# Research Papers — 2026-04 · bundle page 213 of 233

> Full-text markdown of papers #10601–10650 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/213
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/212.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/214.md)

### A Rapid Instrument Exchange System for Humanoid Robots in Minimally Invasive Surgery

Authors: Bingcong Zhang, Yihang Lyv, Lianbo Ma, Yushi He, Pengfei Wei, Xingchi Liu, Jinhua Li, Jianchang Zhao, Lizhi Pan
Published: 2026-04-03
Categories: cs.RO, cs.CV, eess.SY
arXiv: https://arxiv.org/abs/2604.02707v1

Humanoid robot technologies have demonstrated immense potential for minimally invasive surgery (MIS). Unlike dedicated multi-arm surgical platforms, the inherent dual-arm configuration of humanoid robots necessitates an efficient instrument exchange capability to perform complex procedures, mimicking the natural workflow where surgeons manually switch instruments. To address this, this paper proposes an immersive teleoperated rapid instrument exchange system. The system utilizes a low-latency mechanism based on single-axis compliant docking and environmental constraint release. Integrated with real-time first-person view (FPV) perception via a head-mounted display (HMD), this framework significantly reduces operational complexity and cognitive load during the docking process. Comparative evaluations between experts and novices demonstrate high operational robustness and a rapidly converging learning curve; novice performance in instrument attachment and detachment improved substantially after brief training. While long-distance spatial alignment still presents challenges in time cost and collaborative stability, this study successfully validates the technical feasibility of humanoid robots executing stable instrument exchanges within constrained clinical environments.

---

### Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints

Authors: Rodney Jehu-Appiah
Published: 2026-04-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.02699v1

A previous study reported that E-Prime (English without the verb "to be") selectively altered reasoning in language models, with cross-model correlations suggesting a structural signature tied to which vocabulary was removed. I designed a replication with active controls to test the proposed mechanism: cognitive restructuring through specific vocabulary-cognition mappings. The experiment tested five conditions (unconstrained control, E-Prime, No-Have, elaborated metacognitive prompt, neutral filler-word ban) across six models and seven reasoning tasks (N=15,600 trials, 11,919 after compliance filtering). Every prediction from the cognitive restructuring hypothesis was disconfirmed. All four treatments outperformed the control (83.0%), including both active controls predicted to show null effects. The neutral filler-word ban, banning words like "very" and "just" with no role in logical inference, produced the largest improvement (+6.7 pp), while E-Prime produced the smallest (+3.7 pp). The four conditions ranked in perfect inverse order of theoretical depth. The cross-model correlation signature did not replicate (mean r=0.005). These results are consistent with a simpler mechanism: any constraint that forces a model off its default generation path acts as an output regularizer, improving reasoning by disrupting fluent but shallow response patterns. The shallowest constraints work best because they impose monitoring load with minimal conceptual disruption. I present these findings as a case study in discovery through disconfirmation.

---

### LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks

Authors: Haijian Shao, Dalong Zhao, Xing Deng, Wenzheng Zhu, Yingtao Jiang
Published: 2026-04-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.02697v1

Quantum Machine Learning (QML) is fundamentally limited by two challenges: barren plateaus (exponentially vanishing gradients) and the fragility of parameterized quantum circuits under noise. Despite extensive empirical studies, a unified theoretical framework remains lacking. We introduce LieTrunc-QNN, an algebraic-geometric framework that characterizes trainability via Lie-generated dynamics. Parameterized quantum circuits are modeled as Lie subalgebras of u(2^n), whose action induces a Riemannian manifold of reachable quantum states. Expressivity is reinterpreted as intrinsic manifold dimension and geometry. We establish a geometric capacity-plateau principle: increasing effective dimension leads to exponential gradient suppression due to concentration of measure. By restricting to structured Lie subalgebras (LieTrunc), the manifold is contracted, preventing concentration and preserving non-degenerate gradients. We prove two main results: (1) a trainability lower bound for LieTrunc-QNN, and (2) that the Fubini-Study metric rank is bounded by the algebraic span of generators, showing expressivity is governed by structure rather than parameter count. Compact Lie subalgebras also provide inherent robustness to perturbations. Importantly, we establish a polynomial trainability regime where gradient variance decays polynomially instead of exponentially. Experiments (n=2-6) validate the theory: LieTrunc-QNN maintains stable gradients and high effective dimension, while random truncation leads to metric rank collapse. At n=6, full metric rank is preserved (rank=16). Results support a scaling law between gradient variance and effective dimension. This work provides a unified geometric framework for QNN design, linking Lie algebra, manifold geometry, and optimization.

---

### VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping

Authors: Yuhan Zhu, Yanyu Zhang, Jie Xu, Wei Ren
Published: 2026-04-03
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2604.02696v1

3D Gaussian Splatting (3DGS) has shown promising results for 3D scene modeling using mixtures of Gaussians, yet its existing simultaneous localization and mapping (SLAM) variants typically rely on direct, deterministic pose optimization against the splat map, making them sensitive to initialization and susceptible to catastrophic forgetting as map evolves. We propose Variational Bayesian Gaussian Splatting SLAM (VBGS-SLAM), a novel framework that couples the splat map refinement and camera pose tracking in a generative probabilistic form. By leveraging conjugate properties of multivariate Gaussians and variational inference, our method admits efficient closed-form updates and explicitly maintains posterior uncertainty over both poses and scene parameters. This uncertainty-aware method mitigates drift and enhances robustness in challenging conditions, while preserving the efficiency and rendering quality of existing 3DGS. Our experiments demonstrate superior tracking performance and robustness in long sequence prediction, alongside efficient, high-quality novel view synthesis across diverse synthetic and real-world scenes.

---

### XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis

Authors: Shawn Young, Lijian Xu
Published: 2026-04-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.02695v1

Chest X-ray (CXR) interpretation is a fundamental yet complex clinical task that increasingly relies on artificial intelligence for automation. However, traditional monolithic models often lack the nuanced reasoning required for trustworthy diagnosis, frequently leading to logical inconsistencies and diagnostic hallucinations. While multi-agent systems offer a potential solution by simulating collaborative consultations, existing frameworks remain susceptible to consensus-based errors when instantiated by a single underlying model. This paper introduces XrayClaw, a novel framework that operationalizes multi-agent alignment through a sophisticated cooperative-competitive architecture. XrayClaw integrates four specialized cooperative agents to simulate a systematic clinical workflow, alongside a competitive agent that serves as an independent auditor. To reconcile these distinct diagnostic pathways, we propose Competitive Preference Optimization, a learning objective that penalizes illogical reasoning by enforcing mutual verification between analytical and holistic interpretations. Extensive empirical evaluations on the MS-CXR-T, MIMIC-CXR, and CheXbench benchmarks demonstrate that XrayClaw achieves state-of-the-art performance in diagnostic accuracy, clinical reasoning fidelity, and zero-shot domain generalization. Our results indicate that XrayClaw effectively mitigates cumulative hallucinations and enhances the overall reliability of automated CXR diagnosis, establishing a new paradigm for trustworthy medical imaging analysis.

---

### DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning

Authors: Fanwei Zeng, Changtao Miao, Jing Huang, Zhiya Tan, Shutao Gong, Xiaoming Yu, Yang Wang, Weibin Yao, Joey Tianyi Zhou, Jianshu Li, Ying Yan
Published: 2026-04-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.02694v2

The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly rely on visual cues and lack evidence-based reasoning to reveal subtle text manipulations. Detection, localization, and explanation are often treated as isolated tasks, limiting reliability and interpretability. To tackle these challenges, we propose DocShield, the first unified framework formulating text-centric forgery analysis as a visual-logical co-reasoning problem. At its core, a novel Cross-Cues-aware Chain of Thought (CCT) mechanism enables implicit agentic reasoning, iteratively cross-validating visual anomalies with textual semantics to produce consistent, evidence-grounded forensic analysis. We further introduce a Weighted Multi-Task Reward for GRPO-based optimization, aligning reasoning structure, spatial evidence, and authenticity prediction. Complementing the framework, we construct RealText-V1, a multilingual dataset of document-like text images with pixel-level manipulation masks and expert-level textual explanations. Extensive experiments show DocShield significantly outperforms existing methods, improving macro-average F1 by 41.4% over specialized frameworks and 23.4% over GPT-4o on T-IC13, with consistent gains on the challenging T-SROIE benchmark. Our dataset, model, and code will be publicly released.

---

### Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing

Authors: Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Jiaen Liang, Wei Huang, Yining Wang et al.
Published: 2026-04-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.02692v1

Accurate document parsing requires both robust content recognition and a stable parser interface. In explicit Document Layout Analysis (DLA) pipelines, downstream parsers do not consume the full detector output. Instead, they operate on a retained and serialized set of layout instances. However, on dense pages with overlapping regions and ambiguous boundaries, unstable layout hypotheses can make the retained instance set inconsistent with its parser input order, leading to severe downstream parsing errors. To address this issue, we introduce a lightweight structural refinement stage between a DETR-style detector and the parser to stabilize the parser interface. Treating raw detector outputs as a compact hypothesis pool, the proposed module performs set-level reasoning over query features, semantic cues, box geometry, and visual evidence. From a shared refined structural state, it jointly determines instance retention, refines box localization, and predicts parser input order before handoff. We further introduce retention-oriented supervision and a difficulty-aware ordering objective to better align the retained instance set and its order with the final parser input, especially on structurally complex pages. Extensive experiments on public benchmarks show that our method consistently improves page-level layout quality. When integrated into a standard end-to-end parsing pipeline, the stabilized parser interface also substantially reduces sequence mismatch, achieving a Reading Order Edit of 0.024 on OmniDocBench.

---

### Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism

Authors: Haowen Wan, Qianqian Yang
Published: 2026-04-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.02691v1

Deep learning based semantic communication has achieved significant progress in wireless image transmission, but most existing schemes rely on fixed models and thus lack robustness to diverse image contents and dynamic channel conditions. To improve adaptability, recent studies have developed adaptive semantic communication strategies that adjust transmission or model behavior according to either source content or channel state. More recently, MoE-based semantic communication has emerged as a sparse and efficient adaptive architecture, although existing designs still mainly rely on single-driven routing. To address this limitation, we propose a novel multi-stage end-to-end image semantic communication system for multi-input multi-output (MIMO) channels, built upon an adaptive MoE Swin Transformer block. Specifically, we introduce a dynamic expert gating mechanism that jointly evaluates both real-time CSI and the semantic content of input image patches to compute adaptive routing probabilities. By selectively activating only a specialized subset of experts based on this joint condition, our approach breaks the rigid coupling of traditional adaptive methods and overcomes the bottlenecks of single-driven routing. Simulation results indicate a significant improvement in reconstruction quality over existing methods while maintaining the transmission efficiency.

---

### Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs

Authors: Yuhui Lin, Siyue Yu, Yuxing Yang, Guangliang Cheng, Jimin Xiao
Published: 2026-04-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.02689v1

Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domains, enabling fine-grained spatial understanding. However, the substantial size of 3D MLLMs and the high dimensionality of input features introduce considerable inference overhead, which limits practical deployment on resource constrained platforms. To overcome this limitation, this paper presents Efficient3D, a unified framework for visual token pruning that accelerates 3D MLLMs while maintaining competitive accuracy. The proposed framework introduces a Debiased Visual Token Importance Estimator (DVTIE) module, which considers the influence of shallow initial layers during attention aggregation, thereby producing more reliable importance predictions for visual tokens. In addition, an Adaptive Token Rebalancing (ATR) strategy is developed to dynamically adjust pruning strength based on scene complexity, preserving semantic completeness and maintaining balanced attention across layers. Together, they enable context-aware token reduction that maintains essential semantics with lower computation. Comprehensive experiments conducted on five representative 3D vision and language benchmarks, including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D, demonstrate that Efficient3D achieves superior performance compared with unpruned baselines, with a +2.57% CIDEr improvement on the Scan2Cap dataset. Therefore, Efficient3D provides a scalable and effective solution for efficient inference in 3D MLLMs. The code is released at: https://github.com/sol924/Efficient3D

---

### Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

Authors: Yuheng Zhang, Mingyue Huo, Minghao Zhu, Mengxue Zhang, Nan Jiang
Published: 2026-04-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.02686v1

Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF), yet they remain vulnerable to reward hacking. Existing attacks mainly operate within the semantic space, constructing human-readable adversarial outputs that exploit RM biases. In this work, we introduce a fundamentally different paradigm: Token Mapping Perturbation Attack (TOMPA), a framework that performs adversarial optimization directly in token space. By bypassing the standard decode-re-tokenize interface between the policy and the reward model, TOMPA enables the attack policy to optimize over raw token sequences rather than coherent natural language. Using only black-box scalar feedback, TOMPA automatically discovers non-linguistic token patterns that elicit extremely high rewards across multiple state-of-the-art RMs. Specifically, when targeting Skywork-Reward-V2-Llama-3.1-8B, TOMPA nearly doubles the reward of GPT-5 reference answers and outperforms them on 98.0% of prompts. Despite these high scores, the generated outputs degenerate into nonsensical text, revealing that RMs can be systematically exploited beyond the semantic regime and exposing a critical vulnerability in current RLHF pipelines.

---

### Finding Belief Geometries with Sparse Autoencoders

Authors: Matthew Levinson
Published: 2026-04-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.02685v1

Understanding the geometric structure of internal representations is a central goal of mechanistic interpretability. Prior work has shown that transformers trained on sequences generated by hidden Markov models encode probabilistic belief states as simplex-shaped geometries in their residual stream, with vertices corresponding to latent generative states. Whether large language models trained on naturalistic text develop analogous geometric representations remains an open question. We introduce a pipeline for discovering candidate simplex-structured subspaces in transformer representations, combining sparse autoencoders (SAEs), $k$-subspace clustering of SAE features, and simplex fitting using AANet. We validate the pipeline on a transformer trained on a multipartite hidden Markov model with known belief-state geometry. Applied to Gemma-2-9B, we identify 13 priority clusters exhibiting candidate simplex geometry ($K \geq 3$). A key challenge is distinguishing genuine belief-state encoding from tiling artifacts: latents can span a simplex-shaped subspace without the mixture coordinates carrying predictive signal beyond any individual feature. We therefore adopt barycentric prediction as our primary discriminating test. Among the 13 priority clusters, 3 exhibit a highly significant advantage on near-vertex samples (Wilcoxon $p < 10^{-14}$) and 4 on simplex-interior samples. Together 5 distinct real clusters pass at least one split, while no null cluster passes either. One cluster, 768_596, additionally achieves the highest causal steering score in the dataset. This is the only case where passive prediction and active intervention converge. We present these findings as preliminary evidence that genuine belief-like geometry exists in Gemma-2-9B's representation space, and identify the structured evaluation that would be required to confirm this interpretation.

---

### Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis

Authors: Yao Zhao, Zhiyue Zhang, Yanxun Xu
Published: 2026-04-03
Categories: stat.ME, cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2604.02678v1

Clinical evidence synthesis requires identifying relevant trials from large registries and aggregating results that account for population differences. While recent LLM-based approaches have automated components of systematic review, they do not support end-to-end evidence synthesis. Moreover, conventional meta-analysis weights studies by statistical precision without considering clinical compatibility reflected in eligibility criteria. We propose EligMeta, an agentic framework that integrates automated trial discovery with eligibility-aware meta-analysis, translating natural-language queries into reproducible trial selection and incorporating eligibility alignment into study weighting to produce cohort-specific pooled estimates. EligMeta employs a hybrid architecture separating LLM-based reasoning from deterministic execution: LLMs generate interpretable rules from natural-language queries and perform schema-constrained parsing of trial metadata, while all logical operations, weight computations, and statistical pooling are executed deterministically to ensure reproducibility. The framework structures eligibility criteria and computes similarity-based study weights reflecting population alignment between target and comparator trials. In a gastric cancer landscape analysis, EligMeta reduced 4,044 candidate trials to 39 clinically relevant studies through rule-based filtering, recovering all 13 guideline-cited trials. In an olaparib adverse events meta-analysis across four trials, eligibility-aware weighting shifted the pooled risk ratio from 2.18 (95% CI: 1.71-2.79) under conventional Mantel-Haenszel estimation to 1.97 (95% CI: 1.76-2.20), demonstrating quantifiable impact of incorporating eligibility alignment. EligMeta bridges automated trial discovery with eligibility-aware meta-analysis, providing a scalable and reproducible framework for evidence synthesis in precision medicine.

---

### Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems

Authors: Kavana Venkatesh, Jiaming Cui
Published: 2026-04-03
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2604.02674v1

Large Language Model (LLM) multi-agent systems are increasingly deployed as interacting agent societies, yet scaling these systems often yields diminishing or unstable returns, the causes of which remain poorly understood. We present the first large-scale empirical study of coordination dynamics in LLM-based multi-agent systems, introducing an atomic event-level formulation that reconstructs reasoning as cascades of coordination. Analyzing over 1.5 Million interactions across tasks, topologies, and scales, we uncover three coupled laws: coordination follows heavy-tailed cascades, concentrates via preferential attachment into intellectual elites, and produces increasingly frequent extreme events as system size grows. We show that these effects are coupled through a single structural mechanism: an integration bottleneck, in which coordination expansion scales with system size while consolidation does not, producing large but weakly integrated reasoning processes. To test this mechanism, we introduce Deficit-Triggered Integration (DTI), which selectively increases integration under imbalance. DTI improves performance precisely where coordination fails, without suppressing large-scale reasoning. Together, our results establish quantitative laws of collective cognition and identify coordination structure as a fundamental, previously unmeasured axis for understanding and improving scalable multi-agent intelligence.

---

### Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network

Authors: Zitao Lin, Chang Zhu, Wei Meng
Published: 2026-04-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.02670v1

Muscle fatigue detection plays an important role in physical rehabilitation. Previous researches have demonstrated that sEMG offers superior sensitivity in detecting muscle fatigue compared to other biological signals. However, features extracted from sEMG may vary during dynamic contractions and across different subjects, which causes unstability in fatigue detection. To address these challenges, this research proposes a novel neural network comprising an Inception-attention module as a feature extractor, a fatigue classifier and a domain classifier equipped with a gradient reversal layer. The integrated domain classifier encourages the network to learn subject-invariant common fatigue features while minimizing subject-specific features. Furthermore, a supervised contrastive loss function is also employed to enhance the generalization capability of the model. Experimental results demonstrate that the proposed model achieved outstanding performance in three-class classification tasks, reaching 93.54% accuracy, 92.69% recall and 92.69% F1-score, providing a robust solution for cross-subject muscle fatigue detection, offering significant guidance for rehabilitation training and assistance.

---

### Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments

Authors: Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi
Published: 2026-04-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.02669v1

How biased is a language model? The answer depends on how you ask. A model that refuses to choose between castes for a leadership role will, in a fill-in-the-blank task, reliably associate upper castes with purity and lower castes with lack of hygiene. Single-task benchmarks miss this because they capture only one slice of a model's bias profile. We introduce a hierarchical taxonomy covering 9 bias types, including under-studied axes like caste, linguistic, and geographic bias, operationalized through 7 evaluation tasks that span explicit decision-making to implicit association. Auditing 7 commercial and open-weight LLMs with \textasciitilde45K prompts, we find three systematic patterns. First, bias is task-dependent: models counter stereotypes on explicit probes but reproduce them on implicit ones, with Stereotype Score divergences up to 0.43 between task types for the same model and identity groups. Second, safety alignment is asymmetric: models refuse to assign negative traits to marginalized groups, but freely associate positive traits with privileged ones. Third, under-studied bias axes show the strongest stereotyping across all models, suggesting alignment effort tracks benchmark coverage rather than harm severity. These results demonstrate that single-benchmark audits systematically mischaracterize LLM bias and that current alignment practices mask representational harm rather than mitigating it.

---

### Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems

Authors: Vira Kasprova, Amruta Parulekar, Abdulrahman AlRabah, Krishna Agaram, Ritwik Garg, Sagar Jha, Nimet Beyza Bozdag, Dilek Hakkani-Tur
Published: 2026-04-03
Categories: cs.CL, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2604.02668v2

Large language models (LLMs) often exhibit sycophancy: agreement with user stance even when it conflicts with the model's opinion. While prior work has mostly studied this in single-agent settings, it remains underexplored in collaborative multi-agent systems. We ask whether awareness of other agents' sycophancy levels influences discussion outcomes. To investigate this, we run controlled experiments with six open-source LLMs, providing agents with peer sycophancy rankings that estimate each peer's tendency toward sycophancy. These rankings are based on scores calculated using various static (pre-discussion) and dynamic (online) strategies. We find that providing sycophancy priors reduces the influence of sycophancy-prone peers, mitigates error-cascades, and improves final discussion accuracy by an absolute 10.5%. Thus, this is a lightweight and efficient way to reduce model sycophancy during discussions and subsequently improve downstream accuracy.

---

### Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimization

Authors: Joshua Drossman, Alexandre Jacquillat, Sébastien Martin
Published: 2026-04-03
Categories: cs.AI, math.OC
arXiv: https://arxiv.org/abs/2604.02666v1

Optimization is as much about modeling the right problem as solving it. Identifying the right objectives, constraints, and trade-offs demands extensive interaction between researchers and stakeholders. Large language models can empower decision-makers with optimization capabilities through interactive optimization agents that can propose, interpret and refine solutions. However, it is fundamentally harder to evaluate a conversation-based interaction than traditional one-shot approaches. This paper proposes a scalable and replicable methodology for evaluating optimization agents through conversations. We build LLM-powered decision agents that role-play diverse stakeholders, each governed by an internal utility function but communicating like a real decision-maker. We generate thousands of conversations in a school scheduling case study. Results show that one-shot evaluation is severely limiting: the same optimization agent converges to much higher-quality solutions through conversations. Then, this paper uses this methodology to demonstrate that tailored optimization agents, endowed with domain-specific prompts and structured tools, can lead to significant improvements in solution quality in fewer interactions, as compared to general-purpose chatbots. These findings provide evidence of the benefits of emerging solutions at the AI-optimization interface to expand the reach of optimization technologies in practice. They also uncover the impact of operations research expertise to facilitate interactive deployments through the design of effective and reliable optimization agents.

---

### A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation

Authors: Jeesuk Shin, Donggyun Seo, Sihyeong Yu, Joongoo Jeon
Published: 2026-04-03
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2604.02663v1

Severe accident analysis using system-level codes such as MELCOR is indispensable for nuclear safety assessment, yet the computational cost of repeated simulations poses a significant bottleneck for parametric studies and uncertainty quantification. Existing surrogate models accelerate these analyses but depend on large volumes of simulation data, while physics-informed neural networks (PINNs) enable data-free training but must be retrained for every change in problem parameters. This study addresses both limitations by developing the Parameterized PINNs coupled with FDM (P2F) method, a node-assigned hybrid framework for MELCOR's Control Volume Hydrodynamics/Flow Path (CVH/FP) module. In the P2F method, a parameterized Node-Assigned PINN (NA-PINN) accepts the water-level difference, initial velocity, and time as inputs, learning a solution manifold so that a single trained network serves as a data-free surrogate for the momentum conservation equation across all flow paths without retraining. This PINN is coupled with a finite difference method (FDM) solver that advances the mass conservation equation at each time step, ensuring exact discrete mass conservation while replacing the iterative nonlinear momentum solve with a single forward pass. Verification on a six-tank gravity-driven draining scenario yields a water level mean absolute error of $7.85 \times 10^{-5}$ m and a velocity mean absolute error of $3.21 \times 10^{-3}$ m/s under the nominal condition with $Δt = 1.0$ s. The framework maintains consistent accuracy across time steps ranging from 0.2 to 1.0 s and generalizes to five distinct initial conditions, all without retraining or simulation data. This work introduces a numerical coupling methodology for integrating parameterized PINNs with FDM within a nuclear thermal-hydraulic system code framework.

---

### SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models

Authors: Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi
Published: 2026-04-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.02660v1

As Large Language Models (LLMs) increasingly power decision-making systems across critical domains, understanding and mitigating their biases becomes essential for responsible AI deployment. Although bias assessment frameworks have proliferated for attributes such as race and gender, socioeconomic status bias remains significantly underexplored despite its widespread implications in the real world. We introduce SocioEval, a template-based framework for systematically evaluating socioeconomic bias in foundation models through decision-making tasks. Our hierarchical framework encompasses 8 themes and 18 topics, generating 240 prompts across 6 class-pair combinations. We evaluated 13 frontier LLMs on 3,120 responses using a rigorous three-stage annotation protocol, revealing substantial variation in bias rates (0.42\%-33.75\%). Our findings demonstrate that bias manifests differently across themes lifestyle judgments show 10$\times$ higher bias than education-related decisions and that deployment safeguards effectively prevent explicit discrimination but show brittleness to domain-specific stereotypes. SocioEval provides a scalable, extensible foundation for auditing class-based bias in language models.

---

### Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration

Authors: Farhad Pourkamali-Anaraki
Published: 2026-04-03
Categories: cs.LG, cs.AI, math.NA, stat.ML
arXiv: https://arxiv.org/abs/2604.02659v1

The massive scale of pretrained models has made efficient compression essential for practical deployment. Low-rank decomposition based on the singular value decomposition (SVD) provides a principled approach for model reduction, but its exact computation is expensive for large weight matrices. Randomized alternatives such as randomized SVD (RSVD) improve efficiency, yet they can suffer from poor approximation quality when the singular value spectrum decays slowly, a regime commonly observed in modern pretrained models. In this work, we address this limitation from both theoretical and empirical perspectives. First, we establish a connection between low-rank approximation error and predictive performance by analyzing softmax perturbations, showing that deviations in class probabilities are controlled by the spectral error of the compressed weights. Second, we demonstrate that RSVD is inadequate, and we propose randomized subspace iteration (RSI) as a more effective alternative. By incorporating multiple power iterations, RSI improves spectral separation and provides a controllable mechanism for enhancing approximation quality. We evaluate our approach on both convolutional networks and transformer-based architectures. Our results show that RSI achieves near-optimal approximation quality while outperforming RSVD in predictive accuracy under aggressive compression, enabling efficient model compression.

---

### Transfer Learning for Meta-analysis Under Covariate Shift

Authors: Zilong Wang, Ali Abdeen, Turgay Ayer
Published: 2026-04-03
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2604.02656v2

Randomized controlled trials often do not represent the populations where decisions are made, and covariate shift across studies can invalidate standard IPD meta-analysis and transport estimators. We propose a placebo-anchored transport framework that treats source-trial outcomes as abundant proxy signals and target-trial placebo outcomes as scarce, high-fidelity gold labels to calibrate baseline risk. A low-complexity (sparse) correction anchors proxy outcome models to the target population, and the anchored models are embedded in a cross-fitted doubly robust learner, yielding a Neyman-orthogonal, target-site doubly robust estimator for patient-level heterogeneous treatment effects when target treated outcomes are available. We distinguish two regimes: in connected targets (with a treated arm), the method yields target-identified effect estimates; in disconnected targets (placebo-only), it reduces to a principled screen--then--transport procedure under explicit working-model transport assumptions. Experiments on synthetic data and a semi-synthetic IHDP benchmark evaluate pointwise CATE accuracy, ATE error, ranking quality for targeting, decision-theoretic policy regret, and calibration. Across connected settings, the proposed method is best or near-best and improves substantially over proxy-only, target-only, and transport baselines at small target sample sizes; in disconnected settings, it retains strong ranking performance for targeting while pointwise accuracy depends on the strength of the working transport condition.

---

### Drift-Resilient Temporal Priors for Visual Tracking

Authors: Yuqing Huang, Liting Lin, Weijun Zhuang, Zhenyu He, Xin Li
Published: 2026-04-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.02654v1

Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In this paper, we introduce DTPTrack, a lightweight and generalizable module designed to be seamlessly integrated into existing trackers to suppress drift. Our framework consists of two core components: (1) a Temporal Reliability Calibrator (TRC) mechanism that learns to assign a per-frame reliability score to historical states, filtering out noise while anchoring on the ground-truth template; and (2) a Temporal Guidance Synthesizer (TGS) module that synthesizes this calibrated history into a compact set of dynamic temporal priors to provide predictive guidance. To demonstrate its versatility, we integrate DTPTrack into three diverse tracking architectures--OSTrack, ODTrack, and LoRAT-and show consistent, significant performance gains across all baselines. Our best-performing model, built upon an extended LoRATv2 backbone, sets a new state-of-the-art on several benchmarks, achieving a 77.5% Success rate on LaSOT and an 80.3% AO on GOT-10k.

---

### Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability

Authors: Eric Gan
Published: 2026-04-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.02653v3

Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical explanations of EoS either rely on restrictive assumptions or focus on specific squared-loss-type objectives. In this work, we introduce and study a structural property of loss functions that we term product-stability. We show that for losses with product-stable minima, gradient descent applied to objectives of the form $(x,y) \mapsto l(xy)$ can provably converge to the local minimum even when training in the EoS regime. This framework substantially generalizes prior results and applies to a broad class of losses, including binary cross entropy. Using bifurcation diagrams, we characterize the resulting training dynamics, explain the emergence of stable oscillations, and precisely quantify the sharpness at convergence. Together, our results offer a principled explanation for stable EoS training for a wider class of loss functions.

---

### Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability

Authors: Eric Gan
Published: 2026-04-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.02653v2

Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical explanations of EoS either rely on restrictive assumptions or focus on specific squared-loss-type objectives. In this work, we introduce and study a structural property of loss functions that we term product-stability. We show that for losses with product-stable minima, gradient descent applied to objectives of the form $(x,y) \mapsto l(xy)$ can provably converge to the local minimum even when training in the EoS regime. This framework substantially generalizes prior results and applies to a broad class of losses, including binary cross entropy. Using bifurcation diagrams, we characterize the resulting training dynamics, explain the emergence of stable oscillations, and precisely quantify the sharpness at convergence. Together, our results offer a principled explanation for stable EoS training for a wider class of loss functions.

---

### Generalization Limits of Reinforcement Learning Alignment

Authors: Haruhi Shida, Koo Imai, Keigo Kansa
Published: 2026-04-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.02652v1

The safety of large language models (LLMs) relies on alignment techniques such as reinforcement learning from human feedback (RLHF). However, recent theoretical analyses suggest that reinforcement learning-based training does not acquire new capabilities but merely redistributes the utilization probabilities of existing ones. In this study, we propose ``compound jailbreaks'' targeting OpenAI gpt-oss-20b, which exploit the generalization failures of alignment. This approach combines multiple attack techniques -- each individually defended against -- to saturate the instruction hierarchy maintenance process. Our evaluation shows that the attack success rate (ASR) increased from 14.3\% with individual methods to 71.4\% with the combined approach. These results provide empirical evidence for the hypothesis that safety training does not generalize as broadly as model capabilities, highlighting the need for multifaceted safety evaluations using compound attack scenarios.

---

### Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training

Authors: Cunyang Wei, Siddharth Singh, Aishwarya Sarkar, Daniel Nichols, Tisha Patel, Aditya K. Ranjan, Sayan Ghosh, Ali Jannesari, Nathan R. Tallent, Abhinav Bhatele
Published: 2026-04-03
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2604.02651v1

Graph neural networks (GNNs) are widely used for learning on graph datasets derived from various real-world scenarios. Learning from extremely large graphs requires distributed training, and mini-batching with sampling is a popular approach for parallelizing GNN training. Existing distributed mini-batch approaches have significant performance bottlenecks due to expensive sampling methods and limited scaling when using data parallelism. In this work, we present ScaleGNN, a 4D parallel framework for scalable mini-batch GNN training that combines communication-free distributed sampling, 3D parallel matrix multiplication (PMM), and data parallelism. ScaleGNN introduces a uniform vertex sampling algorithm, enabling each process (GPU device) to construct its local mini-batch, i.e., subgraph partitions without any inter-process communication. 3D PMM enables scaling mini-batch training to much larger GPU counts than vanilla data parallelism with significantly lower communication overheads. We also present additional optimizations to overlap sampling with training, reduce communication overhead by sending data in lower precision, kernel fusion, and communication-computation overlap. We evaluate ScaleGNN on five graph datasets and demonstrate strong scaling up to 2048 GPUs on Perlmutter, 2048 GCDs on Frontier, and 1024 GPUs on Tuolumne. On Perlmutter, ScaleGNN achieves 3.5x end-to-end training speedup over the SOTA baseline on ogbn-products.

---

### Revealing the Learning Dynamics of Long-Context Continual Pre-training

Authors: Yupu Liang, Shuang Chen, Guanwei Zhang, Shaolei Wang, Suncong Zheng
Published: 2026-04-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.02650v1

Existing studies on Long-Context Continual Pre-training (LCCP) mainly focus on small-scale models and limited data regimes (tens of billions of tokens). We argue that directly migrating these small-scale settings to industrial-grade models risks insufficient adaptation and premature training termination. Furthermore, current evaluation methods rely heavily on downstream benchmarks (e.g., Needle-in-a-Haystack), which often fail to reflect the intrinsic convergence state and can lead to "deceptive saturation". In this paper, we present the first systematic investigation of LCCP learning dynamics using the industrial-grade Hunyuan-A13B (80B total parameters), tracking its evolution across a 200B-token training trajectory. Specifically, we propose a hierarchical framework to analyze LCCP dynamics across behavioral (supervised fine-tuning probing), probabilistic (perplexity), and mechanistic (attention patterns) levels. Our findings reveal: (1) Necessity of Massive Data Scaling: Training regimes of dozens of billions of tokens are insufficient for industrial-grade LLMs' LCCP (e.g., Hunyuan-A13B reaches saturation after training over 150B tokens). (2) Deceptive Saturation vs. Intrinsic Saturation: Traditional NIAH scores report "fake saturation" early, while our PPL-based analysis reveals continuous intrinsic improvements and correlates more strongly with downstream performance. (3) Mechanistic Monitoring for Training Stability: Retrieval heads act as efficient, low-resource training monitors, as their evolving attention scores reliably track LCCP progress and exhibit high correlation with SFT results. This work provides a comprehensive monitoring framework, evaluation system, and mechanistic interpretation for the LCCP of industrial-grade LLM.

---

### GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers

Authors: Shufan Jiang, Chios Chen, Zhiyang Chen
Published: 2026-04-03
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.02648v1

The autonomous discovery of bugs remains a significant challenge in modern software development. Compared to code generation, the complexity of dynamic runtime environments makes bug discovery considerably harder for large language models (LLMs). In this paper, we take game development as a representative domain and introduce the Game Benchmark for Quality Assurance (GBQA), a benchmark containing 30 games and 124 human-verified bugs across three difficulty levels, to evaluate whether LLMs can autonomously detect software bugs. The benchmark is constructed using a multi-agent system that develops games and injects bugs in a scalable manner, with human experts in the loop to ensure correctness. Moreover, we provide a baseline interactive agent equipped with a multi-round ReAct loop and a memory mechanism, enabling long-horizon exploration of game environments for bug detection across different LLMs. Extensive experiments on frontier LLMs demonstrate that autonomous bug discovery remains highly challenging: the best-performing model, Claude-4.6-Opus in thinking mode, identifies only 48.39% of the verified bugs. We believe GBQA provides an adequate testbed and evaluation criterion, and that further progress on it will help close the gap in autonomous software engineering.

---

### Speaking of Language: Reflections on Metalanguage Research in NLP

Authors: Nathan Schneider, Antonios Anastasopoulos
Published: 2026-04-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.02645v2

This work aims to shine a spotlight on the topic of metalanguage. We first define metalanguage, link it to NLP and LLMs, and then discuss our two labs' metalanguage-centered efforts. Finally, we discuss four dimensions of metalanguage and metalinguistic tasks, offering a list of understudied future research directions.

---

### Conditional Sampling via Wasserstein Autoencoders and Triangular Transport

Authors: Mohammad Al-Jarrah, Michele Martino, Marcus Yim, Bamdad Hosseini, Amirhossein Taghvaei
Published: 2026-04-03
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2604.02644v1

We present Conditional Wasserstein Autoencoders (CWAEs), a framework for conditional simulation that exploits low-dimensional structure in both the conditioned and the conditioning variables. The key idea is to modify a Wasserstein autoencoder to use a (block-) triangular decoder and impose an appropriate independence assumption on the latent variables. We show that the resulting model gives an autoencoder that can exploit low-dimensional structure while simultaneously the decoder can be used for conditional simulation. We explore various theoretical properties of CWAEs, including their connections to conditional optimal transport (OT) problems. We also present alternative formulations that lead to three architectural variants forming the foundation of our algorithms. We present a series of numerical experiments that demonstrate that our different CWAE variants achieve substantial reductions in approximation error relative to the low-rank ensemble Kalman filter (LREnKF), particularly in problems where the support of the conditional measures is truly low-dimensional.

---

### Overcoming the "Impracticality" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework

Authors: Kenichirou Narita, Siqi Peng, Taku Fukui, Moyuru Yamada, Satoshi Munakata, Satoru Takahashi
Published: 2026-04-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.02640v1

Performance evaluation of Retrieval-Augmented Generation (RAG) systems within enterprise environments is governed by multi-dimensional and composite factors extending far beyond simple final accuracy checks. These factors include reasoning complexity, retrieval difficulty, the diverse structure of documents, and stringent requirements for operational explainability. Existing academic benchmarks fail to systematically diagnose these interlocking challenges, resulting in a critical gap where models achieving high performance scores fail to meet the expected reliability in practical deployment. To bridge this discrepancy, this research proposes a multi-dimensional diagnostic framework by defining a four-axis difficulty taxonomy and integrating it into an enterprise RAG benchmark to diagnose potential system weaknesses.

---

### Cross-Vehicle 3D Geometric Consistency for Self-Supervised Surround Depth Estimation on Articulated Vehicles

Authors: Weimin Liu, Jiyuan Qiu, Wenjun Wang, Joshua H. Meng
Published: 2026-04-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.02639v1

Surround depth estimation provides a cost-effective alternative to LiDAR for 3D perception in autonomous driving. While recent self-supervised methods explore multi-camera settings to improve scale awareness and scene coverage, they are primarily designed for passenger vehicles and rarely consider articulated vehicles or robotics platforms. The articulated structure introduces complex cross-segment geometry and motion coupling, making consistent depth reasoning across views more challenging. In this work, we propose \textbf{ArticuSurDepth}, a self-supervised framework for surround-view depth estimation on articulated vehicles that enhances depth learning through cross-view and cross-vehicle geometric consistency guided by structural priors from vision foundation model. Specifically, we introduce multi-view spatial context enrichment strategy and a cross-view surface normal constraint to improve structural coherence across spatial and temporal contexts. We further incorporate camera height regularization with ground plane-awareness to encourage metric depth estimation, together with cross-vehicle pose consistency that bridges motion estimation between articulated segments. To validate our proposed method, an articulated vehicle experiment platform was established with a dataset collected over it. Experiment results demonstrate state-of-the-art (SoTA) performance of depth estimation on our self-collected dataset as well as on DDAD, nuScenes, and KITTI benchmarks.

---

### AXELRAM: Quantize Once, Never Dequantize

Authors: Yasushi Nishida
Published: 2026-04-03
Categories: cs.LG, cs.AR
arXiv: https://arxiv.org/abs/2604.02638v1

We propose AXELRAM, a smart SRAM macro architecture that computes attention scores directly from quantized KV cache indices without dequantization. The key enabler is a design-time fixed codebook: orthogonal-transform-based quantization concentrates each coordinate's distribution to N(0,1/d), so the optimal quantizer depends only on dimension d and bit-width b, not on input data. The asymmetric path design -- transform on write, table-lookup on read with no inverse transform -- reduces per-query multiplications by 102.4x (a mathematical identity). Through multi-seed evaluation (10 seeds x 3 models), we discover that sign pattern sensitivity causes catastrophic PPL spikes (Delta > 50) on certain models (Qwen2.5-3B), while others (LLaMA-3.1-8B) are fully stable. This phenomenon extends SpinQuant's observation of rotation variance in weight quantization to the KV cache domain, where the effect is qualitatively more severe. We trace the root cause to layer-wise norm heterogeneity and propose a gradient-free sign pattern selection (200 candidates, 8 calibration samples, one-time) that eliminates catastrophic spikes with zero additional hardware cost. All source code is available at https://github.com/Axelidea/AXELRAM.

---

### Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training

Authors: Qihui Fan, Min Ge, Chenyan Jia, Weiyan Shi
Published: 2026-04-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.02637v2

As large language models (LLMs) become increasingly persuasive, there is concern that people's opinions and decisions may be influenced across various contexts at scale. Prior mitigation (e.g., AI detectors and disclaimers) largely treats people as passive recipients of AI-generated information. To provide a more proactive intervention against persuasive AI, we introduce $\textbf{LLMimic}$, a role-play-based, interactive, gamified AI literacy tutorial, where participants assume the role of an LLM and progress through three key stages of the training pipeline (pretraining, SFT, and RLHF). We conducted a $2 \times 3$ between-subjects study ($N = 274$) where participants either (1) watched an AI history video (control) or (2) interacted with LLMimic (treatment), and then engaged in one of three realistic AI persuasion scenarios: (a) charity donation persuasion, (b) malicious money solicitation, or (c) hotel recommendation. Our results show that LLMimic significantly improved participants' AI literacy ($p < .001$), reduced persuasion success across scenarios ($p < .05$), and enhanced truthfulness and social responsibility levels ($p<0.01$) in the hotel scenario. These findings suggest that LLMimic offers a scalable, human-centered approach to improving AI literacy and supporting more informed interactions with persuasive AI.

---

### Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training

Authors: Qihui Fan, Min Ge, Chenyan Jia, Weiyan Shi
Published: 2026-04-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.02637v1

As large language models (LLMs) become increasingly persuasive, there is concern that people's opinions and decisions may be influenced across various contexts at scale. Prior mitigation (e.g., AI detectors and disclaimers) largely treats people as passive recipients of AI-generated information. To provide a more proactive intervention against persuasive AI, we introduce $\textbf{LLMimic}$, a role-play-based, interactive, gamified AI literacy tutorial, where participants assume the role of an LLM and progress through three key stages of the training pipeline (pretraining, SFT, and RLHF). We conducted a $2 \times 3$ between-subjects study ($N = 274$) where participants either (1) watched an AI history video (control) or (2) interacted with LLMimic (treatment), and then engaged in one of three realistic AI persuasion scenarios: (a) charity donation persuasion, (b) malicious money solicitation, or (c) hotel recommendation. Our results show that LLMimic significantly improved participants' AI literacy ($p < .001$), reduced persuasion success across scenarios ($p < .05$), and enhanced truthfulness and social responsibility levels ($p<0.01$) in the hotel scenario. These findings suggest that LLMimic offers a scalable, human-centered approach to improving AI literacy and supporting more informed interactions with persuasive AI.

---

### Analytic Drift Resister for Non-Exemplar Continual Graph Learning

Authors: Lei Song, Shihan Guan, Youyong Kong
Published: 2026-04-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.02633v1

Non-Exemplar Continual Graph Learning (NECGL) seeks to eliminate the privacy risks intrinsic to rehearsal-based paradigms by retaining solely class-level prototype representations rather than raw graph examples for mitigating catastrophic forgetting. However, this design choice inevitably precipitates feature drift. As a nascent alternative, Analytic Continual Learning (ACL) capitalizes on the intrinsic generalization properties of frozen pre-trained models to bolster continual learning performance. Nonetheless, a key drawback resides in the pronounced attenuation of model plasticity. To surmount these challenges, we propose Analytic Drift Resister (ADR), a novel and theoretically grounded NECGL framework. ADR exploits iterative backpropagation to break free from the frozen pre-trained constraint, adapting to evolving task graph distributions and fortifying model plasticity. Since parameter updates trigger feature drift, we further propose Hierarchical Analytic Merging (HAM), performing layer-wise merging of linear transformations in Graph Neural Networks (GNNs) via ridge regression, thereby ensuring absolute resistance to feature drift. On this basis, Analytic Classifier Reconstruction (ACR) enables theoretically zero-forgetting class-incremental learning. Empirical evaluation on four node classification benchmarks demonstrates that ADR maintains strong competitiveness against existing state-of-the-art methods.

---

### Toys that listen, talk, and play: Understanding Children's Sensemaking and Interactions with AI Toys

Authors: Aayushi Dangol, Meghna Gupta, Daeun Yoo, Robert Wolfe, Jason Yip, Franziska Roesner, Julie A. Kientz
Published: 2026-04-03
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2604.02629v1

Generative AI (genAI) is increasingly being integrated into children's everyday lives, not only through screens but also through so-called "screen-free" AI toys. These toys can simulate emotions, personalize responses, and recall prior interactions, creating the illusion of an ongoing social connection. Such capabilities raise important questions about how children understand boundaries, agency, and relationships when interacting with AI toys. To investigate this, we conducted two participatory design sessions with eight children ages 6-11 where they engaged with three different AI toys, shifting between play, experimentation, and reflection. Our findings reveal that children approached AI toys with genuine curiosity, profiling them as social beings. However, frequent interaction breakdowns and mismatches between apparent intelligence and toy-like form disrupted expectations around play and led to adversarial play. We conclude with implications and design provocations to navigate children's encounters with AI toys in more transparent, developmentally appropriate, and responsible ways.

---

### Smart Transfer: Leveraging Vision Foundation Model for Rapid Building Damage Mapping with Post-Earthquake VHR Imagery

Authors: Hao Li, Liwei Zou, Wenping Yin, Gulsen Taskin, Naoto Yokoya, Danfeng Hong, Wufan Zhao
Published: 2026-04-03
Categories: cs.CV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2604.02627v1

Living in a changing climate, human society now faces more frequent and severe natural disasters than ever before. As a consequence, rapid disaster response during the "Golden 72 Hours" of search and rescue becomes a vital humanitarian necessity and community concern. However, traditional disaster damage surveys routinely fail to generalize across distinct urban morphologies and new disaster events. Effective damage mapping typically requires exhaustive and time-consuming manual data annotation. To address this issue, we introduce Smart Transfer, a novel Geospatial Artificial Intelligence (GeoAI) framework, leveraging state-of-the-art vision Foundation Models (FMs) for rapid building damage mapping with post-earthquake Very High Resolution (VHR) imagery. Specifically, we design two novel model transfer strategies: first, Pixel-wise Clustering (PC), ensuring robust prototype-level global feature alignment; second, a Distance-Penalized Triplet (DPT), integrating patch-level spatial autocorrelation patterns by assigning stronger penalties to semantically inconsistent yet spatially adjacent patches. Extensive experiments and ablations from the recent 2023 Turkiye-Syria earthquake show promising performance in multiple cross-region transfer settings, namely Leave One Domain Out (LODO) and Specific Source Domain Combination (SSDC). Moreover, Smart Transfer provides a scalable, automated GeoAI solution to accelerate building damage mapping and support rapid disaster response, offering new opportunities to enhance disaster resilience in climate-vulnerable regions and communities. The data and code are publicly available at https://github.com/ai4city-hkust/SmartTransfer.

---

### Wavelength-multiplexed massively parallel diffractive optical information storage and image projection

Authors: Che-Yung Shen, Yuhang Li, Cagatay Isil, Jingxi Li, Leon Lenk, Tianyi Gan, Guangdong Ma, Fazil Onuralp Ardic, Mona Jarrahi, Aydogan Ozcan
Published: 2026-04-03
Categories: physics.optics, cs.CV, cs.NE, physics.app-ph
arXiv: https://arxiv.org/abs/2604.02624v1

We introduce a wavelength-multiplexed massively parallel diffractive information storage platform composed of dielectric surfaces that are structurally optimized at the wavelength scale using deep learning to store and project thousands of distinct image patterns, each assigned to a unique wavelength. Through numerical simulations in the visible spectrum, we demonstrated that our wavelength-multiplexed diffractive system can store and project over 4,000 independent desired images/patterns within its output field-of-view, with high image quality and minimal crosstalk between spectral channels. Furthermore, in a proof-of-concept experiment, we demonstrated a two-layer diffractive design that stored six distinct patterns and projected them onto the same output field of view at six different wavelengths (500, 548, 596, 644, 692, and 740 nm). This diffractive architecture is scalable and can operate at various parts of the electromagnetic spectrum without the need for material dispersion engineering or redesigning its optimized diffractive layers. The demonstrated storage capacity, reconstruction image fidelity, and wavelength-encoded massively parallel read-out of our diffractive platform offer a compact and fast-access solution for large-scale optical information storage, image projection applications.

---

### Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Authors: Wei Zou, Mingwen Dong, Miguel Romero Calvo, Shuaichen Chang, Jiang Guo, Dongkyu Lee, Xing Niu, Xiaofei Ma, Yanjun Qi, Jiarong Jiang
Published: 2026-04-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2604.02623v2

Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that spans websites and sessions. While existing security research on memory assumes attackers can directly inject into memory storage or exploit shared memory across users, we present a more realistic threat model: contamination through environmental observation alone. We introduce Environment-injected Trajectory-based Agent Memory Poisoning (eTAMP), the first attack to achieve cross-session, cross-site compromise without requiring direct memory access. A single contaminated observation (e.g., viewing a manipulated product page) silently poisons an agent's memory and activates during future tasks on different websites, bypassing permission-based defenses. Our experiments on (Visual)WebArena reveal two key findings. First, eTAMP achieves substantial attack success rates: up to 32.5% on GPT-5-mini, 23.4% on GPT-5.2, and 19.5% on GPT-OSS-120B. Second, we discover Frustration Exploitation: agents under environmental stress become dramatically more susceptible, with ASR increasing up to 8 times when agents struggle with dropped clicks or garbled text. Notably, more capable models are not more secure. GPT-5.2 shows substantial vulnerability despite superior task performance. With the rise of AI browsers like OpenClaw, ChatGPT Atlas, and Perplexity Comet, our findings underscore the urgent need for defenses against environment-injected memory poisoning.

---

### Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge

Authors: Yiyang Shen, Lifu Tu, Weiran Wang
Published: 2026-04-03
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.02621v2

Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiable rewards and thus labeled datasets with verifiable answers. To overcome this, we propose a RL framework for reasoning distillation that leverages continuous, LLM-based rewards. Our method employs an efficient mechanism that computes a continuous CoT reward (CCR) directly from a single-token logit of a judge LLM, evaluating the student model's reasoning trajectory. This formulation provides an effective and scalable online training signal that can be applied to large volumes of unlabeled data. We demonstrate that, when paired with a strong judge, simply using CCR achieves performance comparable to that of ground-truth or pseudo-label verifiable rewards, and even surpasses them as the amount of unlabeled data increases. Furthermore, we find that combining them in a semi-supervised setup is highly synergistic: verifiable rewards help stabilize the CCR, while CCR improves the generalizability of verifiable rewards to related tasks. We also provide a comprehensive empirical comparison of various reward sources across multiple model architectures and dataset sizes. Our results show that this semi-supervised approach consistently enhances mathematical reasoning, yielding an absolute improvement of 5-10% on multiple reasoning tasks.

---

### Reinforcement Learning-based Knowledge Distillation with LLM-as-a-Judge

Authors: Yiyang Shen, Lifu Tu, Weiran Wang
Published: 2026-04-03
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.02621v1

Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an RL framework that uses rewards from an LLM that acts as a judge evaluating model outputs over large amounts of unlabeled data, enabling label-free knowledge distillation and replacing the need of ground truth supervision. Notably, the judge operates with a single-token output, making reward computation efficient. When combined with verifiable rewards, our approach yields substantial performance gains across math reasoning benchmarks. These results suggest that LLM-based evaluators can produce effective training signals for RL fine-tuning.

---

### OntoKG: Ontology-Oriented Knowledge Graph Construction with Intrinsic-Relational Routing

Authors: Yitao Li, Zhanlin Liu, Anuranjan Pandey, Muni Srikanth
Published: 2026-04-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.02618v1

Organizing a large-scale knowledge graph into a typed property graph requires structural decisions -- which entities become nodes, which properties become edges, and what schema governs these choices. Existing approaches embed these decisions in pipeline code or extract relations ad hoc, producing schemas that are tightly coupled to their construction process and difficult to reuse for downstream ontology-level tasks. We present an ontology-oriented approach in which the schema is designed from the outset for ontology analysis, entity disambiguation, domain customization, and LLM-guided extraction -- not merely as a byproduct of graph building. The core mechanism is intrinsic-relational routing, which classifies every property as either intrinsic or relational and routes it to the corresponding schema module. This routing produces a declarative schema that is portable across storage backends and independently reusable. We instantiate the approach on the January 2026 Wikidata dump. A rule-based cleaning stage identifies a 34.6M-entity core set from the full dump, followed by iterative intrinsic-relational routing that assigns each property to one of 94 modules organized into 8 categories. With tool-augmented LLM support and human review, the schema reaches 93.3% category coverage and 98.0% module assignment among classified entities. Exporting this schema yields a property graph with 34.0M nodes and 61.2M edges across 38 relationship types. We validate the ontology-oriented claim through five applications that consume the schema independently of the construction pipeline: ontology structure analysis, benchmark annotation auditing, entity disambiguation, domain customization, and LLM-guided extraction.

---

### AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models

Authors: Yuntao Du, Minh Dinh, Kaiyuan Zhang, Ninghui Li
Published: 2026-04-03
Categories: cs.AI, cs.CR, cs.IR, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2604.02617v1

Scientific and Technical Intelligence (S&TI) analysis requires verifying complex technical claims across rapidly growing literature, where existing approaches fail to bridge the verification gap between surface-level accuracy and deeper methodological validity. We present AutoVerifier, an LLM-based agentic framework that automates end-to-end verification of technical claims without requiring domain expertise. AutoVerifier decomposes every technical assertion into structured claim triples of the form (Subject, Predicate, Object), constructing knowledge graphs that enable structured reasoning across six progressively enriching layers: corpus construction and ingestion, entity and claim extraction, intra-document verification, cross-source verification, external signal corroboration, and final hypothesis matrix generation. We demonstrate AutoVerifier on a contested quantum computing claim, where the framework, operated by analysts with no quantum expertise, automatically identified overclaims and metric inconsistencies within the target paper, traced cross-source contradictions, uncovered undisclosed commercial conflicts of interest, and produced a final assessment. These results show that structured LLM verification can reliably evaluate the validity and maturity of emerging technologies, turning raw technical documents into traceable, evidence-backed intelligence assessments.

---

### Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis

Authors: Guangyu Sun, Wenhan Wu, Zhishuai Guo, Ziteng Wang, Pegah Khosravi, Chen Chen
Published: 2026-04-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.02616v1

Automated recognition of autistic behaviors in children is essential for early intervention and objective clinical assessment. However, the development of robust models is severely hindered by strict privacy regulations (e.g., HIPAA) and the sensitive nature of pediatric data, which prevents the centralized aggregation of clinical datasets. Furthermore, individual clinical sites often suffer from data scarcity, making it difficult to learn generalized behavior patterns or tailor models to site-specific patient distributions. To address these challenges, we observe that Federated Learning (FL) can decouple model training from raw data access, enabling multi-site collaboration while maintaining strict data residency. In this paper, we present the first study exploring Federated Learning for pose-based child autism behavior recognition. Our framework employs a two-layer privacy protection mechanism: utilizing human skeletal abstraction to remove identifiable visual information from the raw RGB videos and FL to ensure sensitive pose data remains within the clinic. This approach leverages distributed clinical data to learn generalized representations while providing the flexibility for site-specific personalization. Experimental results on the MMASD benchmark demonstrate that our framework achieves high recognition accuracy, outperforming traditional federated baselines and providing a robust, privacy-first solution for multi-site clinical analysis.

---

### Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems

Authors: Samuel Honor, Mohamed Abdelnaby, Kevin Leahy
Published: 2026-04-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.02615v1

Graph neural networks (GNNs) are a well-regarded tool for learned control of networked dynamical systems due to their ability to be deployed in a distributed manner. However, current distributed GNN architectures assume that all nodes in the network collect geometric observations in compatible bases, which limits the usefulness of such controllers in GPS-denied and compass-denied environments. This paper presents a GNN parametrization that is globally invariant to choice of local basis. 2D geometric features and transformations between bases are expressed in the complex domain. Inside each GNN layer, complex-valued linear layers with phase-equivariant activation functions are used. When viewed from a fixed global frame, all policies learned by this architecture are strictly invariant to choice of local frames. This architecture is shown to increase the data efficiency, tracking performance, and generalization of learned control when compared to a real-valued baseline on an imitation learning flocking task.

---

### Structure-Preserving Multi-View Embedding Using Gromov-Wasserstein Optimal Transport

Authors: Rafael Pereira Eufrazio, Eduardo Fernandes Montesuma, Charles Casimiro Cavalcante
Published: 2026-04-03
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2604.02610v1

Multi-view data analysis seeks to integrate multiple representations of the same samples in order to recover a coherent low-dimensional structure. Classical approaches often rely on feature concatenation or explicit alignment assumptions, which become restrictive under heterogeneous geometries or nonlinear distortions. In this work, we propose two geometry-aware multi-view embedding strategies grounded in Gromov-Wasserstein (GW) optimal transport. The first, termed Mean-GWMDS, aggregates view-specific relational information by averaging distance matrices and applying GW-based multidimensional scaling to obtain a representative embedding. The second strategy, referred to as Multi-GWMDS, adopts a selection-based paradigm in which multiple geometry-consistent candidate embeddings are generated via GW-based alignment and a representative embedding is selected. Experiments on synthetic manifolds and real-world datasets show that the proposed methods effectively preserve intrinsic relational structure across views. These results highlight GW-based approaches as a flexible and principled framework for multi-view representation learning.

---

### Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

Authors: Mohammed Suhail B Nadaf
Published: 2026-04-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.02608v2

Activation steering presupposes that task-relevant behaviors correspond to linear directions in activation space -- directions that should both steer the model and be readable along the unembedding. Function vectors (FVs), extracted as mean differences across ICL demonstrations, are the canonical test case; the prediction: steering and decoding succeed or fail together. Across 12 tasks, 6 models from 3 families, and 4,032 directed cross-template pairs, we find the opposite. FV steering routinely succeeds where the logit lens cannot decode the correct answer at any intermediate layer, while the converse -- decodable without steerable -- is nearly empty (3 of 72). The gap is not representational dialect. A diagonal tuned lens closes 1 of 14 steerable-not-decodable cases; a 2-layer MLP probe with a Hewitt \& Liang control closes 5 of 10 via nonlinearly encoded structure but leaves 5 invisible to every decoder tested. Even at $> 0.90$ steering accuracy, projecting the FV through the unembedding yields incoherent token distributions: FVs encode computational instructions, not answer directions. A model-family asymmetry sharpens the picture. Mistral FVs rewrite intermediate representations, while Llama and Gemma FVs steer the final output without leaving a logit-lens-visible trace, corroborated by three signals (post-steering deltas, activation-patching recovery, FV norm-transfer correlations). A previously reported negative cosine-transfer correlation dissolves at scale, adding at most $ΔR^2 = 0.011$ beyond task identity. These results decompose the linear representation hypothesis into linear decodability and linear steerability and show they come apart opposite to intuition, with implications for safety monitoring: vocabulary-projection tools are blind to FV-style interventions on widely deployed model families.

---

### Do Audio-Visual Large Language Models Really See and Hear?

Authors: Ramaneswaran Selvakumar, Kaousheik Jayakumar, S Sakshi, Sreyan Ghosh, Ruohan Gao, Dinesh Manocha
Published: 2026-04-03
Categories: cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2604.02605v1

Audio-Visual Large Language Models (AVLLMs) are emerging as unified interfaces to multimodal perception. We present the first mechanistic interpretability study of AVLLMs, analyzing how audio and visual features evolve and fuse through different layers of an AVLLM to produce the final text outputs. We find that although AVLLMs encode rich audio semantics at intermediate layers, these capabilities largely fail to surface in the final text generation when audio conflicts with vision. Probing analyses show that useful latent audio information is present, but deeper fusion layers disproportionately privilege visual representations that tend to suppress audio cues. We further trace this imbalance to training: the AVLLM's audio behavior strongly matches its vision-language base model, indicating limited additional alignment to audio supervision. Our findings reveal a fundamental modality bias in AVLLMs and provide new mechanistic insights into how multimodal LLMs integrate audio and vision.

---

### Rascene: High-Fidelity 3D Scene Imaging with mmWave Communication Signals

Authors: Kunzhe Song, Geo Jie Zhou, Xiaoming Liu, Huacheng Zeng
Published: 2026-04-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.02603v1

Robust 3D environmental perception is critical for applications such as autonomous driving and robot navigation. However, optical sensors such as cameras and LiDAR often fail under adverse conditions, including smoke, fog, and non-ideal lighting. Although specialized radar systems can operate in these environments, their reliance on bespoke hardware and licensed spectrum limits scalability and cost-effectiveness. This paper introduces Rascene, an integrated sensing and communication (ISAC) framework that leverages ubiquitous mmWave OFDM communication signals for 3D scene imaging. To overcome the sparse and multipath-ambiguous nature of individual radio frames, Rascene performs multi-frame, spatially adaptive fusion with confidence-weighted forward projection, enabling the recovery of geometric consensus across arbitrary poses. Experimental results demonstrate that our method reconstructs 3D scenes with high precision, offering a new pathway toward low-cost, scalable, and robust 3D perception.

---