# Research Papers — 2026-03 · bundle page 122 of 243

> Full-text markdown of papers #6051–6100 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/122
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/121.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/123.md)

### A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning

Authors: William Solow, Paola Pesantez-Cabrera, Markus Keller, Lav Khot, Sandhya Saisubramanian, Alan Fern
Published: 2026-03-16
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.15411v2

Accurate prediction of crop states (e.g., phenology stages and cold hardiness) is essential for timely farm management decisions such as irrigation, fertilization, and canopy management to optimize crop yield and quality. While traditional biophysical models can be used for season-long predictions, they lack the precision required for site-specific management. Deep learning methods are a compelling alternative, but can produce biologically unrealistic predictions and require large-scale data. We propose a \emph{hybrid modeling} approach that uses a neural network to parameterize a differentiable biophysical model and leverages multi-task learning for efficient data sharing across crop cultivars in data limited settings. By predicting the \emph{parameters} of the biophysical model, our approach improves the prediction accuracy while preserving biological realism. Empirical evaluation using real-world and synthetic datasets demonstrates that our method improves prediction accuracy by 60\% for phenology and 40\% for cold hardiness compared to deployed biophysical models.

---

### SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia

Authors: Pengfei Yue, Xingran Zhao, Juntao Chen, Peng Hou, Wang Longchao, Jianghang Lin, Shengchuan Zhang, Anxiang Zeng, Liujuan Cao
Published: 2026-03-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.15409v1

Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on high-resource languages and fail to evaluate models in realistic multilingual environments. In Southeast Asia, the diversity of languages, complex writing systems, and highly varied document types make this challenge even greater. We introduce SEA-Vision, a benchmark that jointly evaluates Document Parsing and Text-Centric Visual Question Answering (TEC-VQA) across 11 Southeast Asian languages. SEA-Vision contains 15,234 document parsing pages from nine representative document types, annotated with hierarchical page-, block-, and line-level labels. It also provides 7,496 TEC-VQA question-answer pairs that probe text recognition, numerical calculation, comparative analysis, logical reasoning, and spatial understanding. To make such multilingual, multi-task annotation feasible, we design a hybrid pipeline for Document Parsing and TEC-VQA. It combines automated filtering and scoring with MLLM-assisted labeling and lightweight native-speaker verification, greatly reducing manual labeling while maintaining high quality. We evaluate several leading multimodal models and observe pronounced performance degradation on low-resource Southeast Asian languages, highlighting substantial remaining gaps in multilingual document and scene text understanding. We believe SEA-Vision will help drive global progress in document and scene text understanding.

---

### TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems

Authors: Kai Wang, Biaojie Zeng, Zeming Wei, Chang Jin, Hefeng Zhou, Xiangtian Li, Chao Yang, Jingjing Qu, Xingcheng Xu, Xia Hu
Published: 2026-03-16
Categories: cs.CR, cs.AI, cs.CL, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2603.15408v1

With the rapid development of LLM-based multi-agent systems (MAS), their significant safety and security concerns have emerged, which introduce novel risks going beyond single agents or LLMs. Despite attempts to address these issues, the existing literature lacks a cohesive safeguarding system specialized for MAS risks. In this work, we introduce TrinityGuard, a comprehensive safety evaluation and monitoring framework for LLM-based MAS, grounded in the OWASP standards. Specifically, TrinityGuard encompasses a three-tier fine-grained risk taxonomy that identifies 20 risk types, covering single-agent vulnerabilities, inter-agent communication threats, and system-level emergent hazards. Designed for scalability across various MAS structures and platforms, TrinityGuard is organized in a trinity manner, involving an MAS abstraction layer that can be adapted to any MAS structures, an evaluation layer containing risk-specific test modules, alongside runtime monitor agents coordinated by a unified LLM Judge Factory. During Evaluation, TrinityGuard executes curated attack probes to generate detailed vulnerability reports for each risk type, where monitor agents analyze structured execution traces and issue real-time alerts, enabling both pre-development evaluation and runtime monitoring. We further formalize these safety metrics and present detailed case studies across various representative MAS examples, showcasing the versatility and reliability of TrinityGuard. Overall, TrinityGuard acts as a comprehensive framework for evaluating and monitoring various risks in MAS, paving the way for further research into their safety and security.

---

### Fusian: Multi-LoRA Fusion for Fine-Grained Continuous MBTI Personality Control in Large Language Models

Authors: Zehao Chen, Rong Pan
Published: 2026-03-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.15405v1

Large Language Models (LLMs) have demonstrated impressive capabilities in simulating diverse human behaviors and personalities. However, existing methods for personality control, which include prompt engineering and standard Supervised Fine-Tuning (SFT), typically treat personality traits as discrete categories (e.g., "Extroverted" vs. "Introverted"), lacking the ability to precisely control the intensity of a trait on a continuous spectrum. In this paper, we introduce Fusian, a novel framework for fine-grained, continuous personality control in LLMs. Fusian operates in two stages: (1) Trajectory Collection, where we capture the dynamic evolution of personality adoption during SFT by saving a sequence of LoRA adapters, effectively mapping the continuous manifold of a trait; and (2) RL-based Dynamic Fusion, where we train a policy network using Reinforcement Learning to dynamically compute mixing weights for these frozen adapters. By sampling from a Dirichlet distribution parameterized by the policy network, Fusian fuses multiple adapters to align the model's output with a specific numerical target intensity. Experiments on the Qwen3-14B model demonstrate that Fusian achieves high precision in personality control, significantly outperforming baseline methods in aligning with user-specified trait intensities.

---

### Detection of Autonomous Shuttles in Urban Traffic Images Using Adaptive Residual Context

Authors: Mohamed Aziz Younes, Nicolas Saunier, Guillaume-Alexandre Bilodeau
Published: 2026-03-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.15404v1

The progressive automation of transport promises to enhance safety and sustainability through shared mobility. Like other vehicles and road users, and even more so for such a new technology, it requires monitoring to understand how it interacts in traffic and to evaluate its safety. This can be done with fixed cameras and video object detection. However, the addition of new detection targets generally requires a fine-tuning approach for regular detection methods. Unfortunately, this implementation strategy will lead to a phenomenon known as catastrophic forgetting, which causes a degradation in scene understanding. In road safety applications, preserving contextual scene knowledge is of the utmost importance for protecting road users. We introduce the Adaptive Residual Context (ARC) architecture to address this. ARC links a frozen context branch and trainable task-specific branches through a Context-Guided Bridge, utilizing attention to transfer spatial features while preserving pre-trained representations. Experiments on a custom dataset show that ARC matches fine-tuned baselines while significantly improving knowledge retention, offering a data-efficient solution to add new vehicle categories for complex urban environments.

---

### Pointing-Based Object Recognition

Authors: Lukáš Hajdúch, Viktor Kocur
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15403v2

This paper presents a comprehensive pipeline for recognizing objects targeted by human pointing gestures using RGB images. As human-robot interaction moves toward more intuitive interfaces, the ability to identify targets of non-verbal communication becomes crucial. Our proposed system integrates several existing state-of-the-art methods, including object detection, body pose estimation, monocular depth estimation, and vision-language models. We evaluate the impact of 3D spatial information reconstructed from a single image and the utility of image captioning models in correcting classification errors. Experimental results on a custom dataset show that incorporating depth information significantly improves target identification, especially in complex scenes with overlapping objects. The modularity of the approach allows for deployment in environments where specialized depth sensors are unavailable.

---

### A Closer Look into LLMs for Table Understanding

Authors: Jia Wang, Chuanyu Qin, Mingyu Zheng, Qingyi Si, Peize Li, Zheng Lin
Published: 2026-03-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.15402v1

Despite the success of Large Language Models (LLMs) in table understanding, their internal mechanisms remain unclear. In this paper, we conduct an empirical study on 16 LLMs, covering general LLMs, specialist tabular LLMs, and Mixture-of-Experts (MoE) models, to explore how LLMs understand tabular data and perform downstream tasks. Our analysis focus on 4 dimensions including the attention dynamics, the effective layer depth, the expert activation, and the impacts of input designs. Key findings include: (1) LLMs follow a three-phase attention pattern -- early layers scan the table broadly, middle layers localize relevant cells, and late layers amplify their contributions; (2) tabular tasks require deeper layers than math reasoning to reach stable predictions; (3) MoE models activate table-specific experts in middle layers, with early and late layers sharing general-purpose experts; (4) Chain-of-Thought prompting increases table attention, further enhanced by table-tuning. We hope these findings and insights can facilitate interpretability and future research on table-related tasks.

---

### SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Authors: Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu
Published: 2026-03-16
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.15401v1

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.

---

### SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration

Authors: Yu Pan, Wenlong Yu, Tiejun Wu, Xiaohu Ye, Qiannan Si, Guangquan Xu, Bin Wu
Published: 2026-03-16
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.15397v1

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically rely on post hoc filtering applied only to the final output, leaving intermediate reasoning steps unmonitored and vulnerable to adversarial manipulation. To address this gap, this paper proposes a SaFer Chain-of-Thought (SFCoT) framework, which proactively evaluates and calibrates potentially unsafe reasoning steps in real time. SFCoT incorporates a three-tier safety scoring system alongside a multi-perspective consistency verification mechanism, designed to detect potential risks throughout the reasoning process. A dynamic intervention module subsequently performs targeted calibration to redirect reasoning trajectories toward safe outcomes. Experimental results demonstrate that SFCoT reduces the attack success rate from $58.97\%$ to $12.31\%$, demonstrating it as an effective and efficient LLM safety enhancement method without a significant decline in general performance.

---

### AI Evasion and Impersonation Attacks on Facial Re-Identification with Activation Map Explanations

Authors: Noe Claudel, Weisi Guo, Yang Xing
Published: 2026-03-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.15396v1

Facial identification systems are increasingly deployed in surveillance and yet their vulnerability to adversarial evasion and impersonation attacks pose a critical risk. This paper introduces a novel framework for generating adversarial patches capable of both evasion and impersonation attacks against deep re-identification models across non-overlapping cameras. Unlike prior approaches that require iterative patch optimisation for each target, our method employs a conditional encoder-decoder network to synthesize adversarial patches in a single forward pass, guided by multi-scale features from source and target images. The patches are optimised with a dual adversarial objective comprising of pull and push terms. To enhance imperceptibility and aid physical deployment, we further integrate naturalistic patch generation using pre-trained latent diffusion models. Experiments on standard pedestrian (Market-1501, DukeMTMCreID) and facial recognition benchmarks (CelebA-HQ, PubFig) datasets demonstrate the effectiveness of the proposed method. Our adversarial evasion attacks reduce mean Average Precision from 90% to 0.4% in white-box settings and from 72% to 0.4% in black-box settings, showing strong cross-model generalization. In targeted impersonation attacks, our framework achieves a success rate of 27% on CelebA-HQ, competing with other patch-based methods. We go further to use clustering of activation maps to interpret which features are most used by adversarial attacks and propose a pathway for future countermeasures. The results highlight the practicality of adversarial patch attacks on retrieval-based systems and underline the urgent need for robust defense strategies.

---

### When Does Sparsity Mitigate the Curse of Depth in LLMs

Authors: Dilxat Muhtar, Xinyuan Song, Sebastian Pokutta, Max Zimmer, Nico Pelleriti, Thomas Hofmann, Shiwei Liu
Published: 2026-03-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.15389v2

Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-utilization is linked to the accumulated growth of variance in Pre-Layer Normalization, which can push deep blocks toward near-identity behavior. In this paper, we provide evidence that sparsity-like mechanisms can dampen variance propagation and are associated with improved depth utilization Our investigation covers two sources of sparsity: (i) implicit sparsity, which emerges from training and data conditions, including weight sparsity induced by weight decay and attention sparsity induced by long-context inputs; and (ii) explicit sparsity, which is enforced by architectural design, including key/value-sharing in Grouped-Query Attention and expert-activation sparsity in Mixtureof-Experts. Our claim is thoroughly supported by controlled depth-scaling experiments and targeted layer effectiveness interventions. Across settings, we observe a consistent relationship: mechanisms with reduced effective interaction density tend to exhibit lower output variance and better layer differentiation. We eventually distill our findings into a practical rule-of-thumb recipe for training depth-effective LLMs, yielding a notable 4.6 accuracy improvement on downstream tasks. Our results suggest that sparsity-like design choices are an important and previously underemphasized factor in effective depth scaling for LLMs. Code is available at https://github. com/pUmpKin-Co/SparsityAndCoD.

---

### Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimization

Authors: Yanning Dai, Yuhui Wang, Dylan R. Ashley, Jürgen Schmidhuber
Published: 2026-03-16
Categories: cs.LG, cs.AI, cs.RO, stat.ML
arXiv: https://arxiv.org/abs/2603.15388v1

Morphology-control co-design concerns the coupled optimization of an agent's body structure and control policy. This problem exhibits a bi-level structure, where the control dynamically adapts to the morphology to maximize performance. Existing methods typically neglect the control's adaptation dynamics by adopting a single-level formulation that treats the control policy as fixed when optimizing morphology. This can lead to inefficient optimization, as morphology updates may be misaligned with control adaptation. In this paper, we revisit the co-design problem from a game-theoretic perspective, modeling the intrinsic coupling between morphology and control as a novel variant of a Stackelberg game. We propose Stackelberg Proximal Policy Optimization (Stackelberg PPO), which explicitly incorporates the control's adaptation dynamics into morphology optimization. By modeling this intrinsic coupling, our method aligns morphology updates with control adaptation, thereby stabilizing training and improving learning efficiency. Experiments across diverse co-design tasks demonstrate that Stackelberg PPO outperforms standard PPO in both stability and final performance, opening the way for dramatically more efficient robotics designs.

---

### RieMind: Geometry-Grounded Spatial Agent for Scene Understanding

Authors: Fernando Ropero, Erkin Turkoz, Daniel Matos, Junqing Du, Antonio Ruiz, Yanfeng Zhang, Lu Liu, Mingwei Sun, Yongliang Wang
Published: 2026-03-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.15386v1

Visual Language Models (VLMs) have increasingly become the main paradigm for understanding indoor scenes, but they still struggle with metric and spatial reasoning. Current approaches rely on end-to-end video understanding or large-scale spatial question answering fine-tuning, inherently coupling perception and reasoning. In this paper, we investigate whether decoupling perception and reasoning leads to improved spatial reasoning. We propose an agentic framework for static 3D indoor scene reasoning that grounds an LLM in an explicit 3D scene graph (3DSG). Rather than ingesting videos directly, each scene is represented as a persistent 3DSG constructed by a dedicated perception module. To isolate reasoning performance, we instantiate the 3DSG from ground-truth annotations. The agent interacts with the scene exclusively through structured geometric tools that expose fundamental properties such as object dimensions, distances, poses, and spatial relationships. The results we obtain on the static split of VSI-Bench provide an upper bound under ideal perceptual conditions on the spatial reasoning performance, and we find that it is significantly higher than previous works, by up to 16\%, without task specific fine-tuning. Compared to base VLMs, our agentic variant achieves significantly better performance, with average improvements between 33\% to 50\%. These findings indicate that explicit geometric grounding substantially improves spatial reasoning performance, and suggest that structured representations offer a compelling alternative to purely end-to-end visual reasoning.

---

### Persistence Spheres: a Bi-continuous Linear Representation of Measures for Partial Optimal Transport

Authors: Matteo Pegoraro
Published: 2026-03-16
Categories: stat.ML, cs.LG, math.AT, math.ST
arXiv: https://arxiv.org/abs/2603.15384v2

We improve and extend persistence spheres, introduced in~\cite{pegoraro2025persistence}. Persistence spheres map an integrable measure $μ$ on the upper half-plane, including persistence diagrams (PDs) as counting measures, to a function $S(μ)\in C(\mathbb{S}^2)$, and the map is stable with respect to 1-Wasserstein partial transport distance $\mathrm{POT}_1$. Moreover, to the best of our knowledge, persistence spheres are the first explicit representation used in topological machine learning for which continuity of the inverse on the image is established at every compactly supported target. Recent bounded-cardinality bi-Lipschitz embedding results in partial transport spaces, despite being powerful, are not given by the kind of explicit summary map considered here. Our construction is rooted in convex geometry: for positive measures, the defining ReLU integral is the support function of the lift zonoid. Building on~\cite{pegoraro2025persistence}, we refine the definition to better match the $\mathrm{POT}_1$ deletion mechanism, encoding partial transport via a signed diagonal augmentation. In particular, for integrable $μ$, the uniform norm between $S(0)$ and $S(μ)$ depends only on the persistence of $μ$, without any need of ad-hoc re-weightings, reflecting optimal transport to the diagonal at persistence cost. This yields a parameter-free representation at the level of measures (up to numerical discretization), while accommodating future extensions where $μ$ is a smoothed measure derived from PDs (e.g., persistence intensity functions~\citep{wu2024estimation}). Across clustering, regression, and classification tasks involving functional data, time series, graphs, meshes, and point clouds, the updated persistence spheres are competitive and often improve upon persistence images, persistence landscapes, persistence splines, and sliced Wasserstein kernel baselines.

---

### Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science

Authors: Emmanuel Dupoux, Yann LeCun, Jitendra Malik
Published: 2026-03-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.15381v1

We critically examine the limitations of current AI models in achieving autonomous learning and propose a learning architecture inspired by human and animal cognition. The proposed framework integrates learning from observation (System A) and learning from active behavior (System B) while flexibly switching between these learning modes as a function of internally generated meta-control signals (System M). We discuss how this could be built by taking inspiration on how organisms adapt to real-world, dynamic environments across evolutionary and developmental timescales.

---

### More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search

Authors: Gal Dalal, Assaf Hallak, Gal Chechik, Yftah Ziser
Published: 2026-03-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.15377v2

Wider beam search should improve LLM reasoning, but when should you stop widening? Prior work on beam width selection has focused on inference efficiency \citep{qin2025dsbd, freitag2017beam}, without analyzing whether wider search can \emph{hurt} output quality. We present an analysis, grounded in Extreme Value Theory, that answers this question. Beam selection over noisy scorer outputs introduces a systematic overestimation bias that grows with the candidate pool size, and we derive a maximum useful beam width $\hat{k}$ beyond which search degrades performance. This critical width depends on the signal-to-noise ratio of the scorer: $\hat{k}$ grows exponentially with $(Δ/σ)^2$, where $Δ> 0$ is the quality advantage of correct paths over incorrect ones and $σ$ is the scorer noise. We validate this theory by comparing perplexity-guided and PRM-guided beam search across three 7B-parameter models and ten domains on MR-BEN (5,975 questions). Perplexity scoring, with its high noise, yields $\hat{k} = 1$: search provides no benefit at any width tested. PRM scoring, with lower noise, yields $\hat{k} \geq 4$, with gains of up to 8.9 percentage points. The same model, the same algorithm, but different scorers place $\hat{k}$ at opposite ends of the beam width range. Our analysis identifies the scorer's signal-to-noise ratio as the key quantity governing beam width selection, and we propose diagnostic indicators for choosing the beam width in practice.

---

### Spectral Rectification for Parameter-Efficient Adaptation of Foundation Models in Colonoscopy Depth Estimation

Authors: Xiaoxian Zhang, Minghai Shi, Lei Li
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15374v1

Accurate monocular depth estimation is critical in colonoscopy for lesion localization and navigation. Foundation models trained on natural images fail to generalize directly to colonoscopy. We identify the core issue not as a semantic gap, but as a statistical shift in the frequency domain: colonoscopy images lack the strong high-frequency edge and texture gradients that these models rely on for geometric reasoning. To address this, we propose SpecDepth, a parameter-efficient adaptation framework that preserves the robust geometric representations of the pre-trained models while adapting to the colonoscopy domain. Its key innovation is an adaptive spectral rectification module, which uses a learnable wavelet decomposition to explicitly model and amplify the attenuated high-frequency components in feature maps. Different from conventional fine-tuning that risks distorting high-level semantic features, this targeted, low-level adjustment realigns the input signal with the original inductive bias of the foundational model. On the public C3VD and SimCol3D datasets, SpecDepth achieved state-of-the-art performance with an absolute relative error of 0.022 and 0.027, respectively. Our work demonstrates that directly addressing spectral mismatches is a highly effective strategy for adapting vision foundation models to specialized medical imaging tasks. The code will be released publicly after the manuscript is accepted for publication.

---

### GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks

Authors: Jacob Sanderson, Hua Mao, Wai Lok Woo
Published: 2026-03-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.15373v1

Explainable Artificial Intelligence (XAI) is increasingly essential as AI systems are deployed in critical fields such as healthcare and finance, offering transparency into AI-driven decisions. Two major XAI paradigms, counterfactual explanations (CFX) and feature attribution (FA), serve distinct roles in model interpretability. This study introduces GradCFA, a hybrid framework combining CFX and FA to improve interpretability by explicitly optimizing feasibility, plausibility, and diversity - key qualities often unbalanced in existing methods. Unlike most CFX research focused on binary classification, GradCFA extends to multi-class scenarios, supporting a wider range of applications. We evaluate GradCFA's validity, proximity, sparsity, plausibility, and diversity against state-of-the-art methods, including Wachter, DiCE, CARE for CFX, and SHAP for FA. Results show GradCFA effectively generates feasible, plausible, and diverse counterfactuals while offering valuable FA insights. By identifying influential features and validating their impact, GradCFA advances AI interpretability. The code for implementation of this work can be found at: https://github.com/jacob-ws/GradCFs .

---

### SKILLS: Structured Knowledge Injection for LLM-Driven Telecommunications Operations

Authors: Ivo Brett
Published: 2026-03-16
Categories: cs.SE, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2603.15372v1

As telecommunications operators accelerate adoption of AI-enabled automation, a practical question remains unresolved: can general-purpose large language model (LLM) agents reliably execute telecom operations workflows through real API interfaces, or do they require structured domain guidance? We introduce SKILLS (Structured Knowledge Injection for LLM-driven Service Lifecycle operations), a benchmark framework comprising 37 telecom operations scenarios spanning 8 TM Forum Open API domains (TMF620, TMF621, TMF622, TMF628, TMF629, TMF637, TMF639, TMF724). Each scenario is grounded in live mock API servers with seeded production-representative data, MCP tool interfaces, and deterministic evaluation rubrics combining response content checks, tool-call verification, and database state assertions. We evaluate open-weight models under two conditions: baseline (generic agent with tool access but no domain guidance) and with-skill (agent augmented with a portable SKILL.md document encoding workflow logic, API patterns, and business rules). Results across 5 open-weight model conditions and 185 scenario-runs show consistent skill lift across all models. MiniMax M2.5 leads (81.1% with-skill, +13.5pp), followed by Nemotron 120B (78.4%, +18.9pp), GLM-5 Turbo (78.4%, +5.4pp), and Seed 2.0 Lite (75.7%, +18.9pp).

---

### Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning

Authors: Guangfu Hao, Yuming Dai, Xianzhe Qin, Shan Yu
Published: 2026-03-16
Categories: cs.AI, cs.NI
arXiv: https://arxiv.org/abs/2603.15371v1

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of language tasks, yet complex multi-step reasoning remains a fundamental challenge. While Large Reasoning Models (LRMs) equipped with extended chain-of-thought mechanisms demonstrate improved performance over standard LLMs, both model types still suffer from accuracy collapse on sufficiently complex tasks, suggesting that scaling model-level reasoning alone is insufficient. Inspired by the global workspace theory of human cognition, we propose Brain-Inspired Graph Multi-Agent Systems (BIGMAS), in which specialized LLM agents are organized as nodes in a dynamically constructed directed graph and coordinate exclusively through a centralized shared workspace. A problem-adaptive GraphDesigner constructs task-specific agent topologies, while a global Orchestrator leverages the complete shared state for routing decisions, overcoming the local-view bottleneck of reactive approaches. Experiments on Game24, Six Fives, and Tower of London across six frontier LLMs demonstrate that BIGMAS consistently improves reasoning performance for both standard LLMs and LRMs, outperforming existing multi-agent baselines including ReAct and Tree of Thoughts, showing that multi-agent architectural design provides complementary gains orthogonal to model-level reasoning enhancements.

---

### Trajectory-Diversity-Driven Robust Vision-and-Language Navigation

Authors: Jiangyang Li, Cong Wan, SongLin Dong, Chenhao Ding, Qiang Wang, Zhiheng Ma, Yihong Gong
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15370v1

Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions. Current methods predominantly rely on imitation learning, which suffers from limited generalization and poor robustness to execution perturbations. We present NavGRPO, a reinforcement learning framework that learns goal-directed navigation policies through Group Relative Policy Optimization. By exploring diverse trajectories and optimizing via within-group performance comparisons, our method enables agents to distinguish effective strategies beyond expert paths without requiring additional value networks. Built on ScaleVLN, NavGRPO achieves superior robustness on R2R and REVERIE benchmarks with +3.0% and +1.71% SPL improvements in unseen environments. Under extreme early-stage perturbations, we demonstrate +14.89% SPL gain over the baseline, confirming that goal-directed RL training builds substantially more robust navigation policies. Code and models will be released.

---

### IRIS: Intersection-aware Ray-based Implicit Editable Scenes

Authors: Grzegorz Wilczyński, Mikołaj Zieliński, Krzysztof Byrski, Joanna Waczyńska, Dominik Belter, Przemysław Spurek
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15368v1

Neural Radiance Fields achieve high-fidelity scene representation but suffer from costly training and rendering, while 3D Gaussian splatting offers real-time performance with strong empirical results. Recently, solutions that harness the best of both worlds by using Gaussians as proxies to guide neural field evaluations, still suffer from significant computational inefficiencies. They typically rely on stochastic volumetric sampling to aggregate features, which severely limits rendering performance. To address this issue, a novel framework named IRIS (Intersection-aware Ray-based Implicit Editable Scenes) is introduced as a method designed for efficient and interactive scene editing. To overcome the limitations of standard ray marching, an analytical sampling strategy is employed that precisely identifies interaction points between rays and scene primitives, effectively eliminating empty space processing. Furthermore, to address the computational bottleneck of spatial neighbor lookups, a continuous feature aggregation mechanism is introduced that operates directly along the ray. By interpolating latent attributes from sorted intersections, costly 3D searches are bypassed, ensuring geometric consistency, enabling high-fidelity, real-time rendering, and flexible shape editing. Code can be found at https://github.com/gwilczynski95/iris.

---

### Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches

Authors: Alessandro Zambon, Francesca Caruso, Riccardo Zecchina, Guido Tiana
Published: 2026-03-16
Categories: cond-mat.dis-nn, cs.LG
arXiv: https://arxiv.org/abs/2603.15367v1

Sampling the parameter space of artificial neural networks according to a Boltzmann distribution provides insight into the geometry of low-loss solutions and offers an alternative to conventional loss minimization for training. However, exact sampling methods such as hybrid Monte Carlo (hMC), while formally correct, become computationally prohibitive for realistic datasets because they require repeated evaluation of full-batch gradients. We introduce a pseudo-Langevin (pL) dynamics that enables efficient Boltzmann sampling of feed-forward neural networks trained with large datasets by using minibatches in a controlled manner. The method exploits the statistical properties of minibatch gradient noise and adjusts fictitious masses and friction coefficients to ensure that the induced stochastic process samples efficiently the desired equilibrium distribution. We validate numerically the approach by comparing its equilibrium statistics with those obtained from exact hMC sampling. Performance benchmarks demonstrate that, while hMC rapidly becomes inefficient as network size increases, the pL scheme maintains high computational diffusion and scales favorably to networks with over one million parameters. Finally, we show that sampling at intermediate temperatures yields optimal generalization performance, comparable to SGD, without requiring a validation set or early stopping procedure. These results establish controlled minibatch Langevin dynamics as a practical and scalable tool for exploring and exploiting the solution space of large neural networks.

---

### A PPO-Based Bitrate Allocation Conditional Diffusion Model for Remote Sensing Image Compression

Authors: Yuming Han, Jooho Kim, Anish Shakya
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15365v1

Existing remote sensing image compression methods still explore to balance high compression efficiency with the preservation of fine details and task-relevant information. Meanwhile, high-resolution drone imagery offers valuable structural details for urban monitoring and disaster assessment, but large-area datasets can easily reach hundreds of gigabytes, creating significant challenges for storage and long-term management. In this paper, we propose a PPO-based bitrate allocation Conditional Diffusion Compression (PCDC) framework. PCDC integrates a conditional diffusion decoder with a PPO-based block-wise bitrate allocation strategy to achieve high compression ratios while maintaining strong perceptual performance. We also release a high-resolution drone image dataset with richer structural details at a consistent low altitude over residential neighborhoods in coastal urban areas. Experimental results show compression ratios of 19.3x on DIV2K and 21.2x on the drone image dataset. Moreover, downstream object detection experiments demonstrate that the reconstructed images preserve task-relevant information with negligible performance loss.

---

### CRASH: Cognitive Reasoning Agent for Safety Hazards in Autonomous Driving

Authors: Erick Silva, Rehana Yasmin, Ali Shoker
Published: 2026-03-16
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.15364v1

As AVs grow in complexity and diversity, identifying the root causes of operational failures has become increasingly complex. The heterogeneity of system architectures across manufacturers, ranging from end-to-end to modular designs, together with variations in algorithms and integration strategies, limits the standardization of incident investigations and hinders systematic safety analysis. This work examines real-world AV incidents reported in the NHTSA database. We curate a dataset of 2,168 cases reported between 2021 and 2025, representing more than 80 million miles driven. To process this data, we introduce CRASH, Cognitive Reasoning Agent for Safety Hazards, an LLM-based agent that automates reasoning over crash reports by leveraging both standardized fields and unstructured narrative descriptions. CRASH operates on a unified representation of each incident to generate concise summaries, attribute a primary cause, and assess whether the AV materially contributed to the event. Our findings show that (1) CRASH attributes 64% of incidents to perception or planning failures, underscoring the importance of reasoning-based analysis for accurate fault attribution; and (2) approximately 50% of reported incidents involve rear-end collisions, highlighting a persistent and unresolved challenge in autonomous driving deployment. We further validate CRASH with five domain experts, achieving 86% accuracy in attributing AV system failures. Overall, CRASH demonstrates strong potential as a scalable and interpretable tool for automated crash analysis, providing actionable insights to support safety research and the continued development of autonomous driving systems.

---

### Deep learning and the rate of approximation by flows

Authors: Jingpu Cheng, Qianxiao Li, Ting Lin, Zuowei Shen
Published: 2026-03-16
Categories: cs.LG, math.DS
arXiv: https://arxiv.org/abs/2603.15363v2

We investigate the dependence of the approximation capacity of deep residual networks on its depth in a continuous dynamical systems setting. This can be formulated as the general problem of quantifying the minimal time-horizon required to approximate a diffeomorphism by flows driven by a given family $\mathcal F$ of vector fields. We show that this minimal time can be identified as a geodesic distance on a sub-Finsler manifold of diffeomorphisms, where the local geometry is characterised by a variational principle involving $\mathcal F$. This connects the learning efficiency of target relationships to their compatibility with the learning architectural choice. Further, the results suggest that the key approximation mechanism in deep learning, namely the approximation of functions by composition or dynamics, differs in a fundamental way from linear approximation theory, where linear spaces and norm-based rate estimates are replaced by manifolds and geodesic distances.

---

### FuXiWeather2: Learning accurate atmospheric state estimation for operational global weather forecasting

Authors: Xiaoze Xu, Xiuyu Sun, Songling Zhu, Xiaohui Zhong, Yuanqing Huang, Zijian Zhu, Jun Liu, Hao Li
Published: 2026-03-16
Categories: cs.LG, cs.AI, physics.ao-ph
arXiv: https://arxiv.org/abs/2603.15358v1

Numerical weather prediction has long been constrained by the computational bottlenecks inherent in data assimilation and numerical modeling. While machine learning has accelerated forecasting, existing models largely serve as "emulators of reanalysis products," thereby retaining their systematic biases and operational latencies. Here, we present FuXiWeather2, a unified end-to-end neural framework for assimilation and forecasting. We align training objectives directly with a combination of real-world observations and reanalysis data, enabling the framework to effectively rectify inherent errors within reanalysis products. To address the distribution shift between NWP-derived background inputs during training and self-generated backgrounds during deployment, we introduce a recursive unrolling training method to enhance the precision and stability of analysis generation. Furthermore, our model is trained on a hybrid dataset of raw and simulated observations to mitigate the impact of observational distribution inconsistency. FuXiWeather2 generates high-resolution ($0.25^{\circ}$) global analysis fields and 10-day forecasts within minutes. The analysis fields surpass the NCEP-GFS across most variables and demonstrate superior accuracy over both ERA5 and the ECMWF-HRES system in lower-tropospheric and surface variables. These high-quality analysis fields drive deterministic forecasts that exceed the skill of the HRES system in 91\% of evaluated metrics. Additionally, its outstanding performance in typhoon track prediction underscores its practical value for rapid response to extreme weather events. The FuXiWeather2 analysis dataset is available at https://doi.org/10.5281/zenodo.18872728.

---

### Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method

Authors: Haofei Xu, Wei Cheng, Sizhe Li, Jie Xiong
Published: 2026-03-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.15354v1

Seismic inversion is a core problem in geophysical exploration, where traditional methods suffer from high computational costs and are susceptible to initial model dependence. In recent years, deep generative model-based seismic inversion methods have achieved remarkable progress, but existing generative models struggle to balance sampling efficiency and inversion accuracy. This paper proposes an end-to-end fast seismic inversion method based on Conditional Rectified Flow(1), which designs a dedicated seismic encoder to extract multi-scale seismic features and adopts a layer-by-layer injection control strategy to achieve fine-grained conditional control. Experimental results demonstrate that the proposed method achieves excellent inversion accuracy on the OpenFWI(2) benchmark dataset. Compared with Diffusion(3,4) methods, it achieves sampling acceleration; compared with InversionNet(5,6,7) methods, it achieves higher accuracy in generation. Our zero-shot generalization experiments on Marmousi(8,9) real data further verify the practical value of the method. Experimental results show that the proposed method achieves excellent inversion accuracy on the OpenFWI benchmark dataset; compared with Diffusion methods, it achieves sampling acceleration while maintaining higher accuracy than InversionNet methods; experiments based on the Marmousi standard model further verify that this method can generate high-quality initial velocity models in a zero-shot manner, effectively alleviating the initial model dependency problem in traditional Full Waveform Inversion (FWI), and possesses industrial practical value.

---

### NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation

Authors: Qinke Ni, Huan Liao, Dekun Chen, Yuxiang Wang, Zhizheng Wu
Published: 2026-03-16
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2603.15352v2

While recent text-to-speech (TTS) systems increasingly integrate nonverbal vocalizations (NVs), their evaluations lack standardized metrics and reliable ground-truth references. To bridge this gap, we propose NV-Bench, the first benchmark grounded in a functional taxonomy that treats NVs as communicative acts rather than acoustic artifacts. NV-Bench comprises 1,651 multi-lingual, in-the-wild utterances with paired human reference audio, balanced across 14 NV categories. We introduce a dual-dimensional evaluation protocol: (1) Instruction Alignment, utilizing the proposed paralinguistic character error rate (PCER) to assess controllability, (2) Acoustic Fidelity, measuring the distributional gap to real recordings to assess acoustic realism. We evaluate diverse TTS models and develop two baselines. Experimental results demonstrate a strong correlation between our objective metrics and human perception, establishing NV-Bench as a standardized evaluation framework.

---

### PMAx: An Agentic Framework for AI-Driven Process Mining

Authors: Anton Antonov, Humam Kourani, Alessandro Berti, Gyunam Park, Wil M. P. van der Aalst
Published: 2026-03-16
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.15351v1

Process mining provides powerful insights into organizational workflows, but extracting these insights typically requires expertise in specialized query languages and data science tools. Large Language Models (LLMs) offer the potential to democratize process mining by enabling business users to interact with process data through natural language. However, using LLMs as direct analytical engines over raw event logs introduces fundamental challenges: LLMs struggle with deterministic reasoning and may hallucinate metrics, while sending large, sensitive logs to external AI services raises serious data-privacy concerns. To address these limitations, we present PMAx, an autonomous agentic framework that functions as a virtual process analyst. Rather than relying on LLMs to generate process models or compute analytical results, PMAx employs a privacy-preserving multi-agent architecture. An Engineer agent analyzes event-log metadata and autonomously generates local scripts to run established process mining algorithms, compute exact metrics, and produce artifacts such as process models, summary tables, and visualizations. An Analyst agent then interprets these insights and artifacts to compile comprehensive reports. By separating computation from interpretation and executing analysis locally, PMAx ensures mathematical accuracy and data privacy while enabling non-technical users to transform high-level business questions into reliable process insights.

---

### Oscillating Dispersion for Maximal Light-throughput Spectral Imaging

Authors: Jiuyun Zhang, Zhan Shi, Linsen Chen, Xun Cao
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15348v1

Existing computational spectral imaging systems typically rely on coded aperture and beam splitters that block a substantial fraction of incident light, degrading reconstruction quality under light-starved conditions. To address this limitation, we develop the Oscillating Dispersion Imaging Spectrometer (ODIS), which for the first time achieves near-full light throughput by axially translating a disperser between the conjugate image plane and a defocused position, sequentially capturing a panchromatic (PAN) image and a dispersed measurement along a single optical path. We further propose a PAN-guided Dispersion-Aware Deep Unfolding Network (PDAUN) that recovers high-fidelity spectral information from maskless dispersion under PAN structural guidance. Its data-fidelity step derives an FFT-Woodbury preconditioned solver by exploiting the cyclic-convolution property of the ODIS forward model, while a Dispersion-Aware Deformable Convolution module (DADC) corrects sub-pixel spectral misalignment using PAN features. Experiments show state-of-the-art performance on standard benchmarks, and cross-system comparisons confirm that ODIS yields decisive gains under low illumination. High-fidelity reconstruction is validated on a physical prototype.

---

### Intelligent Co-Design: An Interactive LLM Framework for Interior Spatial Design via Multi-Modal Agents

Authors: Ren Jian Lim, Rushi Dai
Published: 2026-03-16
Categories: cs.AI, cs.HC, cs.MA
arXiv: https://arxiv.org/abs/2603.15341v1

In architectural interior design, miscommunication frequently arises as clients lack design knowledge, while designers struggle to explain complex spatial relationships, leading to delayed timelines and financial losses. Recent advancements in generative layout tools narrow the gap by automating 3D visualizations. However, prevailing methodologies exhibit limitations: rule-based systems implement hard-coded spatial constraints that restrict participatory engagement, while data-driven models rely on extensive training datasets. Recent large language models (LLMs) bridge this gap by enabling intuitive reasoning about spatial relationships through natural language. This research presents an LLM-based, multimodal, multi-agent framework that dynamically converts natural language descriptions and imagery into 3D designs. Specialized agents (Reference, Spatial, Interactive, Grader), operating via prompt guidelines, collaboratively address core challenges: the agent system enables real-time user interaction for iterative spatial refinement, while Retrieval-Augmented Generation (RAG) reduces data dependency without requiring task-specific model training. This framework accurately interprets spatial intent and generates optimized 3D indoor design, improving productivity, and encouraging nondesigner participation. Evaluations across diverse floor plans and user questionnaires demonstrate effectiveness. An independent LLM evaluator consistently rated participatory layouts higher in user intent alignment, aesthetic coherence, functionality, and circulation. Questionnaire results indicated 77% satisfaction and a clear preference over traditional design software. These findings suggest the framework enhances user-centric communication and fosters more inclusive, effective, and resilient design processes. Project page: https://rsigktyper.github.io/AICodesign/

---

### DOS: Dependency-Oriented Sampler for Masked Diffusion Language Models

Authors: Xueyu Zhou, Yangrong Hu, Jian Huang
Published: 2026-03-16
Categories: cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2603.15340v1

Masked diffusion language models (MDLMs) have recently emerged as a new paradigm in language modeling, offering flexible generation dynamics and enabling efficient parallel decoding. However, existing decoding strategies for pre-trained MDLMs predominantly rely on token-level uncertainty criteria, while largely overlooking sequence-level information and inter-token dependencies. To address this limitation, we propose Dependency-Oriented Sampler (DOS), a training-free decoding strategy that leverages inter-token dependencies to inform token updates during generation. Specifically, DOS exploits attention matrices from transformer blocks to approximate inter-token dependencies, emphasizing information from unmasked tokens when updating masked positions. Empirical results demonstrate that DOS consistently achieves superior performance on both code generation and mathematical reasoning tasks. Moreover, DOS can be seamlessly integrated with existing parallel sampling methods, leading to improved generation efficiency without sacrificing generation quality.

---

### Active Seriation: Efficient Ordering Recovery with Statistical Guarantees

Authors: James Cheshire, Yann Issartel
Published: 2026-03-16
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.15336v1

Active seriation aims at recovering an unknown ordering of $n$ items by adaptively querying pairwise similarities. The observations are noisy measurements of entries of an underlying $n$ x $n$ permuted Robinson matrix, whose permutation encodes the latent ordering. The framework allows the algorithm to start with partial information on the latent ordering, including seriation from scratch as a special case. We propose an active seriation algorithm that provably recovers the latent ordering with high probability. Under a uniform separation condition on the similarity matrix, optimal performance guarantees are established, both in terms of the probability of error and the number of observations required for successful recovery.

---

### Data Augmentation via Causal-Residual Bootstrapping

Authors: Mateusz Gajewski, Sophia Xiao, Bijan Mazaheri
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.15335v1

Data augmentation integrates domain knowledge into a dataset by making domain-informed modifications to existing data points. For example, image data can be augmented by duplicating images in different tints or orientations, thereby incorporating the knowledge that images may vary in these dimensions. Recent work by Teshima and Sugiyama has explored the integration of causal knowledge (e.g, A causes B causes C) up to conditional independence equivalence. We suggest a related approach for settings with additive noise that can incorporate information beyond a Markov equivalence class. The approach, built on the principle of independent mechanisms, permutes the residuals of models built on marginal probability distributions. Predictive models built on our augmented data demonstrate improved accuracy, for which we provide theoretical backing in linear Gaussian settings.

---

### A scaled TW-PINN: A physics-informed neural network for traveling wave solutions of reaction-diffusion equations with general coefficients

Authors: Seungwan Han, Kwanghyuk Park, Jiaxi Gu, Jae-Hun Jung
Published: 2026-03-16
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2603.15331v1

We propose an efficient and generalizable physics-informed neural network (PINN) framework for computing traveling wave solutions of $n$-dimensional reaction-diffusion equations with various reaction and diffusion coefficients. By applying a scaling transformation with the traveling wave form, the original problem is reduced to a one-dimensional scaled reaction-diffusion equation with unit reaction and diffusion coefficients. This reduction leads to the proposed framework, termed scaled TW-PINN, in which a single PINN solver trained on the scaled equation is reused for different coefficient choices and spatial dimensions. We also prove a universal approximation property of the proposed PINN solver for traveling wave solutions. Numerical experiments in one and two dimensions, together with a comparison to the existing wave-PINN method, demonstrate the accuracy, flexibility, and superior performance of scaled TW-PINN. Finally, we explore an extension of the framework to the Fisher's equation with general initial conditions.

---

### MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction

Authors: Jiacheng Dong, Huan Li, Sicheng Zhou, Wenhao Hu, Weili Xu, Yan Wang
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15330v1

Reconstruction is a fundamental task in 3D vision and a fundamental capability for spatial intelligence. Particularly, streaming 3D reconstruction is central to real-time spatial perception, yet existing recurrent online models often suffer from progressive degradation on long sequences due to state drift and forgetting, motivating inference-time remedies. We present MeMix, a training-free, plug-and-play module that improves streaming reconstruction by recasting the recurrent state into a Memory Mixture. MeMix partitions the state into multiple independent memory patches and updates only the least-aligned memory patches while exactly preserving others. This selective update mitigates catastrophic forgetting while retaining $O(1)$ inference memory, and requires no fine-tuning or additional learnable parameters, making it directly applicable to existing recurrent reconstruction models. Across standard benchmarks (ScanNet, 7-Scenes, KITTI, etc.), under identical backbones and inference settings, MeMix reduces reconstruction completeness error by 15.3% on average (up to 40.0%) across 300--500 frame streams on 7-Scenes. The code is available at https://dongjiacheng06.github.io/MeMix/

---

### Tagarela - A Portuguese speech dataset from podcasts

Authors: Frederico Santos de Oliveira, Lucas Rafael Stefanel Gris, Alef Iury Siqueira Ferreira, Augusto Seben da Rosa, Alexandre Costa Ferro Filho, Edresson Casanova, Christopher Dane Shulby, Rafael Teixeira Sousa, Diogo Fernandes Costa Silva, Anderson da Silva Soares, Arlindo Rodrigues Galvão Filho
Published: 2026-03-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.15326v1

Despite significant advances in speech processing, Portuguese remains under-resourced due to the scarcity of public, large-scale, and high-quality datasets. To address this gap, we present a new dataset, named TAGARELA, composed of over 8,972 hours of podcast audio, specifically curated for training automatic speech recognition (ASR) and text-to-speech (TTS) models. Notably, its scale rivals English's GigaSpeech (10kh), enabling state-of-the-art Portuguese models. To ensure data quality, the corpus was subjected to an audio pre-processing pipeline and subsequently transcribed using a mixed strategy: we applied ASR models that were previously trained on high-fidelity transcriptions generated by proprietary APIs, ensuring a high level of initial accuracy. Finally, to validate the effectiveness of this new resource, we present ASR and TTS models trained exclusively on our dataset and evaluate their performance, demonstrating its potential to drive the development of more robust and natural speech technologies for Portuguese. The dataset is released publicly, available at https://freds0.github.io/TAGARELA/, to foster the development of robust speech technologies.

---

### CASHomon Sets: Efficient Rashomon Sets Across Multiple Model Classes and their Hyperparameters

Authors: Fiona Katharina Ewald, Martin Binder, Matthias Feurer, Bernd Bischl, Giuseppe Casalicchio
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.15321v1

Rashomon sets are model sets within one model class that perform nearly as well as a reference model from the same model class. They reveal the existence of alternative well-performing models, which may support different interpretations. This enables selecting models that match domain knowledge, hidden constraints, or user preferences. However, efficient construction methods currently exist for only a few model classes. Applied machine learning usually searches many model classes, and the best class is unknown beforehand. We therefore study Rashomon sets in the combined algorithm selection and hyperparameter optimization (CASH) setting and call them CASHomon sets. We propose TruVaRImp, a model-based active learning algorithm for level set estimation with an implicit threshold, and provide convergence guarantees. On synthetic and real-world datasets, TruVaRImp reliably identifies CASHomon sets members and matches or outperforms naive sampling, Bayesian optimization, classical and implicit level set estimation methods, and other baselines. Our analyses of predictive multiplicity and feature-importance variability across model classes question the common practice of interpreting data through a single model class.

---

### PYTHEN: A Flexible Framework for Legal Reasoning in Python

Authors: Ha-Thanh Nguyen, Ken Satoh
Published: 2026-03-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.15317v1

This paper introduces PYTHEN, a novel Python-based framework for defeasible legal reasoning. PYTHEN is designed to model the inherently defeasible nature of legal argumentation, providing a flexible and intuitive syntax for representing legal rules, conditions, and exceptions. Inspired by PROLEG (PROlog-based LEGal reasoning support system) and guided by the philosophy of The Zen of Python, PYTHEN leverages Python's built-in any() and all() functions to offer enhanced flexibility by natively supporting both conjunctive (ALL) and disjunctive (ANY) conditions within a single rule, as well as a more expressive exception-handling mechanism. This paper details the architecture of PYTHEN, provides a comparative analysis with PROLEG, and discusses its potential applications in autoformalization and the development of next-generation legal AI systems. By bridging the gap between symbolic reasoning and the accessibility of Python, PYTHEN aims to democratize formal legal reasoning for young researchers, legal tech developers, and professionals without extensive logic programming expertise. We position PYTHEN as a practical bridge between the powerful symbolic reasoning capabilities of logic programming and the rich, ubiquitous ecosystem of Python, making formal legal reasoning accessible to a broader range of developers and legal professionals.

---

### CCTU: A Benchmark for Tool Use under Complex Constraints

Authors: Junjie Ye, Guoqiang Zhang, Wenjie Fu, Zelin Li, Tao Gui, Qi Zhang, Xuanjing Huang
Published: 2026-03-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.15309v2

Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring capabilities such as function calling, instruction following, and self-refinement. However, progress has been hindered by the absence of dedicated evaluations. To address this, we introduce CCTU, a benchmark for evaluating LLM tool use under complex constraints. CCTU is grounded in a taxonomy of 12 constraint categories spanning four dimensions (i.e., resource, behavior, toolset, and response). The benchmark comprises 200 carefully curated and challenging test cases across diverse tool-use scenarios, each involving an average of seven constraint types and an average prompt length exceeding 4,700 tokens. To enable reliable evaluation, we develop an executable constraint validation module that performs step-level validation and enforces compliance during multi-turn interactions between models and their environments. We evaluate nine state-of-the-art LLMs in both thinking and non-thinking modes. Results indicate that when strict adherence to all constraints is required, no model achieves a task completion rate above 20\%. Further analysis reveals that models violate constraints in over 50\% of cases, particularly in the resource and response dimensions. Moreover, LLMs demonstrate limited capacity for self-refinement even after receiving detailed feedback on constraint violations, highlighting a critical bottleneck in the development of robust tool-use agents. To facilitate future research, we release the data and code.

---

### CCTU: A Benchmark for Tool Use under Complex Constraints

Authors: Junjie Ye, Guoqiang Zhang, Wenjie Fu, Tao Gui, Qi Zhang, Xuanjing Huang
Published: 2026-03-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.15309v1

Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring capabilities such as function calling, instruction following, and self-refinement. However, progress has been hindered by the absence of dedicated evaluations. To address this, we introduce CCTU, a benchmark for evaluating LLM tool use under complex constraints. CCTU is grounded in a taxonomy of 12 constraint categories spanning four dimensions (i.e., resource, behavior, toolset, and response). The benchmark comprises 200 carefully curated and challenging test cases across diverse tool-use scenarios, each involving an average of seven constraint types and an average prompt length exceeding 4,700 tokens. To enable reliable evaluation, we develop an executable constraint validation module that performs step-level validation and enforces compliance during multi-turn interactions between models and their environments. We evaluate nine state-of-the-art LLMs in both thinking and non-thinking modes. Results indicate that when strict adherence to all constraints is required, no model achieves a task completion rate above 20%. Further analysis reveals that models violate constraints in over 50% of cases, particularly in the resource and response dimensions. Moreover, LLMs demonstrate limited capacity for self-refinement even after receiving detailed feedback on constraint violations, highlighting a critical bottleneck in the development of robust tool-use agents. To facilitate future research, we release the data and code.

---

### A Kolmogorov-Arnold Surrogate Model for Chemical Equilibria: Application to Solid Solutions

Authors: Leonardo Boledi, Dirk Bosbach, Jenna Poonoosamy
Published: 2026-03-16
Categories: cs.LG, physics.chem-ph
arXiv: https://arxiv.org/abs/2603.15307v1

The computational cost of geochemical solvers is a challenging matter. For reactive transport simulations, where chemical calculations are performed up to billions of times, it is crucial to reduce the total computational time. Existing publications have explored various machine-learning approaches to determine the most effective data-driven surrogate model. In particular, multilayer perceptrons are widely employed due to their ability to recognize nonlinear relationships. In this work, we focus on the recent Kolmogorov-Arnold networks, where learnable spline-based functions replace classical fixed activation functions. This architecture has achieved higher accuracy with fewer trainable parameters and has become increasingly popular for solving partial differential equations. First, we train a surrogate model based on an existing cement system benchmark. Then, we move to an application case for the geological disposal of nuclear waste, i.e., the determination of radionuclide-bearing solids solubilities. To the best of our knowledge, this work is the first to investigate co-precipitation with radionuclide incorporation using data-driven surrogate models, considering increasing levels of thermodynamic complexity from simple mechanical mixtures to non-ideal solid solutions of binary (Ba,Ra)SO$_4$ and ternary (Sr,Ba,Ra)SO$_4$ systems. On the cement benchmark, we demonstrate that the Kolmogorov-Arnold architecture outperforms multilayer perceptrons in both absolute and relative error metrics, reducing them by 62% and 59%, respectively. On the binary and ternary radium solid solution models, Kolmogorov-Arnold networks maintain median prediction errors near $1\times10^{-3}$. This is the first step toward employing surrogate models to speed up reactive transport simulations and optimize the safety assessment of deep geological waste repositories.

---

### xplainfi: Feature Importance and Statistical Inference for Machine Learning in R

Authors: Lukas Burk, Fiona Katharina Ewald, Giuseppe Casalicchio, Marvin N. Wright, Bernd Bischl
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.15306v1

We introduce xplainfi, an R package built on top of the mlr3 ecosystem for global, loss-based feature importance methods for machine learning models. Various feature importance methods exist in R, but significant gaps remain, particularly regarding conditional importance methods and associated statistical inference procedures. The package implements permutation feature importance, conditional feature importance, relative feature importance, leave-one-covariate-out, and generalizations thereof, and both marginal and conditional Shapley additive global importance methods. It provides a modular conditional sampling architecture based on Gaussian distributions, adversarial random forests, conditional inference trees, and knockoff-based samplers, which enable conditional importance analysis for continuous and mixed data. Statistical inference is available through multiple approaches, including variance-corrected confidence intervals and the conditional predictive impact framework. We demonstrate that xplainfi produces importance scores consistent with existing implementations across multiple simulation settings and learner types, while offering competitive runtime performance. The package is available on CRAN and provides researchers and practitioners with a comprehensive toolkit for feature importance analysis and model interpretation in R.

---

### Generative Video Compression with One-Dimensional Latent Representation

Authors: Zihan Zheng, Zhaoyang Jia, Naifu Xue, Jiahao Li, Bin Li, Zongyu Guo, Xiaoyi Zhang, Zhenghao Chen, Houqiang Li, Yan Lu
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15302v1

Recent advancements in generative video codec (GVC) typically encode video into a 2D latent grid and employ high-capacity generative decoders for reconstruction. However, this paradigm still leaves two key challenges in fully exploiting spatial-temporal redundancy: Spatially, the 2D latent grid inevitably preserves intra-frame redundancy due to its rigid structure, where adjacent patches remain highly similar, thereby necessitating a higher bitrate. Temporally, the 2D latent grid is less effective for modeling long-term correlations in a compact and semantically coherent manner, as it hinders the aggregation of common contents across frames. To address these limitations, we introduce Generative Video Compression with One-Dimensional (1D) Latent Representation (GVC1D). GVC1D encodes the video data into extreme compact 1D latent tokens conditioned on both short- and long-term contexts. Without the rigid 2D spatial correspondence, these 1D latent tokens can adaptively attend to semantic regions and naturally facilitate token reduction, thereby reducing spatial redundancy. Furthermore, the proposed 1D memory provides semantically rich long-term context while maintaining low computational cost, thereby further reducing temporal redundancy. Experimental results indicate that GVC1D attains superior compression efficiency, where it achieves bitrate reductions of 60.4\% under LPIPS and 68.8\% under DISTS on the HEVC Class B dataset, surpassing the previous video compression methods.Project: https://gvc1d.github.io/

---

### GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection

Authors: Aggelos Psiris, Yannis Panagakis, Maria Vakalopoulou, Georgios Th. Papadopoulos
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15300v1

Few-Shot Industrial Visual Anomaly Detection (FS-IVAD) comprises a critical task in modern manufacturing settings, where automated product inspection systems need to identify rare defects using only a handful of normal/defect-free training samples. In this context, the current study introduces a novel reconstruction-based approach termed GATE-AD. In particular, the proposed framework relies on the employment of a masked, representation-aligned Graph Attention Network (GAT) encoding scheme to learn robust appearance patterns of normal samples. By leveraging dense, patch-level, visual feature tokens as graph nodes, the model employs stacked self-attentional layers to adaptively encode complex, irregular, non-Euclidean, local relations. The graph is enhanced with a representation alignment component grounded on a learnable, latent space, where high reconstruction residual areas (i.e., defects) are assessed using a Scaled Cosine Error (SCE) objective function. Extensive comparative evaluation on the MVTec AD, VisA, and MPDD industrial defect detection benchmarks demonstrates that GATE-AD achieves state-of-the-art performance across the $1$- to $8$-shot settings, combining the highest detection accuracy (increase up to $1.8\%$ in image AUROC in the 8-shot case in MPDD) with the lowest per-image inference latency (at least $25.05\%$ faster), compared to the best-performing literature methods. In order to facilitate reproducibility and further research, the source code of GATE-AD is available at https://github.com/gthpapadopoulos/GATE-AD.

---

### Enhancing classification accuracy through chaos

Authors: Panos Stinis
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.15299v2

We propose a novel approach which exploits chaos to enhance classification accuracy. Specifically, the available data that need to be classified are treated as vectors that are first lifted into a higher-dimensional space and then used as initial conditions for the evolution of a chaotic dynamical system for a prescribed temporal interval. The evolved state of the dynamical system is then fed to a trainable softmax classifier which outputs the probabilities of the various classes. As proof-of-concept, we use samples of randomly perturbed orthogonal vectors of moderate dimension (2 to 20), with a corresponding number of classes equal to the vector dimension, and show how our approach can both significantly accelerate the training process and improve the classification accuracy compared to a standard softmax classifier which operates on the original vectors, as well as a softmax classifier which only lifts the vectors to a higher-dimensional space without evolving them. We also provide an explanation for the improved performance of the chaos-enhanced classifier and a selection process for the optimal chaotic evolution interval.

---

### Evolutionary Transfer Learning for Dragonchess

Authors: Jim O'Connor, Annika Hoag, Sarah Goyette, Gary B. Parker
Published: 2026-03-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.15297v1

Dragonchess, a three-dimensional chess variant introduced by Gary Gygax, presents unique strategic and computational challenges that make it an ideal environment for studying the transfer of artificial intelligence (AI) heuristics across domains. In this work, we introduce Dragonchess as a novel testbed for AI research and provide an open-source, Python-based game engine for community use. Our research investigates evolutionary transfer learning by adapting heuristic evaluation functions directly from Stockfish, a leading chess engine, and subsequently optimizing them using Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Initial trials showed that direct heuristic transfers were inadequate due to Dragonchess's distinct multi-layer structure and movement rules. However, evolutionary optimization significantly improved AI agent performance, resulting in superior gameplay demonstrated through empirical evaluation in a 50-round Swiss-style tournament. This research establishes the effectiveness of evolutionary methods in adapting heuristic knowledge to structurally complex, previously unexplored game domains.

---

### Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies

Authors: Giuseppe Samo, Paola Merlo
Published: 2026-03-16
Categories: cs.CL, cs.DB
arXiv: https://arxiv.org/abs/2603.15295v1

Large language models (LLMs) have shown remarkable performance across various sentence-based linguistic phenomena, yet their ability to capture cross-sentence paradigmatic patterns, such as verb alternations, remains underexplored. In this work, we present curated paradigm-based datasets for four languages, designed to probe systematic cross-sentence knowledge of verb alternations (change-of-state and object-drop constructions in English, German and Italian, and Hebrew binyanim). The datasets comprise thousands of the Blackbird Language Matrices (BLMs) problems. The BLM task -- an RPM/ARC-like task devised specifically for language -- is a controlled linguistic puzzle where models must select the sentence that completes a pattern according to syntactic and semantic rules. We introduce three types of templates varying in complexity and apply linguistically-informed data augmentation strategies across synthetic and natural data. We provide simple baseline performance results across English, Italian, German, and Hebrew, that demonstrate the diagnostic usefulness of the datasets.

---

### Scalable Simulation-Based Model Inference with Test-Time Complexity Control

Authors: Manuel Gloeckler, J. P. Manzano-Patrón, Stamatios N. Sotiropoulos, Cornelius Schröder, Jakob H. Macke
Published: 2026-03-16
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.15292v1

Simulation plays a central role in scientific discovery. In many applications, the bottleneck is no longer running a simulator; it is choosing among large families of plausible simulators, each corresponding to different forward models/hypotheses consistent with observations. Over large model families, classical Bayesian workflows for model selection are impractical. Furthermore, amortized model selection methods typically hard-code a fixed model prior or complexity penalty at training time, requiring users to commit to a particular parsimony assumption before seeing the data. We introduce PRISM, a simulation-based encoder-decoder that infers a joint posterior over both discrete model structures and associated continuous parameters, while enabling test-time control of model complexity via a tunable model prior that the network is conditioned on. We show that PRISM scales to families with combinatorially many (up to billions) of model instantiations on a synthetic symbolic regression task. As a scientific application, we evaluate PRISM on biophysical modeling for diffusion MRI data, showing the ability to perform model selection across several multi-compartment models, on both synthetic and in vivo neuroimaging data.

---