# Research Papers — 2025-10 · bundle page 131 of 217 > Full-text markdown of papers #6501–6550 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/131 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/130.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/132.md) ### Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning Authors: Sanchit Sinha, Oana Frunza, Kashif Rasul, Yuriy Nevmyvaka, Aidong Zhang Published: 2025-10-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.10973v1 The capabilities of Large Vision-Language Models (LVLMs) have reached state-of-the-art on many visual reasoning tasks, including chart reasoning, yet they still falter on out-of-distribution (OOD) data, and degrade further when asked to produce their chain-of-thought (CoT) rationales, limiting explainability. We present Chart-RVR, a general framework that fine-tunes LVLMs to be more robust and explainable for chart reasoning by coupling Group Relative Policy Optimization (GRPO) with automatically verifiable rewards. Our framework comprises of three rewards that maximize: (i) correct chart-type classification, (ii) faithful chart table reconstruction, and (iii) process conformity. Applied to 3-billion-parameter LVLMs, Chart-RVR consistently outperforms standard supervised fine-tuning (SFT) on both in-distribution and out-of-distribution datasets, closing the OOD performance gap while improving rationale fidelity. The resulting models, the Chart-RVR-3B series, achieve state-of-the-art results on six chart-reasoning benchmarks spanning in-domain and OOD settings, surpassing all existing models of comparable size. Beyond accuracy, Chart-RVR yields more interpretable CoT rationales, strengthening trust and reliability - showcasing the power of verifiable rewards with GRPO for training reliable, interpretable chart-reasoning models. --- ### RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection Authors: Yejin Lee, Hyeseon Ahn, Yo-Sub Han Published: 2025-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.10971v2 Hate speech remains prevalent in human society and continues to evolve in its forms and expressions. Modern advancements in internet and online anonymity accelerate its rapid spread and complicate its detection. However, hate speech datasets exhibit diverse characteristics primarily because they are constructed from different sources and platforms, each reflecting different linguistic styles and social contexts. Despite this diversity, prior studies on hate speech detection often rely on fixed methodologies without adapting to data-specific features. We introduce RV-HATE, a detection framework designed to account for the dataset-specific characteristics of each hate speech dataset. RV-HATE consists of multiple specialized modules, where each module focuses on distinct linguistic or contextual features of hate speech. The framework employs reinforcement learning to optimize weights that determine the contribution of each module for a given dataset. A voting mechanism then aggregates the module outputs to produce the final decision. RV-HATE offers two primary advantages: (1)~it improves detection accuracy by tailoring the detection process to dataset-specific attributes, and (2)~it also provides interpretable insights into the distinctive features of each dataset. Consequently, our approach effectively addresses implicit hate speech and achieves superior performance compared to conventional static methods. Our code is available at https://github.com/leeyejin1231/RV-HATE. --- ### Bringing The Consistency Gap: Explicit Structured Memory for Interleaved Image-Text Generation Authors: Zeteng Lin, Xingxing Li, Wen You, Xiaoyang Li, Zehan Lu, Yujun Cai, Jing Tang Published: 2025-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.10969v3 Existing Vision Language Models (VLMs) often struggle to preserve logic, entity identity, and artistic style during extended, interleaved image-text interactions. We identify this limitation as "Multimodal Context Drift", which stems from the inherent tendency of implicit neural representations to decay or become entangled over long sequences. To bridge this gap, we propose IUT-Plug, a model-agnostic Neuro-Symbolic Structured State Tracking mechanism. Unlike purely neural approaches that rely on transient attention maps, IUT-Plug introduces the Image Understanding Tree (IUT) as an explicit, persistent memory module. The framework operates by (1) parsing visual scenes into hierarchical symbolic structures (entities, attributes, and relationships); (2) performing incremental state updates to logically lock invariant properties while modifying changing elements; and (3) guiding generation through topological constraints. We evaluate our approach on a novel benchmark comprising 3,000 human-annotated samples. Experimental results demonstrate that IUT-Plug effectively mitigates context drift, achieving significantly higher consistency scores compared to unstructured text-prompting baselines. This confirms that explicit symbolic grounding is essential for maintaining robust long-horizon consistency in multimodal generation. --- ### Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priors Authors: Hongkai Zheng, Austin Wang, Zihui Wu, Zhengyu Huang, Ricardo Baptista, Yisong Yue Published: 2025-10-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.10968v3 Derivative-free Bayesian inversion arises in science and engineering applications, particularly when forward model is costly or infeasible to differentiate through. Existing derivative-free methods collapse the posterior to a point estimate or return severely over-confident uncertainty on high-dimensional, nonlinear problems. We introduce Blade, which produces accurate and well-calibrated posteriors using an ensemble of interacting particles. Blade leverages diffusion models as data-driven priors, and only queries the forward model through forward evaluations (i.e., derivative-free). Theoretically, we show the convergence and stability of Blade under forward model approximation and prior score estimation error. Empirically, on nonlinear fluid dynamics, Blade produces well-calibrated posterior samples that existing derivative-free methods cannot, as measured by CRPS, the spread-skill ratio, and the rank histogram. Its accuracy and calibration improve consistently with more iterations and particles, backed by our convergence and stability analysis and empirical experiments. --- ### Judge Before Answer: Can MLLM Discern the False Premise in Question? Authors: Jidong Li, Lingyong Fang, Haodong Zhao, Sufeng Duan, Gongshen Liu Published: 2025-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.10965v1 Multimodal large language models (MLLMs) have witnessed astonishing advancements in recent years. Despite these successes, MLLMs remain vulnerable to flase premise problems. However, existing benchmarks targeting this issue are limited in scope: they often lack fine-grained categorization, exhibit insufficient coverage, and thus fail to provide a rigorous evaluation of the ability of models to recognize false premises. To bridge this gap, we introduce a fully automated pipeline for constructing a comprehensive benchmark of false premise questions. Our method systematically categorizes the premises into three main types and thirteen subtypes according to the abilities required to identify the premises, resulting in the JBA dataset.Results show current MLLMs still struggle with false premise recognition. Building upon this benchmark, we further propose a recognition enhancement framework tailored to strengthen the robustness of MLLMs to detect false premises. Extensive experiments demonstrate that models trained with our framework achieve significant improvements in false premise recognition. --- ### Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models Authors: Junhyuck Kim, Ethan Ewer, Taehong Moon, Jongho Park, Dimitris Papailiopoulos Published: 2025-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.10964v1 While 4-bit quantization has emerged as a memory-optimal choice for non-reasoning models and zero-shot tasks across scales, we show that this universal prescription fails for reasoning models, where the KV cache rather than model size can dominate memory. Through systematic experiments across 1,700 inference scenarios on AIME25 and GPQA-Diamond, we find a scale-dependent trade-off: models with an effective size below 8-bit 4B parameters achieve better accuracy by allocating memory to more weights rather than longer generation, while larger models achieve better accuracy by allocating memory to longer generations. This scale threshold also determines when parallel scaling becomes memory-efficient and whether KV cache eviction outperforms KV quantization. Our findings show that memory optimization for LLMs cannot be scale-agnostic, while providing principled guidelines: for small reasoning models, prioritize model capacity over test-time compute, while for larger ones, maximize test-time compute. Our results suggest that optimizing reasoning models for deployment requires fundamentally different strategies from those established for non-reasoning models. --- ### APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport Authors: Zhuo Li, Yuege Feng, Dandan Guo, Jinpeng Hu, Anningzhe Gao, Xiang Wan Published: 2025-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.10963v1 The reward model (RM) plays a crucial role in aligning Large Language Models (LLMs) with human preferences through Reinforcement Learning, where the Bradley-Terry (BT) objective has been recognized as simple yet powerful, specifically for pairwise preference learning. However, BT-based RMs often struggle to effectively distinguish between similar preference responses, leading to insufficient separation between preferred and non-preferred outputs. Consequently, they may easily overfit easy samples and cannot generalize well to Out-Of-Distribution (OOD) samples, resulting in suboptimal performance. To address these challenges, this paper introduces an effective enhancement to BT-based RMs through an adaptive margin mechanism. Specifically, we design to dynamically adjust the RM focus on more challenging samples through margins, based on both semantic similarity and model-predicted reward differences, which is approached from a distributional perspective solvable with Optimal Transport (OT). By incorporating these factors into a principled OT cost matrix design, our adaptive margin enables the RM to better capture distributional differences between chosen and rejected responses, yielding significant improvements in performance, convergence speed, and generalization capabilities. Experimental results across multiple benchmarks demonstrate that our method outperforms several existing RM techniques, showcasing enhanced performance in both In-Distribution (ID) and OOD settings. Moreover, RLHF experiments support our practical effectiveness in better aligning LLMs with human preferences. Our code is available at https://github.com/BIRlz/APLOT --- ### MC#: Mixture Compressor for Mixture-of-Experts Large Models Authors: Wei Huang, Yue Liao, Yukang Chen, Jianhui Liu, Haoru Tan, Si Liu, Shiming Zhang, Shuicheng Yan, Xiaojuan Qi Published: 2025-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.10962v1 Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all experts into memory and activating multiple experts per input introduces significant computational and memory overhead, making the expert module a major contributor to model size and inference cost. To address this, we propose MC# (Mixture-Compressor-sharp), a framework that combines static quantization and dynamic expert pruning by leveraging the significance of experts and tokens for aggressive compression of MoE-LLMs/VLMs. To reduce storage and loading costs, we introduce Pre-Loading Mixed-Precision Quantization (PMQ), which optimizes bit allocation via linear programming, balancing expert importance and quantization error for a Pareto-optimal trade-off between size and performance. To reduce runtime computation, Online Top-any Pruning (OTP) uses Gumbel-Softmax sampling to dynamically select a subset of experts per token, enabling fine-grained control over activation. By combining PMQ's static bit-width optimization with OTP's dynamic routing, MC# achieves extreme compression with minimal accuracy loss. On DeepSeek-VL2, MC# achieves a 6.2 times weight reduction at 2.57 average bits with only a 1.7% accuracy drop across five multimodal benchmarks. Additionally, OTP reduces expert activation over 20% with less than 1% performance degradation, demonstrating strong potential for efficient MoE-based model deployment. --- ### Obfuscation Rules for Detecting and Detoxifying Korean Toxicity Authors: Yejin Lee, Su-Hyeon Kim, Hyundong Jin, Dayoung Kim, Yeonsoo Kim, Yo-Sub Han Published: 2025-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.10961v4 As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention. Existing studies primarily focus on non-obfuscated text, which limits robustness when users intentionally disguise toxic expressions. In particular, Korean toxic expressions can be easily disguised through agglutinative morphology and Hangeul-specific orthographic variation. However, obfuscation in Korean remains largely unexplored, which motivates us to introduce a KOTOX: Korean toxic dataset for deobfuscation and detoxification. We categorize Korean obfuscation patterns into linguistically grounded classes, define transformation rules derived from real-world examples, and provide the resulting obfuscation framework as an open transformation package. Using these rules, we provide paired neutral and toxic sentences alongside their obfuscated counterparts. Models trained on our dataset better handle obfuscated text without sacrificing performance on non-obfuscated text. This is the first dataset that simultaneously supports deobfuscation and detoxification for the Korean language. We expect the dataset to facilitate better understanding and mitigation of obfuscated toxic content in LLM for Korean. Our code and data are available at https://github.com/leeyejin1231/KOTOX. --- ### Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning Authors: Xiaoyun Zhang, Xiaojian Yuan, Di Huang, Wang You, Chen Hu, Jingqing Ruan, Ai Jian, Kejiang Chen, Xing Hu Published: 2025-10-13 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2510.10959v3 Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy entropy collapse, where the policy becomes overly deterministic, hindering exploration and limiting reasoning performance. While entropy regularization is a common remedy, its effectiveness is highly sensitive to the fixed coefficient, making it unstable across tasks and models. In this work, we revisit entropy regularization in RLVR and argue that its potential has been largely underestimated. Our analysis shows that (i) tasks of varying difficulty demand distinct exploration intensities, and (ii) balanced exploration may require the policy entropy to be maintained within a moderate range below its initial level. Therefore, we propose Adaptive Entropy Regularization (AER)--a framework that dynamically balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment. Experiments on multiple mathematical reasoning benchmarks show that AER consistently outperforms baselines, improving both reasoning accuracy and exploration capability. --- ### Project-Level C-to-Rust Translation via Pointer Knowledge Graphs Authors: Zhiqiang Yuan, Wenjun Mao, Zhuo Chen, Xiyue Shang, Chong Wang, Yiling Lou, Xin Peng Published: 2025-10-13 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.10956v3 Translating C code into safe Rust is an effective way to ensure memory safety. Compared to rule-based approaches, which often produce largely unsafe Rust code, LLM-based methods generate more idiomatic and safer Rust by leveraging extensive training on human-written code. Despite their promise, existing LLM-based approaches still struggle with project-level C-to-Rust translation. They typically partition a C project into smaller units (e.g., functions) based on call graphs and translate them in a bottom-up manner to resolve dependencies. However, this unit-by-unit paradigm often fails to handle pointers due to the lack of a global view of their usage. To address this limitation, we propose a novel C-to-Rust Pointer Knowledge Graph (KG) that augments code dependency graphs with two types of pointer semantics: (i) pointer usage information, which captures global behaviors such as points-to flows and lifts low-level struct interactions to higher-level abstractions; and (ii) Rust-oriented annotations, which encode ownership, mutability, nullability, and lifetime. Building on this KG, we further propose PtrTrans, a project-level C-to-Rust translation approach. In PtrTrans, the KG provides LLMs with comprehensive global pointer semantics, guiding them to generate safe and idiomatic Rust code. Experimental results show that PtrTrans reduces unsafe usages in translated Rust by 99.9% compared to both rule-based and conventional LLM-based methods, while achieving 29.3% higher functional correctness than fuzzing-enhanced LLM approaches. --- ### Comparative Evaluation of Neural Network Architectures for Generalizable Human Spatial Preference Prediction in Unseen Built Environments Authors: Maral Doctorarastoo, Katherine A. Flanigan, Mario Bergés, Christopher McComb Published: 2025-10-13 Categories: cs.CE, cs.CV, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2510.10954v1 The capacity to predict human spatial preferences within built environments is instrumental for developing Cyber-Physical-Social Infrastructure Systems (CPSIS). A significant challenge in this domain is the generalizability of preference models, particularly their efficacy in predicting preferences within environmental configurations not encountered during training. While deep learning models have shown promise in learning complex spatial and contextual dependencies, it remains unclear which neural network architectures are most effective at generalizing to unseen layouts. To address this, we conduct a comparative study of Graph Neural Networks, Convolutional Neural Networks, and standard feedforward Neural Networks using synthetic data generated from a simplified and synthetic pocket park environment. Beginning with this illustrative case study, allows for controlled analysis of each model's ability to transfer learned preference patterns to unseen spatial scenarios. The models are evaluated based on their capacity to predict preferences influenced by heterogeneous physical, environmental, and social features. Generalizability score is calculated using the area under the precision-recall curve for the seen and unseen layouts. This generalizability score is appropriate for imbalanced data, providing insights into the suitability of each neural network architecture for preference-aware human behavior modeling in unseen built environments. --- ### Interpretable Machine Learning for Cognitive Aging: Handling Missing Data and Uncovering Social Determinant Authors: Xi Mao, Zhendong Wang, Jingyu Li, Lingchao Mao, Utibe Essien, Hairong Wang, Xuelei Sherry Ni Published: 2025-10-13 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2510.10952v1 Early detection of Alzheimer's disease (AD) is crucial because its neurodegenerative effects are irreversible, and neuropathologic and social-behavioral risk factors accumulate years before diagnosis. Identifying higher-risk individuals earlier enables prevention, timely care, and equitable resource allocation. We predict cognitive performance from social determinants of health (SDOH) using the NIH NIA-supported PREPARE Challenge Phase 2 dataset derived from the nationally representative Mex-Cog cohort of the 2003 and 2012 Mexican Health and Aging Study (MHAS). Data: The target is a validated composite cognitive score across seven domains-orientation, memory, attention, language, constructional praxis, and executive function-derived from the 2016 and 2021 MHAS waves. Predictors span demographic, socioeconomic, health, lifestyle, psychosocial, and healthcare access factors. Methodology: Missingness was addressed with a singular value decomposition (SVD)-based imputation pipeline treating continuous and categorical variables separately. This approach leverages latent feature correlations to recover missing values while balancing reliability and scalability. After evaluating multiple methods, XGBoost was chosen for its superior predictive performance. Results and Discussion: The framework outperformed existing methods and the data challenge leaderboard, demonstrating high accuracy, robustness, and interpretability. SHAP-based post hoc analysis identified top contributing SDOH factors and age-specific feature patterns. Notably, flooring material emerged as a strong predictor, reflecting socioeconomic and environmental disparities. Other influential factors, age, SES, lifestyle, social interaction, sleep, stress, and BMI, underscore the multifactorial nature of cognitive aging and the value of interpretable, data-driven SDOH modeling. --- ### Punctuation-aware treebank tree binarization Authors: Eitan Klinger, Vivaan Wadhwa, Jungyeul Park Published: 2025-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.10951v1 This article presents a curated resource and evaluation suite for punctuation-aware treebank binarization. Standard binarization pipelines drop punctuation before head selection, which alters constituent shape and harms head-child identification. We release (1) a reproducible pipeline that preserves punctuation as sibling nodes prior to binarization, (2) derived artifacts and metadata (intermediate @X markers, reversibility signatures, alignment indices), and (3) an accompanying evaluation suite covering head-child prediction, round-trip reversibility, and structural compatibility with derivational resources (CCGbank). On the Penn Treebank, punctuation-aware preprocessing improves head prediction accuracy from 73.66\% (Collins rules) and 86.66\% (MLP) to 91.85\% with the same classifier, and achieves competitive alignment against CCGbank derivations. All code, configuration files, and documentation are released to enable replication and extension to other corpora. --- ### Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank Authors: Xuyao Deng, Yanjie Sun, Yong Dou, Kele Xu Published: 2025-10-13 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2510.10948v1 Scaling laws have profoundly shaped our understanding of model performance in computer vision and natural language processing, yet their application to general audio representation learning remains underexplored. A key challenge lies in the multifactorial nature of general audio representation-representation quality is jointly influenced by variables such as audio length, embedding dimensionality, model depth, model architecture, data volume, etc., many of which are difficult to isolate or express analytically. In this work, we present a systematic study of scaling laws for general audio representations by utilizing embedding effective rank (RankMe) as a unifying metric that encapsulates the impact of diverse variables on representation quality. RankMe enables a label-free, information-theoretic quantification of audio embeddings, allowing us to examine scaling behaviors across a wide hyper-parameter space, including model size, training data volume, computational budget, architectural configurations, etc. Our empirical findings reveal a consistent power-law relationship between RankMe and representation quality, suggesting that embedding effective rank serves as a reliable proxy for assessing and predicting model performance in audio representation learning. This work not only validates the applicability of classical scaling principles to the general audio domain but also offers a theoretically grounded and empirically robust framework for guiding future model scaling strategies in audio foundation models. --- ### Towards Distribution-Shift Uncertainty Estimation for Inverse Problems with Generative Priors Authors: Namhoon Kim, Sara Fridovich-Keil Published: 2025-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.10947v1 Generative models have shown strong potential as data-driven priors for solving inverse problems such as reconstructing medical images from undersampled measurements. While these priors improve reconstruction quality with fewer measurements, they risk hallucinating features when test images lie outside the training distribution. Existing uncertainty quantification methods in this setting (i) require an in-distribution calibration dataset, which may not be available, (ii) provide heuristic rather than statistical estimates, or (iii) quantify uncertainty from model capacity or limited measurements rather than distribution shift. We propose an instance-level, calibration-free uncertainty indicator that is sensitive to distribution shift, requires no knowledge of the training distribution, and incurs no retraining cost. Our key hypothesis is that reconstructions of in-distribution images remain stable under random measurement variations, while reconstructions of out-of-distribution (OOD) images exhibit greater instability. We use this stability as a proxy for detecting distribution shift. Our proposed OOD indicator is efficiently computable for any computational imaging inverse problem; we demonstrate it on tomographic reconstruction of MNIST digits, where a learned proximal network trained only on digit "0" is evaluated on all ten digits. Reconstructions of OOD digits show higher variability and correspondingly higher reconstruction error, validating this indicator. These results suggest a deployment strategy that pairs generative priors with lightweight guardrails, enabling aggressive measurement reduction for in-distribution cases while automatically warning when priors are applied out of distribution. --- ### The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems Authors: Thi-Nhung Nguyen, Linhao Luo, Amardeep Kaur, Rollin Omari, Tamas Abraham, Junae Kim, Thuy-Trang Vu, Dinh Phung Published: 2025-10-13 Categories: cs.MA, cs.CL arXiv: https://arxiv.org/abs/2510.10943v2 Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups. While prior work has mainly focused on individual LLMs, the emergence of multi-agent systems (MAS), where multiple LLMs collaborate and communicate, introduces new and underexplored dynamics in how bias emerges, propagates, and amplifies. To systematically investigate these dynamics, we propose a simple evaluation framework with three agent-level metrics that quantify bias emergence, propagation, and amplification throughout multi-agent interaction. We evaluate MAS across three bias benchmarks under varying LLM backbones, social-group configurations, communication behaviors, and adversarial settings. Our results show that communication can trigger up to 70\% new bias emergence, propagate bias across over 80\% of agents, and amplify stereotypes by more than 3$\times$. We further find that denser and competitive communication generally increases bias. Finally, we demonstrate that MAS are highly vulnerable to simple bias injection attacks, and existing defense strategies provide only limited protection. Our findings provide important insights into the fairness and robustness of multi-agent LLM systems. --- ### Scalable and Explainable Enterprise Knowledge Discovery Using Graph-Centric Hybrid Retrieval Authors: Nilima Rao, Jagriti Srivastava, Pradeep Kumar Sharma, Hritvik Shrivastava Published: 2025-10-13 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2510.10942v1 Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis. Conventional retrieval methods based on keyword search or static embeddings often fail to answer complex queries that require contextual reasoning and multi-hop inference across artifacts. We present a modular hybrid retrieval framework for adaptive enterprise information access that integrates Knowledge Base Language-Augmented Models (KBLam), DeepGraph representations, and embedding-driven semantic search. The framework builds a unified knowledge graph from parsed repositories including code, pull requests, and commit histories, enabling semantic similarity search, structural inference, and multi-hop reasoning. Query analysis dynamically determines the optimal retrieval strategy, supporting both structured and unstructured data sources through independent or fused processing. An interactive interface provides graph visualizations, subgraph exploration, and context-aware query routing to generate concise and explainable answers. Experiments on large-scale Git repositories show that the unified reasoning layer improves answer relevance by up to 80 percent compared with standalone GPT-based retrieval pipelines. By combining graph construction, hybrid reasoning, and interactive visualization, the proposed framework offers a scalable, explainable, and user-centric foundation for intelligent knowledge assistants in enterprise environments. --- ### Redundancy as a Structural Information Principle for Learning and Generalization Authors: Yuda Bi, Ying Zhu, Vince D Calhoun Published: 2025-10-13 Categories: cs.LG, cs.AI, cs.IT, stat.ML arXiv: https://arxiv.org/abs/2510.10938v1 We present a theoretical framework that extends classical information theory to finite and structured systems by redefining redundancy as a fundamental property of information organization rather than inefficiency. In this framework, redundancy is expressed as a general family of informational divergences that unifies multiple classical measures, such as mutual information, chi-squared dependence, and spectral redundancy, under a single geometric principle. This reveals that these traditional quantities are not isolated heuristics but projections of a shared redundancy geometry. The theory further predicts that redundancy is bounded both above and below, giving rise to an optimal equilibrium that balances over-compression (loss of structure) and over-coupling (collapse). While classical communication theory favors minimal redundancy for transmission efficiency, finite and structured systems, such as those underlying real-world learning, achieve maximal stability and generalization near this equilibrium. Experiments with masked autoencoders are used to illustrate and verify this principle: the model exhibits a stable redundancy level where generalization peaks. Together, these results establish redundancy as a measurable and tunable quantity that bridges the asymptotic world of communication and the finite world of learning. --- ### Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems Authors: Qizhou Peng, Yang Zheng, Yu Wen, Yanna Wu, Yingying Du Published: 2025-10-13 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2510.10937v1 Reinforcement learning (RL) has been an important machine learning paradigm for solving long-horizon sequential decision-making problems under uncertainty. By integrating deep neural networks (DNNs) into the RL framework, deep reinforcement learning (DRL) has emerged, which achieved significant success in various domains. However, the integration of DNNs also makes it vulnerable to adversarial attacks. Existing adversarial attack techniques mainly focus on either directly manipulating the environment with which a victim agent interacts or deploying an adversarial agent that interacts with the victim agent to induce abnormal behaviors. While these techniques achieve promising results, their adoption in multi-party open systems remains limited due to two major reasons: impractical assumption of full control over the environment and dependent on interactions with victim agents. To enable adversarial attacks in multi-party open systems, in this paper, we redesigned an adversarial policy learning approach that can mislead well-trained victim agents without requiring direct interactions with these agents or full control over their environments. Particularly, we propose a neutral agent-based approach across various task scenarios in multi-party open systems. While the neutral agents seemingly are detached from the victim agents, indirectly influence them through the shared environment. We evaluate our proposed method on the SMAC platform based on Starcraft II and the autonomous driving simulation platform Highway-env. The experimental results demonstrate that our method can launch general and effective adversarial attacks in multi-party open systems. --- ### End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF: A Reproducibility Study Authors: Anirudh Ganesh, Jayavardhan Reddy Published: 2025-10-13 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.10936v1 We present a reproducibility study of the state-of-the-art neural architecture for sequence labeling proposed by Ma and Hovy (2016)\cite{ma2016end}. The original BiLSTM-CNN-CRF model combines character-level representations via Convolutional Neural Networks (CNNs), word-level context modeling through Bi-directional Long Short-Term Memory networks (BiLSTMs), and structured prediction using Conditional Random Fields (CRFs). This end-to-end approach eliminates the need for hand-crafted features while achieving excellent performance on named entity recognition (NER) and part-of-speech (POS) tagging tasks. Our implementation successfully reproduces the key results, achieving 91.18\% F1-score on CoNLL-2003 NER and demonstrating the model's effectiveness across sequence labeling tasks. We provide a detailed analysis of the architecture components and release an open-source PyTorch implementation to facilitate further research. --- ### DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objects Authors: Jiahong Chen, Jinghao Wang, Zi Wang, Ziwen Wang, Banglei Guan, Qifeng Yu Published: 2025-10-13 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2510.10933v1 6D pose estimation of textureless objects is valuable for industrial robotic applications, yet remains challenging due to the frequent loss of depth information. Current multi-view methods either rely on depth data or insufficiently exploit multi-view geometric cues, limiting their performance. In this paper, we propose DKPMV, a pipeline that achieves dense keypoint-level fusion using only multi-view RGB images as input. We design a three-stage progressive pose optimization strategy that leverages dense multi-view keypoint geometry information. To enable effective dense keypoint fusion, we enhance the keypoint network with attentional aggregation and symmetry-aware training, improving prediction accuracy and resolving ambiguities on symmetric objects. Extensive experiments on the ROBI dataset demonstrate that DKPMV outperforms state-of-the-art multi-view RGB approaches and even surpasses the RGB-D methods in the majority of cases. The code will be available soon. --- ### DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models Authors: Zonghuan Xu, Jiayu Li, Yunhan Zhao, Xiang Zheng, Xingjun Ma, Yu-Gang Jiang Published: 2025-10-13 Categories: cs.CR, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.10932v5 Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly vulnerable to behavioral backdoor manipulation: a hidden trigger introduced during training can induce unintended physical actions while nominal task performance remains intact. Prior work on VLA backdoors primarily studies untargeted attacks or task-level hijacking, leaving fine-grained control over individual actions largely unexplored. In this work, we present DropVLA, an action-level backdoor attack that forces a reusable action primitive (e.g., open_gripper) to execute at attacker-chosen decision points under a realistic pipeline-black-box setting with limited data-poisoning access, using a window-consistent relabeling scheme for chunked fine-tuning. On OpenVLA-7B evaluated with LIBERO, vision-only poisoning achieves 98.67%-99.83% attack success rate (ASR) with only 0.31% poisoned episodes while preserving 98.50%-99.17% clean-task retention, and successfully triggers the targeted action within 25 control steps at 500 Hz (0.05 s). Text-only triggers are unstable at low poisoning budgets, and combining text with vision provides no consistent ASR improvement over vision-only attacks. The backdoor remains robust to moderate trigger variations and transfers across evaluation suites (96.27%, 99.09%), whereas text-only largely fails (0.72%). We further validate physical-world feasibility on a 7-DoF Franka arm with pi0-fast, demonstrating non-trivial attack efficacy under camera-relative motion that induces image-plane trigger drift. These results reveal that VLA models can be covertly steered at the granularity of safety-critical actions with minimal poisoning and without observable degradation of nominal performance. --- ### Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents Authors: Shengjie Ma, Chenlong Deng, Jiaxin Mao, Jiadeng Huang, Teng Wang, Junjie Wu, Changwang Zhang, Jun wang Published: 2025-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.10931v3 While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike execution-based tools (e.g., code or math), whose effects are directly observable, the weak observability of causal dependencies between retrieved evidence and reasoning under format- and outcome-level supervision enables agents to maximize surface-level reward signals without genuinely grounding their reasoning in the returned evidence. This leads to distinctive pathologies, including mode collapse via tool overuse and hallucinated tool usage where tool calls are largely decorative. To address this issue, we propose Proof-of-Use (PoU), an evidence grounded RL framework that explicitly optimizes the causal dependency from retrieval to reasoning and final answers. PoU re-fomulate a fine-grained stepwise interaction protocol in which agents must auditably cite normalized evidence identifiers. We operationalize this via a multi-objective reward design consisting of: (1) two progressive process rewards that constrain citation validity at intermediate steps; (2) a global Answer--Support Alignment reward that enforces consistency between final answers and retrieved evidence; and (3) a curriculum-style adaptive reward mixing mechanism that smoothly transitions agents from dense process supervision to sparse outcome-based objectives. Extensive experiments show the strong performance of PoU and demonstrate the effectiveness in mitigating tool-call hacking. Beyond this, PoU exhibits a notable emergent property: adaptive and robust tool-usage patterns naturally arise under domain and tool shifts, even though PoU does not explicitly optimize for tool adaptation. --- ### Evaluating Language Models' Evaluations of Games Authors: Katherine M. Collins, Cedegao E. Zhang, Graham Todd, Lance Ying, Mauricio Barba da Costa, Ryan Liu, Prafull Sharma, Adrian Weller, Ionatan Kuperwajs, Lionel Wong, Joshua B. Tenenbaum, Thomas L. Griffiths Published: 2025-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.10930v3 Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial intelligence (AI) systems primarily focused on problem solving, historically by studying how models play games such as chess and Go. In this paper, we advocate for a new paradigm that assesses AI systems' evaluation of games. First, we introduce a formalism for evaluating such evaluations. We then leverage a large-scale dataset of over 100 novel board games and over 450 human judgments to compare evaluations produced by modern language and reasoning models against those of people and symbolic computational agents. We consider two kinds of evaluative queries: assessing the payoff (or fairness) and the funness of games. These queries span two dimensions relevant to the design of evaluations of AI evaluations: how complex a query is to compute and how difficult a query is to quantify. Our results show that reasoning models are generally more aligned to people in their evaluations of games than non-reasoning language models. However, we observe a non-monotonic relationship: as models get closer to game-theoretic optimal, their fit to human data weakens. We also observe more "jaggedness" across models for assessing funness, in line with the greater difficulty of quantifying this query. Across queries and games, reasoning models show highly variable and unpredictable resource usage when assessing queries, pointing to the importance of imbuing more resource-rational meta-reasoning in language and reasoning models. --- ### GapDNER: A Gap-Aware Grid Tagging Model for Discontinuous Named Entity Recognition Authors: Yawen Yang, Fukun Ma, Shiao Meng, Aiwei Liu, Lijie Wen Published: 2025-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.10927v1 In biomedical fields, one named entity may consist of a series of non-adjacent tokens and overlap with other entities. Previous methods recognize discontinuous entities by connecting entity fragments or internal tokens, which face challenges of error propagation and decoding ambiguity due to the wide variety of span or word combinations. To address these issues, we deeply explore discontinuous entity structures and propose an effective Gap-aware grid tagging model for Discontinuous Named Entity Recognition, named GapDNER. Our GapDNER innovatively applies representation learning on the context gaps between entity fragments to resolve decoding ambiguity and enhance discontinuous NER performance. Specifically, we treat the context gap as an additional type of span and convert span classification into a token-pair grid tagging task. Subsequently, we design two interactive components to comprehensively model token-pair grid features from both intra- and inter-span perspectives. The intra-span regularity extraction module employs the biaffine mechanism along with linear attention to capture the internal regularity of each span, while the inter-span relation enhancement module utilizes criss-cross attention to obtain semantic relations among different spans. At the inference stage of entity decoding, we assign a directed edge to each entity fragment and context gap, then use the BFS algorithm to search for all valid paths from the head to tail of grids with entity tags. Experimental results on three datasets demonstrate that our GapDNER achieves new state-of-the-art performance on discontinuous NER and exhibits remarkable advantages in recognizing complex entity structures. --- ### Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation Authors: Hengyuan Zhang, Shiping Yang, Xiao Liang, Chenming Shang, Yuxuan Jiang, Chaofan Tao, Jing Xiong, Hayden Kwok-Hay So, Ruobing Xie, Angel X. Chang, Ngai Wong Published: 2025-10-13 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2510.10925v3 Training student models on synthetic data generated by strong teacher models is a promising way to distilling the capabilities of teachers. However, recent studies show that stronger models are not always optimal teachers, revealing a mismatch between teacher outputs and student learnability. To address this issue, we propose PerSyn (Personalized data Synthesis), a novel synthesis strategy that operates under a new ``Route then Generate'' paradigm to create data tailored to each student model, enabling it to learn more effectively. Specifically, PerSyn first assigns each prompt to its optimal teacher via a query-level router that jointly considers student learnability and teacher response quality. Each teacher then synthesizes data only for its assigned prompts, making the process more efficient than the conventional ``Generate then Select'' paradigm, where all teachers must generate parallel responses for the entire prompt set before constructing the final dataset. Extensive experiments across different model families and scales demonstrate that PerSyn consistently achieves superior or comparable performance to all baselines in instruct tuning and math reasoning settings. Further analysis verifies the effectiveness of PerSyn and offers extra insights to propel future research. --- ### FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model Authors: Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Ji Ao, Dawei Leng, Yuhui Yin Published: 2025-10-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.10921v3 Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP perform well on global alignment, they often struggle to capture fine-grained details in object attributes, spatial relations, and linguistic expressions, with limited support for bilingual comprehension. To address these challenges, we introduce FG-CLIP 2, a bilingual vision-language model designed to advance fine-grained alignment for both English and Chinese. Our approach leverages rich fine-grained supervision, including region-text matching and long-caption modeling, alongside multiple discriminative objectives. We further introduce the Textual Intra-modal Contrastive (TIC) loss to better distinguish semantically similar captions. Trained on a carefully curated mixture of large-scale English and Chinese data, including a newly released 12M Chinese region-text dataset, FG-CLIP 2 achieves powerful bilingual performance. To enable rigorous evaluation, we present a new benchmark for Chinese multimodal understanding, featuring long-caption retrieval and bounding box classification. Extensive experiments on 29 datasets across 8 tasks show that FG-CLIP 2 outperforms existing methods, achieving state-of-the-art results in both languages. We release the model, code, and benchmark to facilitate future research on bilingual fine-grained vision-language alignment. --- ### Comparative Explanations via Counterfactual Reasoning in Recommendations Authors: Yi Yu, Zhenxing Hu Published: 2025-10-13 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2510.10920v1 Explainable recommendation through counterfactual reasoning seeks to identify the influential aspects of items in recommendations, which can then be used as explanations. However, state-of-the-art approaches, which aim to minimize changes in product aspects while reversing their recommended decisions according to an aggregated decision boundary score, often lead to factual inaccuracies in explanations. To solve this problem, in this work we propose a novel method of Comparative Counterfactual Explanations for Recommendation (CoCountER). CoCountER creates counterfactual data based on soft swap operations, enabling explanations for recommendations of arbitrary pairs of comparative items. Empirical experiments validate the effectiveness of our approach. --- ### DreamMakeup: Face Makeup Customization using Latent Diffusion Models Authors: Geon Yeong Park, Inhwa Han, Serin Yang, Yeobin Hong, Seongmin Jeong, Heechan Jeon, Myeongjin Goh, Sung Won Yi, Jin Nam, Jong Chul Ye Published: 2025-10-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.10918v1 The exponential growth of the global makeup market has paralleled advancements in virtual makeup simulation technology. Despite the progress led by GANs, their application still encounters significant challenges, including training instability and limited customization capabilities. Addressing these challenges, we introduce DreamMakup - a novel training-free Diffusion model based Makeup Customization method, leveraging the inherent advantages of diffusion models for superior controllability and precise real-image editing. DreamMakeup employs early-stopped DDIM inversion to preserve the facial structure and identity while enabling extensive customization through various conditioning inputs such as reference images, specific RGB colors, and textual descriptions. Our model demonstrates notable improvements over existing GAN-based and recent diffusion-based frameworks - improved customization, color-matching capabilities, identity preservation and compatibility with textual descriptions or LLMs with affordable computational costs. --- ### LPCVAE: A Conditional VAE with Long-Term Dependency and Probabilistic Time-Frequency Fusion for Time Series Anomaly Detection Authors: Hanchang Cheng, Weimin Mu, Fan Liu, Weilin Zhu, Can Ma Published: 2025-10-13 Categories: cs.LG, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2510.10915v1 Time series anomaly detection(TSAD) is a critical task in signal processing field, ensuring the reliability of complex systems. Reconstruction-based methods dominate in TSAD. Among these methods, VAE-based methods have achieved promising results. Existing VAE-based methods suffer from the limitation of single-window feature and insufficient leveraging of long-term time and frequency information. We propose a Conditional Variational AutoEncoder with Long-term dependency and Probabilistic time-frequency fusion, named LPCVAE. LPCVAE introduces LSTM to capture long-term dependencies beyond windows. It further incorporates a Product-of-Experts (PoE) mechanism for adaptive and distribution-level probabilistic fusion. This design effectively mitigates time-frequency information loss. Extensive experiments on four public datasets demonstrate it outperforms state-of-the-art methods. The results confirm that integrating long-term time and frequency representations with adaptive fusion yields a robust and efficient solution for TSAD. --- ### ADVICE: Answer-Dependent Verbalized Confidence Estimation Authors: Ki Jung Seo, Sehun Lim, Taeuk Kim Published: 2025-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.10913v3 Recent progress in large language models (LLMs) has enabled them to communicate their confidence in natural language, improving transparency and reliability. However, this expressiveness is often accompanied by systematic overconfidence, whose underlying causes remain poorly understood. In this work, we analyze the dynamics of verbalized confidence estimation and identify answer-independence -- the failure to condition confidence on the model's own answer -- as a primary driver of this behavior. To address this, we introduce ADVICE (Answer-Dependent Verbalized Confidence Estimation), a fine-tuning framework that promotes answer-grounded confidence estimation. Extensive experiments show that ADVICE substantially improves confidence calibration, while exhibiting strong generalization to unseen settings without degrading task performance. We further demonstrate that these gains stem from enhanced answer dependence, shedding light on the origins of overconfidence and enabling trustworthy confidence verbalization. --- ### SceneTextStylizer: A Training-Free Scene Text Style Transfer Framework with Diffusion Model Authors: Honghui Yuan, Keiji Yanai Published: 2025-10-13 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2510.10910v1 With the rapid development of diffusion models, style transfer has made remarkable progress. However, flexible and localized style editing for scene text remains an unsolved challenge. Although existing scene text editing methods have achieved text region editing, they are typically limited to content replacement and simple styles, which lack the ability of free-style transfer. In this paper, we introduce SceneTextStylizer, a novel training-free diffusion-based framework for flexible and high-fidelity style transfer of text in scene images. Unlike prior approaches that either perform global style transfer or focus solely on textual content modification, our method enables prompt-guided style transformation specifically for text regions, while preserving both text readability and stylistic consistency. To achieve this, we design a feature injection module that leverages diffusion model inversion and self-attention to transfer style features effectively. Additionally, a region control mechanism is introduced by applying a distance-based changing mask at each denoising step, enabling precise spatial control. To further enhance visual quality, we incorporate a style enhancement module based on the Fourier transform to reinforce stylistic richness. Extensive experiments demonstrate that our method achieves superior performance in scene text style transformation, outperforming existing state-of-the-art methods in both visual fidelity and text preservation. --- ### PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature Authors: Daoyu Wang, Mingyue Cheng, Shuo Yu, Zirui Liu, Ze Guo, Xin Li, Qi Liu Published: 2025-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.10909v4 Understanding and reasoning on the large-scale scientific literature is a crucial touchstone for large language model (LLM) based agents. However, existing works are mainly restricted to tool-free tasks within single papers, largely due to the lack of a benchmark that evaluates cross-paper reasoning and multi-tool orchestration in authentic research scenarios. In this work, we propose PaperArena, a benchmark to evaluate LLM-based agents on questions that require integrating information across multiple papers with the assistance of external tools. Given a research question, agents should formulate a reasoning plan, interact with multiple papers, and invoke appropriate tools to produce a well-grounded answer. To support standardized evaluation, we provide a platform for agent execution, offering a modular tool environment including multimodal parsing, context retrieval, and programmatic computation. Experiments reveal that even the leading LLM powering a well-established agentic workflow achieves merely 38.78% average accuracy, while on the hard subset, accuracy drops to only 18.47%. We also analyze reasoning traces and diagnose agent behavior, providing the community with insights to develop and evaluate more capable scientific agents. --- ### Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness Authors: Sleem Abdelghafar, Maryam Aliakbarpour, Christopher Jermaine Published: 2025-10-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.10902v3 Auditing information disclosure across every datapoint during the training of LLMs is challenging. We propose a principled, attack-agnostic approach that uses mutual information to measure what the final model reveals about a datapoint's training membership. We show that this final-model disclosure is upper bounded by the sum of per-iteration gradient disclosures and that, under a reasonable set of assumptions, these gradient disclosures increase with Gradient Uniqueness (GNQ), which measures how distinguishable a datapoint's gradient is relative to other gradients in the batch. While naively computing GNQ requires forming and inverting a $P\times P$ matrix for every datapoint (for a model with $P$ parameters), we introduce Batch-Space Ghost (BS-Ghost). This efficient algorithm performs all computations in a much smaller batch space and uses ghost kernels to compute GNQ "in-run" for every datapoint in the training corpus, with minimal computational and memory overhead. Our experiments show the following: (i) GNQ predicts MIA vulnerability without the need for shadow models. (ii) Beyond membership disclosure, GNQ predicts the success of reconstruction attacks. (iii) GNQ-guided removal and retraining identify datapoints that causally contribute to disclosure. (iv) GNQ outperforms counterfactual memorization in text extraction and common-knowledge discrimination without the need for additional model training. (v) For data attribution, GNQ-guided filtering reduces emergent misalignment in Qwen2.5-7B more than baselines. Further, GNQ attributes 1000 datapoints in 17 seconds---roughly $70\times$ faster than the baselines. (vi) GNQ explains how training choices affect training-set disclosure and captures how per-datapoint disclosure emerges during training. --- ### LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach Authors: Renxuan Tan, Rongpeng Li, Fei Wang, Chenghui Peng, Shaoyun Wu, Zhifeng Zhao, Honggang Zhang Published: 2025-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.10895v2 Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured. While deep reinforcement learning (DRL)-based protocols enhance task-specified network performance, they suffer from poor generalizability and resilience, demanding costly retraining to adapt to dynamic environments. To overcome this limitation, we introduce a game-theoretic LLM-empowered multi-agent DRL (MARL) framework, in which the uplink transmission between a base station and a varying number of user equipments is modeled as a dynamic multi-follower Stackelberg game (MFSG), capturing the network's natural hierarchical structure. Within this game, LLM-driven agents, coordinated through proximal policy optimization (PPO), synthesize adaptive, semantic MAC protocols in response to network dynamics. Protocol action grammar (PAG) is employed to ensure the reliability and efficiency of this process. Under this system, we further analyze the existence and convergence behavior in terms of a Stackelberg equilibrium by studying the learning dynamics of LLM-empowered unified policies in response to changing followers. Simulations corroborate that our framework achieves a 77.6% greater throughput and a 65.2% fairness improvement over conventional baselines. Besides, our framework generalizes excellently to a fluctuating number of users without requiring retraining or architectural changes. --- ### LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System Authors: Yu Chao, Siyu Lin, xiaorong wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun Published: 2025-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.10890v2 We introduce LLM x MapReduce-V3, a hierarchically modular agent system designed for long-form survey generation. Building on the prior work, LLM x MapReduce-V2, this version incorporates a multi-agent architecture where individual functional components, such as skeleton initialization, digest construction, and skeleton refinement, are implemented as independent model-context-protocol (MCP) servers. These atomic servers can be aggregated into higher-level servers, creating a hierarchically structured system. A high-level planner agent dynamically orchestrates the workflow by selecting appropriate modules based on their MCP tool descriptions and the execution history. This modular decomposition facilitates human-in-the-loop intervention, affording users greater control and customization over the research process. Through a multi-turn interaction, the system precisely captures the intended research perspectives to generate a comprehensive skeleton, which is then developed into an in-depth survey. Human evaluations demonstrate that our system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning. --- ### Topological Alignment of Shared Vision-Language Embedding Space Authors: Junwon You, Dasol Kang, Jae-Hun Jung Published: 2025-10-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.10889v2 Contrastive Vision-Language Models (VLMs) have demonstrated strong zero-shot capabilities. However, their cross-modal alignment remains biased toward English due to limited multilingual multimodal data. Recent multilingual extensions have alleviated this gap but enforce instance-level alignment while neglecting the global geometry of the shared embedding space. We address this problem by introducing ToMCLIP (Topological Alignment for Multilingual CLIP), a topology-aware framework aligning embedding spaces with topology-preserving constraints. The proposed method applies persistent homology to define a topological alignment loss and approximates persistence diagram with theoretical error bounds using graph sparsification strategy. This work validates the proposed approach, showing enhanced structural coherence of multilingual representations, higher zero-shot accuracy on the CIFAR-100, and stronger multilingual retrieval performance on the xFlickr&CO. Beyond VLMs, the proposed approach provides a general method for incorporating topological alignment into representation learning. Code is available at https://github.com/junwon0/ToMCLIP.git. --- ### Generative AI for Software Project Management: Insights from a Review of Software Practitioner Literature Authors: Lakshana Iruni Assalaarachchi, Zainab Masood, Rashina Hoda, John Grundy Published: 2025-10-13 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.10887v1 Software practitioners are discussing GenAI transformations in software project management openly and widely. To understand the state of affairs, we performed a grey literature review using 47 publicly available practitioner sources including blogs, articles, and industry reports. We found that software project managers primarily perceive GenAI as an "assistant", "copilot", or "friend" rather than as a "PM replacement", with support of GenAI in automating routine tasks, predictive analytics, communication and collaboration, and in agile practices leading to project success. Practitioners emphasize responsible GenAI usage given concerns such as hallucinations, ethics and privacy, and lack of emotional intelligence and human judgment. We present upskilling requirements for software project managers in the GenAI era mapped to the Project Management Institute's talent triangle. We share key recommendations for both practitioners and researchers. --- ### Rethinking Agentic Workflows: Evaluating Inference-Based Test-Time Scaling Strategies in Text2SQL Tasks Authors: Jiajing Guo, Kenil Patel, Jorge Piazentin Ono, Wenbin He, Liu Ren Published: 2025-10-13 Categories: cs.CL, cs.DB arXiv: https://arxiv.org/abs/2510.10885v1 Large language models (LLMs) are increasingly powering Text-to-SQL (Text2SQL) systems, enabling non-expert users to query industrial databases using natural language. While test-time scaling strategies have shown promise in LLM-based solutions, their effectiveness in real-world applications, especially with the latest reasoning models, remains uncertain. In this work, we benchmark six lightweight, industry-oriented test-time scaling strategies and four LLMs, including two reasoning models, evaluating their performance on the BIRD Mini-Dev benchmark. Beyond standard accuracy metrics, we also report inference latency and token consumption, providing insights relevant for practical system deployment. Our findings reveal that Divide-and-Conquer prompting and few-shot demonstrations consistently enhance performance for both general-purpose and reasoning-focused LLMs. However, introducing additional workflow steps yields mixed results, and base model selection plays a critical role. This work sheds light on the practical trade-offs between accuracy, efficiency, and complexity when deploying Text2SQL systems. --- ### Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales Authors: Zhaofang Qian, Hardy Chen, Zeyu Wang, Li Zhang, Zijun Wang, Xiaoke Huang, Hui Liu, Xianfeng Tang, Zeyu Zheng, Haoqin Tu, Cihang Xie, Yuyin Zhou Published: 2025-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.10880v1 Vision-language models (VLMs) have advanced rapidly, yet their capacity for image-grounded geolocation in open-world conditions, a task that is challenging and of demand in real life, has not been comprehensively evaluated. We present EarthWhere, a comprehensive benchmark for VLM image geolocation that evaluates visual recognition, step-by-step reasoning, and evidence use. EarthWhere comprises 810 globally distributed images across two complementary geolocation scales: WhereCountry (i.e., 500 multiple-choice question-answering, with country-level answer and panoramas) and WhereStreet (i.e., 310 fine-grained street-level identification tasks requiring multi-step reasoning with optional web search). For evaluation, we adopt the final-prediction metrics: location accuracies within k km (Acc@k) for coordinates and hierarchical path scores for textual localization. Beyond this, we propose to explicitly score intermediate reasoning chains using human-verified key visual clues and a Shapley-reweighted thinking score that attributes credit to each clue's marginal contribution. We benchmark 13 state-of-the-art VLMs with web searching tools on our EarthWhere and report different types of final answer accuracies as well as the calibrated model thinking scores. Overall, Gemini-2.5-Pro achieves the best average accuracy at 56.32%, while the strongest open-weight model, GLM-4.5V, reaches 34.71%. We reveal that web search and reasoning do not guarantee improved performance when visual clues are limited, and models exhibit regional biases, achieving up to 42.7% higher scores in certain areas than others. These findings highlight not only the promise but also the persistent challenges of models to mitigate bias and achieve robust, fine-grained localization. We open-source our benchmark at https://github.com/UCSC-VLAA/EarthWhere. --- ### rareboost3d: a synthetic lidar dataset with enhanced rare classes Authors: Shutong Lin, Zhengkang Xiang, Jianzhong Qi, Kourosh Khoshelham Published: 2025-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.10876v1 Real-world point cloud datasets have made significant contributions to the development of LiDAR-based perception technologies, such as object segmentation for autonomous driving. However, due to the limited number of instances in some rare classes, the long-tail problem remains a major challenge in existing datasets. To address this issue, we introduce a novel, synthetic point cloud dataset named RareBoost3D, which complements existing real-world datasets by providing significantly more instances for object classes that are rare in real-world datasets. To effectively leverage both synthetic and real-world data, we further propose a cross-domain semantic alignment method named CSC loss that aligns feature representations of the same class across different domains. Experimental results demonstrate that this alignment significantly enhances the performance of LiDAR point cloud segmentation models over real-world data. --- ### Transfer Learning with Distance Covariance for Random Forest: Error Bounds and an EHR Application Authors: Chenze Li, Subhadeep Paul Published: 2025-10-13 Categories: stat.ML, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2510.10870v2 We propose a method for transfer learning in nonparametric regression using a random forest (RF) with distance covariance-based feature weights, assuming the unknown source and target regression functions are sparsely different. Our method obtains residuals from a source domain-trained Centered RF (CRF) in the target domain, then fits another CRF to these residuals with feature splitting probabilities proportional to feature-residual sample distance covariance. We derive an upper bound on the mean square error rate of the procedure as a function of sample sizes and difference dimension, theoretically demonstrating transfer learning benefits in random forests. A major difficulty for transfer learning in random forests is the lack of explicit regularization in the method. Our results explain why shallower trees with preferential selection of features lead to both lower bias and lower variance for fitting a low-dimensional function. We show that in the residual random forest, this implicit regularization is enabled by sample distance covariance. In simulations, we show that the results obtained for the CRFs also hold numerically for the standard RF (SRF) method with data-driven feature split selection. Beyond transfer learning, our results also show the benefit of distance-covariance-based weights on the performance of RF when some features dominate. Our method shows significant gains in predicting the mortality of ICU patients in smaller-bed target hospitals using a large multi-hospital dataset of electronic health records for 200,000 ICU patients. --- ### FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding Authors: Soroush Mehraban, Andrea Iaboni, Babak Taati Published: 2025-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.10868v1 Recent transformer-based models for 3D Human Mesh Recovery (HMR) have achieved strong performance but often suffer from high computational cost and complexity due to deep transformer architectures and redundant tokens. In this paper, we introduce two HMR-specific merging strategies: Error-Constrained Layer Merging (ECLM) and Mask-guided Token Merging (Mask-ToMe). ECLM selectively merges transformer layers that have minimal impact on the Mean Per Joint Position Error (MPJPE), while Mask-ToMe focuses on merging background tokens that contribute little to the final prediction. To further address the potential performance drop caused by merging, we propose a diffusion-based decoder that incorporates temporal context and leverages pose priors learned from large-scale motion capture datasets. Experiments across multiple benchmarks demonstrate that our method achieves up to 2.3x speed-up while slightly improving performance over the baseline. --- ### Quantifying Data Similarity Using Cross Learning Authors: Shudong Sun, Hao Helen Zhang, Joseph C Watkins Published: 2025-10-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.10866v3 Measuring dataset similarity is fundamental in machine learning, particularly for transfer learning and domain adaptation. In the context of supervised learning, most existing approaches quantify similarity of two data sets based on their input feature distributions, neglecting label information and feature-response alignment. To address this, we propose the Cross-Learning Score (CLS), which measures dataset similarity through bidirectional generalization performance of decision rules. We establish its theoretical foundation by linking CLS to cosine similarity between decision boundaries under canonical linear models, providing a geometric interpretation. A robust ensemble-based estimator is developed that is easy to implement and bypasses high-dimensional density estimation entirely. For transfer learning applications, we introduce a "transferable zones" framework that categorizes source datasets into positive, ambiguous, and negative transfer regions. To accommodate deep learning, we extend CLS to encoder-head architectures, aligning with modern representation-based pipelines. Extensive experiments on synthetic and real-world datasets validate the effectiveness of CLS for similarity measurement and transfer assessment. --- ### GRIP: A Unified Framework for Grid-Based Relay and Co-Occurrence-Aware Planning in Dynamic Environments Authors: Ahmed Alanazi, Duy Ho, Yugyung Lee Published: 2025-10-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.10865v1 Robots navigating dynamic, cluttered, and semantically complex environments must integrate perception, symbolic reasoning, and spatial planning to generalize across diverse layouts and object categories. Existing methods often rely on static priors or limited memory, constraining adaptability under partial observability and semantic ambiguity. We present GRIP, Grid-based Relay with Intermediate Planning, a unified, modular framework with three scalable variants: GRIP-L (Lightweight), optimized for symbolic navigation via semantic occupancy grids; GRIP-F (Full), supporting multi-hop anchor chaining and LLM-based introspection; and GRIP-R (Real-World), enabling physical robot deployment under perceptual uncertainty. GRIP integrates dynamic 2D grid construction, open-vocabulary object grounding, co-occurrence-aware symbolic planning, and hybrid policy execution using behavioral cloning, D* search, and grid-conditioned control. Empirical results on AI2-THOR and RoboTHOR benchmarks show that GRIP achieves up to 9.6% higher success rates and over $2\times$ improvement in path efficiency (SPL and SAE) on long-horizon tasks. Qualitative analyses reveal interpretable symbolic plans in ambiguous scenes. Real-world deployment on a Jetbot further validates GRIP's generalization under sensor noise and environmental variation. These results position GRIP as a robust, scalable, and explainable framework bridging simulation and real-world navigation. --- ### HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations Authors: Shuaicheng Zhang, Haohui Wang, Junhong Lin, Xiaojie Guo, Yada Zhu, Si Zhang, Dongqi Fu, Dawei Zhou Published: 2025-10-13 Categories: cs.LG, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2510.10864v1 Graph heterophily, where connected nodes have different labels, has attracted significant interest recently. Most existing works adopt a simplified approach - using low-pass filters for homophilic graphs and high-pass filters for heterophilic graphs. However, we discover that the relationship between graph heterophily and spectral filters is more complex - the optimal filter response varies across frequency components and does not follow a strict monotonic correlation with heterophily degree. This finding challenges conventional fixed filter designs and suggests the need for adaptive filtering to preserve expressiveness in graph embeddings. Formally, natural questions arise: Given a heterophilic graph G, how and to what extent will the varying heterophily degree of G affect the performance of GNNs? How can we design adaptive filters to fit those varying heterophilic connections? Our theoretical analysis reveals that the average frequency response of GNNs and graph heterophily degree do not follow a strict monotonic correlation, necessitating adaptive graph filters to guarantee good generalization performance. Hence, we propose (METHOD NAME), a simple yet powerful GNN, which extracts information across the heterophily spectrum and combines salient representations through adaptive mixing. (METHOD NAME)'s superior performance achieves up to 9.2% accuracy improvement over leading baselines across homophilic and heterophilic graphs. --- ### A Joint Learning Approach to Hardware Caching and Prefetching Authors: Samuel Yuan, Divyanshu Saxena, Jiayi Chen, Nihal Sharma, Aditya Akella Published: 2025-10-13 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2510.10862v1 Several learned policies have been proposed to replace heuristics for scheduling, caching, and other system components in modern systems. By leveraging diverse features, learning from historical trends, and predicting future behaviors, such models promise to keep pace with ever-increasing workload dynamism and continuous hardware evolution. However, policies trained in isolation may still achieve suboptimal performance when placed together. In this paper, we inspect one such instance in the domain of hardware caching -- for the policies of cache replacement and prefetching. We argue that these two policies are bidirectionally interdependent and make the case for training the two jointly. We propose a joint learning approach based on developing shared representations for the features used by the two policies. We present two approaches to develop these shared representations, one based on a joint encoder and another based on contrastive learning of the embeddings, and demonstrate promising preliminary results for both of these. Finally, we lay down an agenda for future research in this direction. --- ### Limits of Emergent Reasoning of Large Language Models in Agentic Frameworks for Deterministic Games Authors: Chris Su, Harrison Li, Matheus Marques, George Flint, Kevin Zhu, Sunishchal Dev Published: 2025-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.15974v1 Recent work reports that Large Reasoning Models (LRMs) undergo a collapse in performance on solving puzzles beyond certain perplexity thresholds. In subsequent discourse, questions have arisen as to whether the nature of the task muddles an evaluation of true reasoning. One potential confound is the requirement that the model keep track of the state space on its own. We provide a large language model (LLM) with an environment interface for Tower of Hanoi problems, allowing it to make a move with a tool call, provide written justification, observe the resulting state space, and reprompt itself for the next move. We observe that access to an environment interface does not delay or eradicate performance collapse. Furthermore, LLM-parameterized policy analysis reveals increasing divergence from both optimal policies and uniformly random policies, suggesting that the model exhibits mode-like collapse at each level of complexity, and that performance is dependent upon whether the mode reflects the correct solution for the problem. We suggest that a similar phenomena might take place in LRMs. --- ### Safeguarding Efficacy in Large Language Models: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts Authors: Tiarnaigh Downey-Webb, Olamide Jogunola, Oluwaseun Ajao Published: 2025-10-12 Categories: cs.CR, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.15973v1 This paper presents a systematic security assessment of four prominent Large Language Models (LLMs) against diverse adversarial attack vectors. We evaluate Phi-2, Llama-2-7B-Chat, GPT-3.5-Turbo, and GPT-4 across four distinct attack categories: human-written prompts, AutoDAN, Greedy Coordinate Gradient (GCG), and Tree-of-Attacks-with-pruning (TAP). Our comprehensive evaluation employs 1,200 carefully stratified prompts from the SALAD-Bench dataset, spanning six harm categories. Results demonstrate significant variations in model robustness, with Llama-2 achieving the highest overall security (3.4% average attack success rate) while Phi-2 exhibits the greatest vulnerability (7.0% average attack success rate). We identify critical transferability patterns where GCG and TAP attacks, though ineffective against their target model (Llama-2), achieve substantially higher success rates when transferred to other models (up to 17% for GPT-4). Statistical analysis using Friedman tests reveals significant differences in vulnerability across harm categories ($p < 0.001$), with malicious use prompts showing the highest attack success rates (10.71% average). Our findings contribute to understanding cross-model security vulnerabilities and provide actionable insights for developing targeted defense mechanisms ---