# Research Papers — 2026-02 · bundle page 127 of 210 > Full-text markdown of papers #6301–6350 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/127 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/126.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/128.md) ### SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents Authors: Zhirui Zhang, Hongbo Zhang, Haoxiang Fei, Zhiyuan Bao, Yubin Chen, Zhengyu Lei, Ziyue Liu, Yixuan Sun, Mingkun Xiao, Zihang Ye, Yu Zhang, Hongcheng Zhu et al. Published: 2026-02-10 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.09447v2 Although large language models (LLMs) have demonstrated impressive coding capabilities, their ability to autonomously build production-scale software from explicit specifications remains an open question. We introduce SWE-AGI, an open-source benchmark for evaluating end-to-end, specification-driven construction of software systems written in MoonBit. SWE-AGI tasks require LLM-based agents to implement parsers, interpreters, binary decoders, and SAT solvers strictly from authoritative standards and RFCs under a fixed API scaffold. Each task involves implementing 1,000-10,000 lines of core logic, corresponding to weeks or months of engineering effort for an experienced human developer. By leveraging the nascent MoonBit ecosystem, SWE-AGI minimizes data leakage, forcing agents to rely on long-horizon architectural reasoning rather than code retrieval. Across frontier models, gpt-5.3-codex achieves the best overall performance (solving 19/22 tasks, 86.4%), outperforming claude-opus-4.6 (15/22, 68.2%), and kimi-2.5 exhibits the strongest performance among open-source models. Performance degrades sharply with increasing task difficulty, particularly on hard, specification-intensive systems. Behavioral analysis further reveals that as codebases scale, code reading, rather than writing, becomes the dominant bottleneck in AI-assisted development. Overall, while specification-driven autonomous software engineering is increasingly viable, substantial challenges remain before it can reliably support production-scale development. --- ### A Scoping Review of Deep Learning for Urban Visual Pollution and Proposal of a Real-Time Monitoring Framework with a Visual Pollution Index Authors: Mohammad Masudur Rahman, Md. Rashedur Rahman, Ashraful Islam, Saadia B Alam, M Ashraful Amin Published: 2026-02-10 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.09446v1 Urban Visual Pollution (UVP) has emerged as a critical concern, yet research on automatic detection and application remains fragmented. This scoping review maps the existing deep learning-based approaches for detecting, classifying, and designing a comprehensive application framework for visual pollution management. Following the PRISMA-ScR guidelines, seven academic databases (Scopus, Web of Science, IEEE Xplore, ACM DL, ScienceDirect, SpringerNatureLink, and Wiley) were systematically searched and reviewed, and 26 articles were found. Most research focuses on specific pollutant categories and employs variations of YOLO, Faster R-CNN, and EfficientDet architectures. Although several datasets exist, they are limited to specific areas and lack standardized taxonomies. Few studies integrate detection into real-time application systems, yet they tend to be geographically skewed. We proposed a framework for monitoring visual pollution that integrates a visual pollution index to assess the severity of visual pollution for a certain area. This review highlights the need for a unified UVP management system that incorporates pollutant taxonomy, a cross-city benchmark dataset, a generalized deep learning model, and an assessment index that supports sustainable urban aesthetics and enhances the well-being of urban dwellers. --- ### Conceptual Cultural Index: A Metric for Cultural Specificity via Relative Generality Authors: Takumi Ohashi, Hitoshi Iyatomi Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.09444v1 Large language models (LLMs) are increasingly deployed in multicultural settings; however, systematic evaluation of cultural specificity at the sentence level remains underexplored. We propose the Conceptual Cultural Index (CCI), which estimates cultural specificity at the sentence level. CCI is defined as the difference between the generality estimate within the target culture and the average generality estimate across other cultures. This formulation enables users to operationally control the scope of culture via comparison settings and provides interpretability, since the score derives from the underlying generality estimates. We validate CCI on 400 sentences (200 culture-specific and 200 general), and the resulting score distribution exhibits the anticipated pattern: higher for culture-specific sentences and lower for general ones. For binary separability, CCI outperforms direct LLM scoring, yielding more than a 10-point improvement in AUC for models specialized to the target culture. Our code is available at https://github.com/IyatomiLab/CCI . --- ### P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads Authors: Yun Luo, Futing Wang, Qianjia Cheng, Fangchen Yu, Haodi Lei, Jianhao Yan, Chenxi Li, Jiacheng Chen, Yufeng Zhao, Haiyuan Wan, Yuchen Zhang, Shenghe Zheng et al. Published: 2026-02-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.09443v1 The transition from symbolic manipulation to science-grade reasoning represents a pivotal frontier for Large Language Models (LLMs), with physics serving as the critical test anchor for binding abstract logic to physical reality. Physics demands that a model maintain physical consistency with the laws governing the universe, a task that fundamentally requires multimodal perception to ground abstract logic in reality. At the Olympiad level, diagrams are often constitutive rather than illustrative, containing essential constraints, such as boundary conditions and spatial symmetries, that are absent from the text. To bridge this visual-logical gap, we introduce P1-VL, a family of open-source vision-language models engineered for advanced scientific reasoning. Our method harmonizes Curriculum Reinforcement Learning, which employs progressive difficulty expansion to stabilize post-training, with Agentic Augmentation, enabling iterative self-verification at inference. Evaluated on HiPhO, a rigorous benchmark of 13 exams from 2024-2025, our flagship P1-VL-235B-A22B becomes the first open-source Vision-Language Model (VLM) to secure 12 gold medals and achieves the state-of-the-art performance in the open-source models. Our agent-augmented system achieves the No.2 overall rank globally, trailing only Gemini-3-Pro. Beyond physics, P1-VL demonstrates remarkable scientific reasoning capacity and generalizability, establishing significant leads over base models in STEM benchmarks. By open-sourcing P1-VL, we provide a foundational step toward general-purpose physical intelligence to better align visual perceptions with abstract physical laws for machine scientific discovery. --- ### Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts Authors: Shweta Parihar, Lu Cheng Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.09442v1 Social biases inherent in large language models (LLMs) raise significant fairness concerns. Retrieval-Augmented Generation (RAG) architectures, which retrieve external knowledge sources to enhance the generative capabilities of LLMs, remain susceptible to the same bias-related challenges. This work focuses on evaluating and understanding the social bias implications of RAG. Through extensive experiments across various retrieval corpora, LLMs, and bias evaluation datasets, encompassing more than 13 different bias types, we surprisingly observe a reduction in bias in RAG. This suggests that the inclusion of external context can help counteract stereotype-driven predictions, potentially improving fairness by diversifying the contextual grounding of the model's outputs. To better understand this phenomenon, we then explore the model's reasoning process by integrating Chain-of-Thought (CoT) prompting into RAG while assessing the faithfulness of the model's CoT. Our experiments reveal that the model's bias inclinations shift between stereotype and anti-stereotype responses as more contextual information is incorporated from the retrieved documents. Interestingly, we find that while CoT enhances accuracy, contrary to the bias reduction observed with RAG, it increases overall bias across datasets, highlighting the need for bias-aware reasoning frameworks that can mitigate this trade-off. --- ### Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning Authors: Xu Ma, Yitian Zhang, Qihua Dong, Yun Fu Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09439v1 High-quality and open datasets remain a major bottleneck for text-to-image (T2I) fine-tuning. Despite rapid progress in model architectures and training pipelines, most publicly available fine-tuning datasets suffer from low resolution, poor text-image alignment, or limited diversity, resulting in a clear performance gap between open research models and enterprise-grade models. In this work, we present Fine-T2I, a large-scale, high-quality, and fully open dataset for T2I fine-tuning. Fine-T2I spans 10 task combinations, 32 prompt categories, 11 visual styles, and 5 prompt templates, and combines synthetic images generated by strong modern models with carefully curated real images from professional photographers. All samples are rigorously filtered for text-image alignment, visual fidelity, and prompt quality, with over 95% of initial candidates removed. The final dataset contains over 6 million text-image pairs, around 2 TB on disk, approaching the scale of pretraining datasets while maintaining fine-tuning-level quality. Across a diverse set of pretrained diffusion and autoregressive models, fine-tuning on Fine-T2I consistently improves both generation quality and instruction adherence, as validated by human evaluation, visual comparison, and automatic metrics. We release Fine-T2I under an open license to help close the data gap in T2I fine-tuning in the open community. --- ### Breaking the Pre-Sampling Barrier: Activation-Informed Difficulty-Aware Self-Consistency Authors: Taewoong Yoon, Geunyeong Jeong, Geon Park, Sihyeong Yeom, Harksoo Kim Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09438v1 Self-Consistency (SC) is an effective decoding strategy that improves the reasoning performance of Large Language Models (LLMs) by generating multiple chain-of-thought reasoning paths and selecting the final answer via majority voting. However, it suffers from substantial inference costs because it requires a large number of samples. To mitigate this issue, Difficulty-Adaptive Self-Consistency (DSC) was proposed to reduce unnecessary token usage for easy problems by adjusting the number of samples according to problem difficulty. However, DSC requires additional model calls and pre-sampling to estimate difficulty, and this process is repeated when applying to each dataset, leading to significant computational overhead. In this work, we propose Activation-Informed Difficulty-Aware Self-Consistency (ACTSC) to address these limitations. ACTSC leverages internal difficulty signals reflected in the feed-forward network neuron activations to construct a lightweight difficulty estimation probe, without any additional token generation or model calls. The probe dynamically adjusts the number of samples for SC and can be applied to new datasets without requiring pre-sampling for difficulty estimation. To validate its effectiveness, we conduct experiments on five benchmarks. Experimental results show that ACTSC effectively reduces inference costs while maintaining accuracy relative to existing methods. --- ### Diffusion-Guided Pretraining for Brain Graph Foundation Models Authors: Xinxu Wei, Rong Zhou, Lifang He, Yu Zhang Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.09437v3 With the growing interest in foundation models for brain signals, graph-based pretraining has emerged as a promising paradigm for learning transferable representations from connectome data. However, existing contrastive and masked autoencoder methods typically rely on naive random dropping or masking for augmentation, which is ill-suited for brain graphs and hypergraphs as it disrupts semantically meaningful connectivity patterns. Moreover, commonly used graph-level readout and reconstruction schemes fail to capture global structural information, limiting the robustness of learned representations. In this work, we propose a unified diffusion-based pretraining framework that addresses both limitations. First, diffusion is designed to guide structure-aware dropping and masking strategies, preserving brain graph semantics while maintaining effective pretraining diversity. Second, diffusion enables topology-aware graph-level readout and node-level global reconstruction by allowing graph embeddings and masked nodes to aggregate information from globally related regions. Extensive experiments across multiple neuroimaging datasets with over 25,000 subjects and 60,000 scans involving various mental disorders and brain atlases demonstrate consistent performance improvements. --- ### A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors Authors: Zhenyu Xu, Victor S. Sheng Published: 2026-02-10 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.09434v1 Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative models. We introduce a novel fingerprinting framework that leverages the behavioral patterns induced by safety alignment, applying the concept of refusal vectors for LLM provenance tracking. These vectors, extracted from directional patterns in a model's internal representations when processing harmful versus harmless prompts, serve as robust behavioral fingerprints. Our contribution lies in developing a fingerprinting system around this concept and conducting extensive validation of its effectiveness for IP protection. We demonstrate that these behavioral fingerprints are highly robust against common modifications, including finetunes, merges, and quantization. Our experiments show that the fingerprint is unique to each model family, with low cosine similarity between independently trained models. In a large-scale identification task across 76 offspring models, our method achieves 100\% accuracy in identifying the correct base model family. Furthermore, we analyze the fingerprint's behavior under alignment-breaking attacks, finding that while performance degrades significantly, detectable traces remain. Finally, we propose a theoretical framework to transform this private fingerprint into a publicly verifiable, privacy-preserving artifact using locality-sensitive hashing and zero-knowledge proofs. --- ### Autonomous Action Runtime Management(AARM):A System Specification for Securing AI-Driven Actions at Runtime Authors: Herman Errico Published: 2026-02-10 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.09433v1 As artificial intelligence systems evolve from passive assistants into autonomous agents capable of executing consequential actions, the security boundary shifts from model outputs to tool execution. Traditional security paradigms - log aggregation, perimeter defense, and post-hoc forensics - cannot protect systems where AI-driven actions are irreversible, execute at machine speed, and originate from potentially compromised orchestration layers. This paper introduces Autonomous Action Runtime Management (AARM), an open specification for securing AI-driven actions at runtime. AARM defines a runtime security system that intercepts actions before execution, accumulates session context, evaluates against policy and intent alignment, enforces authorization decisions, and records tamper-evident receipts for forensic reconstruction. We formalize a threat model addressing prompt injection, confused deputy attacks, data exfiltration, and intent drift. We introduce an action classification framework distinguishing forbidden, context-dependent deny, and context-dependent allow actions. We propose four implementation architectures - protocol gateway, SDK instrumentation, kernel eBPF, and vendor integration - with distinct trust properties, and specify minimum conformance requirements for AARM-compliant systems. AARM is model-agnostic, framework-agnostic, and vendor-neutral, treating action execution as the stable security boundary. This specification aims to establish industry-wide requirements before proprietary fragmentation forecloses interoperability. --- ### SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-turn RL Authors: Yang Zhao, Shizhao Sun, Meisheng Zhang, Yingdong Shi, Xubo Yang, Jiang Bian Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09432v1 Current one-pass 3D scene synthesis methods often suffer from spatial hallucinations, such as collisions, due to a lack of deliberative reasoning. To bridge this gap, we introduce SceneReVis, a vision-grounded self-reflection framework that employs an iterative ``diagnose-and-act'' loop to explicitly intercept and resolve spatial conflicts using multi-modal feedback. To support this step-wise paradigm, we construct SceneChain-12k, a large-scale dataset of causal construction trajectories derived through a novel reverse engineering pipeline. We further propose a two-stage training recipe that transitions from Supervised Fine-Tuning to Agentic Reinforcement Learning, evolving the model into an active spatial planner. Extensive experiments demonstrate that SceneReVis achieves state-of-the-art performance in high-fidelity generation and goal-oriented optimization, with robust generalization to long-tail domains. --- ### Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models Authors: Xinwei Zhang, Li Bai, Tianwei Zhang, Youqian Zhang, Qingqing Ye, Yingnan Zhao, Ruochen Du, Haibo Hu Published: 2026-02-10 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2602.09431v2 Large vision-language models (LVLMs) have achieved impressive performance across multimodal tasks, but their reliance on visual inputs exposes them to adversarial threats. Encoder-based attacks provide an efficient alternative to end-to-end optimization by crafting perturbations through the vision encoder alone. However, existing encoder-based attacks often assume that the surrogate encoder is identical or similar to the victim LVLM's vision encoder. In this work, we present a systematic study of their transferability in more realistic black-box deployments with heterogeneous LVLM architectures. We find that model-specific visual evidence is inconsistent across models, whereas text-conditioned grounding regions are more closely tied to caption-relevant evidence and provide a more stable transfer target. However, existing attacks remain weakly aligned with and insufficiently disrupt these regions. Motivated by these findings, we propose Grounding-Driven Attack (GDA), which aligns perturbation optimization with text-grounded evidence. GDA combines Grounding-Aware Perturbation Allocation to concentrate perturbation budget on grounded evidence regions with Grounding-Centric Evidence Disruption to intensify their global and local disruption. Experiments across diverse victim models and tasks show that GDA consistently outperforms existing encoder-based attacks in black-box transfer. These results highlight the central role of text-grounded evidence in adversarial transferability and motivate grounding-aware robustness evaluation and defense design. --- ### AtomBridge: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments Authors: Yiwen Pang, Bo Zhou, Changjin Li, Xuanhao Wang, Shengxiang Xu, Deng-Bao Wang, Peng Cheng, Shimin Di, Jingkuan Song, Min-Ling Zhang Published: 2026-02-10 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.09430v2 Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent vision-language-action (VLA) models offer a promising foundation for robotic laboratories. However, scientific experiments typically involve long-horizon tasks composed of multiple atomic tasks. Existing VLA models may fail to perform composed tasks formed by reordering and composing these known atomic actions. This limitation can arise from a skill-chaining gap caused by robot-state mismatch: the terminal robot state of one skill can fall outside the valid initial-state distribution of the next. To address this challenge, we propose AtomBridge, an Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments. AtomBridge attaches at inference time to a VLA policy already fine-tuned on atomic tasks, while keeping its weights fixed. At each task boundary, it uses LLM-based transition reasoning and robotic-action code generation to insert transitional actions between consecutive tasks. This plug-and-play design mitigates the skill-chaining gap caused by robot-state mismatch without additional VLA fine-tuning or demonstrations of composed long-horizon sequences. Across scientific manipulation sequences in simulation and a real-world experimental environment, AtomBridge improves execution continuity and per-step atomic-task success. On 8-step composed tasks, AtomBridge improves full-sequence success by 10%~25%. --- ### Sci-VLA: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments Authors: Yiwen Pang, Bo Zhou, Changjin Li, Xuanhao Wang, Shengxiang Xu, Deng-Bao Wang, Min-Ling Zhang, Shimin Di Published: 2026-02-10 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.09430v1 Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent vision-language-action (VLA) models offer a promising foundation for robotic laboratories. However, scientific experiments typically involve long-horizon tasks composed of multiple atomic tasks, posing a fundamental challenge to existing VLA models. While VLA models fine-tuned for scientific tasks can reliably execute atomic experimental actions seen during training, they often fail to perform composite tasks formed by reordering and composing these known atomic actions. This limitation arises from a distributional mismatch between training-time atomic tasks and inference-time composite tasks, which prevents VLA models from executing necessary transitional operations between atomic tasks. To address this challenge, we propose an Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments. It introduces an LLM-based agentic inference mechanism that intervenes when executing sequential manipulation tasks. By performing explicit transition inference and generating transitional robotic action code, the proposed plugin guides VLA models through missing transitional steps, enabling reliable execution of composite scientific workflows without any additional training. This inference-only intervention makes our method computationally efficient, data-efficient, and well-suited for open-ended and long-horizon robotic laboratory tasks. We build 3D assets of scientific instruments and common scientific operating scenes within an existing simulation environment. In these scenes, we have verified that our method increases the average success rate per atomic task by 42\% during inference. Furthermore, we show that our method can be easily transferred from the simulation to real scientific laboratories. --- ### Bridging the Modality Gap in Roadside LiDAR: A Training-Free Vision-Language Model Framework for Vehicle Classification Authors: Yiqiao Li, Bo Shang, Jie Wei Published: 2026-02-10 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.09425v1 Fine-grained truck classification is critical for intelligent transportation systems (ITS), yet current LiDAR-based methods face scalability challenges due to their reliance on supervised deep learning and labor-intensive manual annotation. Vision-Language Models (VLMs) offer promising few-shot generalization, but their application to roadside LiDAR is limited by a modality gap between sparse 3D point clouds and dense 2D imagery. We propose a framework that bridges this gap by adapting off-the-shelf VLMs for fine-grained truck classification without parameter fine-tuning. Our new depth-aware image generation pipeline applies noise removal, spatial and temporal registration, orientation rectification, morphological operations, and anisotropic smoothing to transform sparse, occluded LiDAR scans into depth-encoded 2D visual proxies. Validated on a real-world dataset of 20 vehicle classes, our approach achieves competitive classification accuracy with as few as 16-30 examples per class, offering a scalable alternative to data-intensive supervised baselines. We further observe a "Semantic Anchor" effect: text-based guidance regularizes performance in ultra-low-shot regimes $k < 4$, but degrades accuracy in more-shot settings due to semantic mismatch. Furthermore, we demonstrate the efficacy of this framework as a Cold Start strategy, using VLM-generated labels to bootstrap lightweight supervised models. Notably, the few-shot VLM-based model achieves over correct classification rate of 75 percent for specific drayage categories (20ft, 40ft, and 53ft containers) entirely without the costly training or fine-tuning, significantly reducing the intensive demands of initial manual labeling, thus achieving a method of practical use in ITS applications. --- ### Reward-Guided Discrete Diffusion via Clean-Sample Markov Chain for Molecule and Biological Sequence Design Authors: Prin Phunyaphibarn, Minhyuk Sung Published: 2026-02-10 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2602.09424v1 Discrete diffusion models have recently emerged as a powerful class of generative models for chemistry and biology data. In these fields, the goal is to generate various samples with high rewards (e.g., drug-likeness in molecules), making reward-based guidance crucial. Most existing methods are based on guiding the diffusion model using intermediate rewards but tend to underperform since intermediate rewards are noisy due to the non-smooth nature of reward functions used in scientific domains. To address this, we propose Clean-Sample Markov Chain (CSMC) Sampler, a method that performs effective test-time reward-guided sampling for discrete diffusion models, enabling local search without relying on intermediate rewards. CSMC constructs a Markov chain of clean samples using the Metropolis-Hastings algorithm such that its stationary distribution is the target distribution. We design a proposal distribution by sequentially applying the forward and backward diffusion processes, making the acceptance probability tractable. Experiments on molecule and biological sequence generation with various reward functions demonstrate that our method consistently outperforms prior approaches that rely on intermediate rewards. --- ### Beyond Input-Output: Rethinking Creativity through Design-by-Analogy in Human-AI Collaboration Authors: Xuechen Li, Shuai Zhang, Nan Cao, Qing Chen Published: 2026-02-10 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.09423v1 While the proliferation of foundation models has significantly boosted individual productivity, it also introduces a potential challenge: the homogenization of creative content. In response, we revisit Design-by-Analogy (DbA), a cognitively grounded approach that fosters novel solutions by mapping inspiration across domains. However, prevailing perspectives often restrict DbA to early ideation or specific data modalities, while reducing AI-driven design to simplified input-output pipelines. Such conceptual limitations inadvertently foster widespread design fixation. To address this, we expand the understanding of DbA by embedding it into the entire creative process, thereby demonstrating its capacity to mitigate such fixation. Through a systematic review of 85 studies, we identify six forms of representation and classify techniques across seven stages of the creative process. We further discuss three major application domains: creative industries, intelligent manufacturing, and education and services, demonstrating DbA's practical relevance. Building on this synthesis, we frame DbA as a mediating technology for human-AI collaboration and outline the potential opportunities and inherent risks for advancing creativity support in HCI and design research. --- ### Are Language Models Sensitive to Morally Irrelevant Distractors? Authors: Andrew Shaw, Christina Hahn, Catherine Rasgaitis, Yash Mishra, Alisa Liu, Natasha Jaques, Yulia Tsvetkov, Amy X. Zhang Published: 2026-02-10 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2602.09416v2 With the rapid uptake of large language models (LLMs) across high-stakes settings, it is becoming increasingly important to ensure that LLMs behave in ways that align with human values. Existing moral benchmarks for this purpose often prompt LLMs with value statements, moral scenarios, or psychological questionnaires, with the implicit underlying assumption that LLMs report somewhat stable moral preferences. However, moral psychology research has shown that even human moral judgements are sensitive to morally irrelevant situational factors such as the smell of cinnamon rolls or the level of ambient noise, thereby challenging moral theories which assume that human moral judgements are stable. Here we draw inspiration from this "situationist" view of moral psychology to evaluate whether LLMs exhibit similar cognitive moral biases. We curate a novel multimodal dataset of 60 "moral distractors" from existing psychological datasets of emotionally-valenced images and narratives, which have no moral relevance to the situation presented. After injecting these distractors into existing moral benchmarks, we find that moral distractors can shift the moral judgements of LLMs by over 30% even in unambiguous scenarios, highlighting the instability of LLMs' moral judgements and the need for more contextual approaches to AI alignment. --- ### Stability and Concentration in Nonlinear Inverse Problems with Block-Structured Parameters: Lipschitz Geometry, Identifiability, and an Application to Gaussian Splatting Authors: Joe-Mei Feng, Hsin-Hsiung Kao Published: 2026-02-10 Categories: cs.CV, math.NA arXiv: https://arxiv.org/abs/2602.09415v2 We develop an operator-theoretic framework for stability and statistical concentration in nonlinear inverse problems with block-structured parameters. Under a unified set of assumptions combining blockwise Lipschitz geometry, local identifiability, and sub-Gaussian noise, we establish deterministic stability inequalities, global Lipschitz bounds for least-squares misfit functionals, and nonasymptotic concentration estimates. These results yield high-probability parameter error bounds that are intrinsic to the forward operator and independent of any specific reconstruction algorithm. As a concrete instantiation, we verify that the Gaussian Splatting rendering operator satisfies the proposed assumptions and derive explicit constants governing its Lipschitz continuity and resolution-dependent observability. This leads to a fundamental stability--resolution tradeoff, showing that estimation error is inherently constrained by the ratio between image resolution and model complexity. Overall, the analysis characterizes operator-level limits for a broad class of high-dimensional nonlinear inverse problems arising in modern imaging and differentiable rendering. --- ### LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging Authors: Xinyu Wang, Ke Deng, Fei Dou, Jinbo Bi, Jin Lu Published: 2026-02-10 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.09413v1 Model merging aims to combine multiple fine-tuned models into a single multi-task model without access to training data. Existing task-vector merging methods such as TIES, TSV-M, and Iso-C/CTS differ in their aggregation rules but treat all layers nearly uniformly. This assumption overlooks the strong layer-wise heterogeneity in large vision transformers, where shallow layers are sensitive to interference while deeper layers encode stable task-specific features. We introduce LARV, a training-free, data-free, merger-agnostic Layer-wise Adaptive Rescaling Veneer that plugs into any task-vector merger and assigns a per-layer scale to each task vector before aggregation, and show it consistently boosts diverse merging rules. LARV adaptively suppresses shallow-layer interference and amplifies deeper-layer alignment using a simple deterministic schedule, requiring no retraining or modification to existing mergers. To our knowledge, this is the first work to perform layer-aware scaling for task-vector merging. LARV computes simple data-free layer proxies and turns them into scales through a lightweight rule; we study several instantiations within one framework (e.g., tiered two/three-level scaling with fixed values, or continuous mappings) and show that tiered choices offer the best robustness, while continuous mappings remain an ablation. LARV is orthogonal to the base merger and adds negligible cost. On FusionBench with Vision Transformers, LARV consistently improves all task-vector baselines across 8/14/20-task settings; for example, Iso-C + LARV reaches 85.9% on ViT-B/32, 89.2% on ViT-B/16, and 92.6% on ViT-L/14. Layerwise analysis and corruption tests further indicate that LARV suppresses shallow-layer interference while modestly amplifying deeper, task-stable features, turning model merging into a robust, layer-aware procedure rather than a uniform one. --- ### K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge Authors: Zhikai Li, Jiatong Li, Xuewen Liu, Wangbo Zhao, Pan Du, Kaicheng Zhou, Qingyi Gu, Yang You, Zhen Dong, Kurt Keutzer Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09411v1 The rapid development of visual generative models raises the need for more scalable and human-aligned evaluation methods. While the crowdsourced Arena platforms offer human preference assessments by collecting human votes, they are costly and time-consuming, inherently limiting their scalability. Leveraging vision-language model (VLMs) as substitutes for manual judgments presents a promising solution. However, the inherent hallucinations and biases of VLMs hinder alignment with human preferences, thus compromising evaluation reliability. Additionally, the static evaluation approach lead to low efficiency. In this paper, we propose K-Sort Eval, a reliable and efficient VLM-based evaluation framework that integrates posterior correction and dynamic matching. Specifically, we curate a high-quality dataset from thousands of human votes in K-Sort Arena, with each instance containing the outputs and rankings of K models. When evaluating a new model, it undergoes (K+1)-wise free-for-all comparisons with existing models, and the VLM provide the rankings. To enhance alignment and reliability, we propose a posterior correction method, which adaptively corrects the posterior probability in Bayesian updating based on the consistency between the VLM prediction and human supervision. Moreover, we propose a dynamic matching strategy, which balances uncertainty and diversity to maximize the expected benefit of each comparison, thus ensuring more efficient evaluation. Extensive experiments show that K-Sort Eval delivers evaluation results consistent with K-Sort Arena, typically requiring fewer than 90 model runs, demonstrating both its efficiency and reliability. --- ### Accelerating Post-Quantum Cryptography via LLM-Driven Hardware-Software Co-Design Authors: Yuchao Liao, Tosiron Adegbija, Roman Lysecky Published: 2026-02-10 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2602.09410v1 Post-quantum cryptography (PQC) is crucial for securing data against emerging quantum threats. However, its algorithms are computationally complex and difficult to implement efficiently on hardware. In this paper, we explore the potential of Large Language Models (LLMs) to accelerate the hardware-software co-design process for PQC, with a focus on the FALCON digital signature scheme. We present a novel framework that leverages LLMs to analyze PQC algorithms, identify performance-critical components, and generate candidate hardware descriptions for FPGA implementation. We present the first quantitative comparison between LLM-driven synthesis and conventional HLS-based approaches for low-level compute-intensive kernels in FALCON, showing that human-in-the-loop LLM-generated accelerators can achieve up to 2.6x speedup in kernel execution time with shorter critical paths, while highlighting trade-offs in resource utilization and power consumption. Our results suggest that LLMs can minimize design effort and development time by automating FPGA accelerator design iterations for PQC algorithms, offering a promising new direction for rapid and adaptive PQC accelerator design on FPGAs. --- ### Single-Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D Authors: Yan Luo, Advaith Ravishankar, Serena Liu, Yutong Yang, Mengyu Wang Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09407v2 While three-dimensional imaging is essential for clinical diagnosis, its high cost and long wait times have motivated the use of image-to-3D foundation models to infer volume from two-dimensional modalities. However, because these models are trained on natural images, their learned geometric priors struggle to transfer to inherently planar medical data. A benchmark of five state-of-the-art models (SAM3D, Hunyuan3D-2.1, Direct3D, Hi3DGen, and TripoSG) across six medical and two natural datasets revealed that voxel-based overlap remains uniformly low across all methods due to severe depth ambiguity from single-slice inputs. Despite this fundamental volumetric failure, global distance metrics indicate that SAM3D best captures topological similarity to ground-truth medical shapes, whereas alternative models are prone to oversimplification. Ultimately, these findings quantify the limits of zero-shot single-slice 3D inference, highlighting that reliable medical 3D reconstruction requires domain-specific adaptation and anatomical constraints to overcome complex medical geometries. --- ### Is Memorization Helpful or Harmful? Prior Information Sets the Threshold Authors: Chen Cheng, Rina Foygel Barber Published: 2026-02-10 Categories: stat.ML, cs.IT, cs.LG, math.ST arXiv: https://arxiv.org/abs/2602.09405v2 We examine the connection between training error and generalization error for arbitrary estimating procedures, working in an overparameterized linear model under general priors in a Bayesian setup. We find determining factors inherent to the prior distribution $π$, giving explicit conditions under which optimal generalization necessitates that the training error be (i) near interpolating relative to the noise size (i.e., memorization is necessary), or (ii) close to the noise level (i.e., overfitting is harmful). Remarkably, these phenomena occur when the noise reaches thresholds determined by the Fisher information and the variance parameters of the prior $π$. --- ### Learning with Multiple Correct Answers -- Regret Bounds under Different Feedback Models Authors: Alireza F. Pour, Farnam Mansouri, Shai Ben-David Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.09402v2 We study the problem of learning with multiple correct answers, where each instance admits a set of valid labels. We primarily focus on the online setup, where in each round the learner must output a valid label for the queried example. This setting is motivated by language generation, in which a prompt may admit many acceptable completions, but not every completion is acceptable. We study this problem under three feedback models. For each model, we characterize the optimal mistake bound in the realizable setting using an appropriate combinatorial dimension. We then show that the rate of regret can be constant, linear, or sublinear across the three models in the agnostic setting. Our results also imply sample complexity bounds for the batch setup that depend on the respective combinatorial dimensions. --- ### Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning Authors: Nilaksh, Antoine Clavaud, Mathieu Reymond, François Rivest, Sarath Chandar Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.09396v1 In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes agents notoriously sample-inefficient, since value-based losses alone struggle to extract meaningful representations from transient data. We propose extending Self-Predictive Representations (SPR) to the streaming pipeline to maximize the utility of every observed frame. However, due to the highly correlated samples induced by the streaming regime, naively applying this auxiliary loss results in training instabilities. Thus, we introduce orthogonal gradient updates relative to the momentum target and resolve gradient conflicts arising from streaming-specific optimizers. Validated across the Atari, MinAtar, and Octax suites, our approach systematically outperforms existing streaming baselines. Latent-space analysis, including t-SNE visualizations and effective-rank measurements, confirms that our method learns significantly richer representations, bridging the performance gap caused by the absence of a replay buffer, while remaining efficient enough to train on just a few CPU cores. --- ### Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning Authors: Yifei Cheng, Xianglin Yang, Guoxia Wang, Chao Huang, Fei Ma, Dianhai Yu, Xiaochun Cao, Li Shen Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.09395v1 Sharpness-aware minimization (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning. However, its extra parameter perturbation step doubles the computation cost, which becomes the bottleneck of SAM in the practical implementation. In this work, we propose an approach SL-SAM to break this bottleneck by introducing the sparse technique to layers. Our key innovation is to frame the dynamic selection of layers for both the gradient ascent (perturbation) and descent (update) steps as a multi-armed bandit problem. At the beginning of each iteration, SL-SAM samples a part of the layers of the model according to the gradient norm to participate in the backpropagation of the following parameter perturbation and update steps, thereby reducing the computation complexity. We then provide the analysis to guarantee the convergence of SL-SAM. In the experiments of fine-tuning models in several tasks, SL-SAM achieves the performances comparable to the state-of-the-art baselines, including a \#1 rank on LLM fine-tuning. Meanwhile, SL-SAM significantly reduces the ratio of active parameters in backpropagation compared to vanilla SAM (SL-SAM activates 47\%, 22\% and 21\% parameters on the vision, moderate and large language model respectively while vanilla SAM always activates 100\%), verifying the efficiency of our proposed algorithm. --- ### The Critical Horizon: Inspection Design Principles for Multi-Stage Operations and Deep Reasoning Authors: Seyed Morteza Emadi Published: 2026-02-10 Categories: stat.ML, cs.AI, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2602.09394v2 Manufacturing lines, service journeys, supply chains, and AI reasoning chains share a common challenge: attributing a terminal outcome to the intermediate stage that caused it. We establish an information-theoretic barrier to this credit assignment problem: the signal connecting early steps to final outcomes decays exponentially with depth, creating a critical horizon beyond which reliable learning from endpoint data alone requires exponentially many samples. We prove four results. First, a Signal Decay Bound: sample complexity for attributing outcomes to early stages grows exponentially in the number of intervening steps. Second, Width Limits: parallel rollouts provide only logarithmic relief, with correlation capping the effective number of independent samples. Third, an Objective Mismatch: additive reward aggregation optimizes the wrong quantity when sequential validity requires all steps to be correct. Fourth, Optimal Inspection Design: uniform checkpoint spacing is minimax-optimal under homogeneous signal attenuation, while a greedy algorithm yields optimal non-uniform schedules under heterogeneous attenuation. Together, these results provide a common analytical foundation for inspection design in operations and supervision design in AI. --- ### LLMAC: A Global and Explainable Access Control Framework with Large Language Model Authors: Sharif Noor Zisad, Ragib Hasan Published: 2026-02-10 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.09392v1 Today's business organizations need access control systems that can handle complex, changing security requirements that go beyond what traditional methods can manage. Current approaches, such as Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), and Discretionary Access Control (DAC), were designed for specific purposes. They cannot effectively manage the dynamic, situation-dependent workflows that modern systems require. In this research, we introduce LLMAC, a new unified approach using Large Language Models (LLMs) to combine these different access control methods into one comprehensive, understandable system. We used an extensive synthetic dataset that represents complex real-world scenarios, including policies for ownership verification, version management, workflow processes, and dynamic role separation. Using Mistral 7B, our trained LLM model achieved outstanding results with 98.5% accuracy, significantly outperforming traditional methods (RBAC: 14.5%, ABAC: 58.5%, DAC: 27.5%) while providing clear, human readable explanations for each decision. Performance testing shows that the system can be practically deployed with reasonable response times and computing resources. --- ### TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and Anonymization Authors: Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah, Ricardo Gutierrez-Osuna Published: 2026-02-10 Categories: eess.AS, cs.CL, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2602.09389v1 Real-time voice conversion and speaker anonymization require causal, low-latency synthesis without sacrificing intelligibility or naturalness. Current systems have a core representational mismatch: content is time-varying, while speaker identity is injected as a static global embedding. We introduce a streamable speech synthesizer that aligns the temporal granularity of identity and content via a content-synchronous, time-varying timbre (TVT) representation. A Global Timbre Memory expands a global timbre instance into multiple compact facets; frame-level content attends to this memory, a gate regulates variation, and spherical interpolation preserves identity geometry while enabling smooth local changes. In addition, a factorized vector-quantized bottleneck regularizes content to reduce residual speaker leakage. The resulting system is streamable end-to-end, with <80 ms GPU latency. Experiments show improvements in naturalness, speaker transfer, and anonymization compared to SOTA streaming baselines, establishing TVT as a scalable approach for privacy-preserving and expressive speech synthesis under strict latency budgets. --- ### Effective vocabulary expansion of multilingual language models for extremely low-resource languages Authors: Jianyu Zheng Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09388v2 Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource languages. To further expand the range of languages these models can support, many works focus on continued pre-training of these models. However, few works address how to extend mPLMs to low-resource languages that were previously unsupported. To tackle this issue, we expand the model's vocabulary using a target language corpus. We then screen out a subset from the model's original vocabulary, which is biased towards representing the source language(e.g. English), and utilize bilingual dictionaries to initialize the representations of the expanded vocabulary. Subsequently, we continue to pre-train the mPLMs using the target language corpus, based on the representations of these expanded vocabulary. Experimental results show that our proposed method outperforms the baseline, which uses randomly initialized expanded vocabulary for continued pre-training, in POS tagging and NER tasks, achieving improvements by 0.54% and 2.60%, respectively. Furthermore, our method demonstrates high robustness in selecting the training corpora, and the models' performance on the source language does not degrade after continued pre-training. --- ### Contractual Deepfakes: Can Large Language Models Generate Contracts? Authors: Eliza Mik Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.09384v1 Notwithstanding their unprecedented ability to generate text, LLMs do not understand the meaning of words, have no sense of context and cannot reason. Their output constitutes an approximation of statistically dominant word patterns. And yet, the drafting of contracts is often presented as a typical legal task that could be facilitated by this technology. This paper seeks to put an end to such unreasonable ideas. Predicting words differs from using language in the circumstances of specific transactions and reconstituting common contractual phrases differs from reasoning about the law. LLMs seem to be able to generate generic and superficially plausible contractual documents. In the cold light of day, such documents may turn out to be useless assemblages of inconsistent provisions or contracts that are enforceable but unsuitable for a given transaction. This paper casts a shadow on the simplistic assumption that LLMs threaten the continued viability of the legal industry. --- ### BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation Authors: Peng Lai, Zhihao Ou, Yong Wang, Longyue Wang, Jian Yang, Yun Chen, Guanhua Chen Published: 2026-02-10 Categories: cs.CL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2602.09383v1 LLM-as-a-Judge has been widely adopted across various research and practical applications, yet the robustness and reliability of its evaluation remain a critical issue. A core challenge it faces is bias, which has primarily been studied in terms of known biases and their impact on evaluation outcomes, while automated and systematic exploration of potential unknown biases is still lacking. Nevertheless, such exploration is crucial for enhancing the robustness and reliability of evaluations. To bridge this gap, we propose BiasScope, a LLM-driven framework for automatically and at scale discovering potential biases that may arise during model evaluation. BiasScope can uncover potential biases across different model families and scales, with its generality and effectiveness validated on the JudgeBench dataset. It overcomes the limitations of existing approaches, transforming bias discovery from a passive process relying on manual effort and predefined bias lists into an active and comprehensive automated exploration. Moreover, based on BiasScope, we propose JudgeBench-Pro, an extended version of JudgeBench and a more challenging benchmark for evaluating the robustness of LLM-as-a-judge. Strikingly, even powerful LLMs as evaluators show error rates above 50\% on JudgeBench-Pro, underscoring the urgent need to strengthen evaluation robustness and to mitigate potential biases further. --- ### LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis Authors: Shihao Xu, Tiancheng Zhou, Jiatong Ma, Yanli Ding, Yiming Yan, Ming Xiao, Guoyi Li, Haiyang Geng, Yunyun Han, Jianhua Chen, Yafeng Deng Published: 2026-02-10 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.09379v3 Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely and consistent mental-health assessment. Progress in AI-assisted psychiatric diagnosis is constrained by the absence of benchmarks that simultaneously provide realistic patient simulation, clinician-verified diagnostic labels, and support for dynamic multi-turn consultation. We present LingxiDiagBench, a large-scale multi-agent benchmark that evaluates LLMs on both static diagnostic inference and dynamic multi-turn psychiatric consultation in Chinese. At its core is LingxiDiag-16K, a dataset of 16,000 EMR-aligned synthetic consultation dialogues designed to reproduce real clinical demographic and diagnostic distributions across 12 ICD-10 psychiatric categories. Through extensive experiments across state-of-the-art LLMs, we establish key findings: (1) although LLMs achieve high accuracy on binary depression--anxiety classification (up to 92.3%), performance deteriorates substantially for depression--anxiety comorbidity recognition (43.0%) and 12-way differential diagnosis (28.5%); (2) dynamic consultation often underperforms static evaluation, indicating that ineffective information-gathering strategies significantly impair downstream diagnostic reasoning; (3) consultation quality assessed by LLM-as-a-Judge shows only moderate correlation with diagnostic accuracy, suggesting that well-structured questioning alone does not ensure correct diagnostic decisions. We release LingxiDiag-16K and the full evaluation framework to support reproducible research at https://github.com/Lingxi-mental-health/LingxiDiagBench. --- ### Fully Differentiable Bidirectional Dual-Task Synergistic Learning for Semi-Supervised 3D Medical Image Segmentation Authors: Jun Li Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09378v1 Semi-supervised learning relaxes the need of large pixel-wise labeled datasets for image segmentation by leveraging unlabeled data. The scarcity of high-quality labeled data remains a major challenge in medical image analysis due to the high annotation costs and the need for specialized clinical expertise. Semi-supervised learning has demonstrated significant potential in addressing this bottleneck, with pseudo-labeling and consistency regularization emerging as two predominant paradigms. Dual-task collaborative learning, an emerging consistency-aware paradigm, seeks to derive supplementary supervision by establishing prediction consistency between related tasks. However, current methodologies are limited to unidirectional interaction mechanisms (typically regression-to-segmentation), as segmentation results can only be transformed into regression outputs in an offline manner, thereby failing to fully exploit the potential benefits of online bidirectional cross-task collaboration. Thus, we propose a fully Differentiable Bidirectional Synergistic Learning (DBiSL) framework, which seamlessly integrates and enhances four critical SSL components: supervised learning, consistency regularization, pseudo-supervised learning, and uncertainty estimation. Experiments on two benchmark datasets demonstrate our method's state-of-the-art performance. Beyond technical contributions, this work provides new insights into unified SSL framework design and establishes a new architectural foundation for dual-task-driven SSL, while offering a generic multitask learning framework applicable to broader computer vision applications. The code will be released on github upon acceptance. --- ### Latent Poincaré Shaping for Agentic Reinforcement Learning Authors: Hanchen Xia, Baoyou Chen, Zelin Zang, Yutang Ge, Guojiang Zhao, Siyu Zhu Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.09375v3 We propose LaPha, a method for training AlphaZero-like LLM agents in a Poincaré latent space. Under LaPha, the search process can be visualized as a tree rooted at the prompt and growing outward from the origin toward the boundary of the Poincaré ball, where negative curvature provides exponentially increasing capacity with radius. Using hyperbolic geodesic distance to rule-verified correctness, we define a node potential and assign dense process rewards by potential differences. We further attach a lightweight value head on the same shared latent space, enabling self-guided test-time scaling with almost no additional overhead. On MATH-500, LaPha improves Qwen2.5-Math-1.5B from 66.0% to 88.2%. With value-head-guided search, LaPha-1.5B reaches 56.7% accuracy on AIME'24, and LaPha-7B further achieves 60.0% on AIME'24 and 53.3% on AIME'25. --- ### Surrogate-Guided Quantum Discovery in Black-Box Landscapes with Latent-Quadratic Interaction Embedding Transformers Authors: Saisubramaniam Gopalakrishnan, Dagnachew Birru Published: 2026-02-10 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2602.09374v1 Discovering configurations that are both high-utility and structurally diverse under expensive black-box evaluation and strict query budgets remains a central challenge in data-driven discovery. Many classical optimizers concentrate on dominant modes, while quality-diversity methods require large evaluation budgets to populate high-dimensional archives. Quantum Approximate Optimization Algorithm (QAOA) provides distributional sampling but requires an explicit problem Hamiltonian, which is unavailable in black-box settings. Practical quantum circuits favor quadratic Hamiltonians since higher-order interaction terms are costly to realize. Learned quadratic surrogates such as Factorization Machines (FM) have been used as proxies, but are limited to pairwise structure. We extend this surrogate-to-Hamiltonian approach by modelling higher-order variable dependencies via self-attention and projects them into a valid Positive Semi-Definite quadratic form compatible with QAOA. This enables diversity-oriented quantum sampling from learned energy landscapes while capturing interaction structure beyond pairwise terms. We evaluate on risk discovery for enterprise document processing systems against diverse classical optimizers. Quantum-guided samplers achieve competitive utility while consistently improving structural diversity and exclusive discovery. FM surrogates provide stronger early coverage, whereas ours yields higher-fidelity surrogate landscapes and better extreme-case discovery. Our method recovers roughly twice as many structurally tail-risk outliers as most classical baselines and identify an exclusive non-overlapping fraction of high-utility configurations not found by competing methods, highlighting that an effective mechanism for learning higher-order interaction structure and projecting it into quadratic surrogate Hamiltonians for quantum-assisted black-box discovery. --- ### AfriNLLB: Efficient Translation Models for African Languages Authors: Yasmin Moslem, Aman Kassahun Wassie, Amanuel Gizachew Abebe Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09373v2 In this work, we present AfriNLLB, a series of lightweight models for efficient translation from and into African languages. AfriNLLB supports 15 language pairs (30 translation directions), including Swahili, Hausa, Yoruba, Amharic, Somali, Zulu, Lingala, Afrikaans, Wolof, and Egyptian Arabic, as well as other African Union official languages such as Arabic (MSA), French, Portuguese, and Spanish. Our training data covers bidirectional translation between English and 13 languages, and between French and two languages (Lingala and Wolof). AfriNLLB models are based on NLLB-200 600M, which we compress using iterative layer pruning and quantization. We fine-tune the pruned models on parallel corpora we curated for African languages, employing knowledge distillation from a larger teacher model. Our work aims at enabling efficient deployment of translation models for African languages in resource-constrained settings. Our evaluation results demonstrate that AfriNLLB models achieve performance comparable to the baseline while being significantly faster. We release two versions of the AfriNLLB models, a Transformers version that allows further fine-tuning and a CTranslate2 version for efficient inference. Moreover, we release all the training data that we used for fine-tuning the baseline and pruned models to facilitate further research. --- ### AfriNLLB: Efficient Translation Models for African Languages Authors: Yasmin Moslem, Aman Kassahun Wassie, Amanuel Gizachew Abebe Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09373v1 In this work, we present AfriNLLB, a series of lightweight models for efficient translation from and into African languages. AfriNLLB supports 15 language pairs (30 translation directions), including Swahili, Hausa, Yoruba, Amharic, Somali, Zulu, Lingala, Afrikaans, Wolof, and Egyptian Arabic, as well as other African Union official languages such as Arabic (MSA), French, Portuguese, and Spanish. Our training data covers bidirectional translation between English and 13 languages, and between French and two languages (Lingala and Wolof). AfriNLLB models are based on NLLB-200 600M, which we compress using iterative layer pruning and quantization. We fine-tune the pruned models on parallel corpora we curated for African languages, employing knowledge distillation from a larger teacher model. Our work aims at enabling efficient deployment of translation models for African languages in resource-constrained settings. Our evaluation results demonstrate that AfriNLLB models achieve performance comparable to the baseline while being significantly faster. We release two versions of the AfriNLLB models, a Transformers version that allows further fine-tuning and a CTranslate2 version for efficient inference. Moreover, we release all the training data that we used for fine-tuning the baseline and pruned models to facilitate further research. --- ### AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis Authors: Zexu Sun, Bokai Ji, Hengyi Cai, Shuaiqiang Wang, Lei Wang, Guangxia Li, Xu Chen Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09372v1 Large Language Model agents demonstrate potential in solving real-world problems via tools, yet generalist intelligence is bottlenecked by scarce high-quality, long-horizon data. Existing methods collect privacy-constrained API logs or generate scripted interactions lacking diversity, which struggle to produce data requisite for scaling capabilities. We propose AgentSkiller, a fully automated framework synthesizing multi-turn interaction data across realistic, semantically linked domains. It employs a DAG-based architecture with explicit state transitions to ensure determinism and recoverability. The pipeline builds a domain ontology and Person-Centric Entity Graph, defines tool interfaces via Service Blueprints for Model Context Protocol servers, and populates environments with consistent databases and strict Domain Policies. A cross-domain fusion mechanism links services to simulate complex tasks. Finally, the pipeline creates user tasks by verifying solution paths, filtering via execution-based validation, and generating queries using a Persona-based Simulator for automated rollout. This produces reliable environments with clear state changes. To demonstrate effectiveness, we synthesized $\approx$ 11K interaction samples; experimental results indicate that models trained on this dataset achieve significant improvements on function calling over baselines, particularly in larger parameter regimes. --- ### Unsupervised Cross-Lingual Part-of-Speech Tagging with Monolingual Corpora Only Authors: Jianyu Zheng Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09366v1 Due to the scarcity of part-of-speech annotated data, existing studies on low-resource languages typically adopt unsupervised approaches for POS tagging. Among these, POS tag projection with word alignment method transfers POS tags from a high-resource source language to a low-resource target language based on parallel corpora, making it particularly suitable for low-resource language settings. However, this approach relies heavily on parallel corpora, which are often unavailable for many low-resource languages. To overcome this limitation, we propose a fully unsupervised cross-lingual part-of-speech(POS) tagging framework that relies solely on monolingual corpora by leveraging unsupervised neural machine translation(UNMT) system. This UNMT system first translates sentences from a high-resource language into a low-resource one, thereby constructing pseudo-parallel sentence pairs. Then, we train a POS tagger for the target language following the standard projection procedure based on word alignments. Moreover, we propose a multi-source projection technique to calibrate the projected POS tags on the target side, enhancing to train a more effective POS tagger. We evaluate our framework on 28 language pairs, covering four source languages (English, German, Spanish and French) and seven target languages (Afrikaans, Basque, Finnis, Indonesian, Lithuanian, Portuguese and Turkish). Experimental results show that our method can achieve performance comparable to the baseline cross-lingual POS tagger with parallel sentence pairs, and even exceeds it for certain target languages. Furthermore, our proposed multi-source projection technique further boosts performance, yielding an average improvement of 1.3% over previous methods. --- ### Behavioral Economics of AI: LLM Biases and Corrections Authors: Pietro Bini, Lin William Cong, Xing Huang, Lawrence J. Jin Published: 2026-02-10 Categories: econ.GN, cs.AI arXiv: https://arxiv.org/abs/2602.09362v1 Do generative AI models, particularly large language models (LLMs), exhibit systematic behavioral biases in economic and financial decisions? If so, how can these biases be mitigated? Drawing on the cognitive psychology and experimental economics literatures, we conduct the most comprehensive set of experiments to date$-$originally designed to document human biases$-$on prominent LLM families across model versions and scales. We document systematic patterns in LLM behavior. In preference-based tasks, responses become more human-like as models become more advanced or larger, while in belief-based tasks, advanced large-scale models frequently generate rational responses. Prompting LLMs to make rational decisions reduces biases. --- ### Impact of domain adaptation in deep learning for medical image classifications Authors: Yihang Wu, Ahmad Chaddad Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09355v1 Domain adaptation (DA) is a quickly expanding area in machine learning that involves adjusting a model trained in one domain to perform well in another domain. While there have been notable progressions, the fundamental concept of numerous DA methodologies has persisted: aligning the data from various domains into a shared feature space. In this space, knowledge acquired from labeled source data can improve the model training on target data that lacks sufficient labels. In this study, we demonstrate the use of 10 deep learning models to simulate common DA techniques and explore their application in four medical image datasets. We have considered various situations such as multi-modality, noisy data, federated learning (FL), interpretability analysis, and classifier calibration. The experimental results indicate that using DA with ResNet34 in a brain tumor (BT) data set results in an enhancement of 4.7\% in model performance. Similarly, the use of DA can reduce the impact of Gaussian noise, as it provides $\sim 3\%$ accuracy increase using ResNet34 on a BT dataset. Furthermore, simply introducing DA into FL framework shows limited potential (e.g., $\sim 0.3\%$ increase in performance) for skin cancer classification. In addition, the DA method can improve the interpretability of the models using the gradcam++ technique, which offers clinical values. Calibration analysis also demonstrates that using DA provides a lower expected calibration error (ECE) value $\sim 2\%$ compared to CNN alone on a multi-modality dataset. --- ### Large Language Models for Designing Participatory Budgeting Rules Authors: Nguyen Thach, Xingchen Sha, Hau Chan Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.09349v2 Participatory budgeting (PB) is a democratic paradigm for deciding the funding of public projects given the residents' preferences, which has been adopted in numerous cities across the world. The main focus of PB is designing rules, functions that return feasible budget allocations for a set of projects subject to some budget constraint. Designing PB rules that optimize both utility and fairness objectives based on agent preferences had been challenging due to the extensive domain knowledge required and the proven trade-off between the two notions. Recently, large language models (LLMs) have been increasingly employed for automated algorithmic design. Given the resemblance of PB rules to algorithms for classical knapsack problems, in this paper, we introduce a novel framework, named LLMRule, that addresses the limitations of existing works by incorporating LLMs into an evolutionary search procedure for automating the design of PB rules. Our experimental results, evaluated on more than 600 real-world PB instances obtained from the U.S., Canada, Poland, and the Netherlands with different representations of agent preferences, demonstrate that the LLM-generated rules generally outperform existing handcrafted rules in terms of overall utility while still maintaining a similar degree of fairness. --- ### Image Quality in the Era of Artificial Intelligence Authors: Jana G. Delfino, Jason L. Granstedt, Frank W. Samuelson, Robert Ochs, Krishna Juluru Published: 2026-02-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.09347v1 Artificial intelligence (AI) is being deployed within radiology at a rapid pace. AI has proven an excellent tool for reconstructing and enhancing images that appear sharper, smoother, and more detailed, can be acquired more quickly, and allowing clinicians to review them more rapidly. However, incorporation of AI also introduces new failure modes and can exacerbate the disconnect between perceived quality of an image and information content of that image. Understanding the limitations of AI-enabled image reconstruction and enhancement is critical for safe and effective use of the technology. Hence, the purpose of this communication is to bring awareness to limitations when AI is used to reconstruct or enhance a radiological image, with the goal of enabling users to reap benefits of the technology while minimizing risks. --- ### Digital Linguistic Bias in Spanish: Evidence from Lexical Variation in LLMs Authors: Yoshifumi Kawasaki Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09346v1 This study examines the extent to which Large Language Models (LLMs) capture geographic lexical variation in Spanish, a language that exhibits substantial regional variation. Treating LLMs as virtual informants, we probe their dialectal knowledge using two survey-style question formats: Yes-No questions and multiple-choice questions. To this end, we exploited a large-scale, expert-curated database of Spanish lexical variation. Our evaluation covers more than 900 lexical items across 21 Spanish-speaking countries and is conducted at both the country and dialectal area levels. Across both evaluation formats, the results reveal systematic differences in how LLMs represent Spanish language varieties. Lexical variation associated with Spain, Equatorial Guinea, Mexico & Central America, and the La Plata River is recognized more accurately by the models, while the Chilean variety proves particularly difficult for the models to distinguish. Importantly, differences in the volume of country-level digital resources do not account for these performance patterns, suggesting that factors beyond data quantity shape dialectal representation in LLMs. By providing a fine-grained, large-scale evaluation of geographic lexical variation, this work advances empirical understanding of dialectal knowledge in LLMs and contributes new evidence to discussions of Digital Linguistic Bias in Spanish. --- ### AgentCgroup: Understanding and Controlling OS Resources of AI Agents Authors: Yusheng Zheng, Jiakun Fan, Quanzhi Fu, Yiwei Yang, Wei Zhang, Andi Quinn Published: 2026-02-10 Categories: cs.OS, cs.AI arXiv: https://arxiv.org/abs/2602.09345v3 AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, each call with distinct resource demands and rapid fluctuations. We present a systematic characterization of OS-level resource dynamics in sandboxed AI coding agents, analyzing 144 software engineering tasks from the SWE-rebench benchmark across two LLM models. Our measurements reveal that (1) OS-level execution (tool calls, container and agent initialization) accounts for 55-60% of end-to-end task latency; (2) memory, not CPU, is the concurrency bottleneck; (3) memory spikes are tool-call-driven with a up to 15.4x peak-to-average ratio; and (4) resource demands are highly unpredictable across tasks, runs, and models. Comparing these characteristics against serverless, microservice, and batch workloads, we identify three mismatches in existing resource controls: a granularity mismatch (container-level policies vs. tool-call-level dynamics), a responsiveness mismatch (user-space reaction vs. sub-second unpredictable bursts), and an adaptability mismatch (history-based prediction vs. non-deterministic stateful execution). We propose AgentCgroup, an intent-driven eBPF-based resource controller that exploits agents ability to declare resource needs and reconstruct execution strategies, using hierarchical cgroup structures aligned with tool-call boundaries, in-kernel enforcement via sched_ext and memcg_bpf_ops, and runtime-adaptive policies. Preliminary evaluation demonstrates improved multi-tenant isolation and reduced resource waste. AgentCgroup is open-source at https://github.com/eunomia-bpf/agentcgroup --- ### Not-in-Perspective: Towards Shielding Google's Perspective API Against Adversarial Negation Attacks Authors: Michail S. Alexiou, J. Sukarno Mertoguno Published: 2026-02-10 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.09343v1 The rise of cyberbullying in social media platforms involving toxic comments has escalated the need for effective ways to monitor and moderate online interactions. Existing solutions of automated toxicity detection systems, are based on a machine or deep learning algorithms. However, statistics-based solutions are generally prone to adversarial attacks that contain logic based modifications such as negation in phrases and sentences. In that regard, we present a set of formal reasoning-based methodologies that wrap around existing machine learning toxicity detection systems. Acting as both pre-processing and post-processing steps, our formal reasoning wrapper helps alleviating the negation attack problems and significantly improves the accuracy and efficacy of toxicity scoring. We evaluate different variations of our wrapper on multiple machine learning models against a negation adversarial dataset. Experimental results highlight the improvement of hybrid (formal reasoning and machine-learning) methods against various purely statistical solutions. --- ### Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge Authors: Wei Yang, Shixuan Li, Heng Ping, Peiyu Zhang, Paul Bogdan, Jesse Thomason Published: 2026-02-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.09341v2 Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient. --- ### Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge Authors: Wei Yang, Shixuan Li, Heng Ping, Peiyu Zhang, Paul Bogdan, Jesse Thomason Published: 2026-02-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.09341v1 Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs), yet most frameworks still aggregate agent outputs with majority voting. This heuristic discards the evidential structure of reasoning traces and is brittle under the confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which replaces voting with a path search over a Reasoning Tree that explicitly represents agreements and divergences among agent traces. AgentAuditor resolves conflicts by comparing reasoning branches at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator on majority-failure cases and rewards evidence-based minority selections over popular errors. AgentAuditor is agnostic to MAS setting, and we find across 5 popular settings that it yields up to 5% absolute accuracy improvement over a majority vote, and up to 3% over using LLM-as-Judge. ---