# Research Papers — 2025-10 · bundle page 104 of 217

> Full-text markdown of papers #5151–5200 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/104
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/103.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/105.md)

### Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video

Authors: Yulin Zhang, Cheng Shi, Yang Wang, Sibei Yang
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14560v1

Envision an AI capable of functioning in human-like settings, moving beyond mere observation to actively understand, anticipate, and proactively respond to unfolding events. Towards this vision, we focus on the innovative task where, given ego-streaming video input, an assistant proactively answers diverse, evolving questions at the opportune moment, while maintaining synchronized perception and reasoning. This task embodies three key properties: (1) Proactive Coherence, (2) Just-in-Time Responsiveness, and (3) Synchronized Efficiency. To evaluate and address these properties, we first introduce ESTP-Bench (Ego Streaming Proactive Benchmark) alongside the ESTP-F1 metric-a novel framework designed for their rigorous assessment. Secondly, we propose a comprehensive technical pipeline to enable models to tackle this challenging task. This pipeline comprises: (1) a data engine, (2) a multi-stage training strategy, and (3) a proactive dynamic compression technique. Our proposed model effectively addresses these critical properties while outperforming multiple baselines across diverse online and offline benchmarks. Project Page:https://zhangyl4.github.io/publications/eyes-wide-open/

---

### MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving

Authors: Jungi Lee, Junyong Park, Soohyun Cha, Jaehoon Cho, Jaewoong Sim
Published: 2025-10-16
Categories: cs.LG, cs.AR
arXiv: https://arxiv.org/abs/2510.14557v1

Reduced-precision data formats are crucial for cost-effective serving of large language models (LLMs). While numerous reduced-precision formats have been introduced thus far, they often require intrusive modifications to the software frameworks or are rather unconventional for widespread adoption across hardware vendors. In this paper, we instead focus on recent industry-driven variants of block floating-point (BFP) formats and conduct a comprehensive analysis to push their limits for efficient LLM serving. Our analysis shows that existing ultra low-bit BFP variants struggle to provide reasonable language model performance due to outlier values in blocks. To address the outliers with BFPs, we propose MX+, a cost-effective and non-intrusive extension designed for seamless integration into the microscaling (MX) formats. MX+ builds on the key insight that the outlier does not need to use its exponent field in the element data type, which allows us to repurpose the exponent field as an extended mantissa to increase the precision of the outlier element. Our evaluation shows that MX+ achieves significantly higher model performance compared to the 4-bit MX format (MXFP4) with negligible storage overhead and slowdown, thus offering a compelling alternative to MXFP4 or MXFP6 for efficient LLM inference.

---

### Consistent text-to-image generation via scene de-contextualization

Authors: Song Tang, Peihao Gong, Kunyu Li, Kai Guo, Boyu Wang, Mao Ye, Jianwei Zhang, Xiatian Zhu
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14553v2

Consistent text-to-image (T2I) generation seeks to produce identity-preserving images of the same subject across diverse scenes, yet it often fails due to a phenomenon called identity (ID) shift. Previous methods have tackled this issue, but typically rely on the unrealistic assumption of knowing all target scenes in advance. This paper reveals that a key source of ID shift is the native correlation between subject and scene context, called scene contextualization, which arises naturally as T2I models fit the training distribution of vast natural images. We formally prove the near-universality of this scene-ID correlation and derive theoretical bounds on its strength. On this basis, we propose a novel, efficient, training-free prompt embedding editing approach, called Scene De-Contextualization (SDeC), that imposes an inversion process of T2I's built-in scene contextualization. Specifically, it identifies and suppresses the latent scene-ID correlation within the ID prompt's embedding by quantifying the SVD directional stability to adaptively re-weight the corresponding eigenvalues. Critically, SDeC allows for per-scene use (one scene per prompt) without requiring prior access to all target scenes. This makes it a highly flexible and general solution well-suited to real-world applications where such prior knowledge is often unavailable or varies over time. Experiments demonstrate that SDeC significantly enhances identity preservation while maintaining scene diversity.

---

### LLM Agents Beyond Utility: An Open-Ended Perspective

Authors: Asen Nachkov, Xi Wang, Luc Van Gool
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.14548v1

Recent LLM agents have made great use of chain of thought reasoning and function calling. As their capabilities grow, an important question arises: can this software represent not only a smart problem-solving tool, but an entity in its own right, that can plan, design immediate tasks, and reason toward broader, more ambiguous goals? To study this question, we adopt an open-ended experimental setting where we augment a pretrained LLM agent with the ability to generate its own tasks, accumulate knowledge, and interact extensively with its environment. We study the resulting open-ended agent qualitatively. It can reliably follow complex multi-step instructions, store and reuse information across runs, and propose and solve its own tasks, though it remains sensitive to prompt design, prone to repetitive task generation, and unable to form self-representations. These findings illustrate both the promise and current limits of adapting pretrained LLMs toward open-endedness, and point to future directions for training agents to manage memory, explore productively, and pursue abstract long-term goals.

---

### Agentic Entropy-Balanced Policy Optimization

Authors: Guanting Dong, Licheng Bao, Zhongyuan Wang, Kangzhi Zhao, Xiaoxi Li, Jiajie Jin, Jinghan Yang, Hangyu Mao, Fuzheng Zhang, Kun Gai, Guorui Zhou, Yutao Zhu et al.
Published: 2025-10-16
Categories: cs.LG, cs.AI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.14545v1

Recently, Agentic Reinforcement Learning (Agentic RL) has made significant progress in incentivizing the multi-turn, long-horizon tool-use capabilities of web agents. While mainstream agentic RL algorithms autonomously explore high-uncertainty tool-call steps under the guidance of entropy, excessive reliance on entropy signals can impose further constraints, leading to the training collapse. In this paper, we delve into the challenges caused by entropy and propose the Agentic Entropy-Balanced Policy Optimization (AEPO), an agentic RL algorithm designed to balance entropy in both the rollout and policy update phases. AEPO comprises two core components: (1) a dynamic entropy-balanced rollout mechanism that adaptively allocate global and branch sampling budget through entropy pre-monitoring, while imposing a branch penalty on consecutive high-entropy tool-call steps to prevent over-branching issues; and (2) Entropy-Balanced Policy Optimization that inserts a stop-gradient operation into the high-entropy clipping term to preserve and properly rescale gradients on high-entropy tokens, while incorporating entropy-aware advantage estimation to prioritize learning on high-uncertainty tokens. Results across 14 challenging datasets show that AEPO consistently outperforms 7 mainstream RL algorithms. With just 1K RL samples, Qwen3-14B with AEPO achieves impressive results: 47.6% on GAIA, 11.2% on Humanity's Last Exam, and 43.0% on WebWalker for Pass@1; 65.0% on GAIA, 26.0% on Humanity's Last Exam, and 70.0% on WebWalker for Pass@5. Further analysis reveals that AEPO improves rollout sampling diversity while maintaining stable policy entropy, facilitating scalable web agent training.

---

### Exploring Cross-Modal Flows for Few-Shot Learning

Authors: Ziqi Jiang, Yanghao Wang, Long Chen
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14543v4

Aligning features from different modalities, is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language models can achieve a general alignment between image and text, they often require parameter-efficient fine-tuning (PEFT) for further adjustment. Today's PEFT methods (e.g., prompt tuning, LoRA-based, or adapter-based) always selectively fine-tune a subset of parameters, which can slightly adjust either visual or textual features, and avoid overfitting. In this paper, we are the first to highlight that all existing PEFT methods perform one-step adjustment. It is insufficient for complex (or difficult) datasets, where features of different modalities are highly entangled. To this end, we propose the first model-agnostic multi-step adjustment approach by learning a cross-modal velocity field: Flow Matching Alignment (FMA). Specifically, to ensure the correspondence between categories during training, we first utilize a fixed coupling strategy. Then, we propose a noise augmentation strategy to alleviate the data scarcity issue. Finally, we design an early-stopping solver, which terminates the transformation process earlier, improving both efficiency and accuracy. Compared with one-step PEFT methods, FMA has the multi-step rectification ability to achieve more precise and robust alignment. Extensive results have demonstrated that FMA can consistently yield significant performance gains across various benchmarks and backbones, particularly on challenging datasets.

---

### A Deep State-Space Model Compression Method using Upper Bound on Output Error

Authors: Hiroki Sakamoto, Kazuhiro Sato
Published: 2025-10-16
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2510.14542v2

We study deep state-space models (Deep SSMs) that contain linear quadratic-output (LQO) systems as internal blocks and present a compression method with a provable output error guarantee. We first derive an upper bound on the output error between two Deep SSMs and show that the bound can be expressed in terms of the $h^2$-error norms between the layerwise LQO systems. In particular, we show that reducing the $h^2$ approximation errors of the LQO systems placed in shallow layers is effective in reducing the derived upper bound on the output error. Next, we formulate an optimization problem for the derived upper bound and develop a gradient-based MOR method. In the numerical experiments, using the IMDb task from the LRA benchmark, we demonstrate the effectiveness of the proposed upper-bound-based compression method. In particular, we show that the number of trainable parameters can be reduced by approximately 60\% without retraining while maintaining the performance of the original model.

---

### Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts

Authors: Emanuele Marconato, Samuele Bortolotti, Emile van Krieken, Paolo Morettin, Elena Umili, Antonio Vergari, Efthymia Tsamoura, Andrea Passerini, Stefano Teso
Published: 2025-10-16
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.14538v3

Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.g. safety or structural constraints. As such, it represents one of the most promising avenues for reliable and trustworthy AI. The core idea behind NeSy AI is to combine neural and symbolic steps: neural networks are typically responsible for mapping low-level inputs into high-level symbolic concepts, while symbolic reasoning infers predictions compatible with the extracted concepts and the prior knowledge. Despite their promise, it was recently shown that - whenever the concepts are not supervised directly - NeSy models can be affected by Reasoning Shortcuts (RSs). That is, they can achieve high label accuracy by grounding the concepts incorrectly. RSs can compromise the interpretability of the model's explanations, performance in out-of-distribution scenarios, and therefore reliability. At the same time, RSs are difficult to detect and prevent unless concept supervision is available, which is typically not the case. However, the literature on RSs is scattered, making it difficult for researchers and practitioners to understand and tackle this challenging problem. This overview addresses this issue by providing a gentle introduction to RSs, discussing their causes and consequences in intuitive terms. It also reviews and elucidates existing theoretical characterizations of this phenomenon. Finally, it details methods for dealing with RSs, including mitigation and awareness strategies, and maps their benefits and limitations. By reformulating advanced material in a digestible form, this overview aims to provide a unifying perspective on RSs to lower the bar to entry for tackling them. Ultimately, we hope this overview contributes to the development of reliable NeSy and trustworthy AI models.

---

### JSPLIT: A Taxonomy-based Solution for Prompt Bloating in Model Context Protocol

Authors: Emanuele Antonioni, Stefan Markovic, Anirudha Shankar, Jaime Bernardo, Lovro Markovic, Silvia Pareti, Benedetto Proietti
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.14537v1

AI systems are continually evolving and advancing, and user expectations are concurrently increasing, with a growing demand for interactions that go beyond simple text-based interaction with Large Language Models (LLMs). Today's applications often require LLMs to interact with external tools, marking a shift toward more complex agentic systems. To support this, standards such as the Model Context Protocol (MCP) have emerged, enabling agents to access tools by including a specification of the capabilities of each tool within the prompt. Although this approach expands what agents can do, it also introduces a growing problem: prompt bloating. As the number of tools increases, the prompts become longer, leading to high prompt token costs, increased latency, and reduced task success resulting from the selection of tools irrelevant to the prompt. To address this issue, we introduce JSPLIT, a taxonomy-driven framework designed to help agents manage prompt size more effectively when using large sets of MCP tools. JSPLIT organizes the tools into a hierarchical taxonomy and uses the user's prompt to identify and include only the most relevant tools, based on both the query and the taxonomy structure. In this paper, we describe the design of the taxonomy, the tool selection algorithm, and the dataset used to evaluate JSPLIT. Our results show that JSPLIT significantly reduces prompt size without significantly compromising the agent's ability to respond effectively. As the number of available tools for the agent grows substantially, JSPLIT even improves the tool selection accuracy of the agent, effectively reducing costs while simultaneously improving task success in high-complexity agent environments.

---

### Exploring Image Representation with Decoupled Classical Visual Descriptors

Authors: Chenyuan Qu, Hao Chen, Jianbo Jiao
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14536v1

Exploring and understanding efficient image representations is a long-standing challenge in computer vision. While deep learning has achieved remarkable progress across image understanding tasks, its internal representations are often opaque, making it difficult to interpret how visual information is processed. In contrast, classical visual descriptors (e.g. edge, colour, and intensity distribution) have long been fundamental to image analysis and remain intuitively understandable to humans. Motivated by this gap, we ask a central question: Can modern learning benefit from these classical cues? In this paper, we answer it with VisualSplit, a framework that explicitly decomposes images into decoupled classical descriptors, treating each as an independent but complementary component of visual knowledge. Through a reconstruction-driven pre-training scheme, VisualSplit learns to capture the essence of each visual descriptor while preserving their interpretability. By explicitly decomposing visual attributes, our method inherently facilitates effective attribute control in various advanced visual tasks, including image generation and editing, extending beyond conventional classification and segmentation, suggesting the effectiveness of this new learning approach for visual understanding. Project page: https://chenyuanqu.com/VisualSplit/.

---

### Acquisition of interpretable domain information during brain MR image harmonization for content-based image retrieval

Authors: Keima Abe, Hayato Muraki, Shuhei Tomoshige, Kenichi Oishi, Hitoshi Iyatomi
Published: 2025-10-16
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2510.14535v1

Medical images like MR scans often show domain shifts across imaging sites due to scanner and protocol differences, which degrade machine learning performance in tasks such as disease classification. Domain harmonization is thus a critical research focus. Recent approaches encode brain images $\boldsymbol{x}$ into a low-dimensional latent space $\boldsymbol{z}$, then disentangle it into $\boldsymbol{z_u}$ (domain-invariant) and $\boldsymbol{z_d}$ (domain-specific), achieving strong results. However, these methods often lack interpretability$-$an essential requirement in medical applications$-$leaving practical issues unresolved. We propose Pseudo-Linear-Style Encoder Adversarial Domain Adaptation (PL-SE-ADA), a general framework for domain harmonization and interpretable representation learning that preserves disease-relevant information in brain MR images. PL-SE-ADA includes two encoders $f_E$ and $f_{SE}$ to extract $\boldsymbol{z_u}$ and $\boldsymbol{z_d}$, a decoder to reconstruct the image $f_D$, and a domain predictor $g_D$. Beyond adversarial training between the encoder and domain predictor, the model learns to reconstruct the input image $\boldsymbol{x}$ by summing reconstructions from $\boldsymbol{z_u}$ and $\boldsymbol{z_d}$, ensuring both harmonization and informativeness. Compared to prior methods, PL-SE-ADA achieves equal or better performance in image reconstruction, disease classification, and domain recognition. It also enables visualization of both domain-independent brain features and domain-specific components, offering high interpretability across the entire framework.

---

### Towards Generalist Intelligence in Dentistry: Vision Foundation Models for Oral and Maxillofacial Radiology

Authors: Xinrui Huang, Fan Xiao, Dongming He, Anqi Gao, Dandan Li, Xiaofan Zhang, Shaoting Zhang, Xudong Wang
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14532v1

Oral and maxillofacial radiology plays a vital role in dental healthcare, but radiographic image interpretation is limited by a shortage of trained professionals. While AI approaches have shown promise, existing dental AI systems are restricted by their single-modality focus, task-specific design, and reliance on costly labeled data, hindering their generalization across diverse clinical scenarios. To address these challenges, we introduce DentVFM, the first family of vision foundation models (VFMs) designed for dentistry. DentVFM generates task-agnostic visual representations for a wide range of dental applications and uses self-supervised learning on DentVista, a large curated dental imaging dataset with approximately 1.6 million multi-modal radiographic images from various medical centers. DentVFM includes 2D and 3D variants based on the Vision Transformer (ViT) architecture. To address gaps in dental intelligence assessment and benchmarks, we introduce DentBench, a comprehensive benchmark covering eight dental subspecialties, more diseases, imaging modalities, and a wide geographical distribution. DentVFM shows impressive generalist intelligence, demonstrating robust generalization to diverse dental tasks, such as disease diagnosis, treatment analysis, biomarker identification, and anatomical landmark detection and segmentation. Experimental results indicate DentVFM significantly outperforms supervised, self-supervised, and weakly supervised baselines, offering superior generalization, label efficiency, and scalability. Additionally, DentVFM enables cross-modality diagnostics, providing more reliable results than experienced dentists in situations where conventional imaging is unavailable. DentVFM sets a new paradigm for dental AI, offering a scalable, adaptable, and label-efficient model to improve intelligent dental healthcare and address critical gaps in global oral healthcare.

---

### PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Authors: Cheng Cui, Ting Sun, Suyin Liang, Tingquan Gao, Zelun Zhang, Jiaxuan Liu, Xueqing Wang, Changda Zhou, Hongen Liu, Manhui Lin, Yue Zhang, Yubo Zhang et al.
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14528v4

In this report, we propose PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios. Code is available at https://github.com/PaddlePaddle/PaddleOCR .

---

### Noise Projection: Closing the Prompt-Agnostic Gap Behind Text-to-Image Misalignment in Diffusion Models

Authors: Yunze Tong, Didi Zhu, Zijing Hu, Jinluan Yang, Ziyu Zhao
Published: 2025-10-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.14526v1

In text-to-image generation, different initial noises induce distinct denoising paths with a pretrained Stable Diffusion (SD) model. While this pattern could output diverse images, some of them may fail to align well with the prompt. Existing methods alleviate this issue either by altering the denoising dynamics or by drawing multiple noises and conducting post-selection. In this paper, we attribute the misalignment to a training-inference mismatch: during training, prompt-conditioned noises lie in a prompt-specific subset of the latent space, whereas at inference the noise is drawn from a prompt-agnostic Gaussian prior. To close this gap, we propose a noise projector that applies text-conditioned refinement to the initial noise before denoising. Conditioned on the prompt embedding, it maps the noise to a prompt-aware counterpart that better matches the distribution observed during SD training, without modifying the SD model. Our framework consists of these steps: we first sample some noises and obtain token-level feedback for their corresponding images from a vision-language model (VLM), then distill these signals into a reward model, and finally optimize the noise projector via a quasi-direct preference optimization. Our design has two benefits: (i) it requires no reference images or handcrafted priors, and (ii) it incurs small inference cost, replacing multi-sample selection with a single forward pass. Extensive experiments further show that our prompt-aware noise projection improves text-image alignment across diverse prompts.

---

### Real-Time Surgical Instrument Defect Detection via Non-Destructive Testing

Authors: Qurrat Ul Ain, Atif Aftab Ahmed Jilani, Zunaira Shafqat, Nigar Azhar Butt
Published: 2025-10-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.14525v1

Defective surgical instruments pose serious risks to sterility, mechanical integrity, and patient safety, increasing the likelihood of surgical complications. However, quality control in surgical instrument manufacturing often relies on manual inspection, which is prone to human error and inconsistency. This study introduces SurgScan, an AI-powered defect detection framework for surgical instruments. Using YOLOv8, SurgScan classifies defects in real-time, ensuring high accuracy and industrial scalability. The model is trained on a high-resolution dataset of 102,876 images, covering 11 instrument types and five major defect categories. Extensive evaluation against state-of-the-art CNN architectures confirms that SurgScan achieves the highest accuracy (99.3%) with real-time inference speeds of 4.2-5.8 ms per image, making it suitable for industrial deployment. Statistical analysis demonstrates that contrast-enhanced preprocessing significantly improves defect detection, addressing key limitations in visual inspection. SurgScan provides a scalable, cost-effective AI solution for automated quality control, reducing reliance on manual inspection while ensuring compliance with ISO 13485 and FDA standards, paving the way for enhanced defect detection in medical manufacturing.

---

### On the Identifiability of Tensor Ranks via Prior Predictive Matching

Authors: Eliezer da Silva, Arto Klami, Diego Mesquita, Iñigo Urteaga
Published: 2025-10-16
Categories: cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.14523v2

Selecting the latent dimensions (ranks) in tensor factorization is a central challenge that often relies on heuristic methods. This paper introduces a rigorous approach to determine rank identifiability in probabilistic tensor models, based on prior predictive moment matching. We transform a set of moment matching conditions into a log-linear system of equations in terms of marginal moments, prior hyperparameters, and ranks; establishing an equivalence between rank identifiability and the solvability of such system. We apply this framework to four foundational tensor-models, demonstrating that the linear structure of the PARAFAC/CP model, the chain structure of the Tensor Train model, and the closed-loop structure of the Tensor Ring model yield solvable systems, making their ranks identifiable. In contrast, we prove that the symmetric topology of the Tucker model leads to an underdetermined system, rendering the ranks unidentifiable by this method. For the identifiable models, we derive explicit closed-form rank estimators based on the moments of observed data only. We empirically validate these estimators and evaluate the robustness of the proposal.

---

### Vision Mamba for Permeability Prediction of Porous Media

Authors: Ali Kashefi, Tapan Mukerji
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14516v2

Vision Mamba has recently received attention as an alternative to Vision Transformers (ViTs) for image classification. The network size of Vision Mamba scales linearly with input image resolution, whereas ViTs scale quadratically, a feature that improves computational and memory efficiency. Moreover, Vision Mamba requires a significantly smaller number of trainable parameters than traditional convolutional neural networks (CNNs), and thus, they can be more memory efficient. Because of these features, we introduce, for the first time, a neural network that uses Vision Mamba as its backbone for predicting the permeability of three-dimensional porous media. We compare the performance of Vision Mamba with ViT and CNN models across multiple aspects of permeability prediction and perform an ablation study to assess the effects of its components on accuracy. We demonstrate in practice the aforementioned advantages of Vision Mamba over ViTs and CNNs in the permeability prediction of three-dimensional porous media. We make the source code publicly available to facilitate reproducibility and to enable other researchers to build on and extend this work. We believe the proposed framework has the potential to be integrated into large vision models in which Vision Mamba is used instead of ViTs.

---

### State Your Intention to Steer Your Attention: An AI Assistant for Intentional Digital Living

Authors: Juheon Choi, Juyong Lee, Jian Kim, Chanyoung Kim, Taywon Min, W. Bradley Knox, Min Kyung Lee, Kimin Lee
Published: 2025-10-16
Categories: cs.HC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.14513v3

When working on digital devices, people often face distractions that can lead to a decline in productivity and efficiency, as well as negative psychological and emotional impacts. To address this challenge, we introduce a novel Artificial Intelligence (AI) assistant that elicits a user's intention, assesses whether ongoing activities are in line with that intention, and provides gentle nudges when deviations occur. The system leverages a large language model to analyze screenshots, application titles, and URLs, issuing notifications when behavior diverges from the stated goal. Its detection accuracy is refined through initial clarification dialogues and continuous user feedback. In a three-week, within-subjects field deployment with 22 participants, we compared our assistant to both a rule-based intent reminder system and a passive baseline that only logged activity. Results indicate that our AI assistant effectively supports users in maintaining focus and aligning their digital behavior with their intentions. Our source code is publicly available at https://intentassistant.github.io

---

### Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agents

Authors: Haoyuan Li, Mathias Funk, Aaqib Saeed
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.14512v2

Federated Learning (FL) offers a powerful paradigm for training models on decentralized data, but its promise is often undermined by the immense complexity of designing and deploying robust systems. The need to select, combine, and tune strategies for multifaceted challenges like data heterogeneity and system constraints has become a critical bottleneck, resulting in brittle, bespoke solutions. To address this, we introduce Helmsman, a novel multi-agent system that automates the end-to-end synthesis of federated learning systems from high-level user specifications. It emulates a principled research and development workflow through three collaborative phases: (1) interactive human-in-the-loop planning to formulate a sound research plan, (2) modular code generation by supervised agent teams, and (3) a closed-loop of autonomous evaluation and refinement in a sandboxed simulation environment. To facilitate rigorous evaluation, we also introduce AgentFL-Bench, a new benchmark comprising 16 diverse tasks designed to assess the system-level generation capabilities of agentic systems in FL. Extensive experiments demonstrate that our approach generates solutions competitive with, and often superior to, established hand-crafted baselines. Our work represents a significant step towards the automated engineering of complex decentralized AI systems.

---

### Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective

Authors: Xingjian Wu, Xiangfei Qiu, Hanyin Cheng, Zhengyu Li, Jilin Hu, Chenjuan Guo, Bin Yang
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14510v5

Time Series Forecasting has made significant progress with the help of Patching technique, which partitions time series into multiple patches to effectively retain contextual semantic information into a representation space beneficial for modeling long-term dependencies. However, conventional patching partitions a time series into adjacent patches, which causes a fixed representation space, thus resulting in insufficiently expressful representations. In this paper, we pioneer the exploration of constructing a selective representation space to flexibly include the most informative patches for forecasting. Specifically, we propose the Selective Representation Space (SRS) module, which utilizes the learnable Selective Patching and Dynamic Reassembly techniques to adaptively select and shuffle the patches from the contextual time series, aiming at fully exploiting the information of contextual time series to enhance the forecasting performance of patch-based models. To demonstrate the effectiveness of SRS module, we propose a simple yet effective SRSNet consisting of SRS and an MLP head, which achieves state-of-the-art performance on real-world datasets from multiple domains. Furthermore, as a novel plug-and-play module, SRS can also enhance the performance of existing patch-based models. The resources are available at https://github.com/decisionintelligence/SRSNet.

---

### E2Edev: Benchmarking Large Language Models in End-to-End Software Development Task

Authors: Jingyao Liu, Chen Huang, Zhizhao Guan, Wenqiang Lei, Yang Deng
Published: 2025-10-16
Categories: cs.SE, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.14509v4

The rapid advancement in large language models (LLMs) has demonstrated significant potential in End-to-End Software Development (E2ESD). However, existing E2ESD benchmarks are limited by coarse-grained requirement specifications and unreliable evaluation protocols, hindering a true understanding of current framework capabilities. To address these limitations, we present E2EDev, a novel benchmark grounded in the principles of Behavior-Driven Development (BDD), which evaluates the capabilities of E2ESD frameworks by assessing whether the generated software meets user needs through mimicking real user interactions (Figure 1). E2EDev comprises (i) a fine-grained set of user requirements, (ii) multiple BDD test scenarios with corresponding Python step implementations for each requirement, and (iii) a fully automated testing pipeline built on the Behave framework. To ensure its quality while reducing the annotation effort, E2EDev leverages our proposed Human-in-the-Loop Multi-Agent Annotation Framework (HITL-MAA). By evaluating various E2ESD frameworks and LLM backbones with E2EDev, our analysis reveals a persistent struggle to effectively solve these tasks, underscoring the critical need for more effective and cost-efficient E2ESD solutions. Our codebase and benchmark are publicly available at https://github.com/SCUNLP/E2EDev.

---

### Efficient Seq2seq Coreference Resolution Using Entity Representations

Authors: Matt Grenander, Shay B. Cohen, Mark Steedman
Published: 2025-10-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.14504v1

Seq2seq coreference models have introduced a new paradigm for coreference resolution by learning to generate text corresponding to coreference labels, without requiring task-specific parameters. While these models achieve new state-of-the-art performance, they do so at the cost of flexibility and efficiency. In particular, they do not efficiently handle incremental settings such as dialogue, where text must processed sequentially. We propose a compressed representation in order to improve the efficiency of these methods in incremental settings. Our method works by extracting and re-organizing entity-level tokens, and discarding the majority of other input tokens. On OntoNotes, our best model achieves just 0.6 CoNLL F1 points below a full-prefix, incremental baseline while achieving a compression ratio of 1.8. On LitBank, where singleton mentions are annotated, it passes state-of-the-art performance. Our results indicate that discarding a wide portion of tokens in seq2seq resolvers is a feasible strategy for incremental coreference resolution.

---

### Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signals

Authors: Andrejs Sorstkins, Omer Tariq, Muhammad Bilal
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14503v1

This paper proposes a reversible learning framework to improve the robustness and efficiency of value based Reinforcement Learning agents, addressing vulnerability to value overestimation and instability in partially irreversible environments. The framework has two complementary core mechanisms: an empirically derived transition reversibility measure called Phi of s and a, and a selective state rollback operation. We introduce an online per state action estimator called Phi that quantifies the likelihood of returning to a prior state within a fixed horizon K. This measure is used to adjust the penalty term during temporal difference updates dynamically, integrating reversibility awareness directly into the value function. The system also includes a selective rollback operator. When an action yields an expected return markedly lower than its instantaneous estimated value and violates a predefined threshold, the agent is penalized and returns to the preceding state rather than progressing. This interrupts sub optimal high risk trajectories and avoids catastrophic steps. By combining reversibility aware evaluation with targeted rollback, the method improves safety, performance, and stability. In the CliffWalking v0 domain, the framework reduced catastrophic falls by over 99.8 percent and yielded a 55 percent increase in mean episode return. In the Taxi v3 domain, it suppressed illegal actions by greater than or equal to 99.9 percent and achieved a 65.7 percent improvement in cumulative reward, while also sharply reducing reward variance in both environments. Ablation studies confirm that the rollback mechanism is the critical component underlying these safety and performance gains, marking a robust step toward safe and reliable sequential decision making.

---

### ROC Analysis with Covariate Adjustment Using Neural Network Models: Evaluating the Role of Age in the Physical Activity-Mortality Association

Authors: Ziad Akram Ali Hammouri, Yating Zou, Rahul Ghosal, Juan C. Vidal, Marcos Matabuena
Published: 2025-10-16
Categories: stat.ME, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.14494v1

The receiver operating characteristic (ROC) curve and its summary measure, the Area Under the Curve (AUC), are well-established tools for evaluating the efficacy of biomarkers in biomedical studies. Compared to the traditional ROC curve, the covariate-adjusted ROC curve allows for individual evaluation of the biomarker. However, the use of machine learning models has rarely been explored in this context, despite their potential to develop more powerful and sophisticated approaches for biomarker evaluation. The goal of this paper is to propose a framework for neural network-based covariate-adjusted ROC modeling that allows flexible and nonlinear evaluation of the effectiveness of a biomarker to discriminate between two reference populations. The finite-sample performance of our method is investigated through extensive simulation tests under varying dependency structures between biomarkers, covariates, and referenced populations. The methodology is further illustrated in a clinically case study that assesses daily physical activity - measured as total activity time (TAC), a proxy for daily step count-as a biomarker to predict mortality at three, five and eight years. Analyzes stratified by sex and adjusted for age and BMI reveal distinct covariate effects on mortality outcomes. These results underscore the importance of covariate-adjusted modeling in biomarker evaluation and highlight TAC's potential as a functional capacity biomarker based on specific individual characteristics.

---

### Grazing Detection using Deep Learning and Sentinel-2 Time Series Data

Authors: Aleksis Pirinen, Delia Fano Yela, Smita Chakraborty, Erik Källman
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14493v1

Grazing shapes both agricultural production and biodiversity, yet scalable monitoring of where grazing occurs remains limited. We study seasonal grazing detection from Sentinel-2 L2A time series: for each polygon-defined field boundary, April-October imagery is used for binary prediction (grazed / not grazed). We train an ensemble of CNN-LSTM models on multi-temporal reflectance features, and achieve an average F1 score of 77 percent across five validation splits, with 90 percent recall on grazed pastures. Operationally, if inspectors can visit at most 4 percent of sites annually, prioritising fields predicted by our model as non-grazed yields 17.2 times more confirmed non-grazing sites than random inspection. These results indicate that coarse-resolution, freely available satellite data can reliably steer inspection resources for conservation-aligned land-use compliance. Code and models have been made publicly available.

---

### From Guess2Graph: When and How Can Unreliable Experts Safely Boost Causal Discovery in Finite Samples?

Authors: Sujai Hiremath, Dominik Janzing, Philipp Faller, Patrick Blöbaum, Elke Kirschbaum, Shiva Prasad Kasiviswanathan, Kyra Gan
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.14488v1

Causal discovery algorithms often perform poorly with limited samples. While integrating expert knowledge (including from LLMs) as constraints promises to improve performance, guarantees for existing methods require perfect predictions or uncertainty estimates, making them unreliable for practical use. We propose the Guess2Graph (G2G) framework, which uses expert guesses to guide the sequence of statistical tests rather than replacing them. This maintains statistical consistency while enabling performance improvements. We develop two instantiations of G2G: PC-Guess, which augments the PC algorithm, and gPC-Guess, a learning-augmented variant designed to better leverage high-quality expert input. Theoretically, both preserve correctness regardless of expert error, with gPC-Guess provably outperforming its non-augmented counterpart in finite samples when experts are "better than random." Empirically, both show monotonic improvement with expert accuracy, with gPC-Guess achieving significantly stronger gains.

---

### Semantic representations emerge in biologically inspired ensembles of cross-supervising neural networks

Authors: Roy Urbach, Elad Schneidman
Published: 2025-10-16
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2510.14486v1

Brains learn to represent information from a large set of stimuli, typically by weak supervision. Unsupervised learning is therefore a natural approach for exploring the design of biological neural networks and their computations. Accordingly, redundancy reduction has been suggested as a prominent design principle of neural encoding, but its ``mechanistic'' biological implementation is unclear. Analogously, unsupervised training of artificial neural networks yields internal representations that allow for accurate stimulus classification or decoding, but typically rely on biologically-implausible implementations. We suggest that interactions between parallel subnetworks in the brain may underlie such learning: we present a model of representation learning by ensembles of neural networks, where each network learns to encode stimuli into an abstract representation space by cross-supervising interactions with other networks, for inputs they receive simultaneously or in close temporal proximity. Aiming for biological plausibility, each network has a small ``receptive field'', thus receiving a fixed part of the external input, and the networks do not share weights. We find that for different types of network architectures, and for both visual or neuronal stimuli, these cross-supervising networks learn semantic representations that are easily decodable and that decoding accuracy is comparable to supervised networks -- both at the level of single networks and the ensemble. We further show that performance is optimal for small receptive fields, and that sparse connectivity between networks is nearly as accurate as all-to-all interactions, with far fewer computations. We thus suggest a sparsely interacting collective of cross-supervising networks as an algorithmic framework for representational learning and collective computation in the brain.

---

### Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered Graph Foundation Models

Authors: Xiaoyu Xue, Yuni Lai, Chenxi Huang, Yulin Zhu, Gaolei Li, Xiaoge Zhang, Kai Zhou
Published: 2025-10-16
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.14470v1

The emergence of graph foundation models (GFMs), particularly those incorporating language models (LMs), has revolutionized graph learning and demonstrated remarkable performance on text-attributed graphs (TAGs). However, compared to traditional GNNs, these LM-empowered GFMs introduce unique security vulnerabilities during the unsecured prompt tuning phase that remain understudied in current research. Through empirical investigation, we reveal a significant performance degradation in traditional graph backdoor attacks when operating in attribute-inaccessible constrained TAG systems without explicit trigger node attribute optimization. To address this, we propose a novel dual-trigger backdoor attack framework that operates at both text-level and struct-level, enabling effective attacks without explicit optimization of trigger node text attributes through the strategic utilization of a pre-established text pool. Extensive experimental evaluations demonstrate that our attack maintains superior clean accuracy while achieving outstanding attack success rates, including scenarios with highly concealed single-trigger nodes. Our work highlights critical backdoor risks in web-deployed LM-empowered GFMs and contributes to the development of more robust supervision mechanisms for open-source platforms in the era of foundation models.

---

### Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages

Authors: Haolin Li, Haipeng Zhang, Mang Li, Yaohua Wang, Lijie Wen, Yu Zhang, Biqing Huang
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.14466v3

Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and unstable cross-lingual alignment. To address these challenges, we propose LiRA (Linguistic Robust Anchoring for LLMs)-a plug-and-play framework that requires only lightweight fine-tuning on top of existing pretrained backbones. LiRA jointly optimizes representation stability and cross-lingual semantic consistency by combining two key components: Arca (Anchored Representation Composition Architecture), which aligns low-resource inputs to a shared English semantic space through anchor-based alignment and collaborative encoding; and LaSR (Language-coupled Semantic Reasoner), a lightweight, language-aware head that enforces consistency regularization for unified cross-lingual understanding, retrieval, and reasoning. We theoretically show that under controlled anchoring error and translation-induced bias, LiRA guarantees bounded representation deviation and stable downstream performance under local Lipschitz continuity. To facilitate research, we release a new multilingual product retrieval dataset covering five Southeast Asian and two South Asian languages. Extensive experiments across diverse low-resource benchmarks demonstrate consistent improvements in retrieval, ranking, question answering, and reasoning tasks. Code will be publicly available on GitHub, and the dataset will be hosted on Hugging Face.

---

### Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration

Authors: Thomas Katraouras, Dimitrios Rafailidis
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14463v1

Image quality is a critical factor in delivering visually appealing content on web platforms. However, images often suffer from degradation due to lossy operations applied by online social networks (OSNs), negatively affecting user experience. Image restoration is the process of recovering a clean high-quality image from a given degraded input. Recently, multi-task (all-in-one) image restoration models have gained significant attention, due to their ability to simultaneously handle different types of image degradations. However, these models often come with an excessively high number of trainable parameters, making them computationally inefficient. In this paper, we propose a strategy for compressing multi-task image restoration models. We aim to discover highly sparse subnetworks within overparameterized deep models that can match or even surpass the performance of their dense counterparts. The proposed model, namely MIR-L, utilizes an iterative pruning strategy that removes low-magnitude weights across multiple rounds, while resetting the remaining weights to their original initialization. This iterative process is important for the multi-task image restoration model's optimization, effectively uncovering "winning tickets" that maintain or exceed state-of-the-art performance at high sparsity levels. Experimental evaluation on benchmark datasets for the deraining, dehazing, and denoising tasks shows that MIR-L retains only 10% of the trainable parameters while maintaining high image restoration performance. Our code, datasets and pre-trained models are made publicly available at https://github.com/Thomkat/MIR-L.

---

### Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review

Authors: Youwan Mahé, Elise Bannier, Stéphanie Leplaideur, Elisa Fromont, Francesca Galassi
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14462v3

Unsupervised anomaly detection (UAD) based on deep generative modelling has been increasingly explored for identifying pathological brain abnormalities without requiring voxel-level annotations. By learning the distribution of healthy anatomy and generating pseudo-healthy reconstructions, these methods aim to localise deviations in a pathology-agnostic manner. Despite rapid methodological development - from autoencoders and variational autoencoders to generative adversarial networks and diffusion-based models - a structured synthesis of their application in structural neuroimaging is lacking. We conducted a PRISMA-ScR-guided scoping review of studies published between January 2018-December 2025 that applied unsupervised deep generative models to anomaly detection in brain MRI (and, less frequently, CT). Thirty-three studies met inclusion criteria. Methods were categorised by architectural family, and reported performance was synthesised across major pathology groups, with segmentation (Dice) and detection metrics (AUROC, AUPRC) disaggregated by evaluation level (voxel, slice, subject). For transparency, we also summarised dataset characteristics, dimensionality (2D vs. 3D), and thresholding strategies. Overall, unsupervised generative approaches demonstrate potential for pathology-agnostic anomaly localisation, particularly in settings where annotated data are scarce. However, methodological heterogeneity, limited external validation, and sensitivity to dataset characteristics remain important challenges. Emerging paradigms - including anatomy-aware modelling, diffusion-based frameworks, and alternative normative evaluation metrics - seek to address these limitations and improve robustness and clinical relevance.

---

### Structured Universal Adversarial Attacks on Object Detection for Video Sequences

Authors: Sven Jacob, Weijia Shao, Gjergji Kasneci
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14460v1

Video-based object detection plays a vital role in safety-critical applications. While deep learning-based object detectors have achieved impressive performance, they remain vulnerable to adversarial attacks, particularly those involving universal perturbations. In this work, we propose a minimally distorted universal adversarial attack tailored for video object detection, which leverages nuclear norm regularization to promote structured perturbations concentrated in the background. To optimize this formulation efficiently, we employ an adaptive, optimistic exponentiated gradient method that enhances both scalability and convergence. Our results demonstrate that the proposed attack outperforms both low-rank projected gradient descent and Frank-Wolfe based attacks in effectiveness while maintaining high stealthiness. All code and data are publicly available at https://github.com/jsve96/AO-Exp-Attack.

---

### Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning

Authors: Ling Zhang, Xianliang Yang, Juwon Yu, Park Cheonyoung, Miran Lee, Lei Song, Jiang Bian
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.14459v2

Fine-tuning large pretrained language models is a common approach for aligning them with human preferences, but noisy or off-target examples can dilute supervision. While small, well-chosen datasets often match the performance of much larger ones, systematic and efficient ways to identify high-value training data remain underexplored. Many current methods rely on heuristics or expensive retraining. We present a principled, resource-efficient framework for data selection and reweighting. At its core is an In-Context Approximation (ICA) that estimates the holdout loss a model would incur after training on a candidate example by conditioning on a small, curated holdout set in context. ICA requires no reference model and no additional finetuning. We define the resulting estimate as the ICA score, and derive per-example weights that dynamically reweight gradient updates as model parameters evolve. Across SFT, DPO, and SimPO, and over diverse backbones and datasets, ICA-based reweighting consistently improves model alignment with minimal overhead. We analyze sensitivity to score update frequency and the number of in-context holdout examples. We also discuss limitations in rapidly drifting on-policy settings, highlighting directions for future work. Code and prompts will be released.

---

### Coder as Editor: Code-driven Interpretable Molecular Optimization

Authors: Wenyu Zhu, Chengzhu Li, Xiaohe Tian, Yifan Wang, Yinjun Jia, Jianhui Wang, Bowen Gao, Ya-Qin Zhang, Wei-Ying Ma, Yanyan Lan
Published: 2025-10-16
Categories: cs.LG, q-bio.BM
arXiv: https://arxiv.org/abs/2510.14455v1

Molecular optimization is a central task in drug discovery that requires precise structural reasoning and domain knowledge. While large language models (LLMs) have shown promise in generating high-level editing intentions in natural language, they often struggle to faithfully execute these modifications-particularly when operating on non-intuitive representations like SMILES. We introduce MECo, a framework that bridges reasoning and execution by translating editing actions into executable code. MECo reformulates molecular optimization for LLMs as a cascaded framework: generating human-interpretable editing intentions from a molecule and property goal, followed by translating those intentions into executable structural edits via code generation. Our approach achieves over 98% accuracy in reproducing held-out realistic edits derived from chemical reactions and target-specific compound pairs. On downstream optimization benchmarks spanning physicochemical properties and target activities, MECo substantially improves consistency by 38-86 percentage points to 90%+ and achieves higher success rates over SMILES-based baselines while preserving structural similarity. By aligning intention with execution, MECo enables consistent, controllable and interpretable molecular design, laying the foundation for high-fidelity feedback loops and collaborative human-AI workflows in drug discovery.

---

### Towards Adaptable Humanoid Control via Adaptive Motion Tracking

Authors: Tao Huang, Huayi Wang, Junli Ren, Kangning Yin, Zirui Wang, Xiao Chen, Feiyu Jia, Wentao Zhang, Junfeng Long, Jingbo Wang, Jiangmiao Pang
Published: 2025-10-16
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.14454v1

Humanoid robots are envisioned to adapt demonstrated motions to diverse real-world conditions while accurately preserving motion patterns. Existing motion prior approaches enable well adaptability with a few motions but often sacrifice imitation accuracy, whereas motion-tracking methods achieve accurate imitation yet require many training motions and a test-time target motion to adapt. To combine their strengths, we introduce AdaMimic, a novel motion tracking algorithm that enables adaptable humanoid control from a single reference motion. To reduce data dependence while ensuring adaptability, our method first creates an augmented dataset by sparsifying the single reference motion into keyframes and applying light editing with minimal physical assumptions. A policy is then initialized by tracking these sparse keyframes to generate dense intermediate motions, and adapters are subsequently trained to adjust tracking speed and refine low-level actions based on the adjustment, enabling flexible time warping that further improves imitation accuracy and adaptability. We validate these significant improvements in our approach in both simulation and the real-world Unitree G1 humanoid robot in multiple tasks across a wide range of adaptation conditions. Videos and code are available at https://taohuang13.github.io/adamimic.github.io/.

---

### Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents

Authors: Reid T. Johnson, Michelle D. Pain, Jordan D. West
Published: 2025-10-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.14453v1

We present Natural Language Tools (NLT), a framework that replaces programmatic JSON tool calling in large language models (LLMs) with natural language outputs. By decoupling tool selection from response generation, NLT eliminates task interference and format constraints that degrade tool call performance. When evaluated across 10 models and 6,400 trials spanning customer service and mental health domains, NLT improves tool calling accuracy by 18.4 percentage points while reducing output variance by 70%. Open-weight models see the largest gains, surpassing flagship closed-weight alternatives, with implications for model training in both reinforcement learning and supervised fine-tuning stages. These improvements persist under prompt perturbations and extend tool-calling capabilities to models lacking native support.

---

### Feature Selection and Regularization in Multi-Class Classification: An Empirical Study of One-vs-Rest Logistic Regression with Gradient Descent Optimization and L1 Sparsity Constraints

Authors: Jahidul Arafat, Fariha Tasmin, Sanjaya Poudel
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.14449v2

Multi-class wine classification presents fundamental trade-offs between model accuracy, feature dimensionality, and interpretability - critical factors for production deployment in analytical chemistry. This paper presents a comprehensive empirical study of One-vs-Rest logistic regression on the UCI Wine dataset (178 samples, 3 cultivars, 13 chemical features), comparing from-scratch gradient descent implementation against scikit-learn's optimized solvers and quantifying L1 regularization effects on feature sparsity. Manual gradient descent achieves 92.59 percent mean test accuracy with smooth convergence, validating theoretical foundations, though scikit-learn provides 24x training speedup and 98.15 percent accuracy. Class-specific analysis reveals distinct chemical signatures with heterogeneous patterns where color intensity varies dramatically (0.31 to 16.50) across cultivars. L1 regularization produces 54-69 percent feature reduction with only 4.63 percent accuracy decrease, demonstrating favorable interpretability-performance trade-offs. We propose an optimal 5-feature subset achieving 62 percent complexity reduction with estimated 92-94 percent accuracy, enabling cost-effective deployment with 80 dollars savings per sample and 56 percent time reduction. Statistical validation confirms robust generalization with sub-2ms prediction latency suitable for real-time quality control. Our findings provide actionable guidelines for practitioners balancing comprehensive chemical analysis against targeted feature measurement in resource-constrained environments.

---

### Towards geological inference with process-based and deep generative modeling, part 1: training on fluvial deposits

Authors: Guillaume Rongier, Luk Peeters
Published: 2025-10-16
Categories: cs.LG, physics.geo-ph
arXiv: https://arxiv.org/abs/2510.14445v1

The distribution of resources in the subsurface is deeply linked to the variations of its physical properties. Generative modeling has long been used to predict those physical properties while quantifying the associated uncertainty. But current approaches struggle to properly reproduce geological structures, and fluvial deposits in particular, because of their continuity. This study explores whether a generative adversarial network (GAN) - a type of deep-learning algorithm for generative modeling - can be trained to reproduce fluvial deposits simulated by a process-based model - a more expensive model that mimics geological processes. An ablation study shows that developments from the deep-learning community to generate large 2D images are directly transferable to 3D images of fluvial deposits. Training remains stable, and the generated samples reproduce the non-stationarity and details of the deposits without mode collapse or pure memorization of the training data. Using a process-based model to generate those training data allows us to include valuable properties other than the usual physical properties. We show how the deposition time let us monitor and validate the performance of a GAN by checking that its samples honor the law of superposition. Our work joins a series of previous studies suggesting that GANs are more robust that given credit for, at least for training datasets targeting specific geological structures. Whether this robustness transfers to larger 3D images and multimodal datasets remains to be seen. Exploring how deep generative models can leverage geological principles like the law of superposition shows a lot of promise.

---

### A Free Lunch in LLM Compression: Revisiting Retraining after Pruning

Authors: Moritz Wagner, Christophe Roux, Max Zimmer, Sebastian Pokutta
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.14444v3

Post-training pruning can substantially reduce LLM inference costs, but it often degrades quality unless the remaining weights are adapted. Since global retraining is expensive at LLM scale, recent work has largely focused on increasingly sophisticated pruning criteria that aim to select better sparsity patterns without adaptation. We revisit this trade-off through local reconstruction: after pruning, we adapt one subset of the model parameters at a time on a calibration set, training it to match the corresponding intermediate activations of the dense model. We evaluate local reconstruction across model families and scales, up to 72B parameters, and establish three main findings. First, local reconstruction is an effective adaptation mechanism for LLMs: it matches post-pruning retraining while using over an order of magnitude less data and compute, even when using PEFT techniques. Second, reconstruction exhibits a broad "free-lunch" regime in granularity, i.e., the reconstruction parameter window: as long as the reconstructed region contains at least a nonlinear submodule, final quality is largely insensitive to the window size, allowing granularity to be chosen primarily based on memory constraints. In contrast, reconstructing individual matrices, despite being the natural approach often proposed in the literature, consistently underperforms, as small matrix-level errors accumulate into larger activation drift. Lastly, reconstruction reduces the relative importance of the pruning criterion: performance gaps between sophisticated criteria and simple baselines shrink with model scale, making simple methods competitive again. Overall, our results challenge the prevailing view that post-pruning adaptation is impractical for LLMs.

---

### Big Data Approaches to Bovine Bioacoustics: A FAIR-Compliant Dataset and Scalable ML Framework for Precision Livestock Welfare

Authors: Mayuri Kate, Suresh Neethirajan
Published: 2025-10-16
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.14443v1

The convergence of IoT sensing, edge computing, and machine learning is transforming precision livestock farming. Yet bioacoustic data streams remain underused because of computational complexity and ecological validity challenges. We present one of the most comprehensive bovine vocalization datasets to date, with 569 curated clips covering 48 behavioral classes, recorded across three commercial dairy farms using multiple microphone arrays and expanded to 2900 samples through domain informed augmentation. This FAIR compliant resource addresses major Big Data challenges - volume (90 hours of recordings, 65.6 GB), variety (multi farm and multi zone acoustics), velocity (real time processing), and veracity (noise robust feature extraction). Our distributed processing framework integrates advanced denoising using iZotope RX, multimodal synchronization through audio and video alignment, and standardized feature engineering with 24 acoustic descriptors generated from Praat, librosa, and openSMILE. Preliminary benchmarks reveal distinct class level acoustic patterns for estrus detection, distress classification, and maternal communication. The datasets ecological realism, reflecting authentic barn acoustics rather than controlled settings, ensures readiness for field deployment. This work establishes a foundation for animal centered AI, where bioacoustic data enable continuous and non invasive welfare assessment at industrial scale. By releasing standardized pipelines and detailed metadata, we promote reproducible research that connects Big Data analytics, sustainable agriculture, and precision livestock management. The framework supports UN SDG 9, showing how data science can turn traditional farming into intelligent, welfare optimized systems that meet global food needs while upholding ethical animal care.

---

### WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models

Authors: Rui Wang, Ce Zhang, Jun-Yu Ma, Jianshu Zhang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu et al.
Published: 2025-10-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.14438v2

The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, current agentic systems are often retrieval-heavy but reasoning-light, where success is predominantly determined by simple entity-seeking rather than the multi-step aggregation of scattered evidence. To address this, we propose a data synthesis pipeline WebAggregator, designed to shift the agentic paradigm from retrieval-centric to compositional aggregation. Our approach first employs Proactive Explorer to collect interconnected knowledge, then Compositional Logic Proposer to weave knowledge into complex questions using over 12 composition guidelines derived from a rigorous deconstruction of the Deep Research problem setting. By leveraging 10K verifiable QA pairs grounded on 50K websites, we curate a high-quality SFT dataset via rejection sampling. Fine-tuning on this corpus fundamentally transforms agent behavior, fostering deliberate composition reasoning and reduced tool redundancy. The resulting WebAggregator-32B surpasses GPT-4.1 and matches Claude-3.7-Sonnet on GAIA, WebWalkerQA, and XBench. To address the lack of benchmarks that emphasize both reasoning and retrieval, we introduce the WebAggregatorQA testbed, which reveals that even with perfect retrieval, top-tier models still underperformed. These results demonstrate that compositional reasoning, not retrieval, is the true performance ceiling for next-generation research agents.

---

### MergeMoE: Efficient Compression of MoE Models via Expert Output Merging

Authors: Ruijie Miao, Yilun Yao, Zihan Wang, Zhiming Wang, Bairen Yi, LingJun Liu, Yikai Zhao, Tong Yang
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14436v1

The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However, the substantial memory overhead of MoE models has made their compression an important research direction. In this work, we provide a theoretical analysis of expert merging, a recently proposed technique for compressing MoE models. Rather than interpreting expert merging from the conventional perspective of parameter aggregation, we approach it from the perspective of merging experts' outputs. Our key insight is that the merging process can be interpreted as inserting additional matrices into the forward computation, which naturally leads to an optimization formulation. Building on this analysis, we introduce MergeMoE, a method that leverages mathematical optimization to construct the compression matrices. We evaluate MergeMoE on multiple MoE models and show that our algorithm consistently outperforms the baselines with the same compression ratios.

---

### Real-Time Neural Video Compression with Unified Intra and Inter Coding

Authors: Hui Xiang, Yifan Bian, Li Li, Jingran Wu, Xianguo Zhang, Dong Liu
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14431v6

Neural video compression (NVC) technologies have advanced rapidly in recent years, yielding state-of-the-art schemes such as DCVC-RT that offer superior compression efficiency to H.266/VVC and real-time encoding/decoding capabilities. Nonetheless, existing NVC schemes have several limitations, including inefficiency in dealing with disocclusion and new content, interframe error propagation and accumulation, among others. To eliminate these limitations, we borrow the idea from classic video coding schemes, which allow intra coding within inter-coded frames. With the intra coding tool enabled, disocclusion and new content are properly handled, and interframe error propagation is naturally intercepted without the need for manual refresh mechanisms. We present an NVC framework with unified intra and inter coding, where every frame is processed by a single model that is trained to perform intra/inter coding adaptively. Moreover, we propose a simultaneous two-frame compression design to exploit interframe redundancy not only forwardly but also backwardly. Experimental results show that our scheme outperforms DCVC-RT by an average of 12.1% BD-rate reduction, delivers more stable bitrate and quality per frame, and retains real-time encoding/decoding performances. Code and models will be released.

---

### Deep Compositional Phase Diffusion for Long Motion Sequence Generation

Authors: Ho Yin Au, Jie Chen, Junkun Jiang, Jingyu Xiang
Published: 2025-10-16
Categories: cs.MM, cs.CV
arXiv: https://arxiv.org/abs/2510.14427v1

Recent research on motion generation has shown significant progress in generating semantically aligned motion with singular semantics. However, when employing these models to create composite sequences containing multiple semantically generated motion clips, they often struggle to preserve the continuity of motion dynamics at the transition boundaries between clips, resulting in awkward transitions and abrupt artifacts. To address these challenges, we present Compositional Phase Diffusion, which leverages the Semantic Phase Diffusion Module (SPDM) and Transitional Phase Diffusion Module (TPDM) to progressively incorporate semantic guidance and phase details from adjacent motion clips into the diffusion process. Specifically, SPDM and TPDM operate within the latent motion frequency domain established by the pre-trained Action-Centric Motion Phase Autoencoder (ACT-PAE). This allows them to learn semantically important and transition-aware phase information from variable-length motion clips during training. Experimental results demonstrate the competitive performance of our proposed framework in generating compositional motion sequences that align semantically with the input conditions, while preserving phase transitional continuity between preceding and succeeding motion clips. Additionally, motion inbetweening task is made possible by keeping the phase parameter of the input motion sequences fixed throughout the diffusion process, showcasing the potential for extending the proposed framework to accommodate various application scenarios. Codes are available at https://github.com/asdryau/TransPhase.

---

### Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following

Authors: Qingyu Ren, Qianyu He, Powei Chang, Jie Zeng, Zeye Sun, Fei Yu, Jiaqing Liang, Yanghua Xiao
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.14420v4

Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks. We propose a label-free self-supervised RL framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model training. Our approach introduces constraint decomposition strategies and efficient constraint-wise binary classification to address sparse reward challenges while maintaining computational efficiency. Experiments show that our approach generalizes well, achieving strong improvements across 3 in-domain and 5 out-of-domain datasets, including challenging agentic and multi-turn instruction following. The data and code are publicly available at https://github.com/Rainier-rq/verl-if

---

### Interaction Concordance Index: Performance Evaluation for Interaction Prediction Methods

Authors: Tapio Pahikkala, Riikka Numminen, Parisa Movahedi, Napsu Karmitsa, Antti Airola
Published: 2025-10-16
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.14419v1

Consider two sets of entities and their members' mutual affinity values, say drug-target affinities (DTA). Drugs and targets are said to interact in their effects on DTAs if drug's effect on it depends on the target. Presence of interaction implies that assigning a drug to a target and another drug to another target does not provide the same aggregate DTA as the reversed assignment would provide. Accordingly, correctly capturing interactions enables better decision-making, for example, in allocation of limited numbers of drug doses to their best matching targets. Learning to predict DTAs is popularly done from either solely from known DTAs or together with side information on the entities, such as chemical structures of drugs and targets. In this paper, we introduce interaction directions' prediction performance estimator we call interaction concordance index (IC-index), for both fixed predictors and machine learning algorithms aimed for inferring them. IC-index complements the popularly used DTA prediction performance estimators by evaluating the ratio of correctly predicted directions of interaction effects in data. First, we show the invariance of IC-index on predictors unable to capture interactions. Secondly, we show that learning algorithm's permutation equivariance regarding drug and target identities implies its inability to capture interactions when either drug, target or both are unseen during training. In practical applications, this equivariance is remedied via incorporation of appropriate side information on drugs and targets. We make a comprehensive empirical evaluation over several biomedical interaction data sets with various state-of-the-art machine learning algorithms. The experiments demonstrate how different types of affinity strength prediction methods perform in terms of IC-index complementing existing prediction performance estimators.

---

### Row-wise Fusion Regularization: An Interpretable Personalized Federated Learning Framework in Large-Scale Scenarios

Authors: Runlin Zhou, Letian Li, Zemin Zheng
Published: 2025-10-16
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.14413v2

We study personalized federated learning for multivariate responses where client models are heterogeneous yet share variable-level structure. Existing entry-wise penalties ignore cross-response dependence, while matrix-wise fusion over-couples clients. We propose a Sparse Row-wise Fusion (SROF) regularizer that clusters row vectors across clients and induces within-row sparsity, and we develop RowFed, a communication-efficient federated algorithm that embeds SROF into a linearized ADMM framework with privacy-preserving partial participation. Theoretically, we establish an oracle property for SROF-achieving correct variable-level group recovery with asymptotic normality-and prove convergence of RowFed to a stationary solution. Under random client participation, the iterate gap contracts at a rate that improves with participation probability. Empirically, simulations in heterogeneous regimes show that RowFed consistently lowers estimation and prediction error and strengthens variable-level cluster recovery over NonFed, FedAvg, and a personalized matrix-fusion baseline. A real-data study further corroborates these gains while preserving interpretability. Together, our results position row-wise fusion as an effective and transparent paradigm for large-scale personalized federated multivariate learning, bridging the gap between entry-wise and matrix-wise formulations.

---

### PDDL Axioms Are Equivalent to Least Fixed Point Logic (Extended Version)

Authors: Claudia Grundke, Gabriele Röger
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.14412v2

Axioms are a feature of the Planning Domain Definition Language PDDL that can be considered as a generalization of database query languages such as Datalog. The PDDL standard restricts negative occurrences of predicates in axiom bodies to predicates that are directly set by actions and not derived by axioms. In the literature, authors often deviate from this limitation and only require that the set of axioms is stratifiable. We show that both variants can express exactly the same queries as least fixed point logic. They are thus strictly more expressive than stratified Datalog, which aligns with another restriction on axioms occasionally considered in the planning literature. Complementing this theoretical analysis, we also present a compilation that eliminates negative occurrences of derived predicates from PDDL axioms.

---

### Revisit Modality Imbalance at the Decision Layer

Authors: Xiaoyu Ma, Hao Chen
Published: 2025-10-16
Categories: cs.LG, cs.MM, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2510.14411v1

Multimodal learning integrates information from different modalities to enhance model performance, yet it often suffers from modality imbalance, where dominant modalities overshadow weaker ones during joint optimization. This paper reveals that such an imbalance not only occurs during representation learning but also manifests significantly at the decision layer. Experiments on audio-visual datasets (CREMAD and Kinetic-Sounds) show that even after extensive pretraining and balanced optimization, models still exhibit systematic bias toward certain modalities, such as audio. Further analysis demonstrates that this bias originates from intrinsic disparities in feature-space and decision-weight distributions rather than from optimization dynamics alone. We argue that aggregating uncalibrated modality outputs at the fusion stage leads to biased decision-layer weighting, hindering weaker modalities from contributing effectively. To address this, we propose that future multimodal systems should focus more on incorporate adaptive weight allocation mechanisms at the decision layer, enabling relative balanced according to the capabilities of each modality.

---

### IMAGINE: Integrating Multi-Agent System into One Model for Complex Reasoning and Planning

Authors: Xikai Zhang, Bo Wang, Likang Xiao, Yongzhi Li, Quan Chen, Wenjun Wu, Liu Liu
Published: 2025-10-16
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.14406v2

Although large language models (LLMs) have made significant strides across various tasks, they still face significant challenges in complex reasoning and planning. For example, even with carefully designed prompts and prior information explicitly provided, GPT-4o achieves only a 7% Final Pass Rate on the TravelPlanner dataset in the sole-planning mode. Similarly, even in the thinking mode, Qwen3-8B-Instruct and DeepSeek-R1-671B, only achieve Final Pass Rates of 5.9% and 40%, respectively. Although well-organized Multi-Agent Systems (MAS) can offer improved collective reasoning, they often suffer from high reasoning costs due to multi-round internal interactions, long per-response latency, and difficulties in end-to-end training. To address these challenges, we propose a general and scalable framework called IMAGINE, short for Integrating Multi-Agent System into One Model. This framework not only integrates the reasoning and planning capabilities of MAS into a single, compact model, but also significantly surpass the capabilities of the MAS through a simple end-to-end training. Through this pipeline, a single small-scale model is not only able to acquire the structured reasoning and planning capabilities of a well-organized MAS but can also significantly outperform it. Experimental results demonstrate that, when using Qwen3-8B-Instruct as the base model and training it with our method, the model achieves an 82.7% Final Pass Rate on the TravelPlanner benchmark, far exceeding the 40% of DeepSeek-R1-671B, while maintaining a much smaller model size.

---