# Research Papers — 2025-10 · bundle page 167 of 217

> Full-text markdown of papers #8301–8350 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/167
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/166.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/168.md)

### Evolving and Executing Research Plans via Double-Loop Multi-Agent Collaboration

Authors: Zhi Zhang, Yan Liu, Zhejing Hu, Gong Chen, Sheng-hua Zhong, Jiannong Cao
Published: 2025-10-08
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.06761v1

Automating the end-to-end scientific research process poses a fundamental challenge: it requires both evolving high-level plans that are novel and sound, and executing these plans correctly amidst dynamic and uncertain conditions. To address this bilevel challenge, we propose a novel Double-Loop Multi-Agent (DLMA) framework to solve the given research problem automatically. The leader loop, composed of professor agents, is responsible for evolving research plans. It employs an evolutionary algorithm through involvement, improvement, and integration meetings to iteratively generate and refine a pool of research proposals, exploring the solution space effectively. The follower loop, composed of doctoral student agents, is responsible for executing the best-evolved plan. It dynamically adjusts the plan during implementation via pre-hoc and post-hoc meetings, ensuring each step (e.g., drafting, coding) is well-supported by contextual and external observations. Extensive experiments on benchmarks like ACLAward and Laboratory show that DLMA generates research papers that achieve state-of-the-art scores in automated evaluation, significantly outperforming strong baselines. Ablation studies confirm the critical roles of both loops, with evolution driving novelty and execution ensuring soundness.

---

### Transforming Noise Distributions with Histogram Matching: Towards a Single Denoiser for All

Authors: Sheng Fu, Junchao Zhang, Kailun Yang
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06757v1

Supervised Gaussian denoisers exhibit limited generalization when confronted with out-of-distribution noise, due to the diverse distributional characteristics of different noise types. To bridge this gap, we propose a histogram matching approach that transforms arbitrary noise towards a target Gaussian distribution with known intensity. Moreover, a mutually reinforcing cycle is established between noise transformation and subsequent denoising. This cycle progressively refines the noise to be converted, making it approximate the real noise, thereby enhancing the noise transformation effect and further improving the denoising performance. We tackle specific noise complexities: local histogram matching handles signal-dependent noise, intrapatch permutation processes channel-related noise, and frequency-domain histogram matching coupled with pixel-shuffle down-sampling breaks spatial correlation. By applying these transformations, a single Gaussian denoiser gains remarkable capability to handle various out-of-distribution noises, including synthetic noises such as Poisson, salt-and-pepper and repeating pattern noises, as well as complex real-world noises. Extensive experiments demonstrate the superior generalization and effectiveness of our method.

---

### Verifying Memoryless Sequential Decision-making of Large Language Models

Authors: Dennis Gross, Helge Spieker, Arnaud Gotlieb
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.06756v1

We introduce a tool for rigorous and automated verification of large language model (LLM)- based policies in memoryless sequential decision-making tasks. Given a Markov decision process (MDP) representing the sequential decision-making task, an LLM policy, and a safety requirement expressed as a PCTL formula, our approach incrementally constructs only the reachable portion of the MDP guided by the LLM's chosen actions. Each state is encoded as a natural language prompt, the LLM's response is parsed into an action, and reachable successor states by the policy are expanded. The resulting formal model is checked with Storm to determine whether the policy satisfies the specified safety property. In experiments on standard grid world benchmarks, we show that open source LLMs accessed via Ollama can be verified when deterministically seeded, but generally underperform deep reinforcement learning baselines. Our tool natively integrates with Ollama and supports PRISM-specified tasks, enabling continuous benchmarking in user-specified sequential decision-making tasks and laying a practical foundation for formally verifying increasingly capable LLMs.

---

### UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene

Authors: Christian Maurer, Snehal Jauhri, Sophie Lueth, Georgia Chalvatzaki
Published: 2025-10-08
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.06754v2

Comprehensive visual, geometric, and semantic understanding of a 3D scene is crucial for successful execution of robotic tasks, especially in unstructured and complex environments. Additionally, to make robust decisions, it is necessary for the robot to evaluate the reliability of perceived information. While recent advances in 3D neural feature fields have enabled robots to leverage features from pretrained foundation models for tasks such as language-guided manipulation and navigation, existing methods suffer from two critical limitations: (i) they are typically scene-specific, and (ii) they lack the ability to model uncertainty in their predictions. We present UniFField, a unified uncertainty-aware neural feature field that combines visual, semantic, and geometric features in a single generalizable representation while also predicting uncertainty in each modality. Our approach, which can be applied zero shot to any new environment, incrementally integrates RGB-D images into our voxel-based feature representation as the robot explores the scene, simultaneously updating uncertainty estimation. We evaluate our uncertainty estimations to accurately describe the model prediction errors in scene reconstruction and semantic feature prediction. Furthermore, we successfully leverage our feature predictions and their respective uncertainty for an active object search task using a mobile manipulator robot, demonstrating the capability for robust decision-making.

---

### OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

Authors: Junhan Zhu, Hesong Wang, Mingluo Su, Zefang Wang, Huan Wang
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06751v3

Large-scale text-to-image diffusion models, while powerful, suffer from prohibitive computational cost. Existing one-shot network pruning methods can hardly be directly applied to them due to the iterative denoising nature of diffusion models. To bridge the gap, this paper presents OBS-Diff, a novel one-shot pruning framework that enables accurate and training-free compression of large-scale text-to-image diffusion models. Specifically, (i) OBS-Diff revitalizes the classic Optimal Brain Surgeon (OBS), adapting it to the complex architectures of modern diffusion models and supporting diverse pruning granularity, including unstructured, N:M semi-structured, and structured (MHA heads and FFN neurons) sparsity; (ii) To align the pruning criteria with the iterative dynamics of the diffusion process, by examining the problem from an error-accumulation perspective, we propose a novel timestep-aware Hessian construction that incorporates a logarithmic-decrease weighting scheme, assigning greater importance to earlier timesteps to mitigate potential error accumulation; (iii) Furthermore, a computationally efficient group-wise sequential pruning strategy is proposed to amortize the expensive calibration process. Extensive experiments show that OBS-Diff achieves state-of-the-art one-shot pruning for diffusion models, delivering inference acceleration with minimal degradation in visual quality.

---

### Gold-Switch: Training-Free Superposition of Slow- and Fast- Thinking LLMs

Authors: Jaeseong Lee, Dayoung Kwon, seung-won hwang
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06750v1

Large Reasoning Models (LRMs) excel in structured tasks by emulating deliberate human reasoning but often suffer from overthinking, degrading performance and wasting resources. One possible baseline is to deploy both LLM and LRM, then route input by predicting whether it requires reasoning and may cause overthinking. However, deploying multiple models can be costly or impractical. We propose a superposed deployment strategy with a lightweight, training-free regulation to optimize inference by switching one model on and off. Instead of routing, we selectively unlearn from LRM at inference, scaling down computation while preserving reasoning. By analyzing the cumulative energy of singular values, we identify optimal low-rank projections to adjust reasoning just right.

---

### A Formal Framework for Fluency-based Multi-Reference Evaluation in Grammatical Error Correction

Authors: Eitan Klinger, Zihao Huang, Tran Minh Nguyen, Emma Jayeon Park, Yige Chen, Yang Gu, Qingyu Gao, Siliang Liu, Mengyang Qiu, Jungyeul Park
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06749v1

Evaluating grammatical error correction requires metrics that reflect the diversity of valid human corrections rather than privileging a single reference. Existing frameworks, largely edit-based and English-centric, rely on rigid alignments between system and reference edits, limiting their applicability in multilingual and generative settings. This paper introduces a formal framework for \textit{fluency-based multi-reference evaluation}, framing $n$-gram similarity as an aggregation problem over multiple legitimate corrections. Within this formulation, we instantiate GLEU through four aggregation strategies--\textsc{select-best}, \textsc{simple-average}, \textsc{weighted-average}, and \textsc{merged-counts}--and analyze their properties of boundedness, monotonicity, and sensitivity to reference variation. Empirical results on Czech, Estonian, Ukrainian, and Chinese corpora show that these strategies capture complementary aspects of fluency and coverage. The framework unifies multi-reference evaluation into a principled, fluency-oriented approach that incorporates linguistic diversity without penalizing legitimate variation.

---

### LLMs Enable Bag-of-Texts Representations for Short-Text Clustering

Authors: I-Fan Lin, Faegheh Hasibi, Suzan Verberne
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06747v2

In this paper, we propose a training-free method for unsupervised short text clustering that relies less on careful selection of embedders than other methods. In customer-facing chatbots, companies are dealing with large amounts of user utterances that need to be clustered according to their intent. In these settings, no labeled data is typically available, and the number of clusters is not known. Recent approaches to short-text clustering in label-free settings incorporate LLM output to refine existing embeddings. While LLMs can identify similar texts effectively, the resulting similarities may not be directly represented by distances in the dense vector space, as they depend on the original embedding. We therefore propose a method for transforming LLM judgments directly into a bag-of-texts representation in which texts are initialized to be equidistant, without assuming any prior distance relationships. Our method achieves comparable or superior results to state-of-the-art methods, but without embeddings optimization or assuming prior knowledge of clusters or labels. Experiments on diverse datasets and smaller LLMs show that our method is model agnostic and can be applied to any embedder, with relatively small LLMs, and different clustering methods. We also show how our method scales to large datasets, reducing the computational cost of the LLM use. The flexibility and scalability of our method make it more aligned with real-world training-free scenarios than existing clustering methods.

---

### DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining

Authors: Zhiliang Zhu, Tao Zeng, Tao Yang, Guoliang Luo, Jiyong Zeng
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06746v1

Image deraining is crucial for improving visual quality and supporting reliable downstream vision tasks. Although Mamba-based models provide efficient sequence modeling, their limited ability to capture fine-grained details and lack of frequency-domain awareness restrict further improvements. To address these issues, we propose DeRainMamba, which integrates a Frequency-Aware State-Space Module (FASSM) and Multi-Directional Perception Convolution (MDPConv). FASSM leverages Fourier transform to distinguish rain streaks from high-frequency image details, balancing rain removal and detail preservation. MDPConv further restores local structures by capturing anisotropic gradient features and efficiently fusing multiple convolution branches. Extensive experiments on four public benchmarks demonstrate that DeRainMamba consistently outperforms state-of-the-art methods in PSNR and SSIM, while requiring fewer parameters and lower computational costs. These results validate the effectiveness of combining frequency-domain modeling and spatial detail enhancement within a state-space framework for single image deraining.

---

### Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanities

Authors: Maria Levchenko
Published: 2025-10-08
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.06743v1

Digital humanities scholars increasingly use Large Language Models for historical document digitization, yet lack appropriate evaluation frameworks for LLM-based OCR. Traditional metrics fail to capture temporal biases and period-specific errors crucial for historical corpus creation. We present an evaluation methodology for LLM-based historical OCR, addressing contamination risks and systematic biases in diplomatic transcription. Using 18th-century Russian Civil font texts, we introduce novel metrics including Historical Character Preservation Rate (HCPR) and Archaic Insertion Rate (AIR), alongside protocols for contamination control and stability testing. We evaluate 12 multimodal LLMs, finding that Gemini and Qwen models outperform traditional OCR while exhibiting over-historicization: inserting archaic characters from incorrect historical periods. Post-OCR correction degrades rather than improves performance. Our methodology provides digital humanities practitioners with guidelines for model selection and quality assessment in historical corpus digitization.

---

### MultiCNKG: Integrating Cognitive Neuroscience, Gene, and Disease Knowledge Graphs Using Large Language Models

Authors: Ali Sarabadani, Kheirolah Rahsepar Fard
Published: 2025-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06742v1

The advent of large language models (LLMs) has revolutionized the integration of knowledge graphs (KGs) in biomedical and cognitive sciences, overcoming limitations in traditional machine learning methods for capturing intricate semantic links among genes, diseases, and cognitive processes. We introduce MultiCNKG, an innovative framework that merges three key knowledge sources: the Cognitive Neuroscience Knowledge Graph (CNKG) with 2.9K nodes and 4.3K edges across 9 node types and 20 edge types; Gene Ontology (GO) featuring 43K nodes and 75K edges in 3 node types and 4 edge types; and Disease Ontology (DO) comprising 11.2K nodes and 8.8K edges with 1 node type and 2 edge types. Leveraging LLMs like GPT-4, we conduct entity alignment, semantic similarity computation, and graph augmentation to create a cohesive KG that interconnects genetic mechanisms, neurological disorders, and cognitive functions. The resulting MultiCNKG encompasses 6.9K nodes across 5 types (e.g., Genes, Diseases, Cognitive Processes) and 11.3K edges spanning 7 types (e.g., Causes, Associated with, Regulates), facilitating a multi-layered view from molecular to behavioral domains. Assessments using metrics such as precision (85.20%), recall (87.30%), coverage (92.18%), graph consistency (82.50%), novelty detection (40.28%), and expert validation (89.50%) affirm its robustness and coherence. Link prediction evaluations with models like TransE (MR: 391, MRR: 0.411) and RotatE (MR: 263, MRR: 0.395) show competitive performance against benchmarks like FB15k-237 and WN18RR. This KG advances applications in personalized medicine, cognitive disorder diagnostics, and hypothesis formulation in cognitive neuroscience.

---

### AWM: Accurate Weight-Matrix Fingerprint for Large Language Models

Authors: Boyi Zeng, Lin Chen, Ziwei He, Xinbing Wang, Zhouhan Lin
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06738v3

Protecting the intellectual property of large language models (LLMs) is crucial, given the substantial resources required for their training. Consequently, there is an urgent need for both model owners and third parties to determine whether a suspect LLM is trained from scratch or derived from an existing base model. However, the intensive post-training processes that models typically undergo-such as supervised fine-tuning, extensive continued pretraining, reinforcement learning, multi-modal extension, pruning, and upcycling-pose significant challenges to reliable identification. In this work, we propose a training-free fingerprinting method based on weight matrices. We leverage the Linear Assignment Problem (LAP) and an unbiased Centered Kernel Alignment (CKA) similarity to neutralize the effects of parameter manipulations, yielding a highly robust and high-fidelity similarity metric. On a comprehensive testbed of 60 positive and 90 negative model pairs, our method demonstrates exceptional robustness against all six aforementioned post-training categories while exhibiting a near-zero risk of false positives. By achieving perfect scores on all classification metrics, our approach establishes a strong basis for reliable model lineage verification. Moreover, the entire computation completes within 30s on an NVIDIA 3090 GPU. The code is available at https://github.com/LUMIA-Group/AWM.

---

### Incorporating Expert Knowledge into Bayesian Causal Discovery of Mixtures of Directed Acyclic Graphs

Authors: Zachris Björkman, Jorge Loría, Sophie Wharrie, Samuel Kaski
Published: 2025-10-08
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2510.06735v2

Bayesian causal discovery benefits from prior information elicited from domain experts, and in heterogeneous domains any prior knowledge would be badly needed. However, so far prior elicitation approaches have assumed a single causal graph and hence are not suited to heterogeneous domains. We propose a causal elicitation strategy for heterogeneous settings, based on Bayesian experimental design (BED) principles, and a variational mixture structure learning (VaMSL) method -- extending the earlier differentiable Bayesian structure learning (DiBS) method -- to iteratively infer mixtures of causal Bayesian networks (CBNs). We construct an informative graph prior incorporating elicited expert feedback in the inference of mixtures of CBNs. Our proposed method successfully produces a set of alternative causal models (mixture components or clusters), and achieves an improved structure learning performance on heterogeneous synthetic data when informed by a simulated expert. Finally, we demonstrate that our approach is capable of capturing complex distributions in a breast cancer database.

---

### Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization

Authors: Tiancheng Xing, Jerry Li, Yixuan Du, Xiyang Hu
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.06732v2

Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose this vulnerability, we present Rank Anything First (RAF), a two-stage token optimization method that crafts concise textual perturbations to consistently promote a target item in LLM-generated rankings while remaining hard to detect. Stage 1 uses Greedy Coordinate Gradient to shortlist candidate tokens at the current position by combining the gradient of the rank-target with a readability score; Stage 2 evaluates those candidates under exact ranking and readability losses using an entropy-based dynamic weighting scheme, and selects a token via temperature-controlled sampling. RAF generates ranking-promoting prompts token-by-token, guided by dual objectives: maximizing ranking effectiveness and preserving linguistic naturalness. Experiments across multiple LLMs show that RAF significantly boosts the rank of target items using naturalistic language, with greater robustness than existing methods in both promoting target items and maintaining naturalness. These findings underscore a critical security implication: LLM-based reranking is inherently susceptible to adversarial manipulation, raising new challenges for the trustworthiness and robustness of modern retrieval systems. Our code is available at: https://github.com/glad-lab/RAF.

---

### PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs

Authors: Manuel Frank, Haithem Afli
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06730v3

Current sentence embedding evaluations typically rely on static test beds like the Massive Text Embedding Benchmark (MTEB). While invaluable, repeated tuning on a fixed suite can inflate reported scores and obscure real-world robustness. We introduce the Paraphrasing Text Embedding Benchmark (PTEB), a dynamic protocol that stochastically generates meaning-preserving paraphrases at evaluation time and aggregates results across multiple runs. Using a cost-efficient LLM-based method grounded in gold ratings and human validation, we show that LLMs generate token-diverse but semantically preserving paraphrases. Across 7 MTEB tasks, we validate our hypothesis that the performance of sentence encoders is sensitive to changes in token space even when semantics remain fixed. We also observe that smaller models are not disproportionately affected relative to larger ones. Our results are statistically robust over multiple runs spanning 20 datasets and 25 languages. More generally, we aim to propose a new evaluation paradigm in NLP that relies less on static, pre-defined benchmarks but shifts towards dynamic, stochastic evaluation leveraging eval-time compute. We make the code to run PTEB publicly available.

---

### Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management

Authors: Miao Lu, Weiwei Sun, Weihua Du, Zhan Ling, Xuesong Yao, Kang Liu, Jiecao Chen
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06727v1

We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottleneck. Existing RL pipelines can suffer from degraded instruction following, excessive rollout costs, and most importantly, strict context limits. To address these challenges, we introduce summarization-based context management to training. In specific, it periodically compresses the tool using history by LLM-generated summaries that retain task-relevant information to keep a compact context while enabling the agent to scale beyond the fixed context window. Building on this formulation, we derive a policy gradient representation that seamlessly enables standard LLM RL infrastructures to optimize both tool-use behaviors as well as summarization strategies in an end-to-end fashion. We instantiate this framework with \underline{SU}mmarization augmented \underline{P}olicy \underline{O}ptimization (\texttt{SUPO}), an LLM RL algorithm that enables long-horizon training beyond a fixed context limit. Experiments on interactive function calling and searching tasks demonstrate that \texttt{SUPO} significantly improves the success rate while maintaining the same or even lower working context length compared to baselines. We also demonstrate that for complex searching tasks, \texttt{SUPO} can further improve the evaluation performance when scaling test-time maximum round of summarization beyond that of training time. Our results establish summarization-based context management as a principled and scalable approach for training RL agents beyond a fixed context length limit.

---

### Neuromorphic Computing - An Overview

Authors: Benedikt Jung, Maximilian Kalcher, Merlin Marinova, Piper Powell, Esma Sakalli
Published: 2025-10-08
Categories: cs.NE, cs.ET
arXiv: https://arxiv.org/abs/2510.06721v2

With traditional computing technologies reaching their limit, a new field has emerged seeking to follow the example of the human brain into a new era: neuromorphic computing. This paper provides an introduction to neuromorphic computing, why this and other new computing systems are needed, and what technologies currently exist in the neuromorphic field. It begins with a general introduction into the history of traditional computing and its present problems, and then proceeds to a general overview of neuromorphic systems. It subsequently discusses the main technologies currently in development. For completeness, the paper first discusses neuromorphic-style computing on traditional hardware, and then discusses the two top branches of specialized hardware in this field; neuromorphic chips and photonic systems. Both branches are explained as well as their relative benefits and drawbacks. The paper concludes with a summary and an outlook on the future.

---

### Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)

Authors: Junki Mori, Kazuya Kakizaki, Taiki Miyagawa, Jun Sakuma
Published: 2025-10-08
Categories: cs.CR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.06719v2

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding them in external knowledge. However, its application in sensitive domains is limited by privacy risks. Existing private RAG methods typically rely on query-time differential privacy (DP), which requires repeated noise injection and leads to accumulated privacy loss. To address this issue, we propose DP-SynRAG, a framework that uses LLMs to generate differentially private synthetic RAG databases. Unlike prior methods, the synthetic text can be reused once created, thereby avoiding repeated noise injection and additional privacy costs. To preserve essential information for downstream RAG tasks, DP-SynRAG extends private prediction, which instructs LLMs to generate text that mimics subsampled database records in a DP manner. Experiments show that DP-SynRAG achieves superior performance to the state-of-the-art private RAG systems while maintaining a fixed privacy budget, offering a scalable solution for privacy-preserving RAG.

---

### LLM Company Policies and Policy Implications in Software Organizations

Authors: Ranim Khojah, Mazen Mohamad, Linda Erlenhov, Francisco Gomes de Oliveira Neto, Philipp Leitner
Published: 2025-10-08
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.06718v1

The risks associated with adopting large language model (LLM) chatbots in software organizations highlight the need for clear policies. We examine how 11 companies create these policies and the factors that influence them, aiming to help managers safely integrate chatbots into development workflows.

---

### Dual Goal Representations

Authors: Seohong Park, Deepinder Mann, Sergey Levine
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06714v2

In this work, we introduce dual goal representations for goal-conditioned reinforcement learning (GCRL). A dual goal representation characterizes a state by "the set of temporal distances from all other states"; in other words, it encodes a state through its relations to every other state, measured by temporal distance. This representation provides several appealing theoretical properties. First, it depends only on the intrinsic dynamics of the environment and is invariant to the original state representation. Second, it contains provably sufficient information to recover an optimal goal-reaching policy, while being able to filter out exogenous noise. Based on this concept, we develop a practical goal representation learning method that can be combined with any existing GCRL algorithm. Through diverse experiments on the OGBench task suite, we empirically show that dual goal representations consistently improve offline goal-reaching performance across 20 state- and pixel-based tasks.

---

### Inefficiencies of Meta Agents for Agent Design

Authors: Batu El, Mert Yuksekgonul, James Zou
Published: 2025-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06711v1

Recent works began to automate the design of agentic systems using meta-agents that propose and iteratively refine new agent architectures. In this paper, we examine three key challenges in a common class of meta-agents. First, we investigate how a meta-agent learns across iterations and find that simply expanding the context with all previous agents, as proposed by previous works, performs worse than ignoring prior designs entirely. We show that the performance improves with an evolutionary approach. Second, although the meta-agent designs multiple agents during training, it typically commits to a single agent at test time. We find that the designed agents have low behavioral diversity, limiting the potential for their complementary use. Third, we assess when automated design is economically viable. We find that only in a few cases--specifically, two datasets--the overall cost of designing and deploying the agents is lower than that of human-designed agents when deployed on over 15,000 examples. In contrast, the performance gains for other datasets do not justify the design cost, regardless of scale.

---

### AISysRev -- LLM-based Tool for Title-abstract Screening

Authors: Aleksi Huotala, Miikka Kuutila, Olli-Pekka Turtio, Simo Sipilä, Mika Mäntylä
Published: 2025-10-08
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.06708v3

Conducting systematic reviews is laborious. In the screening or study selection phase, the number of papers can be overwhelming. Recent research has demonstrated that large language models (LLMs) can perform title-abstract screening and support humans in the task. To this end, we developed AISysRev, an LLM-based screening tool implemented as a containerized web application. The tool accepts CSV files containing paper titles and abstracts. Users specify inclusion and exclusion criteria. Multiple different LLMs can be used, such as Gemini, Claude, Mistral or ChatGPT via OpenRouter. We also support locally hosted models and any model compatible with the OpenAI SDK. AISysRev implements both zero-shot and few-shot prompting, and also allows for manual screening through interfaces that display LLM results as guidance for human reviewers. LLM calls are parallelized, meaning screening speed is typically between 100 to 300 papers per minute, depending on the model and the host. To demonstrate the tool's use in practice, we conducted a qualitative trial study with 137 papers using the tool. Our findings indicate that papers can be classified into four categories: Easy Includes, Easy Excludes, Boundary Includes, and Boundary Excludes. The Boundary cases, where LLMs are prone to errors, highlight the need for human intervention. While LLMs do not replace human judgment in systematic reviews, they can reduce the burden of assessing large volumes of scientific literature. Video: https://www.youtube.com/watch?v=HeblemlgnAQ Tool: https://github.com/EvoTestOps/AISysRev

---

### XLSR-Kanformer: A KAN-Intergrated model for Synthetic Speech Detection

Authors: Phuong Tuan Dat, Tran Huy Dat
Published: 2025-10-08
Categories: cs.SD, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2510.06706v1

Recent advancements in speech synthesis technologies have led to increasingly sophisticated spoofing attacks, posing significant challenges for automatic speaker verification systems. While systems based on self-supervised learning (SSL) models, particularly the XLSR-Conformer architecture, have demonstrated remarkable performance in synthetic speech detection, there remains room for architectural improvements. In this paper, we propose a novel approach that replaces the traditional Multi-Layer Perceptron (MLP) in the XLSR-Conformer model with a Kolmogorov-Arnold Network (KAN), a powerful universal approximator based on the Kolmogorov-Arnold representation theorem. Our experimental results on ASVspoof2021 demonstrate that the integration of KAN to XLSR-Conformer model can improve the performance by 60.55% relatively in Equal Error Rate (EER) LA and DF sets, further achieving 0.70% EER on the 21LA set. Besides, the proposed replacement is also robust to various SSL architectures. These findings suggest that incorporating KAN into SSL-based models is a promising direction for advances in synthetic speech detection.

---

### How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects

Authors: Leonardo Bertolazzi, Sandro Pezzelle, Raffaella Bernardi
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06700v3

Both humans and large language models (LLMs) exhibit content effects: biases in which the plausibility of the semantic content of a reasoning problem influences judgments regarding its logical validity. While this phenomenon in humans is best explained by the dual-process theory of reasoning, the mechanisms behind content effects in LLMs remain unclear. In this work, we address this issue by investigating how LLMs encode the concepts of validity and plausibility within their internal representations. We show that both concepts are linearly represented and strongly aligned in representational geometry, leading models to conflate plausibility with validity. Using steering vectors, we demonstrate that plausibility vectors can causally bias validity judgements, and vice versa, and that the degree of alignment between these two concepts predicts the magnitude of behavioral content effects across models. Finally, we construct debiasing vectors that disentangle these concepts, reducing content effects and improving reasoning accuracy. Our findings advance understanding of how abstract logical concepts are represented in LLMs and highlight representational interventions as a path toward more logical systems.

---

### A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking

Authors: Gal Fadlon, Idan Arbiv, Nimrod Berman, Omri Azencot
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06699v1

Generating realistic time series data is critical for applications in healthcare, finance, and science. However, irregular sampling and missing values present significant challenges. While prior methods address these irregularities, they often yield suboptimal results and incur high computational costs. Recent advances in regular time series generation, such as the diffusion-based ImagenTime model, demonstrate strong, fast, and scalable generative capabilities by transforming time series into image representations, making them a promising solution. However, extending ImagenTime to irregular sequences using simple masking introduces "unnatural" neighborhoods, where missing values replaced by zeros disrupt the learning process. To overcome this, we propose a novel two-step framework: first, a Time Series Transformer completes irregular sequences, creating natural neighborhoods; second, a vision-based diffusion model with masking minimizes dependence on the completed values. This approach leverages the strengths of both completion and masking, enabling robust and efficient generation of realistic time series. Our method achieves state-of-the-art performance, achieving a relative improvement in discriminative score by $70\%$ and in computational cost by $85\%$. Code is at https://github.com/azencot-group/ImagenI2R.

---

### Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks

Authors: Qinhao Zhou, Xiang Xiang, Kun He, John E. Hopcroft
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.06695v1

In recent years, the growing interest in Large Language Models (LLMs) has significantly advanced prompt engineering, transitioning from manual design to model-based optimization. Prompts for LLMs generally comprise two components: the \textit{instruction}, which defines the task or objective, and the \textit{input}, which is tailored to the instruction type. In natural language generation (NLG) tasks such as machine translation, the \textit{input} component is particularly critical, while the \textit{instruction} component tends to be concise. Existing prompt engineering methods primarily focus on optimizing the \textit{instruction} component for general tasks, often requiring large-parameter LLMs as auxiliary tools. However, these approaches exhibit limited applicability for tasks like machine translation, where the \textit{input} component plays a more pivotal role. To address this limitation, this paper introduces a novel prompt optimization method specifically designed for machine translation tasks. The proposed approach employs a small-parameter model trained using a back-translation-based strategy, significantly reducing training overhead for single-task optimization while delivering highly effective performance. With certain adaptations, this method can also be extended to other downstream tasks.

---

### SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel View Synthesis

Authors: Jipeng Lyu, Jiahua Dong, Yu-Xiong Wang
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06694v1

Persistent dynamic scene modeling for tracking and novel-view synthesis remains challenging due to the difficulty of capturing accurate deformations while maintaining computational efficiency. We propose SCas4D, a cascaded optimization framework that leverages structural patterns in 3D Gaussian Splatting for dynamic scenes. The key idea is that real-world deformations often exhibit hierarchical patterns, where groups of Gaussians share similar transformations. By progressively refining deformations from coarse part-level to fine point-level, SCas4D achieves convergence within 100 iterations per time frame and produces results comparable to existing methods with only one-twentieth of the training iterations. The approach also demonstrates effectiveness in self-supervised articulated object segmentation, novel view synthesis, and dense point tracking tasks.

---

### Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?

Authors: Akira Ito, Takayuki Miura, Yosuke Todo
Published: 2025-10-08
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2510.06692v3

Deep Neural Networks (DNNs) have attracted significant attention, and their internal models are now considered valuable intellectual assets. Extracting such a model via oracle access to a DNN is conceptually similar to extracting a secret key from a block cipher. Consequently, cryptanalytic techniques, particularly differential-like attacks, have been actively explored. ReLU-based DNNs are the most common and widely deployed architectures. While early works (e.g., Crypto 2020, Eurocrypt 2024) assume access to exact output logits, which are typically not exposed, more recent works (e.g., Asiacrypt 2024, Eurocrypt 2025) focus on the hard-label setting, where only the final classification result (e.g., "dog" or "car") is available. Notably, Carlini et al. (Eurocrypt 2025) showed that model extraction is feasible in polynomial time even under this restricted setting. In this paper, we show that a key assumption underlying their attack becomes increasingly unrealistic as the target depth grows. While prior works noted neurons whose activation states rarely change, we analyze their concrete impact on hard-label extraction: even a single neuron that is (almost) always active can prevent the attack from proceeding unless its parameters are recovered, and ignoring it incurs a non-negligible error. A straightforward solution is to extract these parameters by observing a state switch of such a neuron, but observing such a switch becomes exponentially harder as depth increases, implying that hard-label extraction is not always polynomial time. To address this limitation, we propose a novel attack called cross-layer extraction. Rather than extracting secret parameters (e.g., weights and biases) directly, we exploit cross-layer interactions to recover them from deeper layers, reducing query complexity and addressing limitations of existing approaches.

---

### Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformer

Authors: Jing-Zong Zhang, Shuang Guo, Li-Lin Zhu, Lingxiao Wang, Guo-Liang Ma
Published: 2025-10-08
Categories: hep-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.06691v1

A central challenge in high-energy nuclear physics is to extract informative features from the high-dimensional final-state data of heavy-ion collisions (HIC) in order to enable reliable downstream analyses. Traditional approaches often rely on selected observables, which may miss subtle but physically relevant structures in the data. To address this, we introduce a Transformer-based autoencoder trained with a two-stage paradigm: self-supervised pre-training followed by supervised fine-tuning. The pretrained encoder learns latent representations directly from unlabeled HIC data, providing a compact and information-rich feature space that can be adapted to diverse physics tasks. As a case study, we apply the method to distinguish between large and small collision systems, where it achieves significantly higher classification accuracy than PointNet. Principal component analysis and SHAP interpretation further demonstrate that the autoencoder captures complex nonlinear correlations beyond individual observables, yielding features with strong discriminative and explanatory power. These results establish our two-stage framework as a general and robust foundation for feature learning in HIC, opening the door to more powerful analyses of quark--gluon plasma properties and other emergent phenomena. The implementation is publicly available at https://github.com/Giovanni-Sforza/MaskPoint-AMPT.

---

### Geometry-Aware Cross Modal Alignment for Light Field-LiDAR Semantic Segmentation

Authors: Jie Luo, Yuxuan Jiang, Xin Jin, Mingyu Liu, Yihui Fan
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06687v4

Semantic segmentation serves as a cornerstone of scene understanding in autonomous driving but continues to face significant challenges under complex conditions such as occlusion. Light field and LiDAR modalities provide complementary visual and spatial cues that are beneficial for robust perception; however, their effective integration is hindered by limited viewpoint diversity and inherent modality discrepancies. To address these challenges, the first multimodal semantic segmentation dataset integrating light field data and point cloud data is proposed. Based on this dataset, we proposed a multi-modal light field point-cloud fusion segmentation network(Mlpfseg), incorporating feature completion and depth perception to segment both camera images and LiDAR point clouds simultaneously. The feature completion module addresses the density mismatch between point clouds and image pixels by performing differential reconstruction of point-cloud feature maps, enhancing the fusion of these modalities. The depth perception module improves the segmentation of occluded objects by reinforcing attention scores for better occlusion awareness. Our method outperforms image-only segmentation by 1.71 Mean Intersection over Union(mIoU) and point cloud-only segmentation by 2.38 mIoU, demonstrating its effectiveness.

---

### Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix

Authors: Tomohiro Hayase, Benoît Collins, Ryo Karakida
Published: 2025-10-08
Categories: stat.ML, cs.LG, math.PR
arXiv: https://arxiv.org/abs/2510.06685v2

Self-attention layers have become fundamental building blocks of modern deep neural networks, yet their theoretical understanding remains limited, particularly from the perspective of random matrix theory. In this work, we provide a rigorous analysis of the singular value spectrum of the attention matrix and establish the first Gaussian equivalence result for attention. In a natural regime where the inverse temperature remains of constant order, we show that the singular value distribution of the attention matrix is asymptotically characterized by a tractable linear model. We further demonstrate that the distribution of squared singular values deviates from the Marchenko-Pastur law, which has been believed in previous work. Our proof relies on two key ingredients: precise control of fluctuations in the normalization term and a refined linearization that leverages favorable Taylor expansions of the exponential. This analysis also identifies a threshold for linearization and elucidates why attention, despite not being an entrywise operation, admits a rigorous Gaussian equivalence in this regime.

---

### AutoBalance: An Automatic Balancing Framework for Training Physics-Informed Neural Networks

Authors: Kang An, Chenhao Si, Ming Yan, Shiqian Ma
Published: 2025-10-08
Categories: cs.LG, math.NA, math.OC
arXiv: https://arxiv.org/abs/2510.06684v1

Physics-Informed Neural Networks (PINNs) provide a powerful and general framework for solving Partial Differential Equations (PDEs) by embedding physical laws into loss functions. However, training PINNs is notoriously difficult due to the need to balance multiple loss terms, such as PDE residuals and boundary conditions, which often have conflicting objectives and vastly different curvatures. Existing methods address this issue by manipulating gradients before optimization (a "pre-combine" strategy). We argue that this approach is fundamentally limited, as forcing a single optimizer to process gradients from spectrally heterogeneous loss landscapes disrupts its internal preconditioning. In this work, we introduce AutoBalance, a novel "post-combine" training paradigm. AutoBalance assigns an independent adaptive optimizer to each loss component and aggregates the resulting preconditioned updates afterwards. Extensive experiments on challenging PDE benchmarks show that AutoBalance consistently outperforms existing frameworks, achieving significant reductions in solution error, as measured by both the MSE and $L^{\infty}$ norms. Moreover, AutoBalance is orthogonal to and complementary with other popular PINN methodologies, amplifying their effectiveness on demanding benchmarks.

---

### Distributed Algorithms for Multi-Agent Multi-Armed Bandits with Collision

Authors: Daoyuan Zhou, Xuchuang Wang, Lin Yang, Yang Gao
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06683v1

We study the stochastic Multiplayer Multi-Armed Bandit (MMAB) problem, where multiple players select arms to maximize their cumulative rewards. Collisions occur when two or more players select the same arm, resulting in no reward, and are observed by the players involved. We consider a distributed setting without central coordination, where each player can only observe their own actions and collision feedback. We propose a distributed algorithm with an adaptive, efficient communication protocol. The algorithm achieves near-optimal group and individual regret, with a communication cost of only $\mathcal{O}(\log\log T)$. Our experiments demonstrate significant performance improvements over existing baselines. Compared to state-of-the-art (SOTA) methods, our approach achieves a notable reduction in individual regret. Finally, we extend our approach to a periodic asynchronous setting, proving the lower bound for this problem and presenting an algorithm that achieves logarithmic regret.

---

### TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting

Authors: Zhipeng Liu, Peibo Duan, Xuan Tang, Baixin Li, Yongsheng Huang, Mingyang Geng, Changsheng Zhang, Bin Zhang, Binwu Wang
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06680v1

Although Transformers excel in natural language processing, their extension to time series forecasting remains challenging due to insufficient consideration of the differences between textual and temporal modalities. In this paper, we develop a novel Transformer architecture designed for time series data, aiming to maximize its representational capacity. We identify two key but often overlooked characteristics of time series: (1) unidirectional influence from the past to the future, and (2) the phenomenon of decaying influence over time. These characteristics are introduced to enhance the attention mechanism of Transformers. We propose TimeFormer, whose core innovation is a self-attention mechanism with two modulation terms (MoSA), designed to capture these temporal priors of time series under the constraints of the Hawkes process and causal masking. Additionally, TimeFormer introduces a framework based on multi-scale and subsequence analysis to capture semantic dependencies at different temporal scales, enriching the temporal dependencies. Extensive experiments conducted on multiple real-world datasets show that TimeFormer significantly outperforms state-of-the-art methods, achieving up to a 7.45% reduction in MSE compared to the best baseline and setting new benchmarks on 94.04\% of evaluation metrics. Moreover, we demonstrate that the MoSA mechanism can be broadly applied to enhance the performance of other Transformer-based models.

---

### DreamOmni2: Multimodal Instruction-based Editing and Generation

Authors: Bin Xia, Bohao Peng, Yuechen Zhang, Junjia Huang, Jiyang Liu, Jingyao Li, Haoru Tan, Sitong Wu, Chengyao Wang, Yitong Wang, Xinglong Wu, Bei Yu et al.
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06679v1

Recent advancements in instruction-based image editing and subject-driven generation have garnered significant attention, yet both tasks still face limitations in meeting practical user needs. Instruction-based editing relies solely on language instructions, which often fail to capture specific editing details, making reference images necessary. Meanwhile, subject-driven generation is limited to combining concrete objects or people, overlooking broader, abstract concepts. To address these challenges, we propose two novel tasks: multimodal instruction-based editing and generation. These tasks support both text and image instructions and extend the scope to include both concrete and abstract concepts, greatly enhancing their practical applications. We introduce DreamOmni2, tackling two primary challenges: data creation and model framework design. Our data synthesis pipeline consists of three steps: (1) using a feature mixing method to create extraction data for both abstract and concrete concepts, (2) generating multimodal instruction-based editing training data using the editing and extraction models, and (3) further applying the extraction model to create training data for multimodal instruction-based editing. For the framework, to handle multi-image input, we propose an index encoding and position encoding shift scheme, which helps the model distinguish images and avoid pixel confusion. Additionally, we introduce joint training with the VLM and our generation/editing model to better process complex instructions. In addition, we have proposed comprehensive benchmarks for these two new tasks to drive their development. Experiments show that DreamOmni2 has achieved impressive results. Models and codes will be released.

---

### Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback

Authors: Yisha Wu, Cen Mia Zhao, Yuanpei Cao, Xiaoqing Su, Yashar Mehdad, Mindy Ji, Claire Na Cheng
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06677v2

We introduce an incremental summarization system for customer support agents that intelligently determines when to generate concise bullet notes during conversations, reducing agents' context-switching effort and redundant review. Our approach combines a fine-tuned Mixtral-8x7B model for continuous note generation with a DeBERTa-based classifier to filter trivial content. Agent edits refine the online notes generation and regularly inform offline model retraining, closing the agent edits feedback loop. Deployed in production, our system achieved a 3% reduction in case handling time compared to bulk summarization (with reductions of up to 9% in highly complex cases), alongside high agent satisfaction ratings from surveys. These results demonstrate that incremental summarization with continuous feedback effectively enhances summary quality and agent productivity at scale.

---

### Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support

Authors: Cen Mia Zhao, Tiantian Zhang, Hanchen Su, Yufeng Wayne Zhang, Shaowei Su, Mingzhi Xu, Yu Elaine Liu, Wei Han, Jeremy Werner, Claire Na Cheng, Yashar Mehdad
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.06674v2

We introduce an Agent-in-the-Loop (AITL) framework that implements a continuous data flywheel for iteratively improving an LLM-based customer support system. Unlike standard offline approaches that rely on batch annotations, AITL integrates four key types of annotations directly into live customer operations: (1) pairwise response preferences, (2) agent adoption and rationales, (3) knowledge relevance checks, and (4) identification of missing knowledge. These feedback signals seamlessly feed back into models' updates, reducing retraining cycles from months to weeks. Our production pilot involving US-based customer support agents demonstrated significant improvements in retrieval accuracy (+11.7% recall@75, +14.8% precision@8), generation quality (+8.4% helpfulness) and agent adoption rates (+4.5%). These results underscore the effectiveness of embedding human feedback loops directly into operational workflows to continuously refine LLM-based customer support system.

---

### Heptapod: Language Modeling on Visual Signals

Authors: Yongxin Zhu, Jiawei Chen, Yuanzhe Chen, Zhuo Chen, Dongya Jia, Jian Cong, Xiaobin Zhuang, Yuping Wang, Yuxuan Wang
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06673v1

We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs \textbf{causal attention}, \textbf{eliminates reliance on CFG}, and \textbf{eschews the trend of semantic tokenizers}. Our key innovation is \textit{next 2D distribution prediction}: a causal Transformer with reconstruction-focused visual tokenizer, learns to predict the distribution over the entire 2D spatial grid of images at each timestep. This learning objective unifies the sequential modeling of autoregressive framework with the holistic self-supervised learning of masked autoencoding, enabling the model to capture comprehensive image semantics via generative training. On the ImageNet generation benchmark, Heptapod achieves an FID of $2.70$, significantly outperforming previous causal autoregressive approaches. We hope our work inspires a principled rethinking of language modeling on visual signals and beyond.

---

### XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation

Authors: Udbhav Bamba, Minghao Fang, Yifan Yu, Haizhong Zheng, Fan Lai
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06672v3

Reinforcement learning algorithms such as GRPO have driven recent advances in large language model (LLM) reasoning. While scaling the number of rollouts stabilizes training, existing approaches suffer from limited exploration on challenging prompts and leave informative feedback signals underexploited, due to context-independent rollout allocation across prompts (e.g., generating 16 rollouts per prompt) and relying heavily on sparse rewards. This paper presents XRPO(eXplore - eXploit GRPO), a unified framework that recasts policy optimization through the principled lens of rollout exploration-exploitation. To enhance exploration, XRPO introduces a mathematically grounded rollout allocator that adaptively prioritizes prompts with higher potential for uncertainty reduction. It further addresses stagnation on zero-reward prompts through an in-context seeding strategy that injects curated exemplars, steering the model into more difficult reasoning trajectories. To strengthen exploitation, XRPO develops a group-relative, novelty-aware advantage sharpening mechanism that leverages sequence likelihoods to amplify low-probability yet correct responses, thereby extending the policy's reach beyond sparse rewards. Experiments across diverse math and coding benchmarks on both reasoning and non-reasoning models demonstrate that XRPO outperforms existing advances (e.g., GRPO and GSPO) up to 4% pass@1 and 6% cons@32, while accelerating training convergence by up to 2.7X.

---

### PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch

Authors: Shangjian Yin, Shining Liang, Wenbiao Ding, Yuli Qian, Zhouxing Shi, Hongzhi Li, Yutao Xie
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06670v2

High-quality instruction data is critical for LLM alignment, yet existing open-source datasets often lack efficiency, requiring hundreds of thousands of examples to approach proprietary performance. In this work, we find that beyond the widely recognized importance of prompt-response quality, prompt difficulty itself plays a critical role in driving alignment gains. Motivated by this observation, we introduce PiKa, a data-efficient family of expert-level alignment datasets that concentrates supervision on high-difficulty instructions. The PiKa-SFT dataset contains only 30k examples, an order of magnitude fewer than state-of-the-art open datasets like Magpie-Pro. Despite its small size, fine-tuning Llama-3-8B-Base on PiKa-SFT even outperforms the official Llama-3-8B-Instruct model trained on over 10M proprietary examples on widely used benchmarks such as AlpacaEval 2.0 and Arena-Hard. We also validate the generalizability of PiKa across the Qwen2.5 series (0.5B-7B), consistently surpassing their official instruction-tuned counterparts. Additionally, we provide 30k high-quality preference optimization examples to further enhance alignment. Our results demonstrate that promising alignment is achievable with significantly reduced data, democratizing access for resource-constrained research. Our code and data will be available at https://github.com/SJY8460/PiKa.

---

### Automated Neural Architecture Design for Industrial Defect Detection

Authors: Yuxi Liu, Yunfeng Ma, Yi Tang, Min Liu, Shuai Jiang, Yaonan Wang
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06669v2

Industrial surface defect detection (SDD) is critical for ensuring product quality and manufacturing reliability. Due to the diverse shapes and sizes of surface defects, SDD faces two main challenges: intraclass difference and interclass similarity. Existing methods primarily utilize manually designed models, which require extensive trial and error and often struggle to address both challenges effectively. To overcome this, we propose AutoNAD, an automated neural architecture design framework for SDD that jointly searches over convolutions, transformers, and multi-layer perceptrons. This hybrid design enables the model to capture both fine-grained local variations and long-range semantic context, addressing the two key challenges while reducing the cost of manual network design. To support efficient training of such a diverse search space, AutoNAD introduces a cross weight sharing strategy, which accelerates supernet convergence and improves subnet performance. Additionally, a searchable multi-level feature aggregation module (MFAM) is integrated to enhance multi-scale feature learning. Beyond detection accuracy, runtime efficiency is essential for industrial deployment. To this end, AutoNAD incorporates a latency-aware prior to guide the selection of efficient architectures. The effectiveness of AutoNAD is validated on three industrial defect datasets and further applied within a defect imaging and detection platform. Code is available at https://github.com/Yuxi104/AutoNAD.

---

### ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory

Authors: Yunzhong Xiao, Yangmin Li, Hewei Wang, Yunlong Tang, Zora Zhiruo Wang
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06664v1

Agents utilizing tools powered by large language models (LLMs) or vision-language models (VLMs) have demonstrated remarkable progress in diverse tasks across text and visual modalities. Unlike traditional tools such as calculators, which give deterministic outputs, neural tools perform uncertainly across task scenarios. While different tools for a task may excel in varied scenarios, existing agents typically rely on fixed tools, thus limiting the flexibility in selecting the most suitable tool for specific tasks. In contrast, humans snowball their understanding of the capabilities of different tools by interacting with them, and apply this knowledge to select the optimal tool when solving a future task. To build agents that similarly benefit from this process, we propose ToolMem that enables agents to develop memories of tool capabilities from previous interactions, by summarizing their strengths and weaknesses and storing them in memory; at inference, the agent can retrieve relevant entries from ToolMem, and select the best tool to solve individual tasks more accurately. We evaluate ToolMem on learning varied text generation and text-to-image generation neural tools. Compared to no-memory, generic agents, we find ToolMem-augmented agents predict tool performance 14.8% and 28.7% more accurately across text and multimodal generation scenarios. Moreover, ToolMem facilitates optimal tool selection among multiple choices by 21% and 24% absolute increases in respective scenarios.

---

### The Effect of Attention Head Count on Transformer Approximation

Authors: Penghao Yu, Haotian Jiang, Zeyu Bao, Ruoxi Yu, Qianxiao Li
Published: 2025-10-08
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.06662v2

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of transformers, with particular emphasis on the role of the number of attention heads. Our analysis begins with the introduction of a generalized $D$-retrieval task, which we prove to be dense in the space of continuous functions, thereby providing the basis for our theoretical framework. We then establish both upper and lower bounds on the parameter complexity required for $ε$-approximation. Specifically, we show that transformers with sufficiently many heads admit efficient approximation, whereas with too few heads, the number of parameters must scale at least as $O(1/ε^{cT})$, for some constant $c$ and sequence length $T$. To the best of our knowledge, this constitutes the first rigorous lower bound of this type in a nonlinear and practically relevant setting. We further examine the single-head case and demonstrate that an embedding dimension of order $O(T)$ allows complete memorization of the input, where approximation is entirely achieved by the feed-forward block. Finally, we validate our theoretical findings with experiments on both synthetic data and real-world tasks, illustrating the practical relevance of our results.

---

### Delay Independent Safe Control with Neural Networks: Positive Lur'e Certificates for Risk Aware Autonomy

Authors: Hamidreza Montazeri Hedesh, Milad Siami
Published: 2025-10-08
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2510.06661v1

We present a risk-aware safety certification method for autonomous, learning enabled control systems. Focusing on two realistic risks, state/input delays and interval matrix uncertainty, we model the neural network (NN) controller with local sector bounds and exploit positivity structure to derive linear, delay-independent certificates that guarantee local exponential stability across admissible uncertainties. To benchmark performance, we adopt and implement a state-of-the-art IQC NN verification pipeline. On representative cases, our positivity-based tests run orders of magnitude faster than SDP-based IQC while certifying regimes the latter cannot-providing scalable safety guarantees that complement risk-aware control.

---

### Rethinking Nonlinearity: Trainable Gaussian Mixture Modules for Modern Neural Architectures

Authors: Weiguo Lu, Gangnan Yuan, Hong-kun Zhang, Shangyang Li
Published: 2025-10-08
Categories: cs.LG, math.PR
arXiv: https://arxiv.org/abs/2510.06660v1

Neural networks in general, from MLPs and CNNs to attention-based Transformers, are constructed from layers of linear combinations followed by nonlinear operations such as ReLU, Sigmoid, or Softmax. Despite their strength, these conventional designs are often limited in introducing non-linearity by the choice of activation functions. In this work, we introduce Gaussian Mixture-Inspired Nonlinear Modules (GMNM), a new class of differentiable modules that draw on the universal density approximation Gaussian mixture models (GMMs) and distance properties (metric space) of Gaussian kernal. By relaxing probabilistic constraints and adopting a flexible parameterization of Gaussian projections, GMNM can be seamlessly integrated into diverse neural architectures and trained end-to-end with gradient-based methods. Our experiments demonstrate that incorporating GMNM into architectures such as MLPs, CNNs, attention mechanisms, and LSTMs consistently improves performance over standard baselines. These results highlight GMNM's potential as a powerful and flexible module for enhancing efficiency and accuracy across a wide range of machine learning applications.

---

### Fitzpatrick Thresholding for Skin Image Segmentation

Authors: Duncan Stothers, Sophia Xu, Carlie Reeves, Lia Gracey
Published: 2025-10-08
Categories: eess.IV, cs.LG
arXiv: https://arxiv.org/abs/2510.06655v1

Accurate estimation of the body surface area (BSA) involved by a rash, such as psoriasis, is critical for assessing rash severity, selecting an initial treatment regimen, and following clinical treatment response. Attempts at segmentation of inflammatory skin disease such as psoriasis perform markedly worse on darker skin tones, potentially impeding equitable care. We assembled a psoriasis dataset sourced from six public atlases, annotated for Fitzpatrick skin type, and added detailed segmentation masks for every image. Reference models based on U-Net, ResU-Net, and SETR-small are trained without tone information. On the tuning split we sweep decision thresholds and select (i) global optima and (ii) per Fitzpatrick skin tone optima for Dice and binary IoU. Adapting Fitzpatrick specific thresholds lifted segmentation performance for the darkest subgroup (Fitz VI) by up to +31 % bIoU and +24 % Dice on UNet, with consistent, though smaller, gains in the same direction for ResU-Net (+25 % bIoU, +18 % Dice) and SETR-small (+17 % bIoU, +11 % Dice). Because Fitzpatrick skin tone classifiers trained on Fitzpatrick-17k now exceed 95 % accuracy, the cost of skin tone labeling required for this technique has fallen dramatically. Fitzpatrick thresholding is simple, model-agnostic, requires no architectural changes, no re-training, and is virtually cost free. We demonstrate the inclusion of Fitzpatrick thresholding as a potential future fairness baseline.

---

### Aligning Large Language Models via Fully Self-Synthetic Data

Authors: Shangjian Yin, Zhepei Wei, Xinyu Zhu, Wei-Lin Chen, Yu Meng
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06652v1

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the collection of diverse prompts and corresponding responses, often necessitating external reward models or proprietary models like GPT-4 to annotate preference pairs. In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment, where all training data, including prompts (i.e., user queries), responses, and preferences, are generated by the model itself. Specifically, SAO first instructs the LLM to engage in persona role-play and generate diverse prompts and responses, which are then self-evaluated for preference optimization. Extensive experiments demonstrate that SAO effectively enhances the model's chat capabilities on standard benchmarks like AlpacaEval~2.0, while maintaining strong performance on downstream objective tasks (e.g., question-answering, math reasoning). Our work provides a practical solution for self-improvement in aligning LLMs, and the code for reproducing our results is available at: https://github.com/SJY8460/SAO.

---

### Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions

Authors: Frank Wu, Mengye Ren
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06649v2

The Forward-Forward (FF) Algorithm is a recently proposed learning procedure for neural networks that employs two forward passes instead of the traditional forward and backward passes used in backpropagation. However, FF remains largely confined to supervised settings, leaving a gap at domains where learning signals can be yielded more naturally such as RL. In this work, inspired by FF's goodness function using layer activity statistics, we introduce Action-conditioned Root mean squared Q-Functions (ARQ), a novel value estimation method that applies a goodness function and action conditioning for local RL using temporal difference learning. Despite its simplicity and biological grounding, our approach achieves superior performance compared to state-of-the-art local backprop-free RL methods in the MinAtar and the DeepMind Control Suite benchmarks, while also outperforming algorithms trained with backpropagation on most tasks. Code can be found at https://github.com/agentic-learning-ai-lab/arq.

---

### Q-Learning with Fine-Grained Gap-Dependent Regret

Authors: Haochen Zhang, Zhong Zheng, Lingzhou Xue
Published: 2025-10-08
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.06647v2

We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain coarse and fail to fully capture the structure of suboptimality gaps. We address this limitation by establishing fine-grained gap-dependent regret bounds for both UCB-based and non-UCB-based algorithms. In the UCB-based setting, we develop a novel analytical framework that explicitly separates the analysis of optimal and suboptimal state-action pairs, yielding the first fine-grained regret upper bound for UCB-Hoeffding (Jin et al., 2018). To highlight the generality of this framework, we introduce ULCB-Hoeffding, a new UCB-based algorithm inspired by AMB (Xu et al.,2021) but with a simplified structure, which enjoys fine-grained regret guarantees and empirically outperforms AMB. In the non-UCB-based setting, we revisit the only known algorithm AMB, and identify two key issues in its algorithm design and analysis: improper truncation in the $Q$-updates and violation of the martingale difference condition in its concentration argument. We propose a refined version of AMB that addresses these issues, establishing the first rigorous fine-grained gap-dependent regret for a non-UCB-based method, with experiments demonstrating improved performance over AMB.

---

### The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators

Authors: Mansi Sakarvadia, Kareem Hegazy, Amin Totounferoush, Kyle Chard, Yaoqing Yang, Ian Foster, Michael W. Mahoney
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.06646v2

A core challenge in scientific machine learning, and scientific computing more generally, is modeling continuous phenomena which (in practice) are represented discretely. Machine-learned operators (MLOs) have been introduced as a means to achieve this modeling goal, as this class of architecture can perform inference at arbitrary resolution. In this work, we evaluate whether this architectural innovation is sufficient to perform "zero-shot super-resolution," namely to enable a model to serve inference on higher-resolution data than that on which it was originally trained. We comprehensively evaluate both zero-shot sub-resolution and super-resolution (i.e., multi-resolution) inference in MLOs. We decouple multi-resolution inference into two key behaviors: 1) extrapolation to varying frequency information; and 2) interpolating across varying resolutions. We empirically demonstrate that MLOs fail to do both of these tasks in a zero-shot manner. Consequently, we find MLOs are not able to perform accurate inference at resolutions different from those on which they were trained, and instead they are brittle and susceptible to aliasing. To address these failure modes, we propose a simple, computationally-efficient, and data-driven multi-resolution training protocol that overcomes aliasing and that provides robust multi-resolution generalization.

---