low throughput create bottlenecks for deployment at scale. We propose a novel approach that leverages state-of-the-art open-source VLMs -- Gemma 3 and Qwen3-VL -- to directly generate simulation parameters in JSON format from drone-based remote sensing images. Using a synthetic cowpea plot dataset generated via the Helios 3D procedural plant generation library, we tested five in-context learning methods and evaluated the models across three categories: JSON integrity, geometric evaluations, and biophysical evaluations. Our results show that while VLMs can interpret structural metadata and estimate parameters like plant count and sun azimuth, they often exhibit performance degradation due to contextual bias or rely on dataset means when visual cues are insufficient. Validation on a real-world drone orthophoto dataset and an ablation study using a blind baseline further characterize the models' reasoning capabilities versus their reliance on contextual priors. To the best of our knowledge, this is the first study to utilize VLMs to generate structural JSON configurations for plant simulations, providing a scalable framework for reconstruction 3D plots for digital twin in agriculture.

---

### TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers

Authors: Yihua Liu, Fanjiang Ye, Bowen Lin, Rongyu Fang, Chengming Zhang
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08928v1

Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution, causing especially structural degradation due to attention dilution. Previous approaches attempt to mitigate this by sharpening attention distributions, but fail to preserve fine-grained semantic details and introduce obvious artifacts. In this work, we analyze the characteristics of DiTs and propose TIDE, a training-free text-to-image (T2I) extrapolation method that enables generation with arbitrary resolution and aspect ratio without additional sampling overhead. We identify the core factor for prompt information loss, and introduce a text anchoring mechanism to correct the imbalance between text and image tokens. To further eliminate artifacts, we design a dynamic temperature control mechanism that leverages the pattern of spectral progression in the diffusion process. Extensive evaluations demonstrate that TIDE delivers high-quality resolution extrapolation capability and integrates seamlessly with existing state-of-the-art methods.

---

### MEGC2026: Micro-Expression Grand Challenge on Visual Question Answering

Authors: Xinqi Fan, Jingting Li, John See, Moi Hoon Yap, Su-Jing Wang, Adrian K. Davison
Published: 2026-03-09
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2603.08927v1

Facial micro-expressions (MEs) are involuntary movements of the face that occur spontaneously when a person experiences an emotion but attempts to suppress or repress the facial expression, typically found in a high-stakes environment. In recent years, substantial advancements have been made in the areas of ME recognition, spotting, and generation. The emergence of multimodal large language models (MLLMs) and large vision-language models (LVLMs) offers promising new avenues for enhancing ME analysis through their powerful multimodal reasoning capabilities. The ME grand challenge (MEGC) 2026 introduces two tasks that reflect these evolving research directions: (1) ME video question answering (ME-VQA), which explores ME understanding through visual question answering on relatively short video sequences, leveraging MLLMs or LVLMs to address diverse question types related to MEs; and (2) ME long-video question answering (ME-LVQA), which extends VQA to long-duration video sequences in realistic settings, requiring models to handle temporal reasoning and subtle micro-expression detection across extended time periods. All participating algorithms are required to submit their results on a public leaderboard. More details are available at https://megc2026.github.io.

---