# Research Papers — 2026-01 · bundle page 141 of 189

> Full-text markdown of papers #7001–7050 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/141
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/140.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/142.md)

### Distilling Feedback into Memory-as-a-Tool

Authors: Víctor Gallego
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05960v1

We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the Rubric Feedback Bench, a novel dataset for rubric-based learning. Experiments demonstrate that our augmented LLMs rapidly match the performance of test-time refinement pipelines while drastically reducing inference cost.

---

### On the Robustness of Age for Learning-Based Wireless Scheduling in Unknown Environments

Authors: Juaren Steiger, Bin Li
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.05956v2

The constrained combinatorial multi-armed bandit model has been widely employed to solve problems in wireless networking and related areas, including the problem of wireless scheduling for throughput optimization under unknown channel conditions. Most work in this area uses an algorithm design strategy that combines a bandit learning algorithm with the virtual queue technique to track the throughput constraint violation. These algorithms seek to minimize the virtual queue length in their algorithm design. However, in networks where channel conditions change abruptly, the resulting constraints may become infeasible, leading to unbounded growth in virtual queue lengths. In this paper, we make the key observation that the dynamics of the head-of-line age, i.e. the age of the oldest packet in the virtual queue, make it more robust when used in algorithm design compared to the virtual queue length. We therefore design a learning-based scheduling policy that uses the head-of-line age in place of the virtual queue length. We show that our policy matches state-of-the-art performance under i.i.d. network conditions. Crucially, we also show that the system remains stable even under abrupt changes in channel conditions and can rapidly recover from periods of constraint infeasibility.

---

### On the Robustness of Age for Learning-Based Wireless Scheduling in Unknown Environments

Authors: Juaren Steiger, Bin Li
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.05956v1

The constrained combinatorial multi-armed bandit model has been widely employed to solve problems in wireless networking and related areas, including the problem of wireless scheduling for throughput optimization under unknown channel conditions. Most work in this area uses an algorithm design strategy that combines a bandit learning algorithm with the virtual queue technique to track the throughput constraint violation. These algorithms seek to minimize the virtual queue length in their algorithm design. However, in networks where channel conditions change abruptly, the resulting constraints may become infeasible, leading to unbounded growth in virtual queue lengths. In this paper, we make the key observation that the dynamics of the head-of-line age, i.e. the age of the oldest packet in the virtual queue, make it more robust when used in algorithm design compared to the virtual queue length. We therefore design a learning-based scheduling policy that uses the head-of-line age in place of the virtual queue length. We show that our policy matches state-of-the-art performance under i.i.d. network conditions. Crucially, we also show that the system remains stable even under abrupt changes in channel conditions and can rapidly recover from periods of constraint infeasibility.

---

### A Critical Examination of Active Learning Workflows in Materials Science

Authors: Akhil S. Nair, Lucas Foppa
Published: 2026-01-09
Categories: cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2601.05946v1

Active learning (AL) plays a critical role in materials science, enabling applications such as the construction of machine-learning interatomic potentials for atomistic simulations and the operation of self-driving laboratories. Despite its widespread use, the reliability and effectiveness of AL workflows depend on implicit design assumptions that are rarely examined systematically. Here, we critically assess AL workflows deployed in materials science and investigate how key design choices, such as surrogate models, sampling strategies, uncertainty quantification and evaluation metrics, relate to their performance. By identifying common pitfalls and discussing practical mitigation strategies, we provide guidance to practitioners for the efficient design, assessment, and interpretation of AL workflows in materials science.

---

### WaveRNet: Wavelet-Guided Frequency Learning for Multi-Source Domain-Generalized Retinal Vessel Segmentation

Authors: Chanchan Wang, Yuanfang Wang, Qing Xu, Guanxin Chen
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.05942v1

Domain-generalized retinal vessel segmentation is critical for automated ophthalmic diagnosis, yet faces significant challenges from domain shift induced by non-uniform illumination and varying contrast, compounded by the difficulty of preserving fine vessel structures. While the Segment Anything Model (SAM) exhibits remarkable zero-shot capabilities, existing SAM-based methods rely on simple adapter fine-tuning while overlooking frequency-domain information that encodes domain-invariant features, resulting in degraded generalization under illumination and contrast variations. Furthermore, SAM's direct upsampling inevitably loses fine vessel details. To address these limitations, we propose WaveRNet, a wavelet-guided frequency learning framework for robust multi-source domain-generalized retinal vessel segmentation. Specifically, we devise a Spectral-guided Domain Modulator (SDM) that integrates wavelet decomposition with learnable domain tokens, enabling the separation of illumination-robust low-frequency structures from high-frequency vessel boundaries while facilitating domain-specific feature generation. Furthermore, we introduce a Frequency-Adaptive Domain Fusion (FADF) module that performs intelligent test-time domain selection through wavelet-based frequency similarity and soft-weighted fusion. Finally, we present a Hierarchical Mask-Prompt Refiner (HMPR) that overcomes SAM's upsampling limitation through coarse-to-fine refinement with long-range dependency modeling. Extensive experiments under the Leave-One-Domain-Out protocol on four public retinal datasets demonstrate that WaveRNet achieves state-of-the-art generalization performance. The source code is available at https://github.com/Chanchan-Wang/WaveRNet.

---

### Context-Aware Decoding for Faithful Vision-Language Generation

Authors: Mehrdad Fazli, Bowen Wei, Ziwei Zhu
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.05939v1

Hallucinations, generating responses inconsistent with the visual input, remain a critical limitation of large vision-language models (LVLMs), especially in open-ended tasks such as image captioning and visual reasoning. In this work, we probe the layer-wise generation dynamics that drive hallucinations and propose a training-free mitigation strategy. Employing the Logit Lens, we examine how LVLMs construct next-token distributions across decoder layers, uncovering a pronounced commitment-depth gap: truthful tokens accumulate probability mass on their final candidates earlier than hallucinatory ones. Drawing on this discovery, we introduce Context Embedding Injection (CEI), a lightweight method that harnesses the hidden state of the last input token-the context embedding-as a grounding signal to maintain visual fidelity throughout decoding and curb hallucinations. Evaluated on the CHAIR, AMBER, and MMHal-Bench benchmarks (with a maximum token length of 512), CEI outperforms state-of-the-art baselines across three LVLMs, with its dynamic variant yielding the lowest overall hallucination rates. By integrating novel mechanistic insights with a scalable intervention, this work advances the mitigation of hallucinations in LVLMs.

---

### Performance of a Deep Learning-Based Segmentation Model for Pancreatic Tumors on Public Endoscopic Ultrasound Datasets

Authors: Pankaj Gupta, Priya Mudgil, Niharika Dutta, Kartik Bose, Nitish Kumar, Anupam Kumar, Jimil Shah, Vaneet Jearth, Jayanta Samanta, Vishal Sharma, Harshal Mandavdhare, Surinder Rana et al.
Published: 2026-01-09
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.05937v1

Background: Pancreatic cancer is one of the most aggressive cancers, with poor survival rates. Endoscopic ultrasound (EUS) is a key diagnostic modality, but its effectiveness is constrained by operator subjectivity. This study evaluates a Vision Transformer-based deep learning segmentation model for pancreatic tumors. Methods: A segmentation model using the USFM framework with a Vision Transformer backbone was trained and validated with 17,367 EUS images (from two public datasets) in 5-fold cross-validation. The model was tested on an independent dataset of 350 EUS images from another public dataset, manually segmented by radiologists. Preprocessing included grayscale conversion, cropping, and resizing to 512x512 pixels. Metrics included Dice similarity coefficient (DSC), intersection over union (IoU), sensitivity, specificity, and accuracy. Results: In 5-fold cross-validation, the model achieved a mean DSC of 0.651 +/- 0.738, IoU of 0.579 +/- 0.658, sensitivity of 69.8%, specificity of 98.8%, and accuracy of 97.5%. For the external validation set, the model achieved a DSC of 0.657 (95% CI: 0.634-0.769), IoU of 0.614 (95% CI: 0.590-0.689), sensitivity of 71.8%, and specificity of 97.7%. Results were consistent, but 9.7% of cases exhibited erroneous multiple predictions. Conclusions: The Vision Transformer-based model demonstrated strong performance for pancreatic tumor segmentation in EUS images. However, dataset heterogeneity and limited external validation highlight the need for further refinement, standardization, and prospective studies.

---

### Can We Predict Before Executing Machine Learning Agents?

Authors: Jingsheng Zheng, Jintian Zhang, Yujie Luo, Yuren Mao, Yunjun Gao, Lun Du, Huajun Chen, Ningyu Zhang
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2601.05930v2

Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffer from a severe Execution Bottleneck, as hypothesis evaluation relies strictly on expensive physical execution. To bypass these physical constraints, we internalize execution priors to substitute costly runtime checks with instantaneous predictive reasoning, drawing inspiration from World Models. In this work, we formalize the task of Data-centric Solution Preference and construct a comprehensive corpus of 18,438 pairwise comparisons. We demonstrate that LLMs exhibit significant predictive capabilities when primed with a Verified Data Analysis Report, achieving 61.5% accuracy and robust confidence calibration. Finally, we instantiate this framework in FOREAGENT, an agent that employs a Predict-then-Verify loop, achieving a 6x acceleration in convergence while surpassing execution-based baselines by +6%. Our code and dataset are publicly available at https://github.com/zjunlp/predict-before-execute.

---

### Can We Predict Before Executing Machine Learning Agents?

Authors: Jingsheng Zheng, Jintian Zhang, Yujie Luo, Yuren Mao, Yunjun Gao, Lun Du, Huajun Chen, Ningyu Zhang
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2601.05930v1

Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffer from a severe Execution Bottleneck, as hypothesis evaluation relies strictly on expensive physical execution. To bypass these physical constraints, we internalize execution priors to substitute costly runtime checks with instantaneous predictive reasoning, drawing inspiration from World Models. In this work, we formalize the task of Data-centric Solution Preference and construct a comprehensive corpus of 18,438 pairwise comparisons. We demonstrate that LLMs exhibit significant predictive capabilities when primed with a Verified Data Analysis Report, achieving 61.5% accuracy and robust confidence calibration. Finally, we instantiate this framework in FOREAGENT, an agent that employs a Predict-then-Verify loop, achieving a 6x acceleration in convergence while surpassing execution-based baselines by +6%. Our code and dataset will be publicly available soon at https://github.com/zjunlp/predict-before-execute.

---

### Prophet as a Reproducible Forecasting Framework: A Methodological Guide for Business and Financial Analytics

Authors: Sidney Shapiro, Burhanuddin Panvelwala
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.05929v2

Reproducibility remains a persistent challenge in forecasting research and practice, particularly in business and financial analytics, where forecasts inform high-stakes decisions. Traditional forecasting methods, while theoretically interpretable, often require extensive manual tuning and are difficult to replicate in proprietary environments. Machine learning approaches offer predictive flexibility but introduce challenges related to interpretability, stochastic training procedures, and cross-environment reproducibility. This paper examines Prophet, an open-source forecasting framework developed by Meta, as a reproducibility-enabling solution that balances interpretability, standardized workflows, and accessibility. Rather than proposing a new algorithm, this study evaluates how Prophet's additive structure, open-source implementation, and standardized workflow contribute to transparent and replicable forecasting practice. Using publicly available financial and retail datasets, we compare the performance and interpretability of Prophet with multiple ARIMA specifications (auto-selected, manually specified, and seasonal variants) and Random Forest, under a controlled and fully documented experimental design. This multi-model comparison provides a robust assessment of Prophet's relative performance and reproducibility advantages. Through concrete Python examples, we demonstrate how Prophet facilitates efficient forecasting workflows and integration with analytical pipelines. The study positions Prophet within the broader context of reproducible research. It highlights Prophet's role as a methodological building block that supports verification, auditability, and methodological rigor. This work provides researchers and practitioners with a practical reference framework for reproducible forecasting in Python-based research workflows.

---

### Prophet as a Repro ducible Forecasting Framework: A Methodological Guide for Business and Financial Analytics

Authors: Sidney Shapiro, Burhanuddin Panvelwala
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.05929v1

Reproducibility remains a persistent challenge in forecasting research and practice, particularly in business and financial analytics where forecasts inform high-stakes decisions. Traditional forecasting methods, while theoretically interpretable, often require extensive manual tuning and are difficult to replicate in proprietary environments. Machine learning approaches offer predictive flexibility but introduce challenges related to interpretability, stochastic training procedures, and cross-environment reproducibility. This paper examines Prophet, an open-source forecasting framework developed by Meta, as a reproducibility-enabling solution that balances interpretability, standardized workflows, and accessibility. Rather than proposing a new algorithm, this study evaluates how Prophet's additive structure, open-source implementation, and standardized workflow contribute to transparent and replicable forecasting practice. Using publicly available financial and retail datasets, we compare Prophet's performance and interpretability with multiple ARIMA specifications (auto-selected, manually specified, and seasonal variants) and Random Forest under a controlled and fully documented experimental design. This multi-model comparison provides a robust assessment of Prophet's relative performance and reproducibility advantages. Through concrete Python examples, we demonstrate how Prophet facilitates efficient forecasting workflows and integration with analytical pipelines. The study positions Prophet within the broader context of reproducible research. It highlights Prophet's role as a methodological building block that supports verification, auditability, and methodological rigor. This work provides researchers and practitioners with a practical reference framework for reproducible forecasting in Python-based research workflows.

---

### Adapting Vision Transformers to Ultra-High Resolution Semantic Segmentation with Relay Tokens

Authors: Yohann Perron, Vladyslav Sydorov, Christophe Pottier, Loic Landrieu
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.05927v1

Current approaches for segmenting ultra high resolution images either slide a window, thereby discarding global context, or downsample and lose fine detail. We propose a simple yet effective method that brings explicit multi scale reasoning to vision transformers, simultaneously preserving local details and global awareness. Concretely, we process each image in parallel at a local scale (high resolution, small crops) and a global scale (low resolution, large crops), and aggregate and propagate features between the two branches with a small set of learnable relay tokens. The design plugs directly into standard transformer backbones (eg ViT and Swin) and adds fewer than 2 % parameters. Extensive experiments on three ultra high resolution segmentation benchmarks, Archaeoscape, URUR, and Gleason, and on the conventional Cityscapes dataset show consistent gains, with up to 15 % relative mIoU improvement. Code and pretrained models are available at https://archaeoscape.ai/work/relay-tokens/ .

---

### Cedalion Tutorial: A Python-based framework for comprehensive analysis of multimodal fNIRS & DOT from the lab to the everyday world

Authors: E. Middell, L. Carlton, S. Moradi, T. Codina, T. Fischer, J. Cutler, S. Kelley, J. Behrendt, T. Dissanayake, N. Harmening, M. A. Yücel, D. A. Boas et al.
Published: 2026-01-09
Categories: eess.SP, cs.AI, cs.LG, eess.IV, q-bio.QM
arXiv: https://arxiv.org/abs/2601.05923v1

Functional near-infrared spectroscopy (fNIRS) and diffuse optical tomography (DOT) are rapidly evolving toward wearable, multimodal, and data-driven, AI-supported neuroimaging in the everyday world. However, current analytical tools are fragmented across platforms, limiting reproducibility, interoperability, and integration with modern machine learning (ML) workflows. Cedalion is a Python-based open-source framework designed to unify advanced model-based and data-driven analysis of multimodal fNIRS and DOT data within a reproducible, extensible, and community-driven environment. Cedalion integrates forward modelling, photogrammetric optode co-registration, signal processing, GLM Analysis, DOT image reconstruction, and ML-based data-driven methods within a single standardized architecture based on the Python ecosystem. It adheres to SNIRF and BIDS standards, supports cloud-executable Jupyter notebooks, and provides containerized workflows for scalable, fully reproducible analysis pipelines that can be provided alongside original research publications. Cedalion connects established optical-neuroimaging pipelines with ML frameworks such as scikit-learn and PyTorch, enabling seamless multimodal fusion with EEG, MEG, and physiological data. It implements validated algorithms for signal-quality assessment, motion correction, GLM modelling, and DOT reconstruction, complemented by modules for simulation, data augmentation, and multimodal physiology analysis. Automated documentation links each method to its source publication, and continuous-integration testing ensures robustness. This tutorial paper provides seven fully executable notebooks that demonstrate core features. Cedalion offers an open, transparent, and community extensible foundation that supports reproducible, scalable, cloud- and ML-ready fNIRS/DOT workflows for laboratory-based and real-world neuroimaging.

---

### Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset

Authors: Tianshi Li
Published: 2026-01-09
Categories: cs.CR, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.05918v1

On December 4, 2025, Anthropic released Anthropic Interviewer, an AI tool for running qualitative interviews at scale, along with a public dataset of 1,250 interviews with professionals, including 125 scientists, about their use of AI for research. Focusing on the scientist subset, I show that widely available LLMs with web search and agentic capabilities can link six out of twenty-four interviews to specific scientific works, recovering associated authors and, in some cases, uniquely identifying the interviewees. My contribution is to show that modern LLM-based agents make such re-identification attacks easy and low-effort: off-the-shelf tools can, with a few natural-language prompts, search the web, cross-reference details, and propose likely matches, effectively lowering the technical barrier. Existing safeguards can be bypassed by breaking down the re-identification into benign tasks. I outline the attack at a high level, discuss implications for releasing rich qualitative data in the age of LLM agents, and propose mitigation recommendations and open problems. I have notified Anthropic of my findings.

---

### Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces

Authors: Pattarawat Chormai, Ali Hashemi, Klaus-Robert Müller, Grégoire Montavon
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.05913v1

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address the scenario in which only a few classes and their associated intermediate concepts are relevant to distill. This scenario is common in practice, yet few existing distillation methods explicitly focus on the relevant subtask. To address this gap, we introduce 'SubDistill', a new distillation algorithm with improved numerical properties that only distills the relevant components of the teacher model at each layer. Experiments on CIFAR-100 and ImageNet with Convolutional and Transformer models demonstrate that SubDistill outperforms existing layer-wise distillation techniques on a representative set of subtasks. Our benchmark evaluations are complemented by Explainable AI analyses showing that our distilled student models more closely match the decision structure of the original teacher model.

---

### Pantagruel: Unified Self-Supervised Encoders for French Text and Speech

Authors: Phuong-Hang Le, Valentin Pelloin, Arnault Chatelain, Maryem Bouziane, Mohammed Ghennai, Qianwen Guan, Kirill Milintsevich, Salima Mdhaffar, Aidan Mannion, Nils Defauw, Shuyue Gu, Alexandre Audibert et al.
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05911v2

We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as textual tokens or speech units, Pantagruel learns contextualized target representations in the feature space, allowing modality-specific encoders to capture linguistic and acoustic regularities more effectively. Separate models are pre-trained on large-scale French corpora, including Wikipedia, OSCAR and CroissantLLM for text, together with MultilingualLibriSpeech, LeBenchmark, and INA-100k for speech. INA-100k is a newly introduced 100,000-hour corpus of French audio derived from the archives of the Institut National de l'Audiovisuel (INA), the national repository of French radio and television broadcasts, providing highly diverse audio data. We evaluate Pantagruel across a broad range of downstream tasks spanning both modalities, including those from the standard French benchmarks such as FLUE or LeBenchmark. Across these tasks, Pantagruel models show competitive or superior performance compared to strong French baselines such as CamemBERT, FlauBERT, and LeBenchmark2.0, while maintaining a shared architecture that can seamlessly handle either speech or text inputs. These results confirm the effectiveness of feature-space self-supervised objectives for French representation learning and highlight Pantagruel as a robust foundation for multimodal speech-text understanding.

---

### Pantagruel: Unified Self-Supervised Encoders for French Text and Speech

Authors: Phuong-Hang Le, Valentin Pelloin, Arnault Chatelain, Maryem Bouziane, Mohammed Ghennai, Qianwen Guan, Kirill Milintsevich, Salima Mdhaffar, Aidan Mannion, Nils Defauw, Shuyue Gu, Alexandre Audibert et al.
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05911v1

We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as textual tokens or speech units, Pantagruel learns contextualized target representations in the feature space, allowing modality-specific encoders to capture linguistic and acoustic regularities more effectively. Separate models are pre-trained on large-scale French corpora, including Wikipedia, OSCAR and CroissantLLM for text, together with MultilingualLibriSpeech, LeBenchmark, and INA-100k for speech. INA-100k is a newly introduced 100,000-hour corpus of French audio derived from the archives of the Institut National de l'Audiovisuel (INA), the national repository of French radio and television broadcasts, providing highly diverse audio data. We evaluate Pantagruel across a broad range of downstream tasks spanning both modalities, including those from the standard French benchmarks such as FLUE or LeBenchmark. Across these tasks, Pantagruel models show competitive or superior performance compared to strong French baselines such as CamemBERT, FlauBERT, and LeBenchmark2.0, while maintaining a shared architecture that can seamlessly handle either speech or text inputs. These results confirm the effectiveness of feature-space self-supervised objectives for French representation learning and highlight Pantagruel as a robust foundation for multimodal speech-text understanding.

---

### Multi-task Modeling for Engineering Applications with Sparse Data

Authors: Yigitcan Comlek, R. Murali Krishnan, Sandipp Krishnan Ravi, Amin Moghaddas, Rafael Giorjao, Michael Eff, Anirban Samaddar, Nesar S. Ramachandra, Sandeep Madireddy, Liping Wang
Published: 2026-01-09
Categories: stat.ML, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2601.05910v1

Modern engineering and scientific workflows often require simultaneous predictions across related tasks and fidelity levels, where high-fidelity data is scarce and expensive, while low-fidelity data is more abundant. This paper introduces an Multi-Task Gaussian Processes (MTGP) framework tailored for engineering systems characterized by multi-source, multi-fidelity data, addressing challenges of data sparsity and varying task correlations. The proposed framework leverages inter-task relationships across outputs and fidelity levels to improve predictive performance and reduce computational costs. The framework is validated across three representative scenarios: Forrester function benchmark, 3D ellipsoidal void modeling, and friction-stir welding. By quantifying and leveraging inter-task relationships, the proposed MTGP framework offers a robust and scalable solution for predictive modeling in domains with significant computational and experimental costs, supporting informed decision-making and efficient resource utilization.

---

### Auditing Fairness under Model Updates: Fundamental Complexity and Property-Preserving Updates

Authors: Ayoub Ajarra, Debabrota Basu
Published: 2026-01-09
Categories: cs.LG, cs.AI, cs.CY, stat.ML
arXiv: https://arxiv.org/abs/2601.05909v1

As machine learning models become increasingly embedded in societal infrastructure, auditing them for bias is of growing importance. However, in real-world deployments, auditing is complicated by the fact that model owners may adaptively update their models in response to changing environments, such as financial markets. These updates can alter the underlying model class while preserving certain properties of interest, raising fundamental questions about what can be reliably audited under such shifts. In this work, we study group fairness auditing under arbitrary updates. We consider general shifts that modify the pre-audit model class while maintaining invariance of the audited property. Our goals are two-fold: (i) to characterize the information complexity of allowable updates, by identifying which strategic changes preserve the property under audit; and (ii) to efficiently estimate auditing properties, such as group fairness, using a minimal number of labeled samples. We propose a generic framework for PAC auditing based on an Empirical Property Optimization (EPO) oracle. For statistical parity, we establish distribution-free auditing bounds characterized by the SP dimension, a novel combinatorial measure that captures the complexity of admissible strategic updates. Finally, we demonstrate that our framework naturally extends to other auditing objectives, including prediction error and robust risk.

---

### Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Authors: Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen, Ningyu Zhang
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.HC, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2601.05905v2

As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations. Existing evaluations largely rely on point-wise confidence like Self-Consistency, which can mask brittle belief. We show that even facts answered with perfect self-consistency can rapidly collapse under mild contextual interference. To address this gap, we propose Neighbor-Consistency Belief (NCB), a structural measure of belief robustness that evaluates response coherence across a conceptual neighborhood. To validate the efficiency of NCB, we introduce a new cognitive stress-testing protocol that probes outputs stability under contextual interference. Experiments across multiple LLMs show that the performance of high-NCB data is relatively more resistant to interference. Finally, we present Structure-Aware Training (SAT), which optimizes context-invariant belief structure and reduces long-tail knowledge brittleness by approximately 30%. Code is available at https://github.com/zjunlp/belief.

---

### Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Authors: Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen, Ningyu Zhang
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.HC, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2601.05905v1

As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations. Existing evaluations largely rely on point-wise confidence like Self-Consistency, which can mask brittle belief. We show that even facts answered with perfect self-consistency can rapidly collapse under mild contextual interference. To address this gap, we propose Neighbor-Consistency Belief (NCB), a structural measure of belief robustness that evaluates response coherence across a conceptual neighborhood. To validate the efficiency of NCB, we introduce a new cognitive stress-testing protocol that probes outputs stability under contextual interference. Experiments across multiple LLMs show that the performance of high-NCB data is relatively more resistant to interference. Finally, we present Structure-Aware Training (SAT), which optimizes context-invariant belief structure and reduces long-tail knowledge brittleness by approximately 30%. Code will be available at https://github.com/zjunlp/belief.

---

### Can AI mediation improve democratic deliberation?

Authors: Michael Henry Tessler, Georgina Evans, Michiel A. Bakker, Iason Gabriel, Sophie Bridgers, Rishub Jain, Raphael Koster, Verena Rieser, Anca Dragan, Matthew Botvinick, Christopher Summerfield
Published: 2026-01-09
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.05904v1

The strength of democracy lies in the free and equal exchange of diverse viewpoints. Living up to this ideal at scale faces inherent tensions: broad participation, meaningful deliberation, and political equality often trade off with one another (Fishkin, 2011). We ask whether and how artificial intelligence (AI) could help navigate this "trilemma" by engaging with a recent example of a large language model (LLM)-based system designed to help people with diverse viewpoints find common ground (Tessler, Bakker, et al., 2024). Here, we explore the implications of the introduction of LLMs into deliberation augmentation tools, examining their potential to enhance participation through scalability, improve political equality via fair mediation, and foster meaningful deliberation by, for example, surfacing trustworthy information. We also point to key challenges that remain. Ultimately, a range of empirical, technical, and theoretical advancements are needed to fully realize the promise of AI-mediated deliberation for enhancing citizen engagement and strengthening democratic deliberation.

---

### HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search

Authors: Zihang Tian, Rui Li, Jingsen Zhang, Xiaohe Bo, Wei Huo, Xu Chen
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05903v1

Large language model (LLM) routing aims to exploit the specialized strengths of different LLMs for diverse tasks. However, existing approaches typically focus on selecting LLM architectures while overlooking parameter settings, which are critical for task performance. In this paper, we introduce HAPS, a hierarchical LLM routing framework that jointly searches over model architectures and parameters. Specifically, we use a high-level router to select among candidate LLM architectures, and then search for the optimal parameters for the selected architectures based on a low-level router. We design a parameter generation network to share parameters between the two routers to mutually enhance their capabilities. In the training process, we design a reward-augmented objective to effectively optimize our framework. Experiments on two commonly used benchmarks show that HAPS consistently outperforms strong routing baselines. We have released our code at https://github.com/zihangtian/HAPS.

---

### TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents

Authors: Dawei Wang, Chengming Zhou, Di Zhao, Xinyuan Liu, Marci Chi Ma, Gary Ushaw, Richard Davison
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.05899v2

Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-making emerging as core general-purpose capabilities for adapting to diverse scenarios and tasks. Real-time strategy (RTS) games serve as an ideal testbed for evaluating these two capabilities, as their inherent gameplay requires both macro-level strategic planning and micro-level tactical adaptation and action execution. Existing RTS game-based environments either suffer from relatively high computational demands or lack support for textual observations, which has constrained the use of RTS games for LLM evaluation. Motivated by this, we present TowerMind, a novel environment grounded in the tower defense (TD) subgenre of RTS games. TowerMind preserves the key evaluation strengths of RTS games for assessing LLMs, while featuring low computational demands and a multimodal observation space, including pixel-based, textual, and structured game-state representations. In addition, TowerMind supports the evaluation of model hallucination and provides a high degree of customizability. We design five benchmark levels to evaluate several widely used LLMs under different multimodal input settings. The results reveal a clear performance gap between LLMs and human experts across both capability and hallucination dimensions. The experiments further highlight key limitations in LLM behavior, such as inadequate planning validation, a lack of multifinality in decision-making, and inefficient action use. We also evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight and multimodal design, TowerMind complements the existing RTS game-based environment landscape and introduces a new benchmark for the AI agent field. The source code is publicly available on GitHub(https://github.com/tb6147877/TowerMind).

---

### TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents

Authors: Dawei Wang, Chengming Zhou, Di Zhao, Xinyuan Liu, Marci Chi Ma, Gary Ushaw, Richard Davison
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.05899v1

Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-making emerging as core general-purpose capabilities for adapting to diverse scenarios and tasks. Real-time strategy (RTS) games serve as an ideal testbed for evaluating these two capabilities, as their inherent gameplay requires both macro-level strategic planning and micro-level tactical adaptation and action execution. Existing RTS game-based environments either suffer from relatively high computational demands or lack support for textual observations, which has constrained the use of RTS games for LLM evaluation. Motivated by this, we present TowerMind, a novel environment grounded in the tower defense (TD) subgenre of RTS games. TowerMind preserves the key evaluation strengths of RTS games for assessing LLMs, while featuring low computational demands and a multimodal observation space, including pixel-based, textual, and structured game-state representations. In addition, TowerMind supports the evaluation of model hallucination and provides a high degree of customizability. We design five benchmark levels to evaluate several widely used LLMs under different multimodal input settings. The results reveal a clear performance gap between LLMs and human experts across both capability and hallucination dimensions. The experiments further highlight key limitations in LLM behavior, such as inadequate planning validation, a lack of multifinality in decision-making, and inefficient action use. We also evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight and multimodal design, TowerMind complements the existing RTS game-based environment landscape and introduces a new benchmark for the AI agent field. The source code is publicly available on GitHub(https://github.com/tb6147877/TowerMind).

---

### StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management

Authors: Ruizhe Zhang, Xinke Jiang, Zhibang Yang, Zhixin Zhang, Jiaran Gao, Yuzhen Xiao, Tao Feng, Yue Fang, Yuxuan Liu, Ruiqing Li, Hongbin Lai, Huheng Huang et al.
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.05890v2

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon collaboration due to the lack of memory management, leading to context bloat, error accumulation, and poor cross-task generalization. To address both task-level memory inefficiency and the inability to reuse coordination experience, we propose StackPlanner, a hierarchical multi-agent framework with explicit memory control. StackPlanner addresses these challenges by decoupling high-level coordination from subtask execution with active task-level memory control, and by learning to retrieve and exploit reusable coordination experience via structured experience memory and reinforcement learning. Experiments on multiple deep-search and agent system benchmarks demonstrate the effectiveness of our approach in enabling reliable long-horizon multi-agent collaboration.

---

### StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management

Authors: Ruizhe Zhang, Xinke Jiang, Zhibang Yang, Zhixin Zhang, Jiaran Gao, Yuzhen Xiao, Hongbin Lai, Xu Chu, Junfeng Zhao, Yasha Wang
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.05890v1

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon collaboration due to the lack of memory management, leading to context bloat, error accumulation, and poor cross-task generalization. To address both task-level memory inefficiency and the inability to reuse coordination experience, we propose StackPlanner, a hierarchical multi-agent framework with explicit memory control. StackPlanner addresses these challenges by decoupling high-level coordination from subtask execution with active task-level memory control, and by learning to retrieve and exploit reusable coordination experience via structured experience memory and reinforcement learning. Experiments on multiple deep-search and agent system benchmarks demonstrate the effectiveness of our approach in enabling reliable long-horizon multi-agent collaboration.

---

### GlueNN: gluing patchwise analytic solutions with neural networks

Authors: Doyoung Kim, Donghee Lee, Hye-Sung Lee, Jiheon Lee, Jaeok Yi
Published: 2026-01-09
Categories: cs.LG, astro-ph.CO, physics.comp-ph
arXiv: https://arxiv.org/abs/2601.05889v2

In the analysis of complex physical systems, the objective often extends beyond merely computing a numerical solution to capturing the precise crossover between different regimes and extracting parameters containing meaningful information. However, standard numerical solvers and conventional deep learning approaches, such as Physics-Informed Neural Networks (PINNs), typically operate as black boxes that output solution fields without disentangling the solution into its interpretable constituent parts. In this work, we propose GlueNN, a physics-informed learning framework that decomposes the global solution into interpretable, patchwise analytic components. Rather than approximating the solution directly, GlueNN promotes the integration constants of local asymptotic expansions to learnable, scale-dependent coefficient functions. By constraining these coefficients with the differential equation, the network effectively performs regime transition, smoothly interpolating between asymptotic limits without requiring ad hoc boundary matching. We demonstrate that this coefficient-centric approach reproduces accurate global solutions in various examples and thus directly extracts physical information that is not explicitly available through standard numerical integration.

---

### GlueNN: gluing patchwise analytic solutions with neural networks

Authors: Doyoung Kim, Donghee Lee, Hye-Sung Lee, Jiheon Lee, Jaeok Yi
Published: 2026-01-09
Categories: cs.LG, astro-ph.CO, physics.comp-ph
arXiv: https://arxiv.org/abs/2601.05889v1

In many problems in physics and engineering, one encounters complicated differential equations with strongly scale-dependent terms for which exact analytical or numerical solutions are not available. A common strategy is to divide the domain into several regions (patches) and simplify the equation in each region. When approximate analytic solutions can be obtained in each patch, they are then matched at the interfaces to construct a global solution. However, this patching procedure can fail to reproduce the correct solution, since the approximate forms may break down near the matching boundaries. In this work, we propose a learning framework in which the integration constants of asymptotic analytic solutions are promoted to scale-dependent functions. By constraining these coefficient functions with the original differential equation over the domain, the network learns a globally valid solution that smoothly interpolates between asymptotic regimes, eliminating the need for arbitrary boundary matching. We demonstrate the effectiveness of this framework in representative problems from chemical kinetics and cosmology, where it accurately reproduces global solutions and outperforms conventional matching procedures.

---

### An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift

Authors: Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.05882v2

Preference tuning aligns base language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference tuning degrades performance and reduces helpfulness outside the training domain. However, the extent to which adaptation strategies mitigate this domain shift remains unexplored. We address this challenge by conducting a comprehensive and systematic study of alignment generalization under domain shift. We compare five popular alignment objectives and various adaptation strategies from source to target, including target-domain supervised fine-tuning and pseudo-labeling, across summarization, question-answering helpfulness, and safety alignment tasks. Our findings reveal systematic differences in generalization across alignment objectives under domain shift. We show that adaptation strategies based on pseudo-labeling substantially reduce domain-shift degradation but induce mode collapse, revealing a generalization-diversity trade-off.

---

### An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift

Authors: Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.05882v1

Preference tuning aligns pretrained language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference-tuning degrades performance and reduces helpfulness when evaluated outside the training domain. However, the extent to which adaptation strategies mitigate this domain shift remains unexplored. We address this challenge by conducting a comprehensive and systematic study of alignment generalization under domain shift. We compare five popular alignment objectives and various adaptation strategies from source to target, including target-domain supervised fine-tuning and pseudo-labeling, across summarization and question-answering helpfulness tasks. Our findings reveal systematic differences in generalization across alignment objectives under domain shift. We show that adaptation strategies based on pseudo-labeling can substantially reduce domain-shift degradation

---

### Gender Bias in LLMs: Preliminary Evidence from Shared Parenting Scenario in Czech Family Law

Authors: Jakub Harasta, Matej Vasina, Martin Kornel, Tomas Foltynek
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.05879v1

Access to justice remains limited for many people, leading laypersons to increasingly rely on Large Language Models (LLMs) for legal self-help. Laypeople use these tools intuitively, which may lead them to form expectations based on incomplete, incorrect, or biased outputs. This study examines whether leading LLMs exhibit gender bias in their responses to a realistic family law scenario. We present an expert-designed divorce scenario grounded in Czech family law and evaluate four state-of-the-art LLMs GPT-5 nano, Claude Haiku 4.5, Gemini 2.5 Flash, and Llama 3.3 in a fully zero-shot interaction. We deploy two versions of the scenario, one with gendered names and one with neutral labels, to establish a baseline for comparison. We further introduce nine legally relevant factors that vary the factual circumstances of the case and test whether these variations influence the models' proposed shared-parenting ratios. Our preliminary results highlight differences across models and suggest gender-dependent patterns in the outcomes generated by some systems. The findings underscore both the risks associated with laypeople's reliance on LLMs for legal guidance and the need for more robust evaluation of model behavior in sensitive legal contexts. We present exploratory and descriptive evidence intended to identify systematic asymmetries rather than to establish causal effects.

---

### iReasoner: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Models

Authors: Meghana Sunil, Manikandarajan Venmathimaran, Muthu Subash Kavitha
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05877v3

Recent work shows that large multimodal models (LMMs) can self-improve from unlabeled data via self-play and intrinsic feedback. Yet existing self-evolving frameworks mainly reward final outcomes, leaving intermediate reasoning weakly constrained despite its importance for visually grounded decision making. We propose iReasoner, a self-evolving framework that improves an LMM's implicit reasoning by explicitly eliciting chain-of-thought (CoT) and rewarding its internal agreement. In a Proposer--Solver loop over unlabeled images, iReasoner augments outcome-level intrinsic rewards with a trajectory-aware signal defined over intermediate reasoning steps, providing learning signals that distinguish reasoning paths leading to the same answer without ground-truth labels or external judges. Starting from Qwen2.5-VL-7B, iReasoner yields up to $+2.1$ points across diverse multimodal reasoning benchmarks under fully unsupervised post-training. We hope this work serves as a starting point for reasoning-aware self-improvement in LMMs in purely unsupervised settings. Our code is available at https://meghanaasunil.github.io/iReasoner.

---

### iReasoner: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Models

Authors: Meghana Sunil, Manikandarajan Venmathimaran, Muthu Subash Kavitha
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05877v1

Recent work shows that large multimodal models (LMMs) can self-improve from unlabeled data via self-play and intrinsic feedback. Yet existing self-evolving frameworks mainly reward final outcomes, leaving intermediate reasoning weakly constrained despite its importance for visually grounded decision making. We propose iReasoner, a self-evolving framework that improves an LMM's implicit reasoning by explicitly eliciting chain-of-thought (CoT) and rewarding its internal agreement. In a Proposer--Solver loop over unlabeled images, iReasoner augments outcome-level intrinsic rewards with a trajectory-aware signal defined over intermediate reasoning steps, providing learning signals that distinguish reasoning paths leading to the same answer without ground-truth labels or external judges. Starting from Qwen2.5-VL-7B, iReasoner yields up to $+2.1$ points across diverse multimodal reasoning benchmarks under fully unsupervised post-training. We hope this work serves as a starting point for reasoning-aware self-improvement in LMMs in purely unsupervised settings.

---

### Continual-learning for Modelling Low-Resource Languages from Large Language Models

Authors: Santosh Srinath K, Mudit Somani, Varun Reddy Padala, Prajna Devi Upadhyay, Abhijit Das
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.05874v1

Modelling a language model for a multi-lingual scenario includes several potential challenges, among which catastrophic forgetting is the major challenge. For example, small language models (SLM) built for low-resource languages by adapting large language models (LLMs) pose the challenge of catastrophic forgetting. This work proposes to employ a continual learning strategy using parts-of-speech (POS)-based code-switching along with a replay adapter strategy to mitigate the identified gap of catastrophic forgetting while training SLM from LLM. Experiments conducted on vision language tasks such as visual question answering and language modelling task exhibits the success of the proposed architecture.

---

### IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck

Authors: Huilin Deng, Hongchen Luo, Yue Zhu, Long Li, Zhuoyue Chen, Xinghao Zhao, Ming Li, Jihai Zhang, Mengchang Wang, Yang Cao, Yu Kang
Published: 2026-01-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.05870v1

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for Large Language Model (LLM) reasoning have been hindered by a persistent challenge: exploration collapse. The semantic homogeneity of random rollouts often traps models in narrow, over-optimized behaviors. While existing methods leverage policy entropy to encourage exploration, they face inherent limitations. Global entropy regularization is susceptible to reward hacking, which can induce meaningless verbosity, whereas local token-selective updates struggle with the strong inductive bias of pre-trained models. To address this, we propose Latent Policy Optimization via Iterative Information Bottleneck (IIB-LPO), a novel approach that shifts exploration from statistical perturbation of token distributions to topological branching of reasoning trajectories. IIB-LPO triggers latent branching at high-entropy states to diversify reasoning paths and employs the Information Bottleneck principle both as a trajectory filter and a self-reward mechanism, ensuring concise and informative exploration. Empirical results across four mathematical reasoning benchmarks demonstrate that IIB-LPO achieves state-of-the-art performance, surpassing prior methods by margins of up to 5.3% in accuracy and 7.4% in diversity metrics.

---

### Sequential Bayesian Optimal Experimental Design in Infinite Dimensions via Policy Gradient Reinforcement Learning

Authors: Kaichen Shen, Peng Chen
Published: 2026-01-09
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2601.05868v1

Sequential Bayesian optimal experimental design (SBOED) for PDE-governed inverse problems is computationally challenging, especially for infinite-dimensional random field parameters. High-fidelity approaches require repeated forward and adjoint PDE solves inside nested Bayesian inversion and design loops. We formulate SBOED as a finite-horizon Markov decision process and learn an amortized design policy via policy-gradient reinforcement learning (PGRL), enabling online design selection from the experiment history without repeatedly solving an SBOED optimization problem. To make policy training and reward evaluation scalable, we combine dual dimension reduction -- active subspace projection for the parameter and principal component analysis for the state -- with an adjusted derivative-informed latent attention neural operator (LANO) surrogate that predicts both the parameter-to-solution map and its Jacobian. We use a Laplace-based D-optimality reward while noting that, in general, other expected-information-gain utilities such as KL divergence can also be used within the same framework. We further introduce an eigenvalue-based evaluation strategy that uses prior samples as proxies for maximum a posteriori (MAP) points, avoiding repeated MAP solves while retaining accurate information-gain estimates. Numerical experiments on sequential multi-sensor placement for contaminant source tracking demonstrate approximately $100\times$ speedup over high-fidelity finite element methods, improved performance over random sensor placements, and physically interpretable policies that discover an ``upstream'' tracking strategy.

---

### FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG

Authors: Maxime Dassen, Rebecca Kotula, Kenton Murray, Andrew Yates, Dawn Lawrie, Efsun Kayi, James Mayfield, Kevin Duh
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05866v4

Retrieval-Augmented Generation (RAG) models are critically undermined by citation hallucinations, a deceptive failure where a model cites a source that fails to support its claim. While existing work attributes hallucination to a simple over-reliance on parametric knowledge, we reframe this failure as an evolving, scale-dependent coordination failure between the Attention (reading) and Feed-Forward Network (recalling) pathways. We introduce FACTUM (Framework for Attesting Citation Trustworthiness via Underlying Mechanisms), a framework of four mechanistic scores: Contextual Alignment (CAS), Attention Sink Usage (BAS), Parametric Force (PFS), and Pathway Alignment (PAS). Our analysis reveals that correct citations are consistently marked by higher parametric force (PFS) and greater use of the attention sink (BAS) for information synthesis. Crucially, we find that "one-size-fits-all" theories are insufficient as the signature of correctness evolves with scale: while the 3B model relies on high pathway alignment (PAS), our best-performing 8B detector identifies a shift toward a specialized strategy where pathways provide distinct, orthogonal information. By capturing this complex interplay, FACTUM outperforms state-of-the-art baselines by up to 37.5% in AUC. Our results demonstrate that high parametric force is constructive when successfully coordinated with the Attention pathway, paving the way for more nuanced and reliable RAG systems.

---

### FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG

Authors: Maxime Dassen, Rebecca Kotula, Kenton Murray, Andrew Yates, Dawn Lawrie, Efsun Kayi, James Mayfield, Kevin Duh
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05866v1

Retrieval-Augmented Generation (RAG) models are critically undermined by citation hallucinations, a deceptive failure where a model confidently cites a source that fails to support its claim. Existing work often attributes hallucination to a simple over-reliance on the model's parametric knowledge. We challenge this view and introduce FACTUM (Framework for Attesting Citation Trustworthiness via Underlying Mechanisms), a framework of four mechanistic scores measuring the distinct contributions of a model's attention and FFN pathways, and the alignment between them. Our analysis reveals two consistent signatures of correct citation: a significantly stronger contribution from the model's parametric knowledge and greater use of the attention sink for information synthesis. Crucially, we find the signature of a correct citation is not static but evolves with model scale. For example, the signature of a correct citation for the Llama-3.2-3B model is marked by higher pathway alignment, whereas for the Llama-3.1-8B model, it is characterized by lower alignment, where pathways contribute more distinct, orthogonal information. By capturing this complex, evolving signature, FACTUM outperforms state-of-the-art baselines by up to 37.5% in AUC. Our findings reframe citation hallucination as a complex, scale-dependent interplay between internal mechanisms, paving the way for more nuanced and reliable RAG systems.

---

### What do the metrics mean? A critical analysis of the use of Automated Evaluation Metrics in Interpreting

Authors: Jonathan Downie, Joss Moorkens
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05864v1

With the growth of interpreting technologies, from remote interpreting and Computer-Aided Interpreting to automated speech translation and interpreting avatars, there is now a high demand for ways to quickly and efficiently measure the quality of any interpreting delivered. A range of approaches to fulfil the need for quick and efficient quality measurement have been proposed, each involving some measure of automation. This article examines these recently-proposed quality measurement methods and will discuss their suitability for measuring the quality of authentic interpreting practice, whether delivered by humans or machines, concluding that automatic metrics as currently proposed cannot take into account the communicative context and thus are not viable measures of the quality of any interpreting provision when used on their own. Across all attempts to measure or even categorise quality in Interpreting Studies, the contexts in which interpreting takes place have become fundamental to the final analysis.

---

### Phase4DFD: Multi-Domain Phase-Aware Attention for Deepfake Detection

Authors: Zhen-Xin Lin, Shang-Kuan Chen
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.05861v1

Recent deepfake detection methods have increasingly explored frequency domain representations to reveal manipulation artifacts that are difficult to detect in the spatial domain. However, most existing approaches rely primarily on spectral magnitude, implicitly under exploring the role of phase information. In this work, we propose Phase4DFD, a phase aware frequency domain deepfake detection framework that explicitly models phase magnitude interactions via a learnable attention mechanism. Our approach augments standard RGB input with Fast Fourier Transform (FFT) magnitude and local binary pattern (LBP) representations to expose subtle synthesis artifacts that remain indistinguishable under spatial analysis alone. Crucially, we introduce an input level phase aware attention module that uses phase discontinuities commonly introduced by synthetic generation to guide the model toward frequency patterns that are most indicative of manipulation before backbone feature extraction. The attended multi domain representation is processed by an efficient BNext M backbone, with optional channel spatial attention applied for semantic feature refinement. Extensive experiments on the CIFAKE and DFFD datasets demonstrate that our proposed model Phase4DFD outperforms state of the art spatial and frequency-based detectors while maintaining low computational overhead. Comprehensive ablation studies further confirm that explicit phase modeling provides complementary and non-redundant information beyond magnitude-only frequency representations.

---

### CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning

Authors: Alexandra Dragomir, Florin Brad, Radu Tudor Ionescu
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.05858v2

Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation (MT). Some follow-up works further improved MT performance via preference optimization, but they leave a key aspect largely underexplored: the order in which data samples are given during training. We address this topic by integrating curriculum learning into various state-of-the-art preference optimization algorithms to boost MT performance. We introduce a novel curriculum learning strategy with restarts (CLewR), which reiterates easy-to-hard curriculum multiple times during training to effectively mitigate the catastrophic forgetting of easy examples. We demonstrate consistent gains across several model families (Gemma2, Qwen2.5, Llama3.1) and preference optimization techniques. We publicly release our code at https://github.com/alexandra-dragomir/CLewR.

---

### CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning

Authors: Alexandra Dragomir, Florin Brad, Radu Tudor Ionescu
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.05858v1

Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation (MT). Some follow-up works further improved MT performance via preference optimization, but they leave a key aspect largely underexplored: the order in which data samples are given during training. We address this topic by integrating curriculum learning into various state-of-the-art preference optimization algorithms to boost MT performance. We introduce a novel curriculum learning strategy with restarts (CLewR), which reiterates easy-to-hard curriculum multiple times during training to effectively mitigate the catastrophic forgetting of easy examples. We demonstrate consistent gains across several model families (Gemma2, Qwen2.5, Llama3.1) and preference optimization techniques. We publicly release our code at https://github.com/alexandra-dragomir/CLewR.

---

### Bidirectional Channel-selective Semantic Interaction for Semi-Supervised Medical Segmentation

Authors: Kaiwen Huang, Yizhe Zhang, Yi Zhou, Tianyang Xu, Tao Zhou
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.05855v1

Semi-supervised medical image segmentation is an effective method for addressing scenarios with limited labeled data. Existing methods mainly rely on frameworks such as mean teacher and dual-stream consistency learning. These approaches often face issues like error accumulation and model structural complexity, while also neglecting the interaction between labeled and unlabeled data streams. To overcome these challenges, we propose a Bidirectional Channel-selective Semantic Interaction~(BCSI) framework for semi-supervised medical image segmentation. First, we propose a Semantic-Spatial Perturbation~(SSP) mechanism, which disturbs the data using two strong augmentation operations and leverages unsupervised learning with pseudo-labels from weak augmentations. Additionally, we employ consistency on the predictions from the two strong augmentations to further improve model stability and robustness. Second, to reduce noise during the interaction between labeled and unlabeled data, we propose a Channel-selective Router~(CR) component, which dynamically selects the most relevant channels for information exchange. This mechanism ensures that only highly relevant features are activated, minimizing unnecessary interference. Finally, the Bidirectional Channel-wise Interaction~(BCI) strategy is employed to supplement additional semantic information and enhance the representation of important channels. Experimental results on multiple benchmarking 3D medical datasets demonstrate that the proposed method outperforms existing semi-supervised approaches.

---

### LayerGS: Decomposition and Inpainting of Layered 3D Human Avatars via 2D Gaussian Splatting

Authors: Yinghan Xu, John Dingliana
Published: 2026-01-09
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2601.05853v1

We propose a novel framework for decomposing arbitrarily posed humans into animatable multi-layered 3D human avatars, separating the body and garments. Conventional single-layer reconstruction methods lock clothing to one identity, while prior multi-layer approaches struggle with occluded regions. We overcome both limitations by encoding each layer as a set of 2D Gaussians for accurate geometry and photorealistic rendering, and inpainting hidden regions with a pretrained 2D diffusion model via score-distillation sampling (SDS). Our three-stage training strategy first reconstructs the coarse canonical garment via single-layer reconstruction, followed by multi-layer training to jointly recover the inner-layer body and outer-layer garment details. Experiments on two 3D human benchmark datasets (4D-Dress, Thuman2.0) show that our approach achieves better rendering quality and layer decomposition and recomposition than the previous state-of-the-art, enabling realistic virtual try-on under novel viewpoints and poses, and advancing practical creation of high-fidelity 3D human assets for immersive applications. Our code is available at https://github.com/RockyXu66/LayerGS

---

### Kidney Cancer Detection Using 3D-Based Latent Diffusion Models

Authors: Jen Dusseljee, Sarah de Boer, Alessa Hering
Published: 2026-01-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.05852v1

In this work, we present a novel latent diffusion-based pipeline for 3D kidney anomaly detection on contrast-enhanced abdominal CT. The method combines Denoising Diffusion Probabilistic Models (DDPMs), Denoising Diffusion Implicit Models (DDIMs), and Vector-Quantized Generative Adversarial Networks (VQ-GANs). Unlike prior slice-wise approaches, our method operates directly on an image volume and leverages weak supervision with only case-level pseudo-labels. We benchmark our approach against state-of-the-art supervised segmentation and detection models. This study demonstrates the feasibility and promise of 3D latent diffusion for weakly supervised anomaly detection. While the current results do not yet match supervised baselines, they reveal key directions for improving reconstruction fidelity and lesion localization. Our findings provide an important step toward annotation-efficient, generative modeling of complex abdominal anatomy.

---

### Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs

Authors: Sandeep Mishra, Devichand Budagam, Anubhab Mandal, Bishal Santra, Pawan Goyal, Manish Gupta
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.05851v1

Real-time multimodal auto-completion is essential for digital assistants, chatbots, design tools, and healthcare consultations, where user inputs rely on shared visual context. We introduce Multimodal Auto-Completion (MAC), a task that predicts upcoming characters in live chats using partially typed text and visual cues. Unlike traditional text-only auto-completion (TAC), MAC grounds predictions in multimodal context to better capture user intent. To enable this task, we adapt MMDialog and ImageChat to create benchmark datasets. We evaluate leading vision-language models (VLMs) against strong textual baselines, highlighting trade-offs in accuracy and efficiency. We present Router-Suggest, a router framework that dynamically selects between textual models and VLMs based on dialog context, along with a lightweight variant for resource-constrained environments. Router-Suggest achieves a 2.3x to 10x speedup over the best-performing VLM. A user study shows that VLMs significantly excel over textual models on user satisfaction, notably saving user typing effort and improving the quality of completions in multi-turn conversations. These findings underscore the need for multimodal context in auto-completions, leading to smarter, user-aware assistants.

---

### Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals

Authors: Nate Gillman, Yinghua Zhou, Zitian Tang, Evan Luo, Arjan Chakravarthy, Daksh Aggarwal, Michael Freeman, Charles Herrmann, Chen Sun
Published: 2026-01-09
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.05848v2

Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text instructions are often too abstract to capture physical nuances, while target images are frequently infeasible to specify for dynamic tasks. To address this, we introduce Goal Force, a novel framework that allows users to define goals via explicit force vectors and intermediate dynamics, mirroring how humans conceptualize physical tasks. We train a video generation model on a curated dataset of synthetic causal primitives-such as elastic collisions and falling dominos-teaching it to propagate forces through time and space. Despite being trained on simple physics data, our model exhibits remarkable zero-shot generalization to complex, real-world scenarios, including tool manipulation and multi-object causal chains. Our results suggest that by grounding video generation in fundamental physical interactions, models can emerge as implicit neural physics simulators, enabling precise, physics-aware planning without reliance on external engines. We release all datasets, code, model weights, and interactive video demos at our project page.

---

### Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals

Authors: Nate Gillman, Yinghua Zhou, Zitian Tang, Evan Luo, Arjan Chakravarthy, Daksh Aggarwal, Michael Freeman, Charles Herrmann, Chen Sun
Published: 2026-01-09
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.05848v1

Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text instructions are often too abstract to capture physical nuances, while target images are frequently infeasible to specify for dynamic tasks. To address this, we introduce Goal Force, a novel framework that allows users to define goals via explicit force vectors and intermediate dynamics, mirroring how humans conceptualize physical tasks. We train a video generation model on a curated dataset of synthetic causal primitives-such as elastic collisions and falling dominos-teaching it to propagate forces through time and space. Despite being trained on simple physics data, our model exhibits remarkable zero-shot generalization to complex, real-world scenarios, including tool manipulation and multi-object causal chains. Our results suggest that by grounding video generation in fundamental physical interactions, models can emerge as implicit neural physics simulators, enabling precise, physics-aware planning without reliance on external engines. We release all datasets, code, model weights, and interactive video demos at our project page.

---

### Schema-Grounded LLM Extraction for FHIR Patient Digital Twins

Authors: Rafael Brens, Yuqiao Meng, Luoxi Tang, Zhaohan Xi
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.05847v2

We revisit the problem of constructing interoperable patient digital twins from unstructured electronic health records (EHRs) and argue that the task is better cast not as a cascade of extraction modules but as constrained generation of a valid FHIR bundle. We introduce SG-LLM, a schema-grounded LLM extractor that (i) augments the prompt with candidate SNOMED-CT, RxNorm, and LOINC codes retrieved through a SapBERT index, (ii) decodes under a JSON Schema derived directly from FHIR R4 StructureDefinitions, and (iii) closes a validator-in-the-loop repair stage whose diagnostics are fed back as structured error messages. We argue that the twin's usefulness, not only span-level F1, is the right object of evaluation, and operationalize this with a clinical-utility experiment that measures the gap in 30-day readmission AUROC between classifiers trained on SG-LLM-generated FHIR bundles versus expert-curated ones. On MIMIC-IV and n2c2 2018 Track 2 benchmarks, SG-LLM matches or exceeds strong joint-extraction and vanilla-LLM baselines while producing substantially more valid bundles. Ablations isolate the contributions of retrieval, schema constraint, and the repair loop. All code, prompts, and schemas are released.

---