The paper introduces AGVF, a multi‑agent framework for generating medical‑necessity appeals that must adhere to payer policy and evidence constraints. AGVF treats appeal synthesis as a Constrained Markov Decision Process involving five agents—policy formalization, evidence retrieval, gap analysis, adversarial critique, and gated synthesis—and proves that refining the policy constraint graph monotonically reduces evidence deficiency. A deterministic citation‑grounding gate ensures no unsupported assertions enter the shared state, and validation on 1,000 synthetic cases shows zero citation violations and monotonic deficiency reduction.
By Harshil Lodhiya, Alex McManus, Reese Walker
The paper introduces a hierarchy of four increasingly strict faithfulness criteria—discrimination, logical admissibility, monotonic logical faithfulness, and probabilistic logical faithfulness—for evaluating knowledge base completion models, particularly when the target is a description logic knowledge base. It demonstrates that ranking accuracy alone does not guarantee logical faithfulness and shows that current embedding models fail to satisfy any of the criteria across the hierarchy. The authors provide a formal grounding for the strongest criterion using relative model counts and evaluate several models on εL ontologies, revealing gaps between performance metrics and logical correctness.
By Olga Mashkova, Robert Hoehndorf
COPE (Continual Optimization with Personalized embedding and self-Evaluation) is a new framework that continually personalizes large language models using learnable user embeddings and self‑evaluation to generate proxy rewards. It integrates preference capture, self‑evaluation calibration, and personalized response optimization into a single update step, allowing continuous model updates even when explicit user feedback is sparse. Experiments demonstrate that COPE outperforms both training‑free and training‑based baselines, remains complementary to Retrieval‑Augmented Prompting, and shows reliable self‑evaluation, meaningful preference patterns, stable general capabilities, and robustness to shifting preferences and alternative evaluators.
By Ruike Cao, Fugen Yao, Liang Dong, Jian Xu, Guanjun Jiang, Li Xiao
The paper benchmarks static embedding models—Word2Vec, FastText, and Doc2Vec—for detecting anomalous HTTP requests using a single‑class classification framework. It introduces HEDA, a modular pipeline that trains both embeddings and detectors solely on benign traffic in an unsupervised setting. Experiments on synthetic and real datasets show that FastText embeddings consistently yield high detection rates with controlled false positives.
By Amanda Riverol, Gustavo Betarte, Rodrigo Mart\'inez, \'Alvaro Pardo
The study introduces RCC-Align, a cross‑modal contrastive learning framework that aligns paired histopathology whole‑slide images and CT scans to enhance noninvasive grading of clear cell renal cell carcinoma (ccRCC). Using patient‑level five‑fold cross‑validation on TCGA and CPTAC cohorts, RCC‑Align achieved an AUC of 0.601 and AUPRC of 0.599 for low‑ versus high‑grade ccRCC classification, outperforming CT‑only baselines and showing stronger WSI‑CT embedding alignment. The approach relies solely on CT at inference, potentially aiding grading when biopsy is unsafe or limited by tumor heterogeneity.
By Amit Das, Tanmay Shukla, Naofumi Tomita, Faraz Farhadi, Jessica Sin, Ari Hakimi, Chad Vanderbilt, Jie-Fu Chen, Ritesh Kotecha, Weijie Ma, Bing Ren, Saeed Hassanpour
The paper introduces a scalable subgraph sampling method that uses resistance curvature to guide the selection of nodes and edges for graph neural network training. It builds on ERC‑LG, a curvature approximation technique that employs Johnson‑Lindenstrauss projections and regularized multi‑GPU batched conjugate gradient solvers, thereby avoiding costly Laplacian pseudoinverse calculations and large embedding storage. Experiments demonstrate that ERC‑LG‑based sampling matches pseudoinverse‑based curvature numerically, runs faster than conjugate‑gradient‑only approaches, and achieves the best mean accuracy on six of seven real‑world node‑classification datasets.
By Chaoqun Fei, Tinglve Zhou, Tianyong Hao, Yangyang Li
KATOsuper is an objective‑agnostic framework that accelerates neural topology optimization by coupling neural‑reparameterized TO with a Sensitivity‑Consistent Fourier Neural Operator (SC‑FNO). It uses a forward_split architecture to ensure that sensitivities derived via automatic differentiation remain consistent with predicted objectives, enabling stable optimization. The method demonstrates significant deployment‑time speedups (15–110×) over MATLAB baselines while preserving optimality across 2D and 3D benchmark problems, including compliance and stress minimization, and supports zero‑shot extrapolation to higher resolutions.
By Shengyu Yan, Jasmin Jelovica
LabourCrew is a multi‑agent Retrieval‑Augmented Generation (RAG) framework designed for trustworthy statutory question answering in labour law. It introduces three grounding mechanisms: StatuteGraph, an evidence‑exchange ledger, and a calibrated trust gate that controls false‑accept rates. Evaluated on a Bangla Labour Act QA set, LabourCrew achieves a false‑accept rate of 0.081 and higher answer relevancy than existing RAG methods, demonstrating that calibrated abstention is key to auditable legal QA.
By Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud, M. F. Mridha, Md. Alam Hossain
The paper demonstrates that sharing a deep encoder alone does not eliminate the confounding effects in task-comparison scores. By introducing a conditional two‑discriminator discrepancy within the embedding space, the authors achieve robust detection of task changes, maintaining stability under input rotations and accurately tracking label‑permutation drift. This approach, integrated into a mixture‑of‑heads framework, outperforms traditional novelty triggers and generalizes across multiple backbones and datasets, including ImageNet‑21k ViT‑B/16, DINOv2, and CIFAR‑100.
By Kentaro Oda
RelCheck is a training‑free post‑hoc correction pipeline that addresses relational hallucinations in multimodal large language models. It augments object‑level visual grounding with two forms of relational evidence—learned scene‑graph triples from RelTR and deterministic spatial predicates derived from bounding‑box geometry—forming a three‑layer visual knowledge base. When applied to LLaVA v1 13B, RelCheck improves the overall MME hallucination score from 585.0 to 630.0, with the most significant gain on spatial position accuracy.
By Siddhi Patil, Navrati Saxena, William B. Andreopoulos
The paper investigates whether using non‑Gaussian priors improves fine‑tuning of large behavior models (LBMs) for robot imitation learning. Across more than 100,000 simulation rollouts and 1,250 hardware trials on diverse tasks, the authors find that non‑Gaussian priors do not yield better fine‑tuning performance than standard Gaussian priors, except possibly at very low data fractions. Diagnostic analyses reveal that encoder training dominates fine‑tuning outcomes, while prior choice has minimal impact.
By Chen Xu, Rishi Shah, Hadas Kress-Gazit, Haruki Nishimura, Masha Itkina
LatWeave is a deterministic multi‑hop question‑answering framework that structures knowledge into a multidimensional lattice and reduces QA to three operators—meet, compare, and abstain—while limiting LLM use to extraction and planning. It achieves near‑lossless performance on complete knowledge benchmarks (e.g., MetaQA) and strong results on templated multi‑hop datasets (e.g., 2WikiMultihopQA), while transparently handling incomplete knowledge through abstention. The approach offers reproducible, auditable answer paths with no performance penalty within its operating envelope.
By Yuze Ren, Shaoheng Fan, Tao Wang, Yabo Yan, Han Han
The paper investigates drift detection in deep learning models, showing that sharing a deep encoder alone does not eliminate confounding in task-comparison scores. By introducing a conditional two‑discriminator discrepancy into the embedding space, the authors create a two‑axis gate that remains stable under input rotations and accurately tracks label‑permutation drift. This approach outperforms traditional exchange or novelty triggers, achieving high AUROC in distinguishing semantic novelty from photometric shift across multiple backbones and datasets.
By Kentaro Oda
The paper introduces TEMPS, a modular temporal branch that enhances semantic retrievers by adding a temporal scoring component. TEMPS resolves anchored temporal expressions into intervals, matches them to Gaussian distributions, and trains an anchor-date-conditioned encoder using grounding supervision without hand‑labeled data. On three temporal benchmarks, TEMPS improves MRR across all tested backbones and raises R@1 from 19.92 to 25.39 on the TS‑Retriever, surpassing prior temporal state‑of‑the‑art methods.
By Mourad Hassani, Julien Romero, Amel Bouzeghoub, Christian Jacquelinet
The paper introduces PhyMo, a physics‑grounded multimodal framework that uses a physical‑field modality to represent heterogeneous measurements via PDE‑associated operators. It follows a three‑stage learning process: pretraining a physical‑field encoder with PDE residual supervision, aligning its representations with visual embeddings in a shared latent space, and applying downstream prediction heads to the fused multimodal representations. Experiments on five diverse physical datasets show that PhyMo outperforms the strongest baseline on each dataset, establishing its effectiveness for multimodal representation learning in AI for Physics.
By Henan Sun, Haitao Hu, Jin Liu, Jianfeng Zhang, Lujia Pan, Nuo Chen, Jia Li
InGuard introduces an inner guardrail for text-to-image generation that operates within the model’s own representations, avoiding external classifiers. It grades prompts using the text encoder’s embeddings, modifies risky embeddings with SAGE to produce safe images, and employs a latent detector to halt generation early. Evaluated on the RevGen Safety Benchmark, InGuard achieves a 97.9–98.8% safety rate across five open-weight models while reducing benign disturbances, model parameters, and denoising steps.
By Zeyu Wang, Xiaodan Li, Zhiwen Li, Yuefeng Chen, Hui Xue
The paper introduces Policy-as-Skill (PaS), a modular runtime that packages evidence validation, review routing, version control, and auditability as executable, versioned policy capabilities for large language models. PaS was evaluated on 600 development tasks using a Gemma4 backend, achieving 53.8% exact accuracy and high audit completeness, and deterministic control further improves aggregate accuracy to 61.2% in a task‑dependent manner.
By Kabeh Mohsenzadegan, Vahid Tavakkoli, Kyandoghere Kyamakya
AdaDim introduces a training strategy for self‑supervised learning that adaptively balances dimensionality increase and mutual information reduction. By gradually regularizing the projection head while encouraging feature decorrelation and sample uniformity, AdaDim achieves up to 3% performance gains over standard SSL baselines without relying on costly techniques such as queues or predictor networks. The method demonstrates that optimal SSL models do not simply maximize dimensionality or minimize mutual information, but find a trade‑off between the two.
By Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib
PEARL is a lightweight, prompt‑embedding framework designed for real‑time, anonymous, and heterogeneous collaborative perception. It uses two parallel, low‑rank visual prompt interpreters—sparse‑detection (LWSD) and dense, domain‑invariant (LWDDI)—to align features and select the appropriate interpreter for newly joining agents without needing their configurations. Experiments on simulated and real datasets show that PEARL improves average precision by 8.2% over random selection, runs in 1.67 ms, and reduces communication cost by up to 34.7× while outperforming state‑of‑the‑art offline methods by 5.6% AP.
By Armin Maleki, Hayder Radha
The paper examines LLM-based recommendation rerankers that are often evaluated under an oracle protocol, which guarantees the ground-truth item is present in the scored set. Across Amazon datasets, this protocol overestimates realistic NDCG@10 by 92–95% because realistic retrieval only covers 2–19% of relevant items at K=100, creating a recall ceiling that limits any closed-candidate reranker's top‑k NDCG. The authors find that various optimisation strategies—including prompt engineering, model scaling, sequential models, supervised neural rerankers, LoRA fine‑tuning, hybrid retrieval, score‑aware prompting, and LLM+CF fusion—do not significantly improve over a collaborative‑filtering baseline under realistic retrieval, and they propose a Recall‑Aware Evaluation Protocol (RAEP) to better assess rerankers in low‑recall regimes.
By Zhaohui Wang