# Research Papers — 2026-01 · bundle page 123 of 189

> Full-text markdown of papers #6101–6150 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/123
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/122.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/124.md)

### MLPlatt: Simple Calibration Framework for Ranking Models

Authors: Piotr Bajger, Roman Dusek, Krzysztof Galias, Paweł Młyniec, Aleksander Wawer, Paweł Zawistowski
Published: 2026-01-13
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2601.08345v1

Ranking models are extensively used in e-commerce for relevance estimation. These models often suffer from poor interpretability and no scale calibration, particularly when trained with typical ranking loss functions. This paper addresses the problem of post-hoc calibration of ranking models. We introduce MLPlatt: a simple yet effective ranking model calibration method that preserves the item ordering and converts ranker outputs to interpretable click-through rate (CTR) probabilities usable in downstream tasks. The method is context-aware by design and achieves good calibration metrics globally, and within strata corresponding to different values of a selected categorical field (such as user country or device), which is often important from a business perspective of an E-commerce platform. We demonstrate the superiority of MLPlatt over existing approaches on two datasets, achieving an improvement of over 10\% in F-ECE (Field Expected Calibration Error) compared to other methods. Most importantly, we show that high-quality calibration can be achieved without compromising the ranking quality.

---

### When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges

Authors: Sichu Liang, Zhenglin Wang, Jiajia Chu, Pengfei Xia, Hui Zang, Deyu Zhou
Published: 2026-01-13
Categories: cs.MA, cs.CL
arXiv: https://arxiv.org/abs/2601.08343v1

Multi-agent LLM systems routinely generate multiple candidate responses that are aggregated by an LLM judge. To reduce the dominant prefill cost in such pipelines, recent work advocates KV cache reuse across partially shared contexts and reports substantial speedups for generation agents. In this work, we show that these efficiency gains do not transfer uniformly to judge-centric inference. Across GSM8K, MMLU, and HumanEval, we find that reuse strategies that are effective for execution agents can severely perturb judge behavior: end-task accuracy may appear stable, yet the judge's selection becomes highly inconsistent with dense prefill. We quantify this risk using Judge Consistency Rate (JCR) and provide diagnostics showing that reuse systematically weakens cross-candidate attention, especially for later candidate blocks. Our ablation further demonstrates that explicit cross-candidate interaction is crucial for preserving dense-prefill decisions. Overall, our results identify a previously overlooked failure mode of KV cache reuse and highlight judge-centric inference as a distinct regime that demands dedicated, risk-aware system design.

---

### Detecting Mental Manipulation in Speech via Synthetic Multi-Speaker Dialogue

Authors: Run Chen, Wen Liang, Ziwei Gong, Lin Ai, Julia Hirschberg
Published: 2026-01-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.08342v1

Mental manipulation, the strategic use of language to covertly influence or exploit others, is a newly emerging task in computational social reasoning. Prior work has focused exclusively on textual conversations, overlooking how manipulative tactics manifest in speech. We present the first study of mental manipulation detection in spoken dialogues, introducing a synthetic multi-speaker benchmark SPEECHMENTALMANIP that augments a text-based dataset with high-quality, voice-consistent Text-to-Speech rendered audio. Using few-shot large audio-language models and human annotation, we evaluate how modality affects detection accuracy and perception. Our results reveal that models exhibit high specificity but markedly lower recall on speech compared to text, suggesting sensitivity to missing acoustic or prosodic cues in training. Human raters show similar uncertainty in the audio setting, underscoring the inherent ambiguity of manipulative speech. Together, these findings highlight the need for modality-aware evaluation and safety alignment in multimodal dialogue systems.

---

### From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution

Authors: Chunyu Meng, Wei Long, Shuhang Gu
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08341v2

Single Image Super-Resolution (SISR) is a fundamental computer vision task that aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) input. Transformer-based methods have achieved remarkable performance by modeling long-range dependencies in degraded images. However, their feature-intensive attention computation incurs high computational cost. To improve efficiency, most existing approaches partition images into fixed groups and restrict attention within each group. Such group-wise attention overlooks the inherent asymmetry in token similarities, thereby failing to enable flexible and token-adaptive attention computation. To address this limitation, we propose the Individualized Exploratory Transformer (IET), which introduces a novel Individualized Exploratory Attention (IEA) mechanism that allows each token to adaptively select its own content-aware and independent attention candidates. This token-adaptive and asymmetric design enables more precise information aggregation while maintaining computational efficiency. Extensive experiments on standard SR benchmarks demonstrate that IET achieves state-of-the-art performance under comparable computational complexity.

---

### Tissue Classification and Whole-Slide Images Analysis via Modeling of the Tumor Microenvironment and Biological Pathways

Authors: Junzhuo Liu, Xuemei Du, Daniel Reisenbuchler, Ye Chen, Markus Eckstein, Christian Matek, Friedrich Feuerhake, Dorit Merhof
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08336v1

Automatic integration of whole slide images (WSIs) and gene expression profiles has demonstrated substantial potential in precision clinical diagnosis and cancer progression studies. However, most existing studies focus on individual gene sequences and slide level classification tasks, with limited attention to spatial transcriptomics and patch level applications. To address this limitation, we propose a multimodal network, BioMorphNet, which automatically integrates tissue morphological features and spatial gene expression to support tissue classification and differential gene analysis. For considering morphological features, BioMorphNet constructs a graph to model the relationships between target patches and their neighbors, and adjusts the response strength based on morphological and molecular level similarity, to better characterize the tumor microenvironment. In terms of multimodal interactions, BioMorphNet derives clinical pathway features from spatial transcriptomic data based on a predefined pathway database, serving as a bridge between tissue morphology and gene expression. In addition, a novel learnable pathway module is designed to automatically simulate the biological pathway formation process, providing a complementary representation to existing clinical pathways. Compared with the latest morphology gene multimodal methods, BioMorphNet's average classification metrics improve by 2.67%, 5.48%, and 6.29% for prostate cancer, colorectal cancer, and breast cancer datasets, respectively. BioMorphNet not only classifies tissue categories within WSIs accurately to support tumor localization, but also analyzes differential gene expression between tissue categories based on prediction confidence, contributing to the discovery of potential tumor biomarkers.

---

### Automated Machine Learning in Radiomics: A Comparative Evaluation of Performance, Efficiency and Accessibility

Authors: Jose Lozano-Montoya, Emilio Soria-Olivas, Almudena Fuster-Matanzo, Angel Alberich-Bayarri, Ana Jimenez-Pastor
Published: 2026-01-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.08334v2

Automated machine learning (AutoML) frameworks can lower technical barriers for predictive and prognostic model development in radiomics by enabling researchers without programming expertise to build models. However, their effectiveness in addressing radiomics-specific challenges remains unclear. This study evaluates the performance, efficiency, and accessibility of general-purpose and radiomics-specific AutoML frameworks on diverse radiomics classification tasks, thereby highlighting development needs for radiomics. Ten public/private radiomics datasets with varied imaging modalities (CT/MRI), sizes, anatomies and endpoints were used. Six general-purpose and five radiomics-specific frameworks were tested with predefined parameters using standardized cross-validation. Evaluation metrics included AUC, runtime, together with qualitative aspects related to software status, accessibility, and interpretability. Simplatab, a radiomics-specific tool with a no-code interface, achieved the highest average test AUC (81.81%) with a moderate runtime (~1 hour). LightAutoML, a general-purpose framework, showed the fastest execution with competitive performance (78.74% mean AUC in six minutes). Most radiomics-specific frameworks were excluded from the performance analysis due to obsolescence, extensive programming requirements, or computational inefficiency. Conversely, general-purpose frameworks demonstrated higher accessibility and ease of implementation. Simplatab provides an effective balance of performance, efficiency, and accessibility for radiomics classification problems. However, significant gaps remain, including the lack of accessible survival analysis support and the limited integration of feature reproducibility and harmonization within current AutoML frameworks. Future research should focus on adapting AutoML solutions to better address these radiomics-specific challenges.

---

### Semantic Laundering in AI Agent Architectures: Why Tool Boundaries Do Not Confer Epistemic Warrant

Authors: Oleg Romanchuk, Roman Bondar
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08333v1

LLM-based agent architectures systematically conflate information transport mechanisms with epistemic justification mechanisms. We formalize this class of architectural failures as semantic laundering: a pattern where propositions with absent or weak warrant are accepted by the system as admissible by crossing architecturally trusted interfaces. We show that semantic laundering constitutes an architectural realization of the Gettier problem: propositions acquire high epistemic status without a connection between their justification and what makes them true. Unlike classical Gettier cases, this effect is not accidental; it is architecturally determined and systematically reproducible. The central result is the Theorem of Inevitable Self-Licensing: under standard architectural assumptions, circular epistemic justification cannot be eliminated. We introduce the Warrant Erosion Principle as the fundamental explanation for this effect and show that scaling, model improvement, and LLM-as-judge schemes are structurally incapable of eliminating a problem that exists at the type level.

---

### IGAN: A New Inception-based Model for Stable and High-Fidelity Image Synthesis Using Generative Adversarial Networks

Authors: Ahmed A. Hashim, Ali Al-Shuwaili, Asraa Saeed, Ali Al-Bayaty
Published: 2026-01-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.08332v1

Generative Adversarial Networks (GANs) face a significant challenge of striking an optimal balance between high-quality image generation and training stability. Recent techniques, such as DCGAN, BigGAN, and StyleGAN, improve visual fidelity; however, such techniques usually struggle with mode collapse and unstable gradients at high network depth. This paper proposes a novel GAN structural model that incorporates deeper inception-inspired convolution and dilated convolution. This novel model is termed the Inception Generative Adversarial Network (IGAN). The IGAN model generates high-quality synthetic images while maintaining training stability, by reducing mode collapse as well as preventing vanishing and exploding gradients. Our proposed IGAN model achieves the Frechet Inception Distance (FID) of 13.12 and 15.08 on the CUB-200 and ImageNet datasets, respectively, representing a 28-33% improvement in FID over the state-of-the-art GANs. Additionally, the IGAN model attains an Inception Score (IS) of 9.27 and 68.25, reflecting improved image diversity and generation quality. Finally, the two techniques of dropout and spectral normalization are utilized in both the generator and discriminator structures to further mitigate gradient explosion and overfitting. These findings confirm that the IGAN model potentially balances training stability with image generation quality, constituting a scalable and computationally efficient framework for high-fidelity image synthesis.

---

### CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark

Authors: Daniil Gurgurov, Yusser Al Ghussin, Tanja Baeumel, Cheng-Ting Chou, Patrick Schramowski, Marius Mosbach, Josef van Genabith, Simon Ostermann
Published: 2026-01-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.08331v1

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged as a more efficient and interpretable technique for adapting models to a target language. Yet, no dedicated benchmarks or evaluation protocols exist to quantify the effectiveness of steering techniques. We introduce CLaS-Bench, a lightweight parallel-question benchmark for evaluating language-forcing behavior in LLMs across 32 languages, enabling systematic evaluation of multilingual steering methods. We evaluate a broad array of steering techniques, including residual-stream DiffMean interventions, probe-derived directions, language-specific neurons, PCA/LDA vectors, Sparse Autoencoders, and prompting baselines. Steering performance is measured along two axes: language control and semantic relevance, combined into a single harmonic-mean steering score. We find that across languages simple residual-based DiffMean method consistently outperforms all other methods. Moreover, a layer-wise analysis reveals that language-specific structure emerges predominantly in later layers and steering directions cluster based on language family. CLaS-Bench is the first standardized benchmark for multilingual steering, enabling both rigorous scientific analysis of language representations and practical evaluation of steering as a low-cost adaptation alternative.

---

### Safe Heterogeneous Multi-Agent RL with Communication Regularization for Coordinated Target Acquisition

Authors: Gabriele Calzolari, Vidya Sumathy, Christoforos Kanellakis, George Nikolakopoulos
Published: 2026-01-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.08327v1

This paper introduces a decentralized multi-agent reinforcement learning framework enabling structurally heterogeneous teams of agents to jointly discover and acquire randomly located targets in environments characterized by partial observability, communication constraints, and dynamic interactions. Each agent's policy is trained with the Multi-Agent Proximal Policy Optimization algorithm and employs a Graph Attention Network encoder that integrates simulated range-sensing data with communication embeddings exchanged among neighboring agents, enabling context-aware decision-making from both local sensing and relational information. In particular, this work introduces a unified framework that integrates graph-based communication and trajectory-aware safety through safety filters. The architecture is supported by a structured reward formulation designed to encourage effective target discovery and acquisition, collision avoidance, and de-correlation between the agents' communication vectors by promoting informational orthogonality. The effectiveness of the proposed reward function is demonstrated through a comprehensive ablation study. Moreover, simulation results demonstrate safe and stable task execution, confirming the framework's effectiveness.

---

### AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation

Authors: Yupeng Huo, Yaxi Lu, Zhong Zhang, Haotian Chen, Yankai Lin
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08323v3

Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existing agent memory mechanisms rely on static and hand-crafted workflows. This limits the performance and generalization ability of these memory designs, which highlights the need for a more flexible, learning-based memory framework. In this paper, we propose AtomMem, which reframes memory management as a dynamic decision-making problem. We deconstruct high-level memory processes into fundamental atomic CRUD (Create, Read, Update, Delete) operations, transforming the memory workflow into a learnable decision process. By combining supervised fine-tuning with reinforcement learning, AtomMem learns an autonomous, task-aligned policy to orchestrate memory behaviors tailored to specific task demands. Experimental results across 3 long-context benchmarks demonstrate that the trained AtomMem-8B consistently outperforms prior static-workflow memory methods. Further analysis of training dynamics shows that our learning-based formulation enables the agent to discover structured, task-aligned memory management strategies, highlighting a key advantage over predefined routines.

---

### UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing

Authors: Lichen Ma, Xiaolong Fu, Gaojing Zhou, Zipeng Guo, Ting Zhu, Yichun Liu, Yu Shi, Jason Li, Junshi Huang
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08321v3

With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus generate visual text that is style-consistent with the image. Previous methods often involve complex steps of specifying the text content and attributes, such as font size, color, and layout, without considering the stylistic consistency with the reference image. To address this, we propose UM-Text, a unified multimodal model for context understanding and visual text editing by natural language instructions. Specifically, we introduce a Visual Language Model (VLM) to process the instruction and reference image, so that the text content and layout can be elaborately designed according to the context information. To generate an accurate and harmonious visual text image, we further propose the UM-Encoder to combine the embeddings of various condition information, where the combination is automatically configured by VLM according to the input instruction. During training, we propose a regional consistency loss to offer more effective supervision for glyph generation on both latent and RGB space, and design a tailored three-stage training strategy to further enhance model performance. In addition, we contribute the UM-DATA-200K, a large-scale visual text image dataset on diverse scenes for model training. Extensive qualitative and quantitative results on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance.

---

### YOLOBirDrone: Dataset for Bird vs Drone Detection and Classification and a YOLO based enhanced learning architecture

Authors: Dapinder Kaur, Neeraj Battish, Arnav Bhavsar, Shashi Poddar
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08319v1

The use of aerial drones for commercial and defense applications has benefited in many ways and is therefore utilized in several different application domains. However, they are also increasingly used for targeted attacks, posing a significant safety challenge and necessitating the development of drone detection systems. Vision-based drone detection systems currently have an accuracy limitation and struggle to distinguish between drones and birds, particularly when the birds are small in size. This research work proposes a novel YOLOBirDrone architecture that improves the detection and classification accuracy of birds and drones. YOLOBirDrone has different components, including an adaptive and extended layer aggregation (AELAN), a multi-scale progressive dual attention module (MPDA), and a reverse MPDA (RMPDA) to preserve shape information and enrich features with local and global spatial and channel information. A large-scale dataset, BirDrone, is also introduced in this article, which includes small and challenging objects for robust aerial object identification. Experimental results demonstrate an improvement in performance metrics through the proposed YOLOBirDrone architecture compared to other state-of-the-art algorithms, with detection accuracy reaching approximately 85% across various scenarios.

---

### Disentangling History and Propagation Dependencies in Cross-Subject Knee Contact Stress Prediction Using a Shared MeshGraphNet Backbone

Authors: Zhengye Pan, Jianwei Zuo, Jiajia Luo
Published: 2026-01-13
Categories: q-bio.QM, cs.LG
arXiv: https://arxiv.org/abs/2601.08318v1

Background:Subject-specific finite element analysis accurately characterizes knee joint mechanics but is computationally expensive. Deep surrogate models provide a rapid alternative, yet their generalization across subjects under limited pose and load inputs remains unclear. It remains unclear whether the dominant source of prediction uncertainty arises from temporal history dependence or spatial propagation dependence. Methods:To disentangle these factors, we employed a shared MGN backbone with a fixed mesh topology. A dataset of running trials from nine subjects was constructed using an OpenSim-FEBio workflow. We developed four model variants to isolate specific dependencies: (1) a baseline MGN; (2) CT-MGN, incorporating a Control Transformer to encode short-horizon history; (3) MsgModMGN, applying state-conditioned modulation to message passing for adaptive propagation; (4) CT-MsgModMGN, combining both mechanisms. Models were evaluated using a rigorous grouped 3-fold cross-validation on unseen subjects.Results:The models incorporating history encoding significantly outperformed the baseline MGN and MsgModMGN in global accuracy and spatial consistency. Crucially, the CT module effectively mitigated the peak-shaving defect common in deep surrogates, significantly reducing peak stress prediction errors. In contrast, the spatial propagation modulation alone yielded no significant improvement over the baseline, and combining it with CT provided no additional benefit.Conclusion:Temporal history dependence, rather than spatial propagation modulation, is the primary driver of prediction uncertainty in cross-subject knee contact mechanics. Explicitly encoding short-horizon driver sequences enables the surrogate model to recover implicit phase information, thereby achieving superior fidelity in peak-stress capture and high-risk localization compared to purely state-based approaches.

---

### Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting

Authors: Tomoki Kubo, Ryuken Uda, Yusuke Iida
Published: 2026-01-13
Categories: cs.LG, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2601.08316v1

Deep double descent is one of the key phenomena underlying the generalization capability of deep learning models. In this study, epoch-wise double descent, which is delayed generalization following overfitting, was empirically investigated by focusing on the evolution of internal structures. Fully connected neural networks of three different sizes were trained on the CIFAR-10 dataset with 30% label noise. By decomposing the loss curves into signal contributions from clean and noisy training data, the epoch-wise evolutions of internal signals were analyzed separately. Three main findings were obtained from this analysis. First, the model achieved strong re-generalization on test data even after perfectly fitting noisy training data during the double descent phase, corresponding to a "benign overfitting" state. Second, noisy data were learned after clean data, and as learning progressed, their corresponding internal activations became increasingly separated in outer layers; this enabled the model to overfit only noisy data. Third, a single, very large activation emerged in the shallow layer across all models; this phenomenon is referred as "outliers," "massive activa-tions," and "super activations" in recent large language models and evolves with re-generalization. The magnitude of large activation correlated with input patterns but not with output patterns. These empirical findings directly link the recent key phenomena of "deep double descent," "benign overfitting," and "large activation", and support the proposal of a novel scenario for understanding deep double descent.

---

### Enhancing Image Quality Assessment Ability of LMMs via Retrieval-Augmented Generation

Authors: Kang Fu, Huiyu Duan, Zicheng Zhang, Yucheng Zhu, Jun Zhao, Xiongkuo Min, Jia Wang, Guangtao Zhai
Published: 2026-01-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.08311v1

Large Multimodal Models (LMMs) have recently shown remarkable promise in low-level visual perception tasks, particularly in Image Quality Assessment (IQA), demonstrating strong zero-shot capability. However, achieving state-of-the-art performance often requires computationally expensive fine-tuning methods, which aim to align the distribution of quality-related token in output with image quality levels. Inspired by recent training-free works for LMM, we introduce IQARAG, a novel, training-free framework that enhances LMMs' IQA ability. IQARAG leverages Retrieval-Augmented Generation (RAG) to retrieve some semantically similar but quality-variant reference images with corresponding Mean Opinion Scores (MOSs) for input image. These retrieved images and input image are integrated into a specific prompt. Retrieved images provide the LMM with a visual perception anchor for IQA task. IQARAG contains three key phases: Retrieval Feature Extraction, Image Retrieval, and Integration & Quality Score Generation. Extensive experiments across multiple diverse IQA datasets, including KADID, KonIQ, LIVE Challenge, and SPAQ, demonstrate that the proposed IQARAG effectively boosts the IQA performance of LMMs, offering a resource-efficient alternative to fine-tuning for quality assessment.

---

### ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning

Authors: Kun Liang, Clive Bai, Xin Xu, Chenming Tang, Sanwoo Lee, Weijie Liu, Saiyong Yang, Yunfang Wu
Published: 2026-01-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.08310v2

Recent Large Reasoning Models (LRMs) achieve strong performance by leveraging long-form Chain-of-Thought (CoT) reasoning, but uniformly applying overlong reasoning at inference time incurs substantial and often unnecessary computational cost. To address this, prior work explores various strategies to infer an appropriate reasoning budget from the input. However, such approaches are unreliable in the worst case, as estimating the minimal required reasoning effort is fundamentally difficult, and they implicitly fix the trade-off between reasoning cost and accuracy during training, limiting flexibility under varying deployment scenarios. Motivated by these limitations, we propose ORBIT, a controllable multi-budget reasoning framework with well-separated reasoning modes triggered by input. ORBIT employs multi-stage reinforcement learning to discover Pareto-optimal reasoning behaviors at each effort, followed by on-policy distillation to fuse these behaviors into a single unified model. Experiments show that ORBIT achieves (1) controllable reasoning behavior over multiple modes, (2) competitive reasoning density within each mode, and (3) integration of these frontier policies into a single unified student model while preserving clear mode separation and high per-mode performance.

---

### AgriAgent: Contract-Driven Planning and Capability-Aware Tool Orchestration in Real-World Agriculture

Authors: Bo Yang, Yu Zhang, Yunkui Chen, Lanfei Feng, Xiao Xu, Nueraili Aierken, Shijian Li
Published: 2026-01-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.08308v1

Intelligent agent systems in real-world agricultural scenarios must handle diverse tasks under multimodal inputs, ranging from lightweight information understanding to complex multi-step execution. However, most existing approaches rely on a unified execution paradigm, which struggles to accommodate large variations in task complexity and incomplete tool availability commonly observed in agricultural environments. To address this challenge, we propose AgriAgent, a two-level agent framework for real-world agriculture. AgriAgent adopts a hierarchical execution strategy based on task complexity: simple tasks are handled through direct reasoning by modality-specific agents, while complex tasks trigger a contract-driven planning mechanism that formulates tasks as capability requirements and performs capability-aware tool orchestration and dynamic tool generation, enabling multi-step and verifiable execution with failure recovery. Experimental results show that AgriAgent achieves higher execution success rates and robustness on complex tasks compared to existing tool-centric agent baselines that rely on unified execution paradigms. All code, data will be released at after our work be accepted to promote reproducible research.

---

### SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

Authors: Dongting Hu, Aarush Gupta, Magzhan Gabidolla, Arpit Sahni, Huseyin Coskun, Yanyu Li, Yerlan Idelbayev, Ahsan Mahmood, Aleksei Lebedev, Dishani Lahiri, Anujraaj Goyal, Ju Hu et al.
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08303v3

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT framework tailored for mobile and edge devices that achieves transformer-level generation quality under strict resource constraints. Our design combines three key components. First, we propose a compact DiT architecture with an adaptive global-local sparse attention mechanism that balances global context modeling and local detail preservation. Second, we propose an elastic training framework that jointly optimizes sub-DiTs of varying capacities within a unified supernetwork, allowing a single model to dynamically adjust for efficient inference across different hardware. Finally, we develop Knowledge-Guided Distribution Matching Distillation, a step-distillation pipeline that integrates the DMD objective with knowledge transfer from few-step teacher models, producing high-fidelity and low-latency generation (e.g., 4-step) suitable for real-time on-device use. Together, these contributions enable scalable, efficient, and high-quality diffusion models for deployment on diverse hardware.

---

### Enhancing Sentiment Classification and Irony Detection in Large Language Models through Advanced Prompt Engineering Techniques

Authors: Marvin Schmitt, Anne Schwerk, Sebastian Lempert
Published: 2026-01-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.08302v1

This study investigates the use of prompt engineering to enhance large language models (LLMs), specifically GPT-4o-mini and gemini-1.5-flash, in sentiment analysis tasks. It evaluates advanced prompting techniques like few-shot learning, chain-of-thought prompting, and self-consistency against a baseline. Key tasks include sentiment classification, aspect-based sentiment analysis, and detecting subtle nuances such as irony. The research details the theoretical background, datasets, and methods used, assessing performance of LLMs as measured by accuracy, recall, precision, and F1 score. Findings reveal that advanced prompting significantly improves sentiment analysis, with the few-shot approach excelling in GPT-4o-mini and chain-of-thought prompting boosting irony detection in gemini-1.5-flash by up to 46%. Thus, while advanced prompting techniques overall improve performance, the fact that few-shot prompting works best for GPT-4o-mini and chain-of-thought excels in gemini-1.5-flash for irony detection suggests that prompting strategies must be tailored to both the model and the task. This highlights the importance of aligning prompt design with both the LLM's architecture and the semantic complexity of the task.

---

### ReCo-KD: Region- and Context-Aware Knowledge Distillation for Efficient 3D Medical Image Segmentation

Authors: Qizhen Lan, Yu-Chun Hsu, Nida Saddaf Khan, Xiaoqian Jiang
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08301v1

Accurate 3D medical image segmentation is vital for diagnosis and treatment planning, but state-of-the-art models are often too large for clinics with limited computing resources. Lightweight architectures typically suffer significant performance loss. To address these deployment and speed constraints, we propose Region- and Context-aware Knowledge Distillation (ReCo-KD), a training-only framework that transfers both fine-grained anatomical detail and long-range contextual information from a high-capacity teacher to a compact student network. The framework integrates Multi-Scale Structure-Aware Region Distillation (MS-SARD), which applies class-aware masks and scale-normalized weighting to emphasize small but clinically important regions, and Multi-Scale Context Alignment (MS-CA), which aligns teacher-student affinity patterns across feature levels. Implemented on nnU-Net in a backbone-agnostic manner, ReCo-KD requires no custom student design and is easily adapted to other architectures. Experiments on multiple public 3D medical segmentation datasets and a challenging aggregated dataset show that the distilled lightweight model attains accuracy close to the teacher while markedly reducing parameters and inference latency, underscoring its practicality for clinical deployment.

---

### Demystifying the Slash Pattern in Attention: The Role of RoPE

Authors: Yuan Cheng, Fengzhuo Zhang, Yunlong Hou, Cunxiao Du, Chao Du, Tianyu Pang, Aixin Sun, Zhuoran Yang
Published: 2026-01-13
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.08297v2

Large Language Models (LLMs) often exhibit slash attention patterns, where attention scores concentrate along the $Δ$-th sub-diagonal for some offset $Δ$. These patterns play a key role in passing information across tokens. But why do they emerge? In this paper, we demystify the emergence of these Slash-Dominant Heads (SDHs) from both empirical and theoretical perspectives. First, by analyzing open-source LLMs, we find that SDHs are intrinsic to models and generalize to out-of-distribution prompts. To explain the intrinsic emergence, we analyze the queries, keys, and Rotary Position Embedding (RoPE), which jointly determine attention scores. Our empirical analysis reveals two characteristic conditions of SDHs: (1) Queries and keys are almost rank-one, and (2) RoPE is dominated by medium- and high-frequency components. Under these conditions, queries and keys are nearly identical across tokens, and interactions between medium- and high-frequency components of RoPE give rise to SDHs. Beyond empirical evidence, we theoretically show that these conditions are sufficient to ensure the emergence of SDHs by formalizing them as our modeling assumptions. Particularly, we analyze the training dynamics of a shallow Transformer equipped with RoPE under these conditions, and prove that models trained via gradient descent exhibit SDHs. The SDHs generalize to out-of-distribution prompts.

---

### M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstruction

Authors: Yuze Zhang, Lingjie Li, Qiuzhen Lin, Zhong Ming, Fei Yu, Victor C. M. Leung
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08293v1

The Mamba architecture has been widely applied to various low-level vision tasks due to its exceptional adaptability and strong performance. Although the Mamba architecture has been adopted for spectral reconstruction, it still faces the following two challenges: (1) Single spatial perception limits the ability to fully understand and analyze hyperspectral images; (2) Single-scale feature extraction struggles to capture the complex structures and fine details present in hyperspectral images. To address these issues, we propose a multi-scale, multi-perceptual Mamba architecture for the spectral reconstruction task, called M3SR. Specifically, we design a multi-perceptual fusion block to enhance the ability of the model to comprehensively understand and analyze the input features. By integrating the multi-perceptual fusion block into a U-Net structure, M3SR can effectively extract and fuse global, intermediate, and local features, thereby enabling accurate reconstruction of hyperspectral images at multiple scales. Extensive quantitative and qualitative experiments demonstrate that the proposed M3SR outperforms existing state-of-the-art methods while incurring a lower computational cost.

---

### KidVis: Do Multimodal Large Language Models Possess the Visual Perceptual Capabilities of a 6-Year-Old?

Authors: Xianfeng Wang, Kaiwei Zhang, Qi Jia, Zijian Chen, Guangtao Zhai, Xiongkuo Min
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08292v1

While Multimodal Large Language Models (MLLMs) have demonstrated impressive proficiency in high-level reasoning tasks, such as complex diagrammatic interpretation, it remains an open question whether they possess the fundamental visual primitives comparable to human intuition. To investigate this, we introduce KidVis, a novel benchmark grounded in the theory of human visual development. KidVis deconstructs visual intelligence into six atomic capabilities - Concentration, Tracking, Discrimination, Memory, Spatial, and Closure - already possessed by 6-7 year old children, comprising 10 categories of low-semantic-dependent visual tasks. Evaluating 20 state-of-the-art MLLMs against a human physiological baseline reveals a stark performance disparity. Results indicate that while human children achieve a near-perfect average score of 95.32, the state-of-the-art GPT-5 attains only 67.33. Crucially, we observe a "Scaling Law Paradox": simply increasing model parameters fails to yield linear improvements in these foundational visual capabilities. This study confirms that current MLLMs, despite their reasoning prowess, lack the essential physiological perceptual primitives required for generalized visual intelligence.

---

### OpenMic: A Multi-Agent-Based Stand-Up Comedy Generation System

Authors: Yuyang Wu, Hanzhong Cao, Jianhao Chen, Yufei Li
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08288v1

Chinese stand-up comedy generation goes beyond plain text generation, requiring culturally grounded humor, precise timing, stage-performance cues, and implicit multi-step reasoning. Moreover, commonly used Chinese humor datasets are often better suited for humor understanding and evaluation than for long-form stand-up generation, making direct supervision misaligned with the target task. To address these challenges, we present OpenMic, an end-to-end multi-agent system built on AutoGen that transforms a user-provided life topic into a 3-5 minute Chinese stand-up performance and further produces a narrated comedy video. OpenMic orchestrates multiple specialized agents in a multi-round iterative loop-planning to jointly optimize humor, timing, and performability. To mitigate the dataset-task mismatch, we augment generation with retrieval-augmented generation (RAG) for material grounding and idea expansion, and we fine-tune a dedicated JokeWriter to better internalize stand-up-specific setup-punchline structures and long-range callbacks.

---

### AgriLens: Semantic Retrieval in Agricultural Texts Using Topic Modeling and Language Models

Authors: Heba Shakeel, Tanvir Ahmad, Tanya Liyaqat, Chandni Saxena
Published: 2026-01-13
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2601.08283v1

As the volume of unstructured text continues to grow across domains, there is an urgent need for scalable methods that enable interpretable organization, summarization, and retrieval of information. This work presents a unified framework for interpretable topic modeling, zero-shot topic labeling, and topic-guided semantic retrieval over large agricultural text corpora. Leveraging BERTopic, we extract semantically coherent topics. Each topic is converted into a structured prompt, enabling a language model to generate meaningful topic labels and summaries in a zero-shot manner. Querying and document exploration are supported via dense embeddings and vector search, while a dedicated evaluation module assesses topical coherence and bias. This framework supports scalable and interpretable information access in specialized domains where labeled data is limited.

---

### D$^2$Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning

Authors: Kangcheng Luo, Tinglang Wu, Yansong Feng
Published: 2026-01-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.08282v1

Recent search-augmented LLMs trained with reinforcement learning (RL) can interleave searching and reasoning for multi-hop reasoning tasks. However, they face two critical failure modes as the accumulating context becomes flooded with both crucial evidence and irrelevant information: (1) ineffective search chain construction that produces incorrect queries or omits retrieval of critical information, and (2) reasoning hijacking by peripheral evidence that causes models to misidentify distractors as valid evidence. To address these challenges, we propose **D$^2$Plan**, a **D**ual-agent **D**ynamic global **Plan**ning paradigm for complex retrieval-augmented reasoning. **D$^2$Plan** operates through the collaboration of a *Reasoner* and a *Purifier*: the *Reasoner* constructs explicit global plans during reasoning and dynamically adapts them based on retrieval feedback; the *Purifier* assesses retrieval relevance and condenses key information for the *Reasoner*. We further introduce a two-stage training framework consisting of supervised fine-tuning (SFT) cold-start on synthesized trajectories and RL with plan-oriented rewards to teach LLMs to master the **D$^2$Plan** paradigm. Extensive experiments demonstrate that **D$^2$Plan** enables more coherent multi-step reasoning and stronger resilience to irrelevant information, thereby achieving superior performance on challenging QA benchmarks.

---

### Greedy Is Enough: Sparse Action Discovery in Agentic LLMs

Authors: Angshul Majumdar
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08280v1

Modern agentic systems operate in environments with extremely large action spaces, such as tool-augmented language models with thousands of available APIs or retrieval operations. Despite this scale, empirical evidence suggests that only a small subset of actions meaningfully influences performance in a given deployment. Motivated by this observation, we study a contextual linear reward model in which action relevance is governed by a structured sparsity assumption: only a small number of actions have nonzero effects across latent states. We formulate action discovery as a block-sparse recovery problem and analyze a greedy algorithm inspired by Orthogonal Matching Pursuit. Under standard assumptions on incoherence, signal strength, and action coverage, we prove that the greedy procedure exactly recovers the relevant action set with high probability, using a number of samples that scales polynomially in the sparsity level and latent dimension, and only logarithmically in the total number of actions. We further provide estimation error guarantees for refitted parameters and show that the resulting decision rule is near-optimal for new latent states. Complementing these results, we establish information-theoretic lower bounds demonstrating that sparsity and sufficient coverage are necessary for tractability. Together, our results identify sparse action discovery as a fundamental principle underlying large-action decision-making and provide a theoretical foundation for action pruning in agentic systems.

---

### One-Shot Identification with Different Neural Network Approaches

Authors: Janis Mohr, Jörg Frochte
Published: 2026-01-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.08278v1

Convolutional neural networks (CNNs) have been widely used in the computer vision community, significantly improving the state-of-the-art. But learning good features often is computationally expensive in machine learning settings and is especially difficult when there is a lack of data. One-shot learning is one such area where only limited data is available. In one-shot learning, predictions have to be made after seeing only one example from one class, which requires special techniques. In this paper we explore different approaches to one-shot identification tasks in different domains including an industrial application and face recognition. We use a special technique with stacked images and use siamese capsule networks. It is encouraging to see that the approach using capsule architecture achieves strong results and exceeds other techniques on a wide range of datasets from industrial application to face recognition benchmarks while being easy to use and optimise.

---

### ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web

Authors: Zhiyuan Yao, Zishan Xu, Yifu Guo, Zhiguang Han, Cheng Yang, Shuo Zhang, Weinan Zhang, Xingshan Zeng, Weiwen Liu
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08276v2

With the rise of the Agent Web and Model Context Protocol (MCP), the agent ecosystem is evolving into an open collaborative network, exponentially increasing accessible tools. However, current architectures face severe scalability and generality bottlenecks. To address this, we propose ACE-Router, a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems. By leveraging a dependency-rich candidate Graph to synthesize multi-turn trajectories, we effectively train routers with dynamic context understanding to create the plug-and-play Light Routing Agent. Experiments on the real-world benchmarks MCP-Universe and MCP-Mark demonstrate superior performance. Notably, ACE-Router exhibits critical properties for the future Agent Web: it not only generalizes to multi-agent collaboration with minimal adaptation but also maintains exceptional robustness against noise and scales effectively to massive candidate spaces. These findings provide a strong empirical foundation for universal orchestration in open-ended ecosystems.

---

### Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees

Authors: Kun Li, Zenan Xu, Junan Li, Zengrui Jin, Jinghao Deng, Zexuan Qiu, Bo Zhou
Published: 2026-01-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.08274v2

Tool-Integrated Reasoning has emerged as a key paradigm to augment Large Language Models (LLMs) with computational capabilities, yet integrating tool-use into long Chain-of-Thought (long CoT) remains underexplored, largely due to the scarcity of training data and the challenge of integrating tool-use without compromising the model's intrinsic long-chain reasoning. In this paper, we introduce DART (Discovery And Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees), a reinforcement learning framework that enables spontaneous tool-use during long CoT reasoning without human annotation. DART operates by constructing dynamic rollout trees during training to discover valid tool-use opportunities, branching out at promising positions to explore diverse tool-integrated trajectories. Subsequently, a tree-based process advantage estimation identifies and credits specific sub-trajectories where tool invocation positively contributes to the solution, effectively reinforcing these beneficial behaviors. Extensive experiments on challenging benchmarks like AIME and GPQA-Diamond demonstrate that DART significantly outperforms existing methods, successfully harmonizing tool execution with long CoT reasoning.

---

### HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding

Authors: Qitan Lv, Tianyu Liu, Wen Wu, Xuenan Xu, Bowen Zhou, Feng Wu, Chao Zhang
Published: 2026-01-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.08273v1

Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily focus on pruning redundant visual tokens to mitigate the computational burden of massive visual inputs. However, existing methods do not achieve inference acceleration comparable to text-only LLMs. We observe from extensive experiments that this phenomenon mainly stems from two limitations: (i) their pruning strategies inadequately preserve visual semantic tokens, degrading draft quality and acceptance rates; (ii) even with aggressive pruning (e.g., 90% visual tokens removed), the draft model's remaining inference cost limits overall speedup. To address these limitations, we propose HIPPO, a general holistic-aware parallel speculative decoding framework. Specifically, HIPPO proposes (i) a semantic-aware token preservation method, which fuses global attention scores with local visual semantics to retain semantic information at high pruning ratios; (ii) a video parallel SD algorithm that decouples and overlaps draft generation and target verification phases. Experiments on four video-LLMs across six benchmarks demonstrate HIPPO's effectiveness, yielding up to 3.51x speedup compared to vanilla auto-regressive decoding.

---

### Sparsity Is Necessary: Polynomial-Time Stability for Agentic LLMs in Large Action Spaces

Authors: Angshul Majumdar
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08271v1

Tool-augmented LLM systems expose a control regime that learning theory has largely ignored: sequential decision-making with a massive discrete action universe (tools, APIs, documents) in which only a small, unknown subset is relevant for any fixed task distribution. We formalize this setting as Sparse Agentic Control (SAC), where policies admit block-sparse representations over M >> 1 actions and rewards depend on sparse main effects and (optionally) sparse synergies. We study ell_{1,2}-regularized policy learning through a convex surrogate and establish sharp, compressed-sensing-style results: (i) estimation and value suboptimality scale as k (log M / T)^{1/2} under a Policy-RSC condition; (ii) exact tool-support recovery holds via primal-dual witness arguments when T > k log M under incoherence and beta-min; and (iii) any dense policy class requires Omega(M) samples, explaining the instability of prompt-only controllers. We further show that under partial observability, LLMs matter only through a belief/representation error epsilon_b, yielding an additive O(epsilon_b) degradation while preserving logarithmic dependence on M. Extensions cover tuning-free, online, robust, group-sparse, and interaction-aware SAC.

---

### Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning

Authors: Fan Gao, Sherry T. Tong, Jiwoong Sohn, Jiahao Huang, Junfeng Jiang, Ding Xia, Piyalitt Ittichaiwong, Kanyakorn Veerakanjana, Hyunjae Kim, Qingyu Chen, Edison Marrese Taylor, Kazuma Kobayashi et al.
Published: 2026-01-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.08267v3

While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially weaker reasoning in local languages, limiting equitable global medical deployment. To bridge this gap, we introduce Med-CoReasoner, a language-informed co-reasoning framework that elicits parallel English and local-language reasoning, abstracts them into structured concepts, and integrates local clinical knowledge into an English logical scaffold via concept-level alignment and retrieval. This design combines the structural robustness of English reasoning with the practice-grounded expertise encoded in local languages. To evaluate multilingual medical reasoning beyond multiple-choice settings, we construct MultiMed-X, a benchmark covering seven languages with expert-annotated long-form question answering and natural language inference tasks, comprising 350 instances per language. Experiments across three benchmarks show that Med-CoReasoner improves multilingual reasoning performance by an average of 5%, with particularly substantial gains in low-resource languages. Moreover, model distillation and expert evaluation analysis further confirm that Med-CoReasoner produces clinically sound and culturally grounded reasoning traces.

---

### AIMC-Spec: A Benchmark Dataset for Automatic Intrapulse Modulation Classification under Variable Noise Conditions

Authors: Sebastian L. Cocks, Salvador Dreo, Brian Ng, Feras Dayoub
Published: 2026-01-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.08265v2

A lack of standardized datasets has long hindered progress in automatic intrapulse modulation classification (AIMC), a critical task in radar signal analysis for electronic support systems, particularly under noisy or degraded conditions. AIMC seeks to identify the modulation type embedded within a single radar pulse from its complex in-phase and quadrature (I/Q) representation, enabling automated interpretation of intrapulse structure. This paper introduces AIMC-Spec, a comprehensive synthetic dataset for spectrogram-based image classification, encompassing 30 modulation types across 5 signal-to-noise ratio (SNR) levels. To benchmark AIMC-Spec, five representative deep learning algorithms ranging from lightweight CNNs and denoising architectures to transformer-based networks were re-implemented and evaluated under a unified input format. The results reveal significant performance variation, with frequency-modulated (FM) signals classified more reliably than phase-modulated (PM) types, particularly at low SNRs. A focused FM-only test further highlights how modulation type and network architecture influence classifier robustness. AIMC-Spec establishes a reproducible baseline and provides a foundation for future research and standardization in the AIMC domain.

---

### VGG Induced Deep Hand Sign Language Detection

Authors: Subham Sharma, Sharmila Subudhi
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08262v1

Hand gesture recognition is an important aspect of human-computer interaction. It forms the basis of sign language for the visually impaired people. This work proposes a novel hand gesture recognizing system for the differently-abled persons. The model uses a convolutional neural network, known as VGG-16 net, for building a trained model on a widely used image dataset by employing Python and Keras libraries. Furthermore, the result is validated by the NUS dataset, consisting of 10 classes of hand gestures, fed to the model as the validation set. Afterwards, a testing dataset of 10 classes is built by employing Google's open source Application Programming Interface (API) that captures different gestures of human hand and the efficacy is then measured by carrying out experiments. The experimental results show that by combining a transfer learning mechanism together with the image data augmentation, the VGG-16 net produced around 98% accuracy.

---

### A Usable GAN-Based Tool for Synthetic ECG Generation in Cardiac Amyloidosis Research

Authors: Francesco Speziale, Ugo Lomoio, Fabiola Boccuto, Pierangelo Veltri, Pietro Hiram Guzzi
Published: 2026-01-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.08260v1

Cardiac amyloidosis (CA) is a rare and underdiagnosed infiltrative cardiomyopathy, and available datasets for machine-learning models are typically small, imbalanced and heterogeneous. This paper presents a Generative Adversarial Network (GAN) and a graphical command-line interface for generating realistic synthetic electrocardiogram (ECG) beats to support early diagnosis and patient stratification in CA. The tool is designed for usability, allowing clinical researchers to train class-specific generators once and then interactively produce large volumes of labelled synthetic beats that preserve the distribution of minority classes.

---

### Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment

Authors: Edward Y. Chang
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08258v3

Large language models increasingly fail in a way that scalar accuracy cannot diagnose: they produce a sound reasoning trace and then abandon it under social pressure or an authoritative hint. We argue that this is a control failure, not a knowledge failure, and that it requires an evaluation surface richer than a single accuracy number. We introduce CAUSALT3, a 454 instance expert curated benchmark for causal reasoning across all three rungs of Pearl's ladder, and a three axis evaluation that decomposes performance into Utility (sensitivity to valid causal claims), Safety (specificity against invalid ones), and Wise Refusal (calibrated abstention on genuinely underdetermined items). On this surface we document three reproducible pathologies: a Skepticism Trap at L1 where capable models over refuse sound links, a Sycophancy Trap at L2 where confident user pressure flips correct answers, and a Scaling Paradox at L3 where a frontier model underperforms an older one on counterfactual Safety by 55 points. To mitigate these failures without retraining, we propose Regulated Causal Anchoring (RCA), an inference time process verifier that audits trace output consistency under a PID style feedback loop and abstains rather than ratifying a detected mismatch. Across CAUSALT3 and a supporting CAP-GSM8K stress test, RCA reduces sycophantic acceptance to near zero while preserving valid hint acceptance, recasting trustworthy reasoning as a question of inference time control rather than scale.

---

### On Evaluation of Unsupervised Feature Selection for Pattern Classification

Authors: Gyu-Il Kim, Dae-Won Kim, Jaesung Lee
Published: 2026-01-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.08257v3

Unsupervised feature selection aims to identify a compact subset of features that captures the intrinsic structure of data without supervised label. Most existing studies evaluate the performance of methods using the single-label dataset that can be instantiated by selecting a label from multi-label data while maintaining the original features. Because the chosen label can vary arbitrarily depending on the experimental setting, the superiority among compared methods can be changed with regard to which label happens to be selected. Thus, evaluating unsupervised feature selection methods based solely on single-label accuracy is unreasonable for assessing their true discriminative ability. This study revisits this evaluation paradigm by adopting a multi-label classification framework. Experiments on 21 multi-label datasets using several representative methods demonstrate that performance rankings differ markedly from those reported under single-label settings, suggesting the possibility of multi-label evaluation settings for fair and reliable comparison of unsupervised feature selection methods.

---

### Large Artificial Intelligence Model Guided Deep Reinforcement Learning for Resource Allocation in Non Terrestrial Networks

Authors: Abdikarim Mohamed Ibrahim, Rosdiadee Nordin
Published: 2026-01-13
Categories: cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2601.08254v1

Large AI Model (LAM) have been proposed to applications of Non-Terrestrial Networks (NTN), that offer better performance with its great generalization and reduced task specific trainings. In this paper, we propose a Deep Reinforcement Learning (DRL) agent that is guided by a Large Language Model (LLM). The LLM operates as a high level coordinator that generates textual guidance that shape the reward of the DRL agent during training. The results show that the LAM-DRL outperforms the traditional DRL by 40% in nominal weather scenarios and 64% in extreme weather scenarios compared to heuristics in terms of throughput, fairness, and outage probability.

---

### LDLT L-Lipschitz Network Weight Parameterization Initialization

Authors: Marius F. R. Juston, Ramavarapu S. Sreenivas, Dustin Nottage, Ahmet Soylemezoglu
Published: 2026-01-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.08253v1

We analyze initialization dynamics for LDLT-based $\mathcal{L}$-Lipschitz layers by deriving the exact marginal output variance when the underlying parameter matrix $W_0\in \mathbb{R}^{m\times n}$ is initialized with IID Gaussian entries $\mathcal{N}(0,σ^2)$. The Wishart distribution, $S=W_0W_0^\top\sim\mathcal{W}_m(n,σ^2 \boldsymbol{I}_m)$, used for computing the output marginal variance is derived in closed form using expectations of zonal polynomials via James' theorem and a Laplace-integral expansion of $(α\boldsymbol{I}_m+S)^{-1}$. We develop an Isserlis/Wick-based combinatorial expansion for $\operatorname{\mathbb{E}}\left(\operatorname{tr}(S^k)\right)$ and provide explicit truncated moments up to $k=10$, which yield accurate series approximations for small-to-moderate $σ^2$. Monte Carlo experiments confirm the theoretical estimates. Furthermore, empirical analysis was performed to quantify that, using current He or Kaiming initialization with scaling $1/\sqrt{n}$, the output variance is $0.41$, whereas the new parameterization with $10/ \sqrt{n}$ for $α=1$ results in an output variance of $0.9$. The findings clarify why deep $\mathcal{L}$-Lipschitz networks suffer rapid information loss at initialization and offer practical prescriptions for choosing initialization hyperparameters to mitigate this effect. However, using the Higgs boson classification dataset, a hyperparameter sweep over optimizers, initialization scale, and depth was conducted to validate the results on real-world data, showing that although the derivation ensures variance preservation, empirical results indicate He initialization still performs better.

---

### Hyperbolic Heterogeneous Graph Transformer

Authors: Jongmin Park, Seunghoon Han, Hyewon Lee, Won-Yong Shin, Sungsu Lim
Published: 2026-01-13
Categories: cs.LG, cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2601.08251v1

In heterogeneous graphs, we can observe complex structures such as tree-like or hierarchical structures. Recently, the hyperbolic space has been widely adopted in many studies to effectively learn these complex structures. Although these methods have demonstrated the advantages of the hyperbolic space in learning heterogeneous graphs, most existing methods still have several challenges. They rely heavily on tangent-space operations, which often lead to mapping distortions during frequent transitions. Moreover, their message-passing architectures mainly focus on local neighborhood information, making it difficult to capture global hierarchical structures and long-range dependencies between different types of nodes. To address these limitations, we propose Hyperbolic Heterogeneous Graph Transformer (HypHGT), which effectively and efficiently learns heterogeneous graph representations entirely within the hyperbolic space. Unlike previous message-passing based hyperbolic heterogeneous GNNs, HypHGT naturally captures both local and global dependencies through transformer-based architecture. Furthermore, the proposed relation-specific hyperbolic attention mechanism in HypHGT, which operates with linear time complexity, enables efficient computation while preserving the heterogeneous information across different relation types. This design allows HypHGT to effectively capture the complex structural properties and semantic information inherent in heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness and efficiency of HypHGT, and the results demonstrate that it consistently outperforms state-of-the-art methods in node classification task, with significantly reduced training time and memory usage.

---

### Incorporating Cognitive Biases into Reinforcement Learning for Financial Decision-Making

Authors: Liu He
Published: 2026-01-13
Categories: cs.LG, econ.EM
arXiv: https://arxiv.org/abs/2601.08247v1

Financial markets are influenced by human behavior that deviates from rationality due to cognitive biases. Traditional reinforcement learning (RL) models for financial decision-making assume rational agents, potentially overlooking the impact of psychological factors. This study integrates cognitive biases into RL frameworks for financial trading, hypothesizing that such models can exhibit human-like trading behavior and achieve better risk-adjusted returns than standard RL agents. We introduce biases, such as overconfidence and loss aversion, into reward structures and decision-making processes and evaluate their performance in simulated and real-world trading environments. Despite its inconclusive or negative results, this study provides insights into the challenges of incorporating human-like biases into RL, offering valuable lessons for developing robust financial AI systems.

---

### Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence

Authors: Michele Fiori, Gabriele Civitarese, Marco Colussi, Claudio Bettini
Published: 2026-01-13
Categories: cs.CV, cs.DC
arXiv: https://arxiv.org/abs/2601.08241v1

Unobtrusive sensor-based recognition of Activities of Daily Living (ADLs) in smart homes by processing data collected from IoT sensing devices supports applications such as healthcare, safety, and energy management. Recent zero-shot methods based on Large Language Models (LLMs) have the advantage of removing the reliance on labeled ADL sensor data. However, existing approaches rely on time-based segmentation, which is poorly aligned with the contextual reasoning capabilities of LLMs. Moreover, existing approaches lack methods for estimating prediction confidence. This paper proposes to improve zero-shot ADL recognition with event-based segmentation and a novel method for estimating prediction confidence. Our experimental evaluation shows that event-based segmentation consistently outperforms time-based LLM approaches on complex, realistic datasets and surpasses supervised data-driven methods, even with relatively small LLMs (e.g., Gemma 3 27B). The proposed confidence measure effectively distinguishes correct from incorrect predictions.

---

### Temporal-Enhanced Interpretable Multi-Modal Prognosis and Risk Stratification Framework for Diabetic Retinopathy (TIMM-ProRS)

Authors: Susmita Kar, A S M Ahsanul Sarkar Akib, Abdul Hasib, Samin Yaser, Anas Bin Azim
Published: 2026-01-13
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.08240v1

Diabetic retinopathy (DR), affecting millions globally with projections indicating a significant rise, poses a severe blindness risk and strains healthcare systems. Diagnostic complexity arises from visual symptom overlap with conditions like age-related macular degeneration and hypertensive retinopathy, exacerbated by high misdiagnosis rates in underserved regions. This study introduces TIMM-ProRS, a novel deep learning framework integrating Vision Transformer (ViT), Convolutional Neural Network (CNN), and Graph Neural Network (GNN) with multi-modal fusion. TIMM-ProRS uniquely leverages both retinal images and temporal biomarkers (HbA1c, retinal thickness) to capture multi-modal and temporal dynamics. Evaluated comprehensively across diverse datasets including APTOS 2019 (trained), Messidor-2, RFMiD, EyePACS, and Messidor-1 (validated), the model achieves 97.8\% accuracy and an F1-score of 0.96, demonstrating state-of-the-art performance and outperforming existing methods like RSG-Net and DeepDR. This approach enables early, precise, and interpretable diagnosis, supporting scalable telemedical management and enhancing global eye health sustainability.

---

### The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination

Authors: Haoran Su, Yandong Sun, Congjia Yu
Published: 2026-01-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.08237v1

Reward engineering, the manual specification of reward functions to induce desired agent behavior, remains a fundamental challenge in multi-agent reinforcement learning. This difficulty is amplified by credit assignment ambiguity, environmental non-stationarity, and the combinatorial growth of interaction complexity. We argue that recent advances in large language models (LLMs) point toward a shift from hand-crafted numerical rewards to language-based objective specifications. Prior work has shown that LLMs can synthesize reward functions directly from natural language descriptions (e.g., EUREKA) and adapt reward formulations online with minimal human intervention (e.g., CARD). In parallel, the emerging paradigm of Reinforcement Learning from Verifiable Rewards (RLVR) provides empirical evidence that language-mediated supervision can serve as a viable alternative to traditional reward engineering. We conceptualize this transition along three dimensions: semantic reward specification, dynamic reward adaptation, and improved alignment with human intent, while noting open challenges related to computational overhead, robustness to hallucination, and scalability to large multi-agent systems. We conclude by outlining a research direction in which coordination arises from shared semantic representations rather than explicitly engineered numerical signals.

---

### Structural Dimension Reduction in Bayesian Networks

Authors: Pei Heng, Yi Sun, Jianhua Guo
Published: 2026-01-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.08236v1

This work introduces a novel technique, named structural dimension reduction, to collapse a Bayesian network onto a minimum and localized one while ensuring that probabilistic inferences between the original and reduced networks remain consistent. To this end, we propose a new combinatorial structure in directed acyclic graphs called the directed convex hull, which has turned out to be equivalent to their minimum localized Bayesian networks. An efficient polynomial-time algorithm is devised to identify them by determining the unique directed convex hulls containing the variables of interest from the original networks. Experiments demonstrate that the proposed technique has high dimension reduction capability in real networks, and the efficiency of probabilistic inference based on directed convex hulls can be significantly improved compared with traditional methods such as variable elimination and belief propagation algorithms. The code of this study is open at \href{https://github.com/Balance-H/Algorithms}{https://github.com/Balance-H/Algorithms} and the proofs of the results in the main body are postponed to the appendix.

---

### MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Evaluation of Language Model Agents

Authors: Shouju Wang, Haopeng Zhang
Published: 2026-01-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.08235v3

As language-model agents evolve from passive chatbots into proactive assistants that handle personal data, evaluating their adherence to social norms becomes increasingly critical, often through the lens of Contextual Integrity (CI). However, existing CI benchmarks are largely text-centric and primarily emphasize negative refusal scenarios, overlooking multimodal privacy risks and the fundamental trade-off between privacy and utility. In this paper, we introduce MPCI-Bench, the first Multimodal Pairwise Contextual Integrity benchmark for evaluating privacy behavior in agentic settings. MPCI-Bench consists of paired positive and negative instances derived from the same visual source and instantiated across three tiers: normative Seed judgments, context-rich Story reasoning, and executable agent action Traces. Data quality is ensured through a Tri-Principle Iterative Refinement pipeline. Evaluations of state-of-the-art multimodal models reveal systematic failures to balance privacy and utility and a pronounced modality leakage gap, where sensitive visual information is leaked more frequently than textual information. We will open-source MPCI-Bench to facilitate future research on agentic CI.

---

### GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition

Authors: Hao Deng, Bo Liu
Published: 2026-01-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.08230v1

While Graph Neural Networks (GNNs) excel on graph-structured data, their performance is fundamentally limited by the quality of the observed graph, which often contains noise, missing links, or structural properties misaligned with GNNs' underlying assumptions. To address this, graph structure learning aims to infer a more optimal topology. Existing methods, however, often incur high computational costs due to complex generative models and iterative joint optimization, limiting their practical utility. In this paper, we propose GADPN, a simple yet effective graph structure learning framework that adaptively refines graph topology via low-rank denoising and generalized structural perturbation. Our approach makes two key contributions: (1) we introduce Bayesian optimization to adaptively determine the optimal denoising strength, tailoring the process to each graph's homophily level; and (2) we extend the structural perturbation method to arbitrary graphs via Singular Value Decomposition (SVD), overcoming its original limitation to symmetric structures. Extensive experiments on benchmark datasets demonstrate that GADPN achieves state-of-the-art performance while significantly improving efficiency. It shows particularly strong gains on challenging disassortative graphs, validating its ability to robustly learn enhanced graph structures across diverse network types.

---

### Knowledge-based learning in Text-RAG and Image-RAG

Authors: Alexander Shim, Khalil Saieh, Samuel Clarke
Published: 2026-01-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.08226v1

This research analyzed and compared the multi-modal approach in the Vision Transformer(EVA-ViT) based image encoder with the LlaMA or ChatGPT LLM to reduce the hallucination problem and detect diseases in chest x-ray images. In this research, we utilized the NIH Chest X-ray image to train the model and compared it in image-based RAG, text-based RAG, and baseline. (3) (5) In a result, the text-based RAG(2) e!ectively reduces the hallucination problem by using external knowledge information, and the image-based RAG improved the prediction con"dence and calibration by using the KNN methods. (4) Moreover, the GPT LLM showed better performance, a low hallucination rate, and better Expected Calibration Error(ECE) than Llama Llama-based model. This research shows the challenge of data imbalance, a complex multi-stage structure, but suggests a large experience environment and a balanced example of use.

---