# Research Papers — 2025-11 · bundle page 130 of 197

> Full-text markdown of papers #6451–6500 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/130
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/129.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/131.md)

### Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial Optimization

Authors: Paul Strang, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum, Emmanuel Rachelson
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09219v4

Mixed-Integer Linear Programming (MILP) lies at the core of many real-world combinatorial optimization (CO) problems, traditionally solved by branch-and-bound (B&B). A key driver influencing B&B solvers efficiency is the variable selection heuristic that guides branching decisions. Looking to move beyond static, hand-crafted heuristics, recent work has explored adapting traditional reinforcement learning (RL) algorithms to the B&B setting, aiming to learn branching strategies tailored to specific MILP distributions. In parallel, RL agents have achieved remarkable success in board games, a very specific type of combinatorial problems, by leveraging environment simulators to plan via Monte Carlo Tree Search (MCTS). Building on these developments, we introduce Plan-and-Branch-and-Bound (PlanB&B), a model-based reinforcement learning (MBRL) agent that leverages a learned internal model of the B&B dynamics to discover improved branching strategies. Computational experiments empirically validate our approach, with our MBRL branching agent outperforming previous state-of-the-art RL methods across four standard MILP benchmarks.

---

### Controllable protein design with particle-based Feynman-Kac steering

Authors: Erik Hartman, Jonas Wallin, Johan Malmström, Jimmy Olsson
Published: 2025-11-12
Categories: cs.LG, q-bio.QM, stat.ML
arXiv: https://arxiv.org/abs/2511.09216v2

Proteins underpin most biological function, and the ability to design them with tailored structures and properties is central to advances in biotechnology. Diffusion-based generative models have emerged as powerful tools for protein design, but steering them toward proteins with specified properties remains challenging. The Feynman-Kac (FK) framework provides a principled way to guide diffusion models using user-defined rewards. In this paper, we enable FK-based steering of RFdiffusion through the development of guiding potentials that leverage ProteinMPNN and structural relaxation to guide the diffusion process towards desired properties. We show that steering can be used to consistently improve predicted interface energetics and increase binder designability by $89.5\%$. Together, these results establish that diffusion-based protein design can be effectively steered toward arbitrary, non-differentiable objectives, providing a model-independent framework for controllable protein generation.

---

### Controllable protein design through Feynman-Kac steering

Authors: Erik Hartman, Jonas Wallin, Johan Malmström, Jimmy Olsson
Published: 2025-11-12
Categories: cs.LG, q-bio.QM, stat.ML
arXiv: https://arxiv.org/abs/2511.09216v1

Diffusion-based models have recently enabled the generation of realistic and diverse protein structures, yet they remain limited in their ability to steer outcomes toward specific functional or biochemical objectives, such as binding affinity or sequence composition. Here we extend the Feynman-Kac (FK) steering framework, an inference-time control approach, to diffusion-based protein design. By coupling FK steering with structure generation, the method guides sampling toward desirable structural or energetic features while maintaining the diversity of the underlying diffusion process. To enable simultaneous generation of both sequence and structure properties, rewards are computed on models refined through ProteinMPNN and all-atom relaxation. Applied to binder design, FK steering consistently improves predicted interface energetics across diverse targets with minimal computational overhead. More broadly, this work demonstrates that inference-time FK control generalizes diffusion-based protein design to arbitrary, non-differentiable, and reward-agnostic objectives, providing a unified and model-independent framework for guided molecular generation.

---

### Pretraining Finnish ModernBERTs

Authors: Akseli Reunamo, Laura-Maria Peltonen, Hans Moen, Sampo Pyysalo
Published: 2025-11-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.09213v1

This paper reports on pretraining ModernBERT encoder models in six different sizes, ranging from 51M to 475M parameters, with a focus on limited multilingualism, emphasizing languages relevant to Finland. Our models are competitive with, or superior to, existing multilingual models. They outperform monolingual models on tasks that require a context longer than 512 tokens. We present empirical results on using different data in the final stage of training. The code and models are publicly released.

---

### Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)

Authors: Lijun Zhang, Suyuan Liu, Siwei Wang, Shengju Yu, Xueling Zhu, Miaomiao Li, Xinwang Liu
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09211v3

Clustering is a fundamental task in unsupervised learning, but most existing methods heavily rely on hyperparameters such as the number of clusters or other sensitive settings, limiting their applicability in real-world scenarios. To address this long-standing challenge, we propose a novel and fully parameter-free clustering framework via Self-supervised Consensus Maximization, named SCMax. Our framework performs hierarchical agglomerative clustering and cluster evaluation in a single, integrated process. At each step of agglomeration, it creates a new, structure-aware data representation through a self-supervised learning task guided by the current clustering structure. We then introduce a nearest neighbor consensus score, which measures the agreement between the nearest neighbor-based merge decisions suggested by the original representation and the self-supervised one. The moment at which consensus maximization occurs can serve as a criterion for determining the optimal number of clusters. Extensive experiments on multiple datasets demonstrate that the proposed framework outperforms existing clustering approaches designed for scenarios with an unknown number of clusters.

---

### CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Prediction

Authors: Tianle Pu, Jianing Li, Yingying Gao, Shixuan Liu, Zijie Geng, Haoyang Liu, Chao Chen, Changjun Fan
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09209v1

Mixed-Integer Linear Programming (MILP) is a cornerstone of combinatorial optimization, yet solving large-scale instances remains a significant computational challenge. Recently, Graph Neural Networks (GNNs) have shown promise in accelerating MILP solvers by predicting high-quality solutions. However, we identify that existing methods misalign with the intrinsic structure of MILP problems at two levels. At the leaning objective level, the Binary Cross-Entropy (BCE) loss treats variables independently, neglecting their relative priority and yielding plausible logits. At the model architecture level, standard GNN message passing inherently smooths the representations across variables, missing the natural competitive relationships within constraints. To address these challenges, we propose CoCo-MILP, which explicitly models inter-variable Contrast and intra-constraint Competition for advanced MILP solution prediction. At the objective level, CoCo-MILP introduces the Inter-Variable Contrastive Loss (VCL), which explicitly maximizes the embedding margin between variables assigned one versus zero. At the architectural level, we design an Intra-Constraint Competitive GNN layer that, instead of homogenizing features, learns to differentiate representations of competing variables within a constraint, capturing their exclusionary nature. Experimental results on standard benchmarks demonstrate that CoCo-MILP significantly outperforms existing learning-based approaches, reducing the solution gap by up to 68.12% compared to traditional solvers. Our code is available at https://github.com/happypu326/CoCo-MILP.

---

### Resource-Efficient Variational Quantum Classifier

Authors: Petr Ptáček, Paulina Lewandowska, Ryszard Kukulski
Published: 2025-11-12
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2511.09204v3

We introduce the unambiguous quantum classifier based on Hamming distance measurements combined with classical post-processing. The proposed approach improves classification performance through a more effective use of ansatz expressivity, while requiring significantly fewer circuit evaluations. Moreover, the method demonstrates enhanced robustness to noise, which is crucial for near-term quantum devices. We evaluate the proposed method on a breast cancer classification dataset. The unambiguous classifier achieves an average accuracy of 90%, corresponding to an improvement of 6.9 percentage points over the baseline, while requiring eight times fewer circuit executions per prediction. In the presence of noise, the improvement is reduced to approximately 3.1 percentage points, with the same reduction in execution cost. We substantiate our experimental results with theoretical evidence supporting the practical performance of the approach.

---

### Stochastic Mean-Shift Clustering

Authors: Itshak Lapidot, Yann Sepulcre, Tom Trigano
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09202v1

We present a stochastic version of the mean-shift clustering algorithm. In this stochastic version a randomly chosen sequence of data points move according to partial gradient ascent steps of the objective function. Theoretical results illustrating the convergence of the proposed approach, and its relative performances is evaluated on synthesized 2-dimensional samples generated by a Gaussian mixture distribution and compared with state-of-the-art methods. It can be observed that in most cases the stochastic mean-shift clustering outperforms the standard mean-shift. We also illustrate as a practical application the use of the presented method for speaker clustering.

---

### Sure! Here's a short and concise title for your paper: "Contamination in Generated Text Detection Benchmarks"

Authors: Philipp Dingfelder, Christian Riess
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09200v1

Large language models are increasingly used for many applications. To prevent illicit use, it is desirable to be able to detect AI-generated text. Training and evaluation of such detectors critically depend on suitable benchmark datasets. Several groups took on the tedious work of collecting, curating, and publishing large and diverse datasets for this task. However, it remains an open challenge to ensure high quality in all relevant aspects of such a dataset. For example, the DetectRL benchmark exhibits relatively simple patterns of AI-generation in 98.5% of the Claude-LLM data. These patterns may include introductory words such as "Sure! Here is the academic article abstract:", or instances where the LLM rejects the prompted task. In this work, we demonstrate that detectors trained on such data use such patterns as shortcuts, which facilitates spoofing attacks on the trained detectors. We consequently reprocessed the DetectRL dataset with several cleansing operations. Experiments show that such data cleansing makes direct attacks more difficult. The reprocessed dataset is publicly available.

---

### The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages

Authors: Francois Meyer, Jan Buys
Published: 2025-11-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.09197v2

Subword segmentation is typically applied in preprocessing and stays fixed during training. Alternatively, it can be learned during training to optimise the training objective. In this paper we study the learning dynamics of subword segmentation: if a language model can dynamically optimise tokenisation, how do its subwords evolve during pretraining and finetuning? To explore this, we extend the subword segmental language model (SSLM), a framework for learning subwords during training, to support pretraining and finetuning. We train models for three typologically diverse languages to study learning dynamics across the morphological spectrum: Isi-Xhosa is conjunctive (long word forms composed of many morphemes), Setswana is disjunctive (morphemes written as separate words), and English represents a typological middle ground. We analyse subword dynamics from a linguistic perspective, tracking morphology, productivity, and fertility. We identify four stages of subword learning, with the morphologically complex isi-Xhosa exhibiting greater instability. During finetuning, subword boundaries shift to become finer-grained. Lastly, we show that learnable subwords offers a promising approach to improve text generation and cross-lingual transfer for low-resource, morphologically complex languages.

---

### Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narratives

Authors: Yuhao Shen, Jiahe Qian, Shuping Zhang, Zhangtianyi Chen, Tao Lu, Juexiao Zhou
Published: 2025-11-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.09195v2

Multimodal large language models (LLMs) are increasingly used to generate dermatology diagnostic narratives directly from images. However, reliable evaluation remains the primary bottleneck for responsible clinical deployment. We introduce a novel evaluation framework that combines DermBench, a meticulously curated benchmark, with DermEval, a robust automatic evaluator, to enable clinically meaningful, reproducible, and scalable assessment. We build DermBench, which pairs 4,000 real-world dermatology images with expert-certified diagnostic narratives and uses an LLM-based judge to score candidate narratives across clinically grounded dimensions, enabling consistent and comprehensive evaluation of multimodal models. For individual case assessment, we train DermEval, a reference-free multimodal evaluator. Given an image and a generated narrative, DermEval produces a structured critique along with an overall score and per-dimension ratings. This capability enables fine-grained, per-case analysis, which is critical for identifying model limitations and biases. Experiments on a diverse dataset of 4,500 cases demonstrate that DermBench and DermEval achieve close alignment with expert ratings, with mean deviations of 0.251 and 0.117 (out of 5), respectively, providing reliable measurement of diagnostic ability and trustworthiness across different multimodal LLMs.

---

### Enhancing PIBT via Multi-Action Operations

Authors: Egor Yukhnevich, Anton Andreychuk
Published: 2025-11-12
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2511.09193v2

PIBT is a rule-based Multi-Agent Path Finding (MAPF) solver, widely used as a low-level planner or action sampler in many state-of-the-art approaches. Its primary advantage lies in its exceptional speed, enabling action selection for thousands of agents within milliseconds by considering only the immediate next timestep. However, this short-horizon design leads to poor performance in scenarios where agents have orientation and must perform time-consuming rotation actions. In this work, we present an enhanced version of PIBT that addresses this limitation by incorporating multi-action operations. We detail the modifications introduced to improve PIBT's performance while preserving its hallmark efficiency. Furthermore, we demonstrate how our method, when combined with graph-guidance technique and large neighborhood search optimization, achieves state-of-the-art performance in the online LMAPF-T setting.

---

### Iterated Population Based Training with Task-Agnostic Restarts

Authors: Alexander Chebykin, Tanja Alderliesten, Peter A. N. Bosman
Published: 2025-11-12
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2511.09190v2

Hyperparameter Optimization (HPO) can lift the burden of tuning hyperparameters (HPs) of neural networks. HPO algorithms from the Population Based Training (PBT) family are efficient thanks to dynamically adjusting HPs every few steps of the weight optimization. Recent results indicate that the number of steps between HP updates is an important meta-HP of all PBT variants that can substantially affect their performance. Yet, no method or intuition is available for efficiently setting its value. We introduce Iterated Population Based Training (IPBT), a novel PBT variant that automatically adjusts this HP via restarts that reuse weight information in a task-agnostic way and leverage time-varying Bayesian optimization to reinitialize HPs. Evaluation on 8 image classification and reinforcement learning tasks shows that, on average, our algorithm matches or outperforms 5 previous PBT variants and other HPO algorithms (random search, ASHA, SMAC3), without requiring a budget increase or any changes to its HPs. The source code is available at https://github.com/AwesomeLemon/IPBT.

---

### Iterated Population Based Training with Task-Agnostic Restarts

Authors: Alexander Chebykin, Tanja Alderliesten, Peter A. N. Bosman
Published: 2025-11-12
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2511.09190v1

Hyperparameter Optimization (HPO) can lift the burden of tuning hyperparameters (HPs) of neural networks. HPO algorithms from the Population Based Training (PBT) family are efficient thanks to dynamically adjusting HPs every few steps of the weight optimization. Recent results indicate that the number of steps between HP updates is an important meta-HP of all PBT variants that can substantially affect their performance. Yet, no method or intuition is available for efficiently setting its value. We introduce Iterated Population Based Training (IPBT), a novel PBT variant that automatically adjusts this HP via restarts that reuse weight information in a task-agnostic way and leverage time-varying Bayesian optimization to reinitialize HPs. Evaluation on 8 image classification and reinforcement learning tasks shows that, on average, our algorithm matches or outperforms 5 previous PBT variants and other HPO algorithms (random search, ASHA, SMAC3), without requiring a budget increase or any changes to its HPs. The source code is available at https://github.com/AwesomeLemon/IPBT.

---

### Scalable Mixed-Integer Optimization with Neural Constraints via Dual Decomposition

Authors: Shuli Zeng, Sijia Zhang, Feng Wu, Shaojie Tang, Xiang-Yang Li
Published: 2025-11-12
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2511.09186v1

Embedding deep neural networks (NNs) into mixed-integer programs (MIPs) is attractive for decision making with learned constraints, yet state-of-the-art monolithic linearisations blow up in size and quickly become intractable. In this paper, we introduce a novel dual-decomposition framework that relaxes the single coupling equality u=x with an augmented Lagrange multiplier and splits the problem into a vanilla MIP and a constrained NN block. Each part is tackled by the solver that suits it best-branch and cut for the MIP subproblem, first-order optimisation for the NN subproblem-so the model remains modular, the number of integer variables never grows with network depth, and the per-iteration cost scales only linearly with the NN size. On the public \textsc{SurrogateLIB} benchmark, our method proves \textbf{scalable}, \textbf{modular}, and \textbf{adaptable}: it runs \(120\times\) faster than an exact Big-M formulation on the largest test case; the NN sub-solver can be swapped from a log-barrier interior step to a projected-gradient routine with no code changes and identical objective value; and swapping the MLP for an LSTM backbone still completes the full optimisation in 47s without any bespoke adaptation.

---

### Context is Enough: Empirical Validation of $\textit{Sequentiality}$ on Essays

Authors: Amal Sunny, Advay Gupta, Vishnu Sreekumar
Published: 2025-11-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.09185v1

Recent work has proposed using Large Language Models (LLMs) to quantify narrative flow through a measure called sequentiality, which combines topic and contextual terms. A recent critique argued that the original results were confounded by how topics were selected for the topic-based component, and noted that the metric had not been validated against ground-truth measures of flow. That work proposed using only the contextual term as a more conceptually valid and interpretable alternative. In this paper, we empirically validate that proposal. Using two essay datasets with human-annotated trait scores, ASAP++ and ELLIPSE, we show that the contextual version of sequentiality aligns more closely with human assessments of discourse-level traits such as Organization and Cohesion. While zero-shot prompted LLMs predict trait scores more accurately than the contextual measure alone, the contextual measure adds more predictive value than both the topic-only and original sequentiality formulations when combined with standard linguistic features. Notably, this combination also outperforms the zero-shot LLM predictions, highlighting the value of explicitly modeling sentence-to-sentence flow. Our findings support the use of context-based sequentiality as a validated, interpretable, and complementary feature for automated essay scoring and related NLP tasks.

---

### DBINDS -- Can Initial Noise from Diffusion Model Inversion Help Reveal AI-Generated Videos?

Authors: Yanlin Wu, Xiaogang Yuan, Dezhi An
Published: 2025-11-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.09184v1

AI-generated video has advanced rapidly and poses serious challenges to content security and forensic analysis. Existing detectors rely mainly on pixel-level visual cues and generalize poorly to unseen generators. We propose DBINDS, a diffusion-model-inversion based detector that analyzes latent-space dynamics rather than pixels. We find that initial noise sequences recovered by diffusion inversion differ systematically between real and generated videos. Building on this, DBINDS forms an Initial Noise Difference Sequence (INDS) and extracts multi-domain, multi-scale features. With feature optimization and a LightGBM classifier tuned by Bayesian search, DBINDS (trained on a single generator) achieves strong cross-generator performance on GenVidBench, demonstrating good generalization and robustness in limited-data settings.

---

### FSampler: Training Free Acceleration of Diffusion Sampling via Epsilon Extrapolation

Authors: Michael A. Vladimir
Published: 2025-11-12
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.09180v1

FSampler is a training free, sampler agnostic execution layer that accelerates diffusion sampling by reducing the number of function evaluations (NFE). FSampler maintains a short history of denoising signals (epsilon) from recent real model calls and extrapolates the next epsilon using finite difference predictors at second order, third order, or fourth order, falling back to lower order when history is insufficient. On selected steps the predicted epsilon substitutes the model call while keeping each sampler's update rule unchanged. Predicted epsilons are validated for finiteness and magnitude; a learning stabilizer rescales predictions on skipped steps to correct drift, and an optional gradient estimation stabilizer compensates local curvature. Protected windows, periodic anchors, and a cap on consecutive skips bound deviation over the trajectory. Operating at the sampler level, FSampler integrates with Euler/DDIM, DPM++ 2M/2S, LMS/AB2, and RES family exponential multistep methods and drops into standard workflows. FLUX.1 dev, Qwen Image, and Wan 2.2, FSampler reduces time by 8 to 22% and model calls by 15 to 25% at high fidelity (Structural Similarity Index (SSIM) 0.95 to 0.99), without altering sampler formulas. With an aggressive adaptive gate, reductions can reach 45 to 50% fewer model calls at lower fidelity (SSIM 0.73 to 0.74).

---

### A Hybrid Search for Complex Table Question Answering in Securities Report

Authors: Daiki Shirafuji, Koji Tanaka, Tatsuhiko Saito
Published: 2025-11-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.09179v1

Recently, Large Language Models (LLMs) are gaining increased attention in the domain of Table Question Answering (TQA), particularly for extracting information from tables in documents. However, directly entering entire tables as long text into LLMs often leads to incorrect answers because most LLMs cannot inherently capture complex table structures. In this paper, we propose a cell extraction method for TQA without manual identification, even for complex table headers. Our approach estimates table headers by computing similarities between a given question and individual cells via a hybrid retrieval mechanism that integrates a language model and TF-IDF. We then select as the answer the cells at the intersection of the most relevant row and column. Furthermore, the language model is trained using contrastive learning on a small dataset of question-header pairs to enhance performance. We evaluated our approach in the TQA dataset from the U4 shared task at NTCIR-18. The experimental results show that our pipeline achieves an accuracy of 74.6\%, outperforming existing LLMs such as GPT-4o mini~(63.9\%). In the future, although we used traditional encoder models for retrieval in this study, we plan to incorporate more efficient text-search models to improve performance and narrow the gap with human evaluation results.

---

### Perspectives on a Reliability Monitoring Framework for Agentic AI Systems

Authors: Niclas Flehmig, Mary Ann Lundteigen, Shen Yin
Published: 2025-11-12
Categories: cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2511.09178v1

The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one of their flaws is the insufficient reliability which makes them especially unsuitable for high-risk domains such as healthcare or process industry. Unreliable systems pose a risk in terms of unexpected behavior during operation and mitigation techniques are needed. In this work, we derive the main reliability challenges of agentic AI systems during operation based on their characteristics. We draw the connection to traditional AI systems and formulate a fundamental reliability challenge during operation which is inherent to traditional and agentic AI systems. As our main contribution, we propose a two-layered reliability monitoring framework for agentic AI systems which consists of a out-of-distribution detection layer for novel inputs and AI transparency layer to reveal internal operations. This two-layered monitoring approach gives a human operator the decision support which is needed to decide whether an output is potential unreliable or not and intervene. This framework provides a foundation for developing mitigation techniques to reduce risk stemming from uncertain reliability during operation.

---

### Tractable Weighted First-Order Model Counting with Bounded Treewidth Binary Evidence

Authors: Václav Kůla, Qipeng Kuang, Yuyi Wang, Yuanhong Wang, Ondřej Kuželka
Published: 2025-11-12
Categories: cs.LO, cs.AI
arXiv: https://arxiv.org/abs/2511.09174v2

The Weighted First-Order Model Counting Problem (WFOMC) asks to compute the weighted sum of models of a given first-order logic sentence over a given domain. Conditioning WFOMC on evidence -- fixing the truth values of a set of ground literals -- has been shown impossible in time polynomial in the domain size (unless $\mathsf{\#P \subseteq FP}$) even for fragments of logic that are otherwise tractable for WFOMC without evidence. In this work, we address the barrier by restricting the binary evidence to the case where the underlying Gaifman graph has bounded treewidth. We present a polynomial-time algorithm in the domain size for computing WFOMC for the two-variable fragments $\text{FO}^2$ and $\text{C}^2$ conditioned on such binary evidence. Furthermore, we show the applicability of our algorithm in combinatorial problems by solving the stable seating arrangement problem on bounded-treewidth graphs of bounded degree, which was an open problem. We also conducted experiments to show the scalability of our algorithm compared to the existing model counting solvers.

---

### Target-Aligned Fusion for Decision-Sequence Learning under Dynamics Shift

Authors: Guojian Wang, Quinson Hon, Xuyang Chen, Lin Zhao
Published: 2025-11-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.09173v3

External trajectories can improve offline decision-sequence learning, but dynamics shift may make some source subsequences inconsistent with the target environment. We study how to fuse such trajectories with limited target data for Decision Transformer learning under dynamics shift. We propose Target-Aligned Fusion (TAF), a principled framework that derives source-data fusion from a target-domain Bellman-risk criterion. Our analysis bounds this risk by two measurable data-alignment quantities: $Δ_m$, the state-structure mismatch of retained fragments, and $Δ_w$, the weighted transport cost from source to target transitions. This decomposition yields a gate--then--weight rule: source fragments are first filtered by target-side state-structure alignment, and retained transitions are then reweighted by local target feasibility. We instantiate this principle as TAF-DT, which uses maximum mean discrepancy (MMD) for fragment selection, optimal transport for feasibility-aware weighting, and the resulting fused law for advantage-token relabeling and Q-regularized Transformer training. Across gravity, kinematic, and morphology shifts on D4RL-style control tasks, TAF-DT achieves the strongest aggregate performance against strong offline RL and sequence-model baselines and produces more stable stitch-junction sequence semantics. Overall, these results indicate that aligning external trajectories to target-domain structure and feasibility is a practical way to exploit source data under dynamics shift.

---

### Data Fusion-Enhanced Decision Transformer for Stable Cross-Domain Generalization

Authors: Guojian Wang, Quinson Hon, Xuyang Chen, Lin Zhao
Published: 2025-11-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.09173v1

Cross-domain shifts present a significant challenge for decision transformer (DT) policies. Existing cross-domain policy adaptation methods typically rely on a single simple filtering criterion to select source trajectory fragments and stitch them together. They match either state structure or action feasibility. However, the selected fragments still have poor stitchability: state structures can misalign, the return-to-go (RTG) becomes incomparable when the reward or horizon changes, and actions may jump at trajectory junctions. As a result, RTG tokens lose continuity, which compromises DT's inference ability. To tackle these challenges, we propose Data Fusion-Enhanced Decision Transformer (DFDT), a compact pipeline that restores stitchability. Particularly, DFDT fuses scarce target data with selectively trusted source fragments via a two-level data filter, maximum mean discrepancy (MMD) mismatch for state-structure alignment, and optimal transport (OT) deviation for action feasibility. It then trains on a feasibility-weighted fusion distribution. Furthermore, DFDT replaces RTG tokens with advantage-conditioned tokens, which improves the continuity of the semantics in the token sequence. It also applies a $Q$-guided regularizer to suppress junction value and action jumps. Theoretically, we provide bounds that tie state value and policy performance gaps to the MMD-mismatch and OT-deviation measures, and show that the bounds tighten as these two measures shrink. We show that DFDT improves return and stability over strong offline RL and sequence-model baselines across gravity, kinematic, and morphology shifts on D4RL-style control tasks, and further corroborate these gains with token-stitching and sequence-semantics stability analyses.

---

### HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests

Authors: Ethan Griffiths, Maryam Haghighat, Simon Denman, Clinton Fookes, Milad Ramezani
Published: 2025-11-12
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.09170v2

This article presents HOTFLoc++, an end-to-end hierarchical framework for LiDAR place recognition, re-ranking, and 6-DoF metric localisation in forests. Leveraging an octree-based transformer, our approach extracts features at multiple granularities to increase robustness to clutter, self-similarity, and viewpoint changes in challenging scenarios, including ground-to-ground and ground-to-aerial in forest and urban environments. We propose learnable multi-scale geometric verification to reduce re-ranking failures due to degraded single-scale correspondences. Our joint training protocol enforces multi-scale geometric consistency of the octree hierarchy via joint optimisation of place recognition with re-ranking and localisation, improving place recognition convergence. Our system achieves comparable or lower localisation errors to baselines, with runtime improvements of almost two orders of magnitude over RANSAC-based registration for dense point clouds. Experimental results on public datasets show the superiority of our approach compared to state-of-the-art methods, achieving an average Recall@1 of 90.7% on CS-Wild-Places: an improvement of 29.6 percentage points over baselines, while maintaining high performance on single-source benchmarks with an average Recall@1 of 91.7% and 97.9% on Wild-Places and MulRan, respectively. Our method achieves under 2m and 5$^{\circ}$ error for 97.2% of 6-DoF registration attempts, with our multi-scale re-ranking module reducing localisation errors by ~2x on average. The code is available at https://github.com/csiro-robotics/HOTFLoc.

---

### Compact Memory for Continual Logistic Regression

Authors: Yohan Jung, Hyungi Lee, Wenlong Chen, Thomas Möllenhoff, Yingzhen Li, Juho Lee, Mohammad Emtiyaz Khan
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09167v1

Despite recent progress, continual learning still does not match the performance of batch training. To avoid catastrophic forgetting, we need to build compact memory of essential past knowledge, but no clear solution has yet emerged, even for shallow neural networks with just one or two layers. In this paper, we present a new method to build compact memory for logistic regression. Our method is based on a result by Khan and Swaroop (2021) who show the existence of optimal memory for such models. We formulate the search for the optimal memory as Hessian-matching and propose a probabilistic PCA method to estimate them. Our approach can drastically improve accuracy compared to Experience Replay. For instance, on Split-ImageNet, we get 60% accuracy compared to 30% obtained by replay with memory-size equivalent to 0.3% of the data size. Increasing the memory size to 2% further boosts the accuracy to 74%, closing the gap to the batch accuracy of 77.6% on this task. Our work opens a new direction for building compact memory that can also be useful in the future for continual deep learning.

---

### Unsupervised Feature Selection Through Group Discovery

Authors: Shira Lifshitz, Ofir Lindenbaum, Gal Mishne, Ron Meir, Hadas Benisty
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09166v1

Unsupervised feature selection (FS) is essential for high-dimensional learning tasks where labels are not available. It helps reduce noise, improve generalization, and enhance interpretability. However, most existing unsupervised FS methods evaluate features in isolation, even though informative signals often emerge from groups of related features. For example, adjacent pixels, functionally connected brain regions, or correlated financial indicators tend to act together, making independent evaluation suboptimal. Although some methods attempt to capture group structure, they typically rely on predefined partitions or label supervision, limiting their applicability. We propose GroupFS, an end-to-end, fully differentiable framework that jointly discovers latent feature groups and selects the most informative groups among them, without relying on fixed a priori groups or label supervision. GroupFS enforces Laplacian smoothness on both feature and sample graphs and applies a group sparsity regularizer to learn a compact, structured representation. Across nine benchmarks spanning images, tabular data, and biological datasets, GroupFS consistently outperforms state-of-the-art unsupervised FS in clustering and selects groups of features that align with meaningful patterns.

---

### Efficient Reasoning via Reward Model

Authors: Yuhao Wang, Xiaopeng Li, Cheng Gong, Ziru Liu, Suiyun Zhang, Rui Liu, Xiangyu Zhao
Published: 2025-11-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.09158v1

Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reasoning models (LRMs). However, LRMs such as DeepSeek-R1 and OpenAI o1 often generate verbose responses containing redundant or irrelevant reasoning step-a phenomenon known as overthinking-which substantially increases computational costs. Prior efforts to mitigate this issue commonly incorporate length penalties into the reward function, but we find they frequently suffer from two critical issues: length collapse and training collapse, resulting in sub-optimal performance. To address them, we propose a pipeline for training a Conciseness Reward Model (CRM) that scores the conciseness of reasoning path. Additionally, we introduce a novel reward formulation named Conciseness Reward Function (CRF) with explicit dependency between the outcome reward and conciseness score, thereby fostering both more effective and more efficient reasoning. From a theoretical standpoint, we demonstrate the superiority of the new reward from the perspective of variance reduction and improved convergence properties. Besides, on the practical side, extensive experiments on five mathematical benchmark datasets demonstrate the method's effectiveness and token efficiency, which achieves an 8.1% accuracy improvement and a 19.9% reduction in response token length on Qwen2.5-7B. Furthermore, the method generalizes well to other LLMs including Llama and Mistral. The implementation code and datasets are publicly available for reproduction: https://anonymous.4open.science/r/CRM.

---

### ProBench: Benchmarking GUI Agents with Accurate Process Information

Authors: Leyang Yang, Ziwei Wang, Xiaoxuan Tang, Sheng Zhou, Dajun Chen, Wei Jiang, Yong Li
Published: 2025-11-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.09157v1

With the deep integration of artificial intelligence and interactive technology, Graphical User Interface (GUI) Agent, as the carrier connecting goal-oriented natural language and real-world devices, has received widespread attention from the community. Contemporary benchmarks aim to evaluate the comprehensive capabilities of GUI agents in GUI operation tasks, generally determining task completion solely by inspecting the final screen state. However, GUI operation tasks consist of multiple chained steps while not all critical information is presented in the final few pages. Although a few research has begun to incorporate intermediate steps into evaluation, accurately and automatically capturing this process information still remains an open challenge. To address this weakness, we introduce ProBench, a comprehensive mobile benchmark with over 200 challenging GUI tasks covering widely-used scenarios. Remaining the traditional State-related Task evaluation, we extend our dataset to include Process-related Task and design a specialized evaluation method. A newly introduced Process Provider automatically supplies accurate process information, enabling presice assessment of agent's performance. Our evaluation of advanced GUI agents reveals significant limitations for real-world GUI scenarios. These shortcomings are prevalent across diverse models, including both large-scale generalist models and smaller, GUI-specific models. A detailed error analysis further exposes several universal problems, outlining concrete directions for future improvements.

---

### Enabling Agents to Communicate Entirely in Latent Space

Authors: Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying
Published: 2025-11-12
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2511.09149v5

While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint. The process of downsampling rich, internal latent states into discrete tokens inherently limits the depth and nuance of information that can be transmitted, thereby hindering collaborative problem-solving. Inspired by telepathy, which bypasses symbolic language in communication, we propose Interlat (Inter-agent Latent Space Communication), a paradigm that leverages the continuous last hidden states of an LLM as a representation of its thought for direct communication (termed latent communication). An additional learned compression process further compresses latent communication via latent space reasoning. Experiments demonstrate that Interlat outperforms both fine-tuned chain-of-thought (CoT) prompting and single-agent baselines, even across heterogeneous models, promoting more exploratory behavior and enabling genuine utilization of latent information. Further compression not only substantially accelerates inference by up to 24 times but also maintains competitive performance through an efficient information-preserving mechanism. We position this work as a feasibility study of entirely latent space inter-agent communication, and our results highlight its potential, offering valuable insights for future research. Our code is available at https://github.com/XiaoDu-flying/Interlat.

---

### Enabling Agents to Communicate Entirely in Latent Space

Authors: Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Bo Zheng, Wei Chen, Haochao Ying
Published: 2025-11-12
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2511.09149v1

While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint. The process of downsampling rich, internal latent states into discrete tokens inherently limits the depth and nuance of information that can be transmitted, thereby hindering collaborative problem-solving. Inspired by human mind-reading, we propose Interlat (Inter-agent Latent Space Communication), a paradigm that leverages the last hidden states of an LLM as a representation of its mind for direct transmission (termed latent communication). An additional compression process further compresses latent communication via entirely latent space reasoning. Experiments demonstrate that Interlat outperforms both fine-tuned chain-of-thought (CoT) prompting and single-agent baselines, promoting more exploratory behavior and enabling genuine utilization of latent information. Further compression not only substantially accelerates inference but also maintains competitive performance through an efficient information-preserving mechanism. We position this work as a feasibility study of entirely latent space inter-agent communication, and our results highlight its potential, offering valuable insights for future research.

---

### LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls

Authors: Kangning Zhang, Wenxiang Jiao, Kounianhua Du, Yuan Lu, Weiwen Liu, Weinan Zhang, Yong Yu
Published: 2025-11-12
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.09148v2

Augmenting Large Language Models (LLMs) with external tools enables them to execute complex, multi-step tasks. However, tool learning is hampered by the static synthetic data pipelines where data generation and model training are executed as two separate, non-interactive processes. This approach fails to adaptively focus on a model's specific weaknesses and allows noisy labels to persist, degrading training efficiency. We introduce LoopTool, a fully automated, model-aware data evolution framework that closes this loop by tightly integrating data synthesis and model training. LoopTool iteratively refines both the data and the model through three synergistic modules: (1) Greedy Capability Probing (GCP) diagnoses the model's mastered and failed capabilities; (2) Judgement-Guided Label Verification (JGLV) uses an open-source judge model to find and correct annotation errors, progressively purifying the dataset; and (3) Error-Driven Data Expansion (EDDE) generates new, challenging samples based on identified failures. This closed-loop process operates within a cost-effective, open-source ecosystem, eliminating dependence on expensive closed-source APIs. Experiments show that our 8B model trained with LoopTool significantly surpasses its 32B data generator and achieves new state-of-the-art results on the BFCL-v3 and ACEBench benchmarks for its scale. Our work demonstrates that closed-loop, self-refining data pipelines can dramatically enhance the tool-use capabilities of LLMs.

---

### LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls

Authors: Kangning Zhang, Wenxiang Jiao, Kounianhua Du, Yuan Lu, Weiwen Liu, Weinan Zhang, Lei Zhang, Yong Yu
Published: 2025-11-12
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.09148v1

Augmenting Large Language Models (LLMs) with external tools enables them to execute complex, multi-step tasks. However, tool learning is hampered by the static synthetic data pipelines where data generation and model training are executed as two separate, non-interactive processes. This approach fails to adaptively focus on a model's specific weaknesses and allows noisy labels to persist, degrading training efficiency. We introduce LoopTool, a fully automated, model-aware data evolution framework that closes this loop by tightly integrating data synthesis and model training. LoopTool iteratively refines both the data and the model through three synergistic modules: (1) Greedy Capability Probing (GCP) diagnoses the model's mastered and failed capabilities; (2) Judgement-Guided Label Verification (JGLV) uses an open-source judge model to find and correct annotation errors, progressively purifying the dataset; and (3) Error-Driven Data Expansion (EDDE) generates new, challenging samples based on identified failures. This closed-loop process operates within a cost-effective, open-source ecosystem, eliminating dependence on expensive closed-source APIs. Experiments show that our 8B model trained with LoopTool significantly surpasses its 32B data generator and achieves new state-of-the-art results on the BFCL-v3 and ACEBench benchmarks for its scale. Our work demonstrates that closed-loop, self-refining data pipelines can dramatically enhance the tool-use capabilities of LLMs.

---

### PressTrack-HMR: Pressure-Based Top-Down Multi-Person Global Human Mesh Recovery

Authors: Jiayue Yuan, Fangting Xie, Guangwen Ouyang, Changhai Ma, Ziyu Wu, Heyu Ding, Quan Wan, Yi Ke, Yuchen Wu, Xiaohui Cai
Published: 2025-11-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.09147v2

Multi-person global human mesh recovery (HMR) is crucial for understanding crowd dynamics and interactions. Traditional vision-based HMR methods sometimes face limitations in real-world scenarios due to mutual occlusions, insufficient lighting, and privacy concerns. Human-floor tactile interactions offer an occlusion-free and privacy-friendly alternative for capturing human motion. Existing research indicates that pressure signals acquired from tactile mats can effectively estimate human pose in single-person scenarios. However, when multiple individuals walk randomly on the mat simultaneously, how to distinguish intermingled pressure signals generated by different persons and subsequently acquire individual temporal pressure data remains a pending challenge for extending pressure-based HMR to the multi-person situation. In this paper, we present \textbf{PressTrack-HMR}, a top-down pipeline that recovers multi-person global human meshes solely from pressure signals. This pipeline leverages a tracking-by-detection strategy to first identify and segment each individual's pressure signal from the raw pressure data, and subsequently performs HMR for each extracted individual signal. Furthermore, we build a multi-person interaction pressure dataset \textbf{MIP}, which facilitates further research into pressure-based human motion analysis in multi-person scenarios. Experimental results demonstrate that our method excels in multi-person HMR using pressure data, with 89.2 $mm$ MPJPE and 112.6 $mm$ WA-MPJPE$_{100}$, and these showcase the potential of tactile mats for ubiquitous, privacy-preserving multi-person action recognition. Our dataset & code are available at https://github.com/Jiayue-Yuan/PressTrack-HMR.

---

### PressTrack-HMR: Pressure-Based Top-Down Multi-Person Global Human Mesh Recovery

Authors: Jiayue Yuan, Fangting Xie, Guangwen Ouyang, Changhai Ma, Ziyu Wu, Heyu Ding, Quan Wan, Yi Ke, Yuchen Wu, Xiaohui Cai
Published: 2025-11-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.09147v1

Multi-person global human mesh recovery (HMR) is crucial for understanding crowd dynamics and interactions. Traditional vision-based HMR methods sometimes face limitations in real-world scenarios due to mutual occlusions, insufficient lighting, and privacy concerns. Human-floor tactile interactions offer an occlusion-free and privacy-friendly alternative for capturing human motion. Existing research indicates that pressure signals acquired from tactile mats can effectively estimate human pose in single-person scenarios. However, when multiple individuals walk randomly on the mat simultaneously, how to distinguish intermingled pressure signals generated by different persons and subsequently acquire individual temporal pressure data remains a pending challenge for extending pressure-based HMR to the multi-person situation. In this paper, we present \textbf{PressTrack-HMR}, a top-down pipeline that recovers multi-person global human meshes solely from pressure signals. This pipeline leverages a tracking-by-detection strategy to first identify and segment each individual's pressure signal from the raw pressure data, and subsequently performs HMR for each extracted individual signal. Furthermore, we build a multi-person interaction pressure dataset \textbf{MIP}, which facilitates further research into pressure-based human motion analysis in multi-person scenarios. Experimental results demonstrate that our method excels in multi-person HMR using pressure data, with 89.2~$mm$ MPJPE and 112.6~$mm$ WA-MPJPE$_{100}$, and these showcase the potential of tactile mats for ubiquitous, privacy-preserving multi-person action recognition. Our dataset \& code are available at https://github.com/Jiayue-Yuan/PressTrack-HMR.

---

### DoPE: Denoising Rotary Position Embedding

Authors: Jing Xiong, Liyang Fan, Hui Shen, Zunhai Su, Min Yang, Lingpeng Kong, Ngai Wong
Published: 2025-11-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.09146v2

Positional encoding is essential for large language models (LLMs) to represent sequence order, yet recent studies show that Rotary Position Embedding (RoPE) can induce massive activation. We investigate the source of these instabilities via a spectral analysis of RoPE, and show that its low-frequency components concentrate structured energy, producing low-rank, over-aligned attention patterns. We theoretically reveal that this low-frequency alignment manifests as activation noise, degrading stability during long-context extrapolation. To mitigate this effect, we introduce Denoising Rotary Position Embedding (DoPE), a training-free method that identifies and suppresses noisy attention heads using truncated matrix entropy, then reparameterizes their attention maps with an isotropic Gaussian distribution. Across a range of settings, DoPE improves length extrapolation performance without fine-tuning, increases robustness to perturbations, and boosts both needle-in-a-haystack and many-shot in-context learning tasks. These results suggest that selective positional encoding is key to robust extrapolation. Our project page is Project: https://The-physical-picture-of-LLMs.github.io

---

### Practical Global and Local Bounds in Gaussian Process Regression via Chaining

Authors: Junyi Liu, Stanley Kok
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09144v4

Gaussian process regression (GPR) is a popular nonparametric Bayesian method that provides predictive uncertainty estimates and is widely used in safety-critical applications. While prior research has introduced various uncertainty bounds, most existing approaches require access to specific input features, and rely on posterior mean and variance estimates or the tuning of hyperparameters. These limitations hinder robustness and fail to capture the model's global behavior in expectation. To address these limitations, we propose a chaining-based framework for estimating upper and lower bounds on the expected extreme values over unseen data, without requiring access to specific input features. We provide kernel-specific refinements for commonly used kernels such as RBF and Matérn, in which our bounds are tighter than generic constructions. We further improve numerical tightness by avoiding analytical relaxations. In addition to global estimation, we also develop a novel method for local uncertainty quantification at specified inputs. This approach leverages chaining geometry through partition diameters, adapting to local structures without relying on posterior variance scaling. Our experimental results validate the theoretical findings and demonstrate that our method outperforms existing approaches on both synthetic and real-world datasets.

---

### MACEval: A Multi-Agent Continual Evaluation Network for Large Models

Authors: Zijian Chen, Yuze Sun, Yuan Tian, Wenjun Zhang, Guangtao Zhai
Published: 2025-11-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.09139v2

Hundreds of benchmarks dedicated to evaluating large models have been presented over the past few years. However, most of them remain closed-ended and are prone to overfitting due to the potential data contamination. Moreover, the increasing scale and scope of current benchmarks with transient metrics, as well as the heavily human-dependent curation procedure, pose significant challenges for timely maintenance and adaptation. In this paper, we introduce MACEval, a Multi-Agent Continual Evaluation network for dynamic evaluation of large models, and define new metrics to quantify performance longitudinally. MACEval employs an interactive and autonomous evaluation mode, utilizing role assignment, in-process data generation, and evaluation routing through a cascaded agent network. Extensive experiments on 23 large models demonstrate the effectiveness of MACEval, which also lightens the evaluation process and reduces a considerable amount of overhead. We hope that MACEval can broaden future directions of large model evaluation. Project page: https://github.com/zijianchen98/MACEval.

---

### Trusted Multi-view Learning for Long-tailed Classification

Authors: Chuanqing Tang, Yifei Shi, Guanghao Lin, Lei Xing, Long Shi
Published: 2025-11-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09138v1

Class imbalance has been extensively studied in single-view scenarios; however, addressing this challenge in multi-view contexts remains an open problem, with even scarcer research focusing on trustworthy solutions. In this paper, we tackle a particularly challenging class imbalance problem in multi-view scenarios: long-tailed classification. We propose TMLC, a Trusted Multi-view Long-tailed Classification framework, which makes contributions on two critical aspects: opinion aggregation and pseudo-data generation. Specifically, inspired by Social Identity Theory, we design a group consensus opinion aggregation mechanism that guides decision making toward the direction favored by the majority of the group. In terms of pseudo-data generation, we introduce a novel distance metric to adapt SMOTE for multi-view scenarios and develop an uncertainty-guided data generation module that produces high-quality pseudo-data, effectively mitigating the adverse effects of class imbalance. Extensive experiments on long-tailed multi-view datasets demonstrate that our model is capable of achieving superior performance. The code is released at https://github.com/cncq-tang/TMLC.

---

### One-Topic-Doesn't-Fit-All: Transcreating Reading Comprehension Test for Personalized Learning

Authors: Jieun Han, Daniel Lee, Haneul Yoo, Jinsung Yoon, Junyeong Park, Suin Kim, So-Yeon Ahn, Alice Oh
Published: 2025-11-12
Categories: cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2511.09135v1

Personalized learning has gained attention in English as a Foreign Language (EFL) education, where engagement and motivation play crucial roles in reading comprehension. We propose a novel approach to generating personalized English reading comprehension tests tailored to students' interests. We develop a structured content transcreation pipeline using OpenAI's gpt-4o, where we start with the RACE-C dataset, and generate new passages and multiple-choice reading comprehension questions that are linguistically similar to the original passages but semantically aligned with individual learners' interests. Our methodology integrates topic extraction, question classification based on Bloom's taxonomy, linguistic feature analysis, and content transcreation to enhance student engagement. We conduct a controlled experiment with EFL learners in South Korea to examine the impact of interest-aligned reading materials on comprehension and motivation. Our results show students learning with personalized reading passages demonstrate improved comprehension and motivation retention compared to those learning with non-personalized materials.

---

### Assessing the Capabilities of LLMs in Humor:A Multi-dimensional Analysis of Oogiri Generation and Evaluation

Authors: Ritsu Sakabe, Hwichan Kim, Tosho Hirasawa, Mamoru Komachi
Published: 2025-11-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.09133v1

Computational humor is a frontier for creating advanced and engaging natural language processing (NLP) applications, such as sophisticated dialogue systems. While previous studies have benchmarked the humor capabilities of Large Language Models (LLMs), they have often relied on single-dimensional evaluations, such as judging whether something is simply ``funny.'' This paper argues that a multifaceted understanding of humor is necessary and addresses this gap by systematically evaluating LLMs through the lens of Oogiri, a form of Japanese improvisational comedy games. To achieve this, we expanded upon existing Oogiri datasets with data from new sources and then augmented the collection with Oogiri responses generated by LLMs. We then manually annotated this expanded collection with 5-point absolute ratings across six dimensions: Novelty, Clarity, Relevance, Intelligence, Empathy, and Overall Funniness. Using this dataset, we assessed the capabilities of state-of-the-art LLMs on two core tasks: their ability to generate creative Oogiri responses and their ability to evaluate the funniness of responses using a six-dimensional evaluation. Our results show that while LLMs can generate responses at a level between low- and mid-tier human performance, they exhibit a notable lack of Empathy. This deficit in Empathy helps explain their failure to replicate human humor assessment. Correlation analyses of human and model evaluation data further reveal a fundamental divergence in evaluation criteria: LLMs prioritize Novelty, whereas humans prioritize Empathy. We release our annotated corpus to the community to pave the way for the development of more emotionally intelligent and sophisticated conversational agents.

---

### PIFF: A Physics-Informed Generative Flow Model for Real-Time Flood Depth Mapping

Authors: ChunLiang Wu, Tsunhua Yang, Hungying Chen
Published: 2025-11-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.09130v1

Flood mapping is crucial for assessing and mitigating flood impacts, yet traditional methods like numerical modeling and aerial photography face limitations in efficiency and reliability. To address these challenges, we propose PIFF, a physics-informed, flow-based generative neural network for near real-time flood depth estimation. Built on an image-to-image generative framework, it efficiently maps Digital Elevation Models (DEM) to flood depth predictions. The model is conditioned on a simplified inundation model (SPM) that embeds hydrodynamic priors into the training process. Additionally, a transformer-based rainfall encoder captures temporal dependencies in precipitation. Integrating physics-informed constraints with data-driven learning, PIFF captures the causal relationships between rainfall, topography, SPM, and flooding, replacing costly simulations with accurate, real-time flood maps. Using a 26 km study area in Tainan, Taiwan, with 182 rainfall scenarios ranging from 24 mm to 720 mm over 24 hours, our results demonstrate that PIFF offers an effective, data-driven alternative for flood prediction and response.

---

### History-Aware Reasoning for GUI Agents

Authors: Ziwei Wang, Leyang Yang, Xiaoxuan Tang, Sheng Zhou, Dajun Chen, Wei Jiang, Yong Li
Published: 2025-11-12
Categories: cs.AI, cs.CL, cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2511.09127v1

Advances in Multimodal Large Language Models have significantly enhanced Graphical User Interface (GUI) automation. Equipping GUI agents with reliable episodic reasoning capabilities is essential for bridging the gap between users' concise task descriptions and the complexities of real-world execution. Current methods integrate Reinforcement Learning (RL) with System-2 Chain-of-Thought, yielding notable gains in reasoning enhancement. For long-horizon GUI tasks, historical interactions connect each screen to the goal-oriented episode chain, and effectively leveraging these clues is crucial for the current decision. However, existing native GUI agents exhibit weak short-term memory in their explicit reasoning, interpreting the chained interactions as discrete screen understanding, i.e., unawareness of the historical interactions within the episode. This history-agnostic reasoning challenges their performance in GUI automation. To alleviate this weakness, we propose a History-Aware Reasoning (HAR) framework, which encourages an agent to reflect on its own errors and acquire episodic reasoning knowledge from them via tailored strategies that enhance short-term memory in long-horizon interaction. The framework mainly comprises constructing a reflective learning scenario, synthesizing tailored correction guidelines, and designing a hybrid RL reward function. Using the HAR framework, we develop a native end-to-end model, HAR-GUI-3B, which alters the inherent reasoning mode from history-agnostic to history-aware, equipping the GUI agent with stable short-term memory and reliable perception of screen details. Comprehensive evaluations across a range of GUI-related benchmarks demonstrate the effectiveness and generalization of our method.

---

### Vendor-Aware Industrial Agents: RAG-Enhanced LLMs for Secure On-Premise PLC Code Generation

Authors: Joschka Kersting, Michael Rummel, Gesa Benndorf
Published: 2025-11-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.09122v2

Programmable Logic Controllers are operated by proprietary code dialects; this makes it challenging to train coding assistants. Current LLMs are trained on large code datasets and are capable of writing IEC 61131-3 compatible code out of the box, but they neither know specific function blocks, nor related project code. Moreover, companies like Mitsubishi Electric and their customers do not trust cloud providers. Hence, an own coding agent is the desired solution to cope with this. In this study, we present our work on a low-data domain coding assistant solution for industrial use. We show how we achieved high quality code generation without fine-tuning large models and by fine-tuning small local models for edge device usage. Our tool lets several AI models compete with each other, uses reasoning, corrects bugs automatically and checks code validity by compiling it directly in the chat interface. We support our approach with an extensive evaluation that comes with code compilation statistics and user ratings. We found that a Retrieval-Augmented Generation (RAG) supported coding assistant can work in low-data domains by using extensive prompt engineering and directed retrieval.

---

### Differentially Private Rankings via Outranking Methods and Performance Data Aggregation

Authors: Luis Del Vasto-Terrientes
Published: 2025-11-12
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.09120v1

Multiple-Criteria Decision Making (MCDM) is a sub-discipline of Operations Research that helps decision-makers in choosing, ranking, or sorting alternatives based on conflicting criteria. Over time, its application has been expanded into dynamic and data-driven domains, such as recommender systems. In these contexts, the availability and handling of personal and sensitive data can play a critical role in the decision-making process. Despite this increased reliance on sensitive data, the integration of privacy mechanisms with MCDM methods is underdeveloped. This paper introduces an integrated approach that combines MCDM outranking methods with Differential Privacy (DP), safeguarding individual contributions' privacy in ranking problems. This approach relies on a pre-processing step to aggregate multiple user evaluations into a comprehensive performance matrix. The evaluation results show a strong to very strong statistical correlation between the true rankings and their anonymized counterparts, ensuring robust privacy parameter guarantees.

---

### Learning to Validate Generative Models: a Goodness-of-Fit Approach

Authors: Pietro Cappelli, Gaia Grosso, Marco Letizia, Humberto Reyes-González, Marco Zanetti
Published: 2025-11-12
Categories: stat.ML, cs.LG, hep-ex, hep-ph
arXiv: https://arxiv.org/abs/2511.09118v2

Generative models are increasingly central to scientific workflows, yet their systematic use and interpretation require a proper understanding of their limitations through rigorous validation. Classic approaches struggle with scalability, statistical power, or interpretability when applied to high-dimensional data, making it difficult to certify the reliability of these models in realistic, high-dimensional scientific settings. Here, we propose the use of the New Physics Learning Machine (NPLM), a learning-based approach to goodness-of-fit testing inspired by the Neyman--Pearson construction, to test generative networks trained on high-dimensional scientific data. We demonstrate the performance of NPLM for validation in two benchmark cases: generative models trained on mixtures of Gaussian models with increasing dimensionality, and a public end-to-end model, known as FlowSim, developed to generate high-energy physics collision events. We demonstrate that the NPLM can serve as a powerful validation method while also providing a means to diagnose sub-optimally modeled regions of the data.

---

### Learning to Validate Generative Models: a Goodness-of-Fit Approach

Authors: Pietro Cappelli, Gaia Grosso, Marco Letizia, Humberto Reyes-González, Marco Zanetti
Published: 2025-11-12
Categories: stat.ML, cs.LG, hep-ex, hep-ph
arXiv: https://arxiv.org/abs/2511.09118v1

Generative models are increasingly central to scientific workflows, yet their systematic use and interpretation require a proper understanding of their limitations through rigorous validation. Classic approaches struggle with scalability, statistical power, or interpretability when applied to high-dimensional data, making it difficult to certify the reliability of these models in realistic, high-dimensional scientific settings. Here, we propose the use of the New Physics Learning Machine (NPLM), a learning based approach to goodness-of-fit testing inspired by the Neyman-Pearson construction, to test generative networks trained on high-dimensional scientific data. We demonstrate the performance of NPLM for validation in two benchmark cases: generative models trained on mixtures of Gaussian models with increasing dimensionality, and a public end-to-end generator for the Large Hadron Collider called FlashSim, trained on jet data, typical in the field of high-energy physics. We demonstrate that the NPLM can serve as a powerful validation method while also providing a means to diagnose sub-optimally modeled regions of the data.

---

### DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization

Authors: Rui-Yang Ju, Kohei Yamashita, Hirotaka Kameko, Shinsuke Mori
Published: 2025-11-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.09117v4

Kuzushiji, a pre-modern Japanese cursive script, can currently be read and understood by only a few thousand trained experts in Japan. With the rapid development of deep learning, researchers have begun applying Optical Character Recognition (OCR) techniques to transcribe Kuzushiji into modern Japanese. Although existing OCR methods perform well on clean pre-modern Japanese documents written in Kuzushiji, they often fail to consider various types of noise, such as document degradation and seals, which significantly affect recognition accuracy. To the best of our knowledge, no existing dataset specifically addresses these challenges. To address this gap, we introduce the Degraded Kuzushiji Documents with Seals (DKDS) dataset as a new benchmark for related tasks. We describe the dataset construction process, which involves the assistance of a trained Kuzushiji expert, and define two benchmark tracks: (1) Kuzushiji character and seal detection and (2) document binarization. For the Kuzushiji character and seal detection track, we provide baseline results using several recent versions of YOLO to detect Kuzushiji characters and seals. For the document binarization track, we present baseline results from traditional binarization algorithms, traditional algorithms combined with K-means clustering, two state-of-the-art (SOTA) generative adversarial network (GAN) methods, and our improved conditional GAN (cGAN)-based method. The DKDS dataset and the implementation code for baseline methods are available at https://ruiyangju.github.io/DKDS.

---

### Towards a Generalisable Cyber Defence Agent for Real-World Computer Networks

Authors: Tim Dudman, Martyn Bull
Published: 2025-11-12
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2511.09114v2

Recent advances in deep reinforcement learning for autonomous cyber defence have resulted in agents that can successfully defend simulated computer networks against cyber-attacks. However, many of these agents would need retraining to defend networks with differing topology or size, making them poorly suited to real-world networks where topology and size can vary over time. In this research we introduce a novel set of Topological Extensions for Reinforcement Learning Agents (TERLA) that provide generalisability for the defence of networks with differing topology and size, without the need for retraining. Our approach involves the use of heterogeneous graph neural network layers to produce a fixed-size latent embedding representing the observed network state. This representation learning stage is coupled with a reduced, fixed-size, semantically meaningful and interpretable action space. We apply TERLA to a standard deep reinforcement learning Proximal Policy Optimisation (PPO) agent model, and to reduce the sim-to-real gap, conduct our research using Cyber Autonomy Gym for Experimentation (CAGE) Challenge 4. This Cyber Operations Research Gym environment has many of the features of a real-world network, such as realistic Intrusion Detection System (IDS) events and multiple agents defending network segments of differing topology and size. TERLA agents retain the defensive performance of vanilla PPO agents whilst showing improved action efficiency. Generalisability has been demonstrated by showing that all TERLA agents have the same network-agnostic neural network architecture, and by deploying a single TERLA agent multiple times to defend network segments with differing topology and size, showing improved defensive performance and efficiency.

---

### Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning

Authors: Wenda Wei, Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Lixin Su, Shuaiqiang Wang, Dawei Yin, Maarten de Rijke, Xueqi Cheng
Published: 2025-11-12
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2511.09109v3

Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step reasoning scenarios. Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval. Most approaches rely on outcome-based supervision, offering no explicit guidance for intermediate steps. This often leads to reward hacking and degraded response quality. We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions. To assess the information completeness of each step, we introduce a bidirectional information distance grounded in Kolmogorov complexity, approximated via language model generation probabilities. This quantification measures both how far the current reasoning is from the answer and how well it addresses the question. To optimize reasoning under these bidirectional signals, we adopt a multi-objective reinforcement learning framework with a cascading reward structure that emphasizes early trajectory alignment. Empirical results on seven question answering benchmarks demonstrate that Bi-RAR surpasses previous methods and enables efficient interaction and reasoning with the search engine during training and inference.

---

### Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning

Authors: Wenda Wei, Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Lixin Su, Shuaiqiang Wang, Dawei Yin, Maarten de Rijke, Xueqi Cheng
Published: 2025-11-12
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2511.09109v1

Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step reasoning scenarios.Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval. Most approaches rely on outcome-based supervision, offering no explicit guidance for intermediate steps. This often leads to reward hacking and degraded response quality. We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions. To assess the information completeness of each step, we introduce a bidirectional information distance grounded in Kolmogorov complexity, approximated via language model generation probabilities. This quantification measures both how far the current reasoning is from the answer and how well it addresses the question. To optimize reasoning under these bidirectional signals, we adopt a multi-objective reinforcement learning framework with a cascading reward structure that emphasizes early trajectory alignment. Empirical results on seven question answering benchmarks demonstrate that Bi-RAR surpasses previous methods and enables efficient interaction and reasoning with the search engine during training and inference.

---