# Research Papers — 2026-03 · bundle page 52 of 243

> Full-text markdown of papers #2551–2600 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/52
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/51.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/53.md)

### AgentChemist: A Multi-Agent Experimental Robotic Platform Integrating Chemical Perception and Precise Control

Authors: Xiangyi Wei, Fei Wang, Haotian Zhang, Xin An, Haitian Zhu, Lianrui Hu, Yang Li, Changbo Wang, Xiao He
Published: 2026-03-25
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.23886v1

Chemical laboratory automation has long been constrained by rigid workflows and poor adaptability to the long-tail distribution of experimental tasks. While most automated platforms perform well on a narrow set of standardized procedures, real laboratories involve diverse, infrequent, and evolving operations that fall outside predefined protocols. This mismatch prevents existing systems from generalizing to novel reaction conditions, uncommon instrument configurations, and unexpected procedural variations. We present a multi-agent robotic platform designed to address this long-tail challenge through collaborative task decomposition, dynamic scheduling, and adaptive control. The system integrates chemical perception for real-time reaction monitoring with feedback-driven execution, enabling it to adjust actions based on evolving experimental states rather than fixed scripts. Validation via acid-base titration demonstrates autonomous progress tracking, adaptive dispensing control, and reliable end-to-end experiment execution. By improving generalization across diverse laboratory scenarios, this platform provides a practical pathway toward intelligent, flexible, and scalable laboratory automation.

---

### Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training

Authors: Gengluo Li, Pengyuan Lyu, Chengquan Zhang, Huawen Shen, Liang Wu, Xingyu Wan, Gangyan Zeng, Han Hu, Can Ma, Yu Zhou
Published: 2026-03-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.23885v3

Document parsing has recently advanced with multimodal large language models (MLLMs) that directly map document images to structured outputs. Traditional cascaded pipelines depend on precise layout analysis and often fail under casually captured or non-standard conditions. Although end-to-end approaches mitigate this dependency, they still exhibit repetitive, hallucinated, and structurally inconsistent predictions - primarily due to the scarcity of large-scale, high-quality full-page (document-level) end-to-end parsing data and the lack of structure-aware training strategies. To address these challenges, we propose a data-training co-design framework for robust end-to-end document parsing. A Realistic Scene Synthesis strategy constructs large-scale, structurally diverse full-page end-to-end supervision by composing layout templates with rich document elements, while a Document-Aware Training Recipe introduces progressive learning and structure-token optimization to enhance structural fidelity and decoding stability. We further build Wild-OmniDocBench, a benchmark derived from real-world captured documents for robustness evaluation. Integrated into a 1B-parameter MLLM, our method achieves superior accuracy and robustness across both scanned/digital and real-world captured scenarios. All models, data synthesis pipelines, and benchmarks will be publicly released to advance future research in document understanding.

---

### BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment

Authors: Risa Shinoda, Kaede Shiohara, Nakamasa Inoue, Kuniaki Saito, Hiroaki Santo, Fumio Okura
Published: 2026-03-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.23883v1

Understanding animal species from multimodal data poses an emerging challenge at the intersection of computer vision and ecology. While recent biological models, such as BioCLIP, have demonstrated strong alignment between images and textual taxonomic information for species identification, the integration of the audio modality remains an open problem. We propose BioVITA, a novel visual-textual-acoustic alignment framework for biological applications. BioVITA involves (i) a training dataset, (ii) a representation model, and (iii) a retrieval benchmark. First, we construct a large-scale training dataset comprising 1.3 million audio clips and 2.3 million images, covering 14,133 species annotated with 34 ecological trait labels. Second, building upon BioCLIP2, we introduce a two-stage training framework to effectively align audio representations with visual and textual representations. Third, we develop a cross-modal retrieval benchmark that covers all possible directional retrieval across the three modalities (i.e., image-to-audio, audio-to-text, text-to-image, and their reverse directions), with three taxonomic levels: Family, Genus, and Species. Extensive experiments demonstrate that our model learns a unified representation space that captures species-level semantics beyond taxonomy, advancing multimodal biodiversity understanding. The project page is available at: https://dahlian00.github.io/BioVITA_Page/

---

### The Luna Bound Propagator for Formal Analysis of Neural Networks

Authors: Henry LeCates, Haoze Wu
Published: 2026-03-25
Categories: cs.LG, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2603.23878v3

The parameterized CROWN analysis, a.k.a., alpha-CROWN has emerged as a practically successful abstract interpretation method for neural network verification. However, existing implementations of alpha-CROWN are limited to Python, which complicates integration into existing DNN verifiers and long-term production-level systems. We introduce Luna, a new abstract-interpretation-based bound propagator implemented in C++. Luna supports Interval Bound Propagation, the DeepPoly/CROWN analysis, and the alpha-CROWN analysis over a general computational graph. We describe the architecture of Luna and show that it outperforms the state-of-the-art alpha-CROWN implementation in terms of both bound tightness and computational efficiency on supported benchmarks from VNN-COMP 2025. Luna is publicly available at https://github.com/ai-ar-research/luna.

---

### EnvSocial-Diff: A Diffusion-Based Crowd Simulation Model with Environmental Conditioning and Individual-Group Interaction

Authors: Bingxue Zhao, Qi Zhang, Hui Huang
Published: 2026-03-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.23874v1

Modeling realistic pedestrian trajectories requires accounting for both social interactions and environmental context, yet most existing approaches largely emphasize social dynamics. We propose \textbf{EnvSocial-Diff}: a diffusion-based crowd simulation model informed by social physics and augmented with environmental conditioning and individual--group interaction. Our structured environmental conditioning module explicitly encodes obstacles, objects of interest, and lighting levels, providing interpretable signals that capture scene constraints and attractors. In parallel, the individual--group interaction module goes beyond individual-level modeling by capturing both fine-grained interpersonal relations and group-level conformity through a graph-based design. Experiments on multiple benchmark datasets demonstrate that EnvSocial-Diff outperforms the latest state-of-the-art methods, underscoring the importance of explicit environmental conditioning and multi-level social interaction for realistic crowd simulation. Code is here: https://github.com/zqyq/EnvSocial-Diff.

---

### The DeepXube Software Package for Solving Pathfinding Problems with Learned Heuristic Functions and Search

Authors: Forest Agostinelli
Published: 2026-03-25
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.23873v1

DeepXube is a free and open-source Python package and command-line tool that seeks to automate the solution of pathfinding problems by using machine learning to learn heuristic functions that guide heuristic search algorithms tailored to deep neural networks (DNNs). DeepXube is comprised of the latest advances in deep reinforcement learning, heuristic search, and formal logic for solving pathfinding problems. This includes limited-horizon Bellman-based learning, hindsight experience replay, batched heuristic search, and specifying goals with answer-set programming. A robust multiple-inheritance structure simplifies the definition of pathfinding domains and the generation of training data. Training heuristic functions is made efficient through the automatic parallelization of the generation of training data across central processing units (CPUs) and reinforcement learning updates across graphics processing units (GPUs). Pathfinding algorithms that take advantage of the parallelism of GPUs and DNN architectures, such as batch weighted A* and Q* search and beam search are easily employed to solve pathfinding problems through command-line arguments. Finally, several convenient features for visualization, code profiling, and progress monitoring during training and solving are available. The GitHub repository is publicly available at https://github.com/forestagostinelli/deepxube.

---

### HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation

Authors: Ken Ding
Published: 2026-03-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.23871v1

Large language models trained with reinforcement learning (RL) for mathematical reasoning face a fundamental challenge: on problems the model cannot solve at all - "cliff" prompts - the RL gradient vanishes entirely, preventing any learning signal from reaching these failure modes. We introduce Hybrid Distillation Policy Optimization (HDPO), which augments standard RL with privileged self-distillation targeting cliff prompts. On each training step, HDPO identifies prompts where all rollouts fail, generates privileged rollouts by providing the model with ground-truth information, filters for correct solutions, and distills the teacher's token-level distribution into the student. Because teacher and student share the same weights - differing only in their input - the realizability gap is provably bounded, unlike cross-model distillation. We prove that R=1 filtered privileged generation recovers the optimal KL-regularized RL policy in the hard-threshold limit. Experiments on OpenMathInstruct-2 with Qwen2.5-Math-1.5B-Instruct show that HDPO consistently improves coverage metrics (pass@4 by +0.8-1.1%, pass@8 by +0.4-1.7%) while maintaining greedy accuracy, with the distillation weight lambda providing direct control over the exploration-exploitation tradeoff.

---

### MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection

Authors: Yuang Geng, Junkai Zhou, Kang Yang, Pan He, Zhuoyang Zhou, Jose C. Principe, Joel Harley, Ivan Ruchkin
Published: 2026-03-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.23868v2

In this paper, we address the challenging problem of single-scene, fully unsupervised video anomaly detection (VAD), where raw videos containing both normal and abnormal events are used directly for training and testing without any labels. This differs sharply from prior work that either requires extensive labeling (fully or weakly supervised) or depends on normal-only videos (one-class classification), which are vulnerable to distribution shifts and contamination. We propose an entropy-guided autoencoder that detects anomalies through reconstruction error by reconstructing normal frames well while making anomalies reconstruct poorly. The key idea is to combine the standard reconstruction loss with a novel Minimal Latent Entropy (MLE) loss in the autoencoder. Reconstruction loss alone maps normal and abnormal inputs to distinct latent clusters due to their inherent differences, but also risks reconstructing anomalies too well to detect. Therefore, MLE loss addresses this by minimizing the entropy of latent embeddings, encouraging them to concentrate around high-density regions. Since normal frames dominate the raw video, sparse anomalous embeddings are pulled into the normal cluster, so the decoder emphasizes normal patterns and produces poor reconstructions for anomalies. This dual-loss design produces a clear reconstruction gap that enables effective anomaly detection. Extensive experiments on two widely used benchmarks and a challenging self-collected driving dataset demonstrate that our method achieves robust and superior performance over baselines.

---

### Can VLMs Reason Robustly? A Neuro-Symbolic Investigation

Authors: Weixin Chen, Antonio Vergari, Han Zhao
Published: 2026-03-25
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.23867v2

Vision-Language Models (VLMs) have been applied to a wide range of reasoning tasks, yet it remains unclear whether they can reason robustly under distribution shifts. In this paper, we study covariate shifts in which the perceptual input distribution changes while the underlying prediction rules do not. To investigate this question, we consider visual deductive reasoning tasks, where a model is required to answer a query given an image and logical rules defined over the object concepts in the image. Empirically, we find that VLMs fine-tuned through gradient-based end-to-end training can achieve high in-distribution accuracy but fail to generalize under such shifts, suggesting that fine-tuning does not reliably induce the underlying reasoning function. This motivates a neuro-symbolic perspective that decouples perception from reasoning. However, we further observe that recent neuro-symbolic approaches that rely on black-box components for reasoning can still exhibit inconsistent robustness across tasks. To address this issue, we propose VLC, a neuro-symbolic method that combines VLM-based concept recognition with circuit-based symbolic reasoning. In particular, task rules are compiled into a symbolic program, specifically a circuit, which executes the rules exactly over the object concepts recognized by the VLM. Experiments on three simple visual deductive reasoning tasks with distinct rule sets show that VLC consistently achieves higher task accuracy on out-of-distribution data than other reasoning paradigms. Code is available at https://github.com/uiuctml/VLC.

---

### See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning

Authors: Yuxi Wei, Wei Huang, Qirui Chen, Lu Hou, Xiaojuan Qi
Published: 2026-03-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.23864v1

Spatial understanding is fundamental for embodied agents, yet most spatial VLMs and benchmarks remain offline-evaluating post-hoc QA over pre-recorded inputs and overlooking two crucial deployment-critical requirements: long-horizon streaming inference and active perception when the current view is insufficient. To address this gap, we introduce S3-Bench, a benchmark suite for streaming spatial question answering with active exploration, where queries are temporally grounded to specific timestamps and must be answered using only observations available up to that moment. S3-Bench adopts a dual-domain design, combining a scalable simulator with controllable trajectories and exploration actions, and real-world streaming videos that capture practical sensing artifacts for rigorous generalization evaluation. Overall, it spans 10K+ scenes and 26K+ trajectories, with dedicated training (S3-Train) and evaluation (S3-Eval) splits. We further propose AMF-VLM, which supports streaming spatial reasoning under bounded computing via (i) memory folding, which compresses long-horizon observations into compact structured memory, and (ii) active exploration, which outputs explicit actions (e.g. move/rotate/scan) to acquire missing evidence before answering. Extensive experiments demonstrate that, compared to models using identical training data, our approach yields improvements of 8.8% and 13.3% on the simulated and real splits of S3-Eval, respectively, while maintaining competitive transferability to standard spatial benchmarks.

---

### Generative AI User Experience: Developing Human--AI Epistemic Partnership

Authors: Xiaoming Zhai
Published: 2026-03-25
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2603.23863v1

Generative AI (GenAI) has rapidly entered education, yet its user experience is often explained through adoption-oriented constructs such as usefulness, ease of use, and engagement. We argue that these constructs are no longer sufficient because systems such as ChatGPT do not merely support learning tasks but also participate in knowledge construction. Existing theories cannot explain why GenAI frequently produces experiences characterized by negotiated authority, redistributed cognition, and accountability tension. To address this gap, this paper develops the Human--AI Epistemic Partnership Theory (HAEPT), explaining the GenAI user experience as a form of epistemic partnership that features a dynamic negotiation of three interlocking contracts: epistemic, agency, and accountability. We argue that findings on trust, over-reliance, academic integrity, teacher caution, and relational interaction about GenAI can be reinterpreted as tensions within these contracts rather than as isolated issues. Instead of holding a single, stable view of GenAI, users adjust how they relate to it over time through calibration cycles. These repeated interactions account for why trust and skepticism often coexist and for how partnership modes describe recurrent configurations of human--AI collaboration across tasks. To demonstrate the usefulness of HAEPT, we applied it to analyze the UX of collaborative learning with AI speakers and AI-facilitated scientific argumentation, illustrating different contract configurations.

---

### Deep Convolutional Neural Networks for predicting highest priority functional group in organic molecules

Authors: Kunal Khatri, Vineet Mehta
Published: 2026-03-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.23862v1

Our work addresses the problem of predicting the highest priority functional group present in an organic molecule. Functional Groups are groups of bound atoms that determine the physical and chemical properties of organic molecules. In the presence of multiple functional groups, the dominant functional group determines the compound's properties. Fourier-transform Infrared spectroscopy (FTIR) is a commonly used spectroscopic method for identifying the presence or absence of functional groups within a compound. We propose the use of a Deep Convolutional Neural Networks (CNN) to predict the highest priority functional group from the Fourier-transform infrared spectrum (FTIR) of the organic molecule. We have compared our model with other previously applied Machine Learning (ML) method Support Vector Machine (SVM) and reasoned why CNN outperforms it.

---

### An Invariant Compiler for Neural ODEs in AI-Accelerated Scientific Simulation

Authors: Fangzhou Yu, Yiqi Su, Ray Lee, Shenfeng Cheng, Naren Ramakrishnan
Published: 2026-03-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.23861v1

Neural ODEs are increasingly used as continuous-time models for scientific and sensor data, but unconstrained neural ODEs can drift and violate domain invariants (e.g., conservation laws), yielding physically implausible solutions. In turn, this can compound error in long-horizon prediction and surrogate simulation. Existing solutions typically aim to enforce invariance by soft penalties or other forms of regularization, which can reduce overall error but do not guarantee that trajectories will not leave the constraint manifold. We introduce the invariant compiler, a framework that enforces invariants by construction: it treats invariants as first-class types and uses an LLM-driven compilation workflow to translate a generic neural ODE specification into a structure-preserving architecture whose trajectories remain on the admissible manifold in continuous time (and up to numerical integration error in practice). This compiler view cleanly separates what must be preserved (scientific structure) from what is learned from data (dynamics within that structure). It provides a systematic design pattern for invariant-respecting neural surrogates across scientific domains.

---

### Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness

Authors: Yunrui Yu, Hang Su, Jun Zhu
Published: 2026-03-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.23860v1

This work investigates the critical role of activation function curvature -- quantified by the maximum second derivative $\max|σ''|$ -- in adversarial robustness. Using the Recursive Curvature-Tunable Activation Family (RCT-AF), which enables precise control over curvature through parameters $α$ and $β$, we systematically analyze this relationship. Our study reveals a fundamental trade-off: insufficient curvature limits model expressivity, while excessive curvature amplifies the normalized Hessian diagonal norm of the loss, leading to sharper minima that hinder robust generalization. This results in a non-monotonic relationship where optimal adversarial robustness consistently occurs when $\max|σ''|$ falls within 4 to 10, a finding that holds across diverse network architectures, datasets, and adversarial training methods. We provide theoretical insights into how activation curvature affects the diagonal elements of the hessian matrix of the loss, and experimentally demonstrate that the normalized Hessian diagonal norm exhibits a U-shaped dependence on $\max|σ''|$, with its minimum within the optimal robustness range, thereby validating the proposed mechanism.

---

### When AI output tips to bad but nobody notices: Legal implications of AI's mistakes

Authors: Dylan J. Restrepo, Nicholas J. Restrepo, Frank Y. Huo, Neil F. Johnson
Published: 2026-03-25
Categories: cs.AI, cs.CY, cs.SI, nlin.CD, physics.soc-ph
arXiv: https://arxiv.org/abs/2603.23857v1

The adoption of generative AI across commercial and legal professions offers dramatic efficiency gains -- yet for law in particular, it introduces a perilous failure mode in which the AI fabricates fictitious case law, statutes, and judicial holdings that appear entirely authentic. Attorneys who unknowingly file such fabrications face professional sanctions, malpractice exposure, and reputational harm, while courts confront a novel threat to the integrity of the adversarial process. This failure mode is commonly dismissed as random `hallucination', but recent physics-based analysis of the Transformer's core mechanism reveals a deterministic component: the AI's internal state can cross a calculable threshold, causing its output to flip from reliable legal reasoning to authoritative-sounding fabrication. Here we present this science in a legal-industry setting, walking through a simulated brief-drafting scenario. Our analysis suggests that fabrication risk is not an anomalous glitch but a foreseeable consequence of the technology's design, with direct implications for the evolving duty of technological competence. We propose that legal professionals, courts, and regulators replace the outdated `black box' mental model with verification protocols based on how these systems actually fail.

---

### Symbolic--KAN: Kolmogorov-Arnold Networks with Discrete Symbolic Structure for Interpretable Learning

Authors: Salah A Faroughi, Farinaz Mostajeran, Amirhossein Arzani, Shirko Faroughi
Published: 2026-03-25
Categories: cs.LG, cs.CE, math.AP, math.DS
arXiv: https://arxiv.org/abs/2603.23854v1

Symbolic discovery of governing equations is a long-standing goal in scientific machine learning, yet a fundamental trade-off persists between interpretability and scalable learning. Classical symbolic regression methods yield explicit analytic expressions but rely on combinatorial search, whereas neural networks scale efficiently with data and dimensionality but produce opaque representations. In this work, we introduce Symbolic Kolmogorov-Arnold Networks (Symbolic-KANs), a neural architecture that bridges this gap by embedding discrete symbolic structure directly within a trainable deep network. Symbolic-KANs represent multivariate functions as compositions of learned univariate primitives applied to learned scalar projections, guided by a library of analytic primitives, hierarchical gating, and symbolic regularization that progressively sharpens continuous mixtures into one-hot selections. After gated training and discretization, each active unit selects a single primitive and projection direction, yielding compact closed-form expressions without post-hoc symbolic fitting. Symbolic-KANs further act as scalable primitive discovery mechanisms, identifying the most relevant analytic components that can subsequently inform candidate libraries for sparse equation-learning methods. We demonstrate that Symbolic-KAN reliably recovers correct primitive terms and governing structures in data-driven regression and inverse dynamical systems. Moreover, the framework extends to forward and inverse physics-informed learning of partial differential equations, producing accurate solutions directly from governing constraints while constructing compact symbolic representations whose selected primitives reflect the true analytical structure of the underlying equations. These results position Symbolic-KAN as a step toward scalable, interpretable, and mechanistically grounded learning of governing laws.

---

### SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systems

Authors: Chung-En Johnny Yu, Brian Jalaian, Nathaniel D. Bastian
Published: 2026-03-25
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.23853v3

Combining multiple Vision-Language Models (VLMs) can enhance multimodal reasoning and robustness, but aggregating heterogeneous models' outputs amplifies uncertainty and increases the risk of hallucinations. We propose SCoOP (Semantic-Consistent Opinion Pooling), a training-free uncertainty quantification (UQ) framework for multi-VLM systems through uncertainty-weighted linear opinion pooling. The core idea is to treat each VLM as a probabilistic "expert," sample multiple outputs, map them to a unified space, aggregate their opinions, and produce a system-level uncertainty score. Unlike prior UQ methods designed for single models, SCoOP explicitly measures collective, system-level uncertainty across multiple VLMs, enabling effective hallucination detection and abstention for highly uncertain samples. On ScienceQA, SCoOP achieves an AUROC of 0.866 for hallucination detection, outperforming baselines (0.732-0.757) by approximately 10-13%. For abstention, it attains an AURAC of 0.907, exceeding baselines (0.818-0.840) by 7-9%. Despite these gains, SCoOP introduces only microsecond-level aggregation overhead relative to the baselines, which is trivial compared to typical VLM inference time (on the order of seconds). These results demonstrate that SCoOP provides an efficient and principled mechanism for uncertainty-aware aggregation, advancing the reliability of multimodal AI systems. Our code is publicly available at https://github.com/chungenyu6/SCoOP.

---

### BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents

Authors: Praveen Kumar Myakala, Manan Agrawal, Rahul Manche
Published: 2026-03-25
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2603.23848v1

LLMs are increasingly used as long-running conversational agents, yet every major benchmark evaluating their memory treats user information as static facts to be stored and retrieved. That's the wrong model. People change their minds, and over extended interactions, phenomena like opinion drift, over-alignment, and confirmation bias start to matter a lot. BeliefShift introduces a longitudinal benchmark designed specifically to evaluate belief dynamics in multi-session LLM interactions. It covers three tracks: Temporal Belief Consistency, Contradiction Detection, and Evidence-Driven Revision. The dataset includes 2,400 human-annotated multi-session interaction trajectories spanning health, politics, personal values, and product preferences. We evaluate seven models including GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, LLaMA-3, and Mistral-Large under zero-shot and retrieval-augmented generation (RAG) settings. Results reveal a clear trade-off: models that personalize aggressively resist drift poorly, while factually grounded models miss legitimate belief updates. We further introduce four novel evaluation metrics: Belief Revision Accuracy (BRA), Drift Coherence Score (DCS), Contradiction Resolution Rate (CRR), and Evidence Sensitivity Index (ESI).

---

### 3D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation

Authors: Kyeonghun Kim, Jaehyeok Bae, Youngung Han, Joo Young Bae, Seoyoung Ju, Junsu Lim, Gyeongmin Kim, Nam-Joon Kim, Woo Kyoung Jeong, Ken Ying-Kai Liao, Won Jae Lee, Pa Hong et al.
Published: 2026-03-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.23845v1

Deep learning and generative models are advancing rapidly, with synthetic data increasingly being integrated into training pipelines for downstream analysis tasks. However, in medical imaging, their adoption remains constrained by the scarcity of reliable annotated datasets. To address this limitation, we propose 3D-LLDM, a label-guided 3D latent diffusion model that generates high-quality synthetic magnetic resonance (MR) volumes with corresponding anatomical segmentation masks. Our approach uses hepatobiliary phase MR images enhanced with the Gd-EOB-DTPA contrast agent to derive structural masks for the liver, portal vein, hepatic vein, and hepatocellular carcinoma, which then guide volumetric synthesis through a ControlNet-based architecture. Trained on 720 real clinical hepatobiliary phase MR scans from Samsung Medical Center, 3D-LLDM achieves a Fréchet Inception Distance (FID) of 28.31, improving over GANs by 70.9% and over state-of-the-art diffusion baselines by 26.7%. When used for data augmentation, the synthetic volumes improve hepatocellular carcinoma segmentation by up to 11.153% Dice score across five CNN architectures.

---

### Language Models as Higher-Order Planning Formalizers

Authors: Owen Jiang, Cassie Huang, Ashish Sabharwal, Li Zhang
Published: 2026-03-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.23844v2

Recent work provides overwhelming evidence that LLMs, even those trained to scale their reasoning trace, quickly deteriorate at planning as problems become more complex. LLM-as-Formalizers aim to address this by employing LLMs as a bridge to translate natural language descriptions into structured planning representations such as PDDL, which are then fed to a programmatic solver. We observe that its success may be overstated because planning problem descriptions in standard benchmarks often have a one-to-one mapping to PDDL, which departs from real use cases. To address this, we introduce the notion of unraveling problems where a natural yet succinct description translates into a very large PDDL representation. Using unraveling variants of four standard planning domains, we demonstrate that LLM Formalizers also do not always scale. We tackle this challenge by introducing a new paradigm, LLM-as-Higher-Order-Formalizer, where the LLM generates a high-level program that captures the recurrent logic within the description and in turn generates the larger PDDL representation. This decouples token output from the combinatorial explosion of the underlying formalization and search space, leading to improved performance for complex problems.

---

### PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay

Authors: Rohan Khetan, Ashna Khetan
Published: 2026-03-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.23841v2

While Large Language Models (LLMs) are increasingly used as primary sources of information, their potential for political bias may impact their objectivity. Existing benchmarks of LLM social bias primarily evaluate demographic stereotypes, and when political bias is measured, it is done so at a coarse level, overlooking the values that shape sociopolitical reasoning. We introduce PoliticsBench, a multi-stage roleplay benchmark for evaluating fine-grained value expression in LLMs. Across twenty evolving scenarios, models articulate tradeoffs, take positions, and make decisions under competing pressures. Across eight prominent LLMs, we show that scenario-based prompting elicits broader and more strongly expressed value profiles than direct political questions, with peak interaction stages increasing the number of strongly activated value dimensions by approximately $0.75$ (out of 10 total dimensions), a statistically significant increase relative to baseline prompting ($p < 0.05$). In addition, commitment to a stance increases over the course of interaction, rising by approximately $1.4$ points on a $(0,5)$ scale from initial to decision stages. While responses become less robust to scenario paraphrasing in later interaction stages, inter-judge agreement remains relatively stable. Our results suggest that evaluating LLM political behavior requires moving beyond static prompts toward longer interactive settings that capture how values are applied in context.

---

### VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents

Authors: Yuhao Chen, Yi Xu, Xinyun Ding, Xiang Fang, Shuochen Liu, Luxi Lin, Qingyu Zhang, Ya Li, Quan Liu, Tong Xu
Published: 2026-03-25
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.23840v1

With the growing demand for intelligent in-vehicle experiences, vehicle-based agents are evolving from simple assistants to long-term companions. This evolution requires agents to continuously model multi-user preferences and make reliable decisions in the face of inter-user preference conflicts and changing habits over time. However, existing benchmarks are largely limited to single-user, static question-answer settings, failing to capture the temporal evolution of preferences and the multi-user, tool-interactive nature of real vehicle environments. To address this gap, we introduce VehicleMemBench, a multi-user long-context memory benchmark built on an executable in-vehicle simulation environment. The benchmark evaluates tool use and memory by comparing the post-action environment state with a predefined target state, enabling objective and reproducible evaluation without LLM-based or human scoring. VehicleMemBench includes 23 tool modules, and each sample contains over 80 historical memory events. Experiments show that powerful models perform well on direct instruction tasks but struggle in scenarios involving memory evolution, particularly when user preferences change dynamically. Even advanced memory systems struggle to handle domain-specific memory requirements in this environment. These findings highlight the need for more robust and specialized memory management mechanisms to support long-term adaptive decision-making in real-world in-vehicle systems. To facilitate future research, we release the data and code.

---

### Learning-guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation

Authors: Han Zheng, Yining Ma, Brandon Araki, Jingkai Chen, Cathy Wu
Published: 2026-03-25
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2603.23838v1

Lifelong Multi-Agent Path Finding (MAPF) is critical for modern warehouse automation, which requires multiple robots to continuously navigate conflict-free paths to optimize the overall system throughput. However, the complexity of warehouse environments and the long-term dynamics of lifelong MAPF often demand costly adaptations to classical search-based solvers. While machine learning methods have been explored, their superiority over search-based methods remains inconclusive. In this paper, we introduce Reinforcement Learning (RL) guided Rolling Horizon Prioritized Planning (RL-RH-PP), the first framework integrating RL with search-based planning for lifelong MAPF. Specifically, we leverage classical Prioritized Planning (PP) as a backbone for its simplicity and flexibility in integrating with a learning-based priority assignment policy. By formulating dynamic priority assignment as a Partially Observable Markov Decision Process (POMDP), RL-RH-PP exploits the sequential decision-making nature of lifelong planning while delegating complex spatial-temporal interactions among agents to reinforcement learning. An attention-based neural network autoregressively decodes priority orders on-the-fly, enabling efficient sequential single-agent planning by the PP planner. Evaluations in realistic warehouse simulations show that RL-RH-PP achieves the highest total throughput among baselines and generalizes effectively across agent densities, planning horizons, and warehouse layouts. Our interpretive analyses reveal that RL-RH-PP proactively prioritizes congested agents and strategically redirects agents from congestion, easing traffic flow and boosting throughput. These findings highlight the potential of learning-guided approaches to augment traditional heuristics in modern warehouse automation.

---

### Beyond Consistency: Inference for the Relative risk functional in Deep Nonparametric Cox Models

Authors: Sattwik Ghosal, Xuran Meng, Yi Li
Published: 2026-03-25
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2603.23835v1

There remain theoretical gaps in deep neural network estimators for the nonparametric Cox proportional hazards model. In particular, it is unclear how gradient-based optimization error propagates to population risk under partial likelihood, how pointwise bias can be controlled to permit valid inference, and how ensemble-based uncertainty quantification behaves under realistic variance decay regimes. We develop an asymptotic distribution theory for deep Cox estimators that addresses these issues. First, we establish nonasymptotic oracle inequalities for general trained networks that link in-sample optimization error to population risk without requiring the exact empirical risk optimizer. We then construct a structured neural parameterization that achieves infinity-norm approximation rates compatible with the oracle bound, yielding control of the pointwise bias. Under these conditions and using the Hajek--Hoeffding projection, we prove pointwise and multivariate asymptotic normality for subsampled ensemble estimators. We derive a range of subsample sizes that balances bias correction with the requirement that the Hajek--Hoeffding projection remain dominant. This range accommodates decay conditions on the single-overlap covariance, which measures how strongly a single shared observation influences the estimator, and is weaker than those imposed in the subsampling literature. An infinitesimal jackknife representation provides analytic covariance estimation and valid Wald-type inference for relative risk contrasts such as log-hazard ratios. Finally, we illustrate the finite-sample implications of the theory through simulations and a real data application.

---

### Unveiling Hidden Convexity in Deep Learning: a Sparse Signal Processing Perspective

Authors: Emi Zeger, Mert Pilanci
Published: 2026-03-25
Categories: cs.LG, eess.SP, stat.ML
arXiv: https://arxiv.org/abs/2603.23831v1

Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processing, and language modeling. Despite this success, the non-convex nature of DNN loss functions complicates optimization and limits theoretical understanding. In this paper, we highlight how recently developed convex equivalences of ReLU NNs and their connections to sparse signal processing models can address the challenges of training and understanding NNs. Recent research has uncovered several hidden convexities in the loss landscapes of certain NN architectures, notably two-layer ReLU networks and other deeper or varied architectures. This paper seeks to provide an accessible and educational overview that bridges recent advances in the mathematics of deep learning with traditional signal processing, encouraging broader signal processing applications.

---

### Circuit Complexity of Hierarchical Knowledge Tracing and Implications for Log-Precision Transformers

Authors: Naiming Liu, Richard Baraniuk, Shashank Sonkar
Published: 2026-03-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.23823v1

Knowledge tracing models mastery over interconnected concepts, often organized by prerequisites. We analyze hierarchical prerequisite propagation through a circuit-complexity lens to clarify what is provable about transformer-style computation on deep concept hierarchies. Using recent results that log-precision transformers lie in logspace-uniform $\mathsf{TC}^0$, we formalize prerequisite-tree tasks including recursive-majority mastery propagation. Unconditionally, recursive-majority propagation lies in $\mathsf{NC}^1$ via $O(\log n)$-depth bounded-fanin circuits, while separating it from uniform $\mathsf{TC}^0$ would require major progress on open lower bounds. Under a monotonicity restriction, we obtain an unconditional barrier: alternating ALL/ANY prerequisite trees yield a strict depth hierarchy for \emph{monotone} threshold circuits. Empirically, transformer encoders trained on recursive-majority trees converge to permutation-invariant shortcuts; explicit structure alone does not prevent this, but auxiliary supervision on intermediate subtrees elicits structure-dependent computation and achieves near-perfect accuracy at depths 3--4. These findings motivate structure-aware objectives and iterative mechanisms for prerequisite-sensitive knowledge tracing on deep hierarchies.

---

### How Vulnerable Are Edge LLMs?

Authors: Ao Ding, Hongzong Li, Zi Liang, Zhanpeng Shi, Shuxin Zhuang, Shiqin Tang, Rong Feng, Ping Lu
Published: 2026-03-25
Categories: cs.CR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.23822v1

Large language models (LLMs) are increasingly deployed on edge devices under strict computation and quantization constraints, yet their security implications remain unclear. We study query-based knowledge extraction from quantized edge-deployed LLMs under realistic query budgets and show that, although quantization introduces noise, it does not remove the underlying semantic knowledge, allowing substantial behavioral recovery through carefully designed queries. To systematically analyze this risk, we propose \textbf{CLIQ} (\textbf{Cl}ustered \textbf{I}nstruction \textbf{Q}uerying), a structured query construction framework that improves semantic coverage while reducing redundancy. Experiments on quantized Qwen models (INT8/INT4) demonstrate that CLIQ consistently outperforms original queries across BERTScore, BLEU, and ROUGE, enabling more efficient extraction under limited budgets. These results indicate that quantization alone does not provide effective protection against query-based extraction, highlighting a previously underexplored security risk in edge-deployed LLMs.

---

### Perturbation: A simple and efficient adversarial tracer for representation learning in language models

Authors: Joshua Rozner, Cory Shain
Published: 2026-03-25
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.23821v2

Linguistic representation learning in deep neural language models (LMs) has been studied for decades, but finding representations in LMs remains an unsolved problem. On the one hand, unconstrained alignments may trivialize the notion of representation (Sutter et al., 2025); on the other, even recently popularized linear approaches may not always be faithful to natural model behavior (Arora et al. 2024). Here we escape this dilemma by reconceptualizing representations not as patterns of activation but as conduits for learning. Our approach is simple: we perturb an LM by fine-tuning it on a single adversarial example and measure how this perturbation "infects" other examples. Perturbation makes no geometric assumptions, and unlike other methods, it does not find representations where it should not (e.g., in untrained LMs). But in trained LMs, perturbation reveals structured transfer at multiple linguistic grain sizes, suggesting that LMs both generalize along representational lines and acquire linguistic abstractions from experience alone.

---

### Perturbation: A simple and efficient adversarial tracer for representation learning in language models

Authors: Joshua Rozner, Cory Shain
Published: 2026-03-25
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.23821v1

Linguistic representation learning in deep neural language models (LMs) has been studied for decades, for both practical and theoretical reasons. However, finding representations in LMs remains an unsolved problem, in part due to a dilemma between enforcing implausible constraints on representations (e.g., linearity; Arora et al. 2024) and trivializing the notion of representation altogether (Sutter et al., 2025). Here we escape this dilemma by reconceptualizing representations not as patterns of activation but as conduits for learning. Our approach is simple: we perturb an LM by fine-tuning it on a single adversarial example and measure how this perturbation ``infects'' other examples. Perturbation makes no geometric assumptions, and unlike other methods, it does not find representations where it should not (e.g., in untrained LMs). But in trained LMs, perturbation reveals structured transfer at multiple linguistic grain sizes, suggesting that LMs both generalize along representational lines and acquire linguistic abstractions from experience alone.

---

### Willful Disobedience: Automatically Detecting Failures in Agentic Traces

Authors: Reshabh K Sharma, Shraddha Barke, Benjamin Zorn
Published: 2026-03-25
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.23806v2

AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make validation difficult. Outcome-only benchmarks can miss critical procedural failures, such as incorrect workflow routing, unsafe tool usage, or violations of prompt-specified rules. This paper presents AgentPex, an AI-powered tool designed to systematically evaluate agentic traces. AgentPex extracts behavioral rules from agent prompts and system instructions, then uses these specifications to automatically evaluate traces for compliance. We evaluate AgentPex on 424 traces from $τ^2$-bench across models in telecom, retail, and airline customer service. Our results show that AgentPex distinguishes agent behavior across models and surfaces specification violations that are not captured by outcome-only scoring. It also provides fine-grained analysis by domain and metric, enabling developers to understand agent strengths and weaknesses at scale. The source code of AgentPex is available at https://github.com/microsoft/agentpex.

---

### Deep Neural Regression Collapse

Authors: Akshay Rangamani, Altay Unal
Published: 2026-03-25
Categories: cs.LG, cs.AI, cs.NE, stat.ML
arXiv: https://arxiv.org/abs/2603.23805v1

Neural Collapse is a phenomenon that helps identify sparse and low rank structures in deep classifiers. Recent work has extended the definition of neural collapse to regression problems, albeit only measuring the phenomenon at the last layer. In this paper, we establish that Neural Regression Collapse (NRC) also occurs below the last layer across different types of models. We show that in the collapsed layers of neural regression models, features lie in a subspace that corresponds to the target dimension, the feature covariance aligns with the target covariance, the input subspace of the layer weights aligns with the feature subspace, and the linear prediction error of the features is close to the overall prediction error of the model. In addition to establishing Deep NRC, we also show that models that exhibit Deep NRC learn the intrinsic dimension of low rank targets and explore the necessity of weight decay in inducing Deep NRC. This paper provides a more complete picture of the simple structure learned by deep networks in the context of regression.

---

### Object Search in Partially-Known Environments via LLM-informed Model-based Planning and Prompt Selection

Authors: Abhishek Paudel, Abhish Khanal, Raihan I. Arnob, Shahriar Hossain, Gregory J. Stein
Published: 2026-03-25
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.23800v2

We present a novel LLM-informed model-based planning framework, and a novel prompt selection method, for object search in partially-known environments. Our approach uses an LLM to estimate statistics about the likelihood of finding the target object when searching various locations throughout the scene that, combined with travel costs extracted from the environment map, are used to instantiate a model, thus using the LLM to inform planning and achieve effective search performance. Moreover, the abstraction upon which our approach relies is amenable to deployment-time model selection via the recent offline replay approach, an insight we leverage to enable fast prompt and LLM selection during deployment. Simulation experiments demonstrate that our LLM-informed model-based planning approach outperforms the baseline planning strategy that fully relies on LLM and optimistic strategy with as much as 11.8% and 39.2% improvements respectively, and our bandit-like selection approach enables quick selection of best prompts and LLMs resulting in 6.5% lower average cost and 33.8% lower average cumulative regret over baseline UCB bandit selection. Real-robot experiments in an apartment demonstrate similar improvements and so further validate our approach.

---

### Resolving gradient pathology in physics-informed epidemiological models

Authors: Nickson Golooba, Woldegebriel Assefa Woldegerima
Published: 2026-03-25
Categories: cs.LG, math.NA, math.OC
arXiv: https://arxiv.org/abs/2603.23799v1

Physics-informed neural networks (PINNs) are increasingly used in mathematical epidemiology to bridge the gap between noisy clinical data and compartmental models, such as the susceptible-exposed-infected-removed (SEIR) model. However, training these hybrid networks is often unstable due to competing optimization objectives. As established in recent literature on ``gradient pathology," the gradient vectors derived from the data loss and the physical residual often point in conflicting directions, leading to slow convergence or optimization deadlock. While existing methods attempt to resolve this by balancing gradient magnitudes or projecting conflicting vectors, we propose a novel method, conflict-gated gradient scaling (CGGS), to address gradient conflicts in physics-informed neural networks for epidemiological modelling, ensuring stable and efficient training and a computationally efficient alternative. This method utilizes the cosine similarity between the data and physics gradients to dynamically modulate the penalty weight. Unlike standard annealing schemes that only normalize scales, CGGS acts as a geometric gate: it suppresses the physical constraint when directional conflict is high, allowing the optimizer to prioritize data fidelity, and restores the constraint when gradients align. We prove that this gating mechanism preserves the standard $O(1/T)$ convergence rate for smooth non-convex objectives, a guarantee that fails under fixed-weight or magnitude-balanced training when gradients conflict. We demonstrate that this mechanism autonomously induces a curriculum learning effect, improving parameter estimation in stiff epidemiological systems compared to magnitude-based baselines. Our empirical results show improved peak recovery and convergence over magnitude-based methods.

---

### Infrequent Child-Directed Speech Is Bursty and May Draw Infant Vocalizations

Authors: Margaret Cychosz, Adriana Weisleder
Published: 2026-03-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.23797v1

Children in many parts of the world hear relatively little speech directed to them, yet still reach major language development milestones. What differs about the speech input that infants learn from when directed input is rare? Using longform, infant-centered audio recordings taken in rural Bolivia and the urban U.S., we examined temporal patterns of infants' speech input and their pre-linguistic vocal behavior. We find that child-directed speech in Bolivia, though less frequent, was just as temporally clustered as speech input in the U.S, arriving in concentrated bursts rather than spread across the day. In both communities, infants were most likely to produce speech-like vocalizations during periods of speech directed to them, with the probability of infants' speech-like vocalizations during target child-directed speech nearly double that during silence. In Bolivia, infants' speech-like vocalizations were also more likely to occur during bouts of directed speech from older children than from adults. Together, these findings suggest that the developmental impact of child-directed speech may depend not only on quantity, but on temporal concentration and source, with older children serving as an important source of input in some communities, including where adult speech to infants is less frequent.

---

### Shu Dao: A Calligraphy Score Framework Linking Calligraphy, Music, and Performance

Authors: Lican Huang
Published: 2026-03-24
Categories: cs.HC, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2606.00001v1

This paper introduces Calligraphy Writing Score Representation (CWSR) and proposes Shu Dao as a framework that interprets East Asian calligraphy as a performative art rather than a static visual artifact. Inspired by traditions such as Japanese Shodō and embodied cultural practices such as Chadao , the framework models calligraphy as a structured performance analogous to musical notation. Instead of representing characters as fixed images, the proposed approach encodes each brush stroke as an ordered and executable action, forming a calligraphy score. Characters are organized within a structured spatial grid, and strokes are annotated with attributes including stroke type, execution order, spatial coordinates, trajectory, compositional role, and dynamic properties such as brush pressure and pacing. This representation captures temporal and expressive aspects of calligraphic writing that are typically absent from image-based representations. The paper makes three main contributions. First, it introduces CWSR as a structured notation system for representing calligraphy across multiple levels, including strokes, character structures, and compositional organization (e.g., layout and zhangfa), together with their rhythmic and performative dynamics. Second, it conceptualizes Shu Dao as a score-mediated framework that models calligraphy as structured performance. Third, it establishes a computational foundation for the analysis, visualization, and executable generation of calligraphic works by AI-based calligraphic agents. Together, these contributions bridge calligraphy, musical notation, and performative cultural practices, supporting human--AI co-creation in computational calligraphy and digital humanities research.

---

### Patchwork: A compact representation for 3D polygonal shapes

Authors: Ruichen Zheng, Biao Zhang, Michael Birsak, Mikhail Skopenkov, Peter Wonka
Published: 2026-03-24
Categories: cs.GR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.16266v1

We introduce Patchwork, a new general-purpose shape representation capable of modeling 2D and 3D geometry with a small number of parameters. Patchwork is grounded in a rigorous mathematical framework, providing provable complexity bounds and the ability to approximate arbitrary shapes with arbitrary precision in any dimension. We propose an efficient gradient-based optimization scheme to fit Patchwork representations to 2D and 3D data, along with a novel regularization loss that progressively prunes redundant elements, yielding high compactness after convergence. Our approach offers fast fitting performance, a fraction of the required parameters compared to existing alternatives, and native support for inside-outside classification, making it a versatile and compact representation for geometric learning and reconstruction tasks, with future potential for 3D generation. Our implementation is available at: https://github.com/Ankbzpx/patchwork-experiment.

---

### AgentWall: A Runtime Safety Layer for Local AI Agents

Authors: Ashwin Aravind
Published: 2026-03-24
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2605.16265v1

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing the web, the consequences of unsafe or adversarially manipulated behavior become immediate and tangible. Existing AI safety work has focused primarily on model alignment and input filtering, but these approaches do not address what happens at the moment an agent's intent becomes a real action on a real machine. This gap is especially acute in local environments, where developers run agents against their own filesystems, credentials, and infrastructure with little runtime control. This paper introduces AgentWall, a runtime safety and observability layer for local AI agents. AgentWall intercepts every proposed agent action before it reaches the host environment, evaluates it against an explicit declarative policy, requires human approval for sensitive operations, and records a complete execution trail for audit and replay. It is implemented as a policy-enforcing MCP proxy and native OpenClaw plugin, working across Claude Desktop, Cursor, Windsurf, Claude Code, and OpenClaw with a single install command. We present the design, architecture, threat model, and policy model of AgentWall, and demonstrate 92.9% policy enforcement accuracy with sub-millisecond overhead across 14 benchmark tests. AgentWall is open-source at https://github.com/agentwall/Agentwall.

---

### Representing Higher-Order Networks: A Survey of Graph-Based Frameworks

Authors: Takaaki Fujita, Florentin Smarandache
Published: 2026-03-24
Categories: cs.SI, cs.AI, cs.CE, math.CO
arXiv: https://arxiv.org/abs/2605.12509v3

Many real-world phenomena can be naturally represented using graphs and networks. Classical graph models, however, are generally restricted to pairwise interactions and may therefore be insufficient for capturing the richer structural relationships encountered in practical systems. Higher-order graph formalisms extend the classical framework by incorporating multiway, hierarchical, temporal, multilayer, recursive, and tensor-based interactions, thereby enabling more expressive representations of complex systems. This book provides a comprehensive overview of mathematical concepts and frameworks for modeling higher-order networks. It surveys foundational notions, extended frameworks, and newly introduced formalisms, with particular emphasis on their underlying structural principles, interrelationships, and respective modeling roles. Its primary objective is to offer a unified perspective that enables readers to compare diverse higher-order network models and to identify suitable mathematical tools for both theoretical investigation and practical application. Now in its fourth edition, this volume presents an expanded, revised, and corrected treatment of foundational concepts, established extensions, and recently introduced structures, while maintaining a unifying focus on the relationships among these models. It is intended to serve as a reference for researchers and students studying and comparing higher-order network models in combinatorics, topology, applied mathematics, and related fields.

---

### Are Flat Minima an Illusion?

Authors: Michael Timothy Bennett
Published: 2026-03-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.05209v2

Flat minima are an account of why deep networks generalise. However flatness is a matter of form (parameters), while generalisation is of function. The same function can be a result of many different parameterisations. I demonstrate this by rescaling ReLU networks, changing raw Hessian trace by up to $99$ times while every prediction remains fixed. Raw curvature cannot identify a function-level explanation. Previous theoretical work traced generalisation to the weakness of constraints implied by function, meaning the freedom a model retains within the bounds of what it has learned to be correct. A policy is weaker when more future commitments remain compatible with what it has learned, allowing more freedom to adapt. To measure this for neural networks, I freeze the last hidden representation and ask whether each of 512 sampled label bundles can be met by a replacement affine classifier. The resulting joint completion score is invariant under invertible linear mixing and translation of feature coordinates. Across two predeclared cohorts of 100 networks, it predicts held-out accuracy with rank correlations $0.29$ and $0.47$. Raw Hessian trace and relative flatness have no multiplicity-corrected association. To put it provocatively, freedom is correlated with adaptability, while flatness is a matter of description.

---

### The Imbalanced User-AI Relationships as an Ethical Failure of Front-End Design in Healthcare AI

Authors: Maureen Mghambi Mwadime
Published: 2026-03-24
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2604.22767v1

Ethical discourse on AI in healthcare has focused predominantly on back-end concerns such as bias, fairness and explainability, while the front-end interface, where patients and clinicians actually encounter AI outputs, remains under explored. This paper identifies imbalanced user-AI relationships as a distinct class of front-end ethical failure: patients are rendered highly visible to AI systems through data inference, yet cannot understand, question or influence how they are represented. Through the concept of asymmetric legibility and a chat-based telemedicine case, we show how design choices e.g., default recommendations, restricted inputs and suppressed uncertainty, undermine agency, clinician judgment and human oversight even where systems are technically accurate. We propose reciprocity as a design orientation and offer interventions for more balanced, participatory user-AI relationships in healthcare.

---

### Artificial General Intelligence Forecasting and Scenario Analysis: State of the Field, Methodological Gaps, and Strategic Implications

Authors: Gopal P. Sarma, Sunny D. Bhatt, Michael Jacob, Rachel Steratore
Published: 2026-03-24
Categories: cs.CY, cs.AI, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2604.22766v1

In this report, we review the current state of methodologies to forecast the arrival of artificial general intelligence, assess their reliability, and analyze the implications for strategy and policy. We synthesize diverse forecasting approaches, document significant limitations in existing methods, and propose a research agenda for developing more-robust forecasting infrastructure. The report does not endorse a specific forecast or scenario but rather provides a framework for interpreting forecasts under conditions of deep uncertainty. We experimented with an iterative approach to human and artificial intelligence collaboration for this report. The primary drafting of the text was performed by large language models (GPT 5.1, Gemini 3 Pro, and Claude 4.5 Opus), with human researchers providing direction, peer review, fact-checking, and revision.

---

### Algorithmic Administration and the EU AI Act: Legal Principles for Public Sector Use of AI

Authors: Georgios Pavlidis, Ioannis Kastanas
Published: 2026-03-24
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2604.22765v1

The increasing use of artificial intelligence (AI) by public authorities introduces both opportunities for innovation and significant challenges for the administrative rule of law. This article examines how the EU AI Act interacts with the fundamental principles of administrative law, with a particular focus on administrative discretion, the duty to state reasons, and proportionality. It analyses the regulatory obligations imposed by the AI Act on public sector deployers of high-risk systems, especially in sensitive domains such as social benefits, migration, education, and law enforcement. It also explores whether the AI Act adequately ensures accountability, transparency, and reviewability in automated public decision-making. The article further considers how the AI Act's risk-based approach aligns (or fails to align) with the principle of proportionality and it proposes safeguards and interpretative strategies to ensure the ethical and lawful deployment of AI in the public sector.

---

### Reciprocal Co-Training (RCT): Coupling Gradient-Based and Non-Differentiable Models via Reinforcement Learning

Authors: Yunshuo Tian, Akayou Kitessa, Tanuja Chitnis, Yijun Zhao
Published: 2026-03-24
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.16378v2

Language models (LMs) and classical machine learning methods offer complementary strengths for predictive modeling, yet their fundamentally different representations and training paradigms hinder effective integration: LMs rely on gradient-based optimization over textual data, whereas models such as Random Forests (RF) employ non-differentiable feature partitioning. This work introduces a reciprocal co-training framework that couples an LM with an RF classifier via reinforcement learning, creating an iterative feedback loop in which each model improves using signals from the other. Tabular data are reformulated into standardized textual representations for the LM, whose embeddings augment the RF feature space, while calibrated RF probability estimates provide feedback signals that guide reinforcement learning updates of the LM. Experiments across three medical datasets, evaluated with both a domain-adapted clinical encoder (ClinicalBERT) and a larger instruction-tuned language model (Qwen2-7B-Instruct), demonstrate consistent performance gains for both model components. Ablation analyses indicate that iterative refinement, hybrid reward design, and dimensionality control jointly contribute to these gains. SHAP analysis further confirms that LM-derived representations are among the most important inputs to the RF predictions. The proposed framework provides a general mechanism that allows incompatible model families to leverage each other's strengths through bidirectional adaptation.

---

### GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution

Authors: Nitin Choudhury, Bikrant Bikram Pratap Maurya, Bhavinkumar Vinodbhai Kuwar, Arun Balaji Buduru
Published: 2026-03-24
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2604.16377v2

Large Language Models (LLMs) trained on massive code corpora are now increasingly capable of generating code that is hard to distinguish from human-written code. This raises practical concerns, including security vulnerabilities and licensing ambiguity, and also motivates a forensic question: 'Who (or which LLM) wrote this piece of code?' We present GoCoMA, a multimodal framework that models an extrinsic hierarchy between (i) code stylometry, capturing higher-level structural and stylistic signatures, and (ii) image representations of binary pre-executable artifacts (BPEA), capturing lower-level, execution-oriented byte semantics shaped by compilation and toolchains. GoCoMA projects modality embeddings into a hyperbolic Poincaré ball, fuses them via a geodesic-cosine similarity-based cross-modal attention (GCSA) fusion mechanism, and back-projects the fused representation to Euclidean space for final LLM-source attribution. Experiments on two open-source benchmarks (CoDET-M4 and LLMAuthorBench) show that GoCoMA consistently outperforms unimodal and Euclidean multimodal baselines under identical evaluation protocols.

---

### Foundational Study on Authorship Attribution of Japanese Web Reviews for Actor Analysis

Authors: Hiroshi Matsubara, Shingo Matsugaya, Taichi Aoki, Masaki Hashimoto
Published: 2026-03-24
Categories: cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2604.16376v1

This study investigates the applicability of authorship attribution based on stylistic features to support actor analysis in threat intelligence. As a foundational step toward future application to dark web forums, we conducted experiments using Japanese review data from clear web sources. We constructed datasets from Rakuten Ichiba reviews and compared four methods: TF-IDF with logistic regression (TF-IDF+LR), BERT embeddings with logistic regression (BERT-Emb+LR), BERT fine-tuning (BERT-FT), and metric learning with $k$-nearest neighbors (Metric+kNN). Results showed that BERT-FT achieved the best performance; however, training became unstable as the number of authors scaled to several hundred, where TF-IDF+LR proved superior in terms of accuracy, stability, and computational cost. Furthermore, Top-$k$ evaluation demonstrated the utility of candidate screening, and error analysis revealed that boilerplate text, topic dependency, and short text length were primary factors causing misclassification.

---

### SAGE Celer 2.6 Technical Card

Authors: SAGEA Research Team, Basab Jha, Firoj Paudel, Ujjwal Puri, Adrian Liu, Ethan Henkel, Zhang Yuting, Mateusz Kowalczyk, Mei Huang, Choi Donghyuk, Wang Junhao
Published: 2026-03-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.14168v1

We introduce SAGE Celer 2.6, the latest in our line of general-purpose Celer models from SAGEA. Celer 2.6 is available in 5B, 10B, and 27B parameter sizes and benefits from extensive architectural modifications and further pre-training on an undisclosed model. Using our Inverse Reasoning (IR) pipeline, SAGEA natively trains Celer 2.6 to validate its own logic paths, minimizing cascading error and hallucination in complex reasoning tasks. Celer 2.6 also boasts natively integrated multimodal functionality with an end-to-end vision encoder to avoid common pitfalls in adapter-based approaches. Celer 2.6 provides highly competitive results on mathematics, coding, and general intelligence benchmarks (ACUMEN), along with low latency. Most importantly, Celer 2.6 is specifically optimized for South Asian language support, with a custom tokenizer for the Devanagari script and strong performance in both Nepali and Hindi without sacrificing English reasoning ability.

---

### Chinese Essay Rhetoric Recognition Using LoRA, In-context Learning and Model Ensemble

Authors: Yuxuan Lai, Xiajing Wang, Chen Zheng
Published: 2026-03-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.14167v1

Rhetoric recognition is a critical component in automated essay scoring. By identifying rhetorical elements in student writing, AI systems can better assess linguistic and higher-order thinking skills, making it an essential task in the area of AI for education. In this paper, we leverage Large Language Models (LLMs) for the Chinese rhetoric recognition task. Specifically, we explore Low-Rank Adaptation (LoRA) based fine-tuning and in-context learning to integrate rhetoric knowledge into LLMs. We formulate the outputs as JSON to obtain structural outputs and translate keys to Chinese. To further enhance the performance, we also investigate several model ensemble methods. Our method achieves the best performance on all three tracks of CCL 2025 Chinese essay rhetoric recognition evaluation task, winning the first prize.

---

### Hierarchical Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text

Authors: Filippo Morbiato, Markus Keller, Priya Nair, Luca Romano
Published: 2026-03-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.14166v1

Mapping Cyber Threat Intelligence (CTI) text to MITRE ATT\&CK technique IDs is a critical task for understanding adversary behaviors and automating threat defense. While recent Retrieval-Augmented Generation (RAG) approaches have demonstrated promising capabilities in this domain, they fundamentally rely on a flat retrieval paradigm. By treating all techniques uniformly, these methods overlook the inherent taxonomy of the ATT\&CK framework, where techniques are structurally organized under high-level tactics. In this paper, we propose H-TechniqueRAG, a novel hierarchical RAG framework that injects this tactic-technique taxonomy as a strong inductive bias to achieve highly efficient and accurate annotation. Our approach introduces a two-stage hierarchical retrieval mechanism: it first identifies the macro-level tactics (the adversary's technical goals) and subsequently narrows the search to techniques within those tactics, effectively reducing the candidate search space by 77.5\%. To further bridge the gap between retrieval and generation, we design a tactic-aware reranking module and a hierarchy-constrained context organization strategy that mitigates LLM context overload and improves reasoning precision. Comprehensive experiments across three diverse CTI datasets demonstrate that H-TechniqueRAG not only outperforms the state-of-the-art TechniqueRAG by 3.8\% in F1 score, but also achieves a 62.4\% reduction in inference latency and a 60\% decrease in LLM API calls. Further analysis reveals that our hierarchical structural priors equip the model with superior cross-domain generalization and provide security analysts with highly interpretable, step-by-step decision paths.

---

### Detecting Corporate AI-Washing via Cross-Modal Semantic Inconsistency Learning

Authors: Zhanjie Wen, Jingqiao Guo
Published: 2026-03-24
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2604.09644v1

Corporate AI-washing-the strategic misrepresentation of AI capabilities via exaggerated or fabricated cross-channel disclosures-has emerged as a systemic threat to capital market information integrity with the widespread adoption of generative AI. Existing detection methods rely on single-modal text frequency analysis, suffering from vulnerability to adversarial reformulation and cross-channel obfuscation. This paper presents AWASH, a multimodal framework that redefines AI-washing detection as cross-modal claim-evidence reasoning (instead of surface-level similarity measurement), built on AW-Bench-the first large-scale trimodal benchmark for this task, including 88412 aligned annual report text, disclosure image, and earnings call video triplets from 4892 A-share listed firms during 2019Q1-2025Q2. We propose the Cross-Modal Inconsistency Detection (CMID) network, integrating a tri-modal encoder, a structured natural language inference module for claim-evidence entailment reasoning, and an operational grounding layer that cross-validates AI claims against verifiable physical evidence (patent filing trajectories, AI-specific talent recruitment, compute infrastructure proxies). Evaluated against six competitive baselines, CMID achieves an F1 score of 0.882 and an AUC-ROC of 0.921, outperforming the strongest text-only baseline by 17.4 percentage points and the latest multimodal competitor by 11.3 percentage points. A pre-registered user study with 14 regulatory analysts verifies that CMID-generated evidence reports cut case review time by 43% while increasing true positive detection rates by 28%. These findings confirm the technical superiority and practical applicability of structured multimodal reasoning for large-scale corporate disclosure surveillance.

---

### Customized User Plane Processing via Code Generating AI Agents for Next Generation Mobile Networks

Authors: Xiaowen Ma, Onur Ayan, Yunpu Ma, Xueli An
Published: 2026-03-24
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2604.03282v1

Generative AI is envisioned to have a crucial impact on next generation mobile networking, making the sixth generation (6G) system considerably more autonomous, flexible, and adaptive than its predecessors. By leveraging their natural language processing and code generation capabilities, AI agents enable novel interactions and services between networks and vertical applications. A particularly promising and interesting use case is the customization of connectivity services for vertical applications by generating new customized processing blocks based on text-based service requests. More specifically, AI agents are able to generate code for a new function block that handles user plane traffic, allowing it to inspect and decode a protocol data unit (PDU) and perform specified actions as requested by the application. In this study, we investigate the code generation problem for generating such customized processing blocks on-demand. We evaluate various factors affecting the accuracy of the code generation process in this context, including model selection, prompt design, and the provision of a code template for the agent to utilize. Our findings indicate that AI agents are capable of generating such blocks with the desired behavior on-demand under suitable conditions. We believe that exploring the code generation for network-specific tasks is a very interesting problem for 6G and beyond, enabling networks to achieve a new level of customization by generating new capabilities on-demand.

---