# Research Papers — 2025-11 · bundle page 109 of 197

> Full-text markdown of papers #5401–5450 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/109
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/108.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/110.md)

### On the Trade-Off Between Transparency and Security in Adversarial Machine Learning

Authors: Lucas Fenaux, Christopher Srinivasa, Florian Kerschbaum
Published: 2025-11-14
Categories: cs.LG, cs.CR, cs.GT
arXiv: https://arxiv.org/abs/2511.11842v1

Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of transparency for agents through the lens of transferable adversarial example attacks. In transferable adversarial example attacks, attackers maliciously perturb their inputs using surrogate models to fool a defender's target model. These models can be defended or undefended, with both players having to decide which to use. Using a large-scale empirical evaluation of nine attacks across 181 models, we find that attackers are more successful when they match the defender's decision; hence, obscurity could be beneficial to the defender. With game theory, we analyze this trade-off between transparency and security by modeling this problem as both a Nash game and a Stackelberg game, and comparing the expected outcomes. Our analysis confirms that only knowing whether a defender's model is defended or not can sometimes be enough to damage its security. This result serves as an indicator of the general trade-off between transparency and security, suggesting that transparency in AI systems can be at odds with security. Beyond adversarial machine learning, our work illustrates how game-theoretic reasoning can uncover conflicts between transparency and security.

---

### MP-GFormer: A 3D-Geometry-Aware Dynamic Graph Transformer Approach for Machining Process Planning

Authors: Fatemeh Elhambakhsh, Gaurav Ameta, Aditi Roy, Hyunwoong Ko
Published: 2025-11-14
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.11837v1

Machining process planning (MP) is inherently complex due to structural and geometrical dependencies among part features and machining operations. A key challenge lies in capturing dynamic interdependencies that evolve with distinct part geometries as operations are performed. Machine learning has been applied to address challenges in MP, such as operation selection and machining sequence prediction. Dynamic graph learning (DGL) has been widely used to model dynamic systems, thanks to its ability to integrate spatio-temporal relationships. However, in MP, while existing DGL approaches can capture these dependencies, they fail to incorporate three-dimensional (3D) geometric information of parts and thus lack domain awareness in predicting machining operation sequences. To address this limitation, we propose MP-GFormer, a 3D-geometry-aware dynamic graph transformer that integrates evolving 3D geometric representations into DGL through an attention mechanism to predict machining operation sequences. Our approach leverages StereoLithography surface meshes representing the 3D geometry of a part after each machining operation, with the boundary representation method used for the initial 3D designs. We evaluate MP-GFormer on a synthesized dataset and demonstrate that the method achieves improvements of 24\% and 36\% in accuracy for main and sub-operation predictions, respectively, compared to state-of-the-art approaches.

---

### Securing Generative AI in Healthcare: A Zero-Trust Architecture Powered by Confidential Computing on Google Cloud

Authors: Adaobi Amanna, Ishana Shinde
Published: 2025-11-14
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.11836v1

The integration of Generative Artificial Intelligence (GenAI) in healthcare is impeded by significant security challenges unaddressed by traditional frameworks, precisely the data-in-use gap where sensitive patient data and proprietary AI models are exposed during active processing. To address this, the paper proposes the Confidential Zero-Trust Framework (CZF), a novel security paradigm that synergistically combines Zero-Trust Architecture for granular access control with the hardware-enforced data isolation of Confidential Computing. We detailed a multi-tiered architectural blueprint for implementing the CZF on Google Cloud and analyzed its efficacy against real-world threats. The CZF provides a defense-in-depth architecture where data remains encrypted while in-use within a hardware-based Trusted Execution Environment (TEE). The framework's use of remote attestation offers cryptographic proof of workload integrity, transforming compliance from a procedural exercise into a verifiable technical fact and enabling secure, multi-party collaborations previously blocked by security and intellectual property concerns. By closing the data-in-use gap and enforcing Zero-Trust principles, the CZF provides a robust and verifiable framework that establishes the necessary foundation of trust to enable the responsible adoption of transformative AI technologies in healthcare.

---

### Volatility in Certainty (VC): A Metric for Detecting Adversarial Perturbations During Inference in Neural Network Classifiers

Authors: Vahid Hemmati, Ahmad Mohammadi, Abdul-Rauf Nuhu, Reza Ahmari, Parham Kebria, Abdollah Homaifar
Published: 2025-11-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11834v1

Adversarial robustness remains a critical challenge in deploying neural network classifiers, particularly in real-time systems where ground-truth labels are unavailable during inference. This paper investigates \textit{Volatility in Certainty} (VC), a recently proposed, label-free metric that quantifies irregularities in model confidence by measuring the dispersion of sorted softmax outputs. Specifically, VC is defined as the average squared log-ratio of adjacent certainty values, capturing local fluctuations in model output smoothness. We evaluate VC as a proxy for classification accuracy and as an indicator of adversarial drift. Experiments are conducted on artificial neural networks (ANNs) and convolutional neural networks (CNNs) trained on MNIST, as well as a regularized VGG-like model trained on CIFAR-10. Adversarial examples are generated using the Fast Gradient Sign Method (FGSM) across varying perturbation magnitudes. In addition, mixed test sets are created by gradually introducing adversarial contamination to assess VC's sensitivity under incremental distribution shifts. Our results reveal a strong negative correlation between classification accuracy and log(VC) (correlation rho < -0.90 in most cases), suggesting that VC effectively reflects performance degradation without requiring labeled data. These findings position VC as a scalable, architecture-agnostic, and real-time performance metric suitable for early-warning systems in safety-critical applications.

---

### TopoPerception: A Shortcut-Free Evaluation of Global Visual Perception in Large Vision-Language Models

Authors: Wenhao Zhou, Hao Zheng, Rong Zhao
Published: 2025-11-14
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.11831v1

Large Vision-Language Models (LVLMs) typically align visual features from an encoder with a pre-trained Large Language Model (LLM). However, this makes the visual perception module a bottleneck, which constrains the overall capabilities of LVLMs. Conventional evaluation benchmarks, while rich in visual semantics, often contain unavoidable local shortcuts that can lead to an overestimation of models' perceptual abilities. Here, we introduce TopoPerception, a benchmark that leverages topological properties to rigorously evaluate the global visual perception capabilities of LVLMs across various granularities. Since topology depends on the global structure of an image and is invariant to local features, TopoPerception enables a shortcut-free assessment of global perception, fundamentally distinguishing it from semantically rich tasks. We evaluate state-of-the-art models on TopoPerception and find that even at the coarsest perceptual granularity, all models perform no better than random chance, indicating a profound inability to perceive global visual features. Notably, a consistent trend emerge within model families: more powerful models with stronger reasoning capabilities exhibit lower accuracy. This suggests that merely scaling up models is insufficient to address this deficit and may even exacerbate it. Progress may require new training paradigms or architectures. TopoPerception not only exposes a critical bottleneck in current LVLMs but also offers a lens and direction for improving their global visual perception. The data and code are publicly available at: https://github.com/Wenhao-Zhou/TopoPerception.

---

### A Computational Method for Solving the Stochastic Joint Replenishment Problem in High Dimensions

Authors: Barış Ata, Wouter van Eekelen, Yuan Zhong
Published: 2025-11-14
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2511.11830v2

We consider a discrete-time formulation for a class of high-dimensional stochastic joint replenishment problems. First, we approximate the problem by a continuous-time impulse control problem. Exploiting connections among the impulse control problem, backward stochastic differential equations (BSDEs) with jumps, and the stochastic target problem, we develop a novel, simulation-based computational method that relies on deep neural networks to solve the impulse control problem. Based on that solution, we propose an implementable inventory control policy for the original (discrete-time) stochastic joint replenishment problem, and test it against the best available benchmarks in a series of test problems. For the problems studied thus far, our method matches or beats the best benchmark we could find, and it is computationally feasible up to at least 50 dimensions -- that is, 50 stock-keeping units (SKUs).

---

### Towards Autoformalization of LLM-generated Outputs for Requirement Verification

Authors: Mihir Gupte, Ramesh S
Published: 2025-11-14
Categories: cs.CL, cs.AI, cs.FL, cs.LO
arXiv: https://arxiv.org/abs/2511.11829v1

Autoformalization, the process of translating informal statements into formal logic, has gained renewed interest with the emergence of powerful Large Language Models (LLMs). While LLMs show promise in generating structured outputs from natural language (NL), such as Gherkin Scenarios from NL feature requirements, there's currently no formal method to verify if these outputs are accurate. This paper takes a preliminary step toward addressing this gap by exploring the use of a simple LLM-based autoformalizer to verify LLM-generated outputs against a small set of natural language requirements. We conducted two distinct experiments. In the first one, the autoformalizer successfully identified that two differently-worded NL requirements were logically equivalent, demonstrating the pipeline's potential for consistency checks. In the second, the autoformalizer was used to identify a logical inconsistency between a given NL requirement and an LLM-generated output, highlighting its utility as a formal verification tool. Our findings, while limited, suggest that autoformalization holds significant potential for ensuring the fidelity and logical consistency of LLM-generated outputs, laying a crucial foundation for future, more extensive studies into this novel application.

---

### Conformal Constrained Policy Optimization for Cost-Effective LLM Agents

Authors: Wenwen Si, Sooyong Jang, Insup Lee, Osbert Bastani
Published: 2025-11-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11828v2

While large language models (LLMs) have recently made tremendous progress towards solving challenging AI problems, they have done so at increasingly steep computational and API costs. We propose a novel strategy where we combine multiple LLM models with varying cost/accuracy tradeoffs in an agentic manner, where models and tools are run in sequence as determined by an orchestration model to minimize cost subject to a user-specified level of reliability; this constraint is formalized using conformal prediction to provide guarantees. To solve this problem, we propose Conformal Constrained Policy Optimization (CCPO), a training paradigm that integrates constrained policy optimization with off-policy reinforcement learning and recent advances in online conformal prediction. CCPO jointly optimizes a cost-aware policy (score function) and an adaptive threshold. Across two multi-hop question answering benchmarks, CCPO achieves up to a 30% cost reduction compared to other cost-aware baselines and LLM-guided methods without compromising reliability. Our approach provides a principled and practical framework for deploying LLM agents that are significantly more cost-effective while maintaining reliability.

---

### Real-Time Speech Enhancement via a Hybrid ViT: A Dual-Input Acoustic-Image Feature Fusion

Authors: Behnaz Bahmei, Siamak Arzanpour, Elina Birmingham
Published: 2025-11-14
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2511.11825v1

Speech quality and intelligibility are significantly degraded in noisy environments. This paper presents a novel transformer-based learning framework to address the single-channel noise suppression problem for real-time applications. Although existing deep learning networks have shown remarkable improvements in handling stationary noise, their performance often diminishes in real-world environments characterized by non-stationary noise (e.g., dog barking, baby crying). The proposed dual-input acoustic-image feature fusion using a hybrid ViT framework effectively models both temporal and spectral dependencies in noisy signals. Designed for real-world audio environments, the proposed framework is computationally lightweight and suitable for implementation on embedded devices. To evaluate its effectiveness, four standard and commonly used quality measurements, namely PESQ, STOI, Seg SNR, and LLR, are utilized. Experimental results obtained using the Librispeech dataset as the clean speech source and the UrbanSound8K and Google Audioset datasets as the noise sources, demonstrate that the proposed method significantly improves noise reduction, speech intelligibility, and perceptual quality compared to the noisy input signal, achieving performance close to the clean reference.

---

### SOTFormer: A Minimal Transformer for Unified Object Tracking and Trajectory Prediction

Authors: Zhongping Dong, Pengyang Yu, Shuangjian Li, Liming Chen, Mohand Tahar Kechadi
Published: 2025-11-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.11824v1

Accurate single-object tracking and short-term motion forecasting remain challenging under occlusion, scale variation, and temporal drift, which disrupt the temporal coherence required for real-time perception. We introduce \textbf{SOTFormer}, a minimal constant-memory temporal transformer that unifies object detection, tracking, and short-horizon trajectory prediction within a single end-to-end framework. Unlike prior models with recurrent or stacked temporal encoders, SOTFormer achieves stable identity propagation through a ground-truth-primed memory and a burn-in anchor loss that explicitly stabilizes initialization. A single lightweight temporal-attention layer refines embeddings across frames, enabling real-time inference with fixed GPU memory. On the Mini-LaSOT (20%) benchmark, SOTFormer attains 76.3 AUC and 53.7 FPS (AMP, 4.3 GB VRAM), outperforming transformer baselines such as TrackFormer and MOTRv2 under fast motion, scale change, and occlusion.

---

### Scaling Open-Weight Large Language Models for Hydropower Regulatory Information Extraction: A Systematic Analysis

Authors: Hong-Jun Yoon, Faisal Ashraf, Thomas A. Ruggles, Debjani Singh
Published: 2025-11-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.11821v1

Information extraction from regulatory documents using large language models presents critical trade-offs between performance and computational resources. We evaluated seven open-weight models (0.6B-70B parameters) on hydropower licensing documentation to provide empirical deployment guidance. Our analysis identified a pronounced 14B parameter threshold where validation methods transition from ineffective (F1 $<$ 0.15) to viable (F1 = 0.64). Consumer-deployable models achieve 64\% F1 through appropriate validation, while smaller models plateau at 51\%. Large-scale models approach 77\% F1 but require enterprise infrastructure. We identified systematic hallucination patterns where perfect recall indicates extraction failure rather than success in smaller models. Our findings establish the first comprehensive resource-performance mapping for open-weight information extraction in regulatory contexts, enabling evidence-based model selection. These results provide immediate value for hydropower compliance while contributing insights into parameter scaling effects that generalize across information extraction tasks.

---

### Simplicial covering dimension of extremal concept classes

Authors: Ari Blondal, Hamed Hatami, Pooya Hatami, Chavdar Lalov, Sivan Tretiak
Published: 2025-11-14
Categories: cs.LG, math.AT
arXiv: https://arxiv.org/abs/2511.11819v1

Dimension theory is a branch of topology concerned with defining and analyzing dimensions of geometric and topological spaces in purely topological terms. In this work, we adapt the classical notion of topological dimension (Lebesgue covering) to binary concept classes. The topological space naturally associated with a concept class is its space of realizable distributions. The loss function and the class itself induce a simplicial structure on this space, with respect to which we define a simplicial covering dimension. We prove that for finite concept classes, this simplicial covering dimension exactly characterizes the list replicability number (equivalently, global stability) in PAC learning. This connection allows us to apply tools from classical dimension theory to compute the exact list replicability number of the broad family of extremal concept classes.

---

### FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition

Authors: Zhongde An, Jinhong You, Jiyanglin Li, Yiming Tang, Wen Li, Heming Du, Shouguo Du
Published: 2025-11-14
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.11817v2

Time series forecasting is essential in a wide range of real world applications. Recently, frequency-domain methods have attracted increasing interest for their ability to capture global dependencies. However, when applied to non-stationary time series, these methods encounter the $\textit{spectral entanglement}$ and the computational burden of complex-valued learning. The $\textit{spectral entanglement}$ refers to the overlap of trends, periodicities, and noise across the spectrum due to $\textit{spectral leakage}$ and the presence of non-stationarity. However, existing decompositions are not suited to resolving spectral entanglement. To address this, we propose the Frequency Decomposition Network (FreDN), which introduces a learnable Frequency Disentangler module to separate trend and periodic components directly in the frequency domain. Furthermore, we propose a theoretically supported ReIm Block to reduce the complexity of complex-valued operations while maintaining performance. We also re-examine the frequency-domain loss function and provide new theoretical insights into its effectiveness. Extensive experiments on seven long-term forecasting benchmarks demonstrate that FreDN outperforms state-of-the-art methods by up to 10\%. Furthermore, compared with standard complex-valued architectures, our real-imaginary shared-parameter design reduces the parameter count and computational cost by at least 50\%.

---

### Do LLMs Really Struggle at NL-FOL Translation? Revealing their Strengths via a Novel Benchmarking Strategy

Authors: Andrea Brunello, Luca Geatti, Michele Mignani, Angelo Montanari, Nicola Saccomanno
Published: 2025-11-14
Categories: cs.AI, cs.CL, cs.LO
arXiv: https://arxiv.org/abs/2511.11816v1

Due to its expressiveness and unambiguous nature, First-Order Logic (FOL) is a powerful formalism for representing concepts expressed in natural language (NL). This is useful, e.g., for specifying and verifying desired system properties. While translating FOL into human-readable English is relatively straightforward, the inverse problem, converting NL to FOL (NL-FOL translation), has remained a longstanding challenge, for both humans and machines. Although the emergence of Large Language Models (LLMs) promised a breakthrough, recent literature provides contrasting results on their ability to perform NL-FOL translation. In this work, we provide a threefold contribution. First, we critically examine existing datasets and protocols for evaluating NL-FOL translation performance, revealing key limitations that may cause a misrepresentation of LLMs' actual capabilities. Second, to overcome these shortcomings, we propose a novel evaluation protocol explicitly designed to distinguish genuine semantic-level logical understanding from superficial pattern recognition, memorization, and dataset contamination. Third, using this new approach, we show that state-of-the-art, dialogue-oriented LLMs demonstrate strong NL-FOL translation skills and a genuine grasp of sentence-level logic, whereas embedding-centric models perform markedly worse.

---

### On the Notion that Language Models Reason

Authors: Bertram Højer
Published: 2025-11-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.11810v1

Language models (LMs) are said to be exhibiting reasoning, but what does this entail? We assess definitions of reasoning and how key papers in the field of natural language processing (NLP) use the notion and argue that the definitions provided are not consistent with how LMs are trained, process information, and generate new tokens. To illustrate this incommensurability we assume the view that transformer-based LMs implement an \textit{implicit} finite-order Markov kernel mapping contexts to conditional token distributions. In this view, reasoning-like outputs correspond to statistical regularities and approximate statistical invariances in the learned kernel rather than the implementation of explicit logical mechanisms. This view is illustrative of the claim that LMs are "statistical pattern matchers"" and not genuine reasoners and provides a perspective that clarifies why reasoning-like outputs arise in LMs without any guarantees of logical consistency. This distinction is fundamental to how epistemic uncertainty is evaluated in LMs. We invite a discussion on the importance of how the computational processes of the systems we build and analyze in NLP research are described.

---

### MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

Authors: MiroMind Team, Song Bai, Lidong Bing, Carson Chen, Guanzheng Chen, Yuntao Chen, Zhe Chen, Ziyi Chen, Jifeng Dai, Xuan Dong, Wenhan Dou, Yue Deng et al.
Published: 2025-11-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.11793v3

We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or context length, MiroThinker explores interaction scaling at the model level, systematically training the model to handle deeper and more frequent agent-environment interactions as a third dimension of performance improvement. Unlike LLM test-time scaling, which operates in isolation and risks degradation with longer reasoning chains, interactive scaling leverages environment feedback and external information acquisition to correct errors and refine trajectories. Through reinforcement learning, the model achieves efficient interaction scaling: with a 256K context window, it can perform up to 600 tool calls per task, enabling sustained multi-turn reasoning and complex real-world research workflows. Across four representative benchmarks-GAIA, HLE, BrowseComp, and BrowseComp-ZH-the 72B variant achieves up to 81.9%, 37.7%, 47.1%, and 55.6% accuracy respectively, surpassing previous open-source agents and approaching commercial counterparts such as GPT-5-high. Our analysis reveals that MiroThinker benefits from interactive scaling consistently: research performance improves predictably as the model engages in deeper and more frequent agent-environment interactions, demonstrating that interaction depth exhibits scaling behaviors analogous to model size and context length. These findings establish interaction scaling as a third critical dimension for building next-generation open research agents, complementing model capacity and context windows.

---

### Differences in the Moral Foundations of Large Language Models

Authors: Peter Kirgis
Published: 2025-11-14
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2511.11790v1

Large language models are increasingly being used in critical domains of politics, business, and education, but the nature of their normative ethical judgment remains opaque. Alignment research has, to date, not sufficiently utilized perspectives and insights from the field of moral psychology to inform training and evaluation of frontier models. I perform a synthetic experiment on a wide range of models from most major model providers using Jonathan Haidt's influential moral foundations theory (MFT) to elicit diverse value judgments from LLMs. Using multiple descriptive statistical approaches, I document the bias and variance of large language model responses relative to a human baseline in the original survey. My results suggest that models rely on different moral foundations from one another and from a nationally representative human baseline, and these differences increase as model capabilities increase. This work seeks to spur further analysis of LLMs using MFT, including finetuning of open-source models, and greater deliberation by policymakers on the importance of moral foundations for LLM alignment.

---

### From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions

Authors: Jiayi Li, Xiao Liu, Yansong Feng
Published: 2025-11-14
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2511.11789v1

Large Language Model (LLM)-based multi-agent systems are increasingly used to simulate human interactions and solve collaborative tasks. A common practice is to assign agents with personas to encourage behavioral diversity. However, this raises a critical yet underexplored question: do personas introduce biases into multi-agent interactions? This paper presents a systematic investigation into persona-induced biases in multi-agent interactions, with a focus on social traits like trustworthiness (how an agent's opinion is received by others) and insistence (how strongly an agent advocates for its opinion). Through a series of controlled experiments in collaborative problem-solving and persuasion tasks, we reveal that (1) LLM-based agents exhibit biases in both trustworthiness and insistence, with personas from historically advantaged groups (e.g., men and White individuals) perceived as less trustworthy and demonstrating less insistence; and (2) agents exhibit significant in-group favoritism, showing a higher tendency to conform to others who share the same persona. These biases persist across various LLMs, group sizes, and numbers of interaction rounds, highlighting an urgent need for awareness and mitigation to ensure the fairness and reliability of multi-agent systems.

---

### MALBO: Optimizing LLM-Based Multi-Agent Teams via Multi-Objective Bayesian Optimization

Authors: Antonio Sabbatella
Published: 2025-11-14
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2511.11788v1

The optimal assignment of Large Language Models (LLMs) to specialized roles in multi-agent systems is a significant challenge, defined by a vast combinatorial search space, expensive black-box evaluations, and an inherent trade-off between performance and cost. Current optimization methods focus on single-agent settings and lack a principled framework for this multi-agent, multi-objective problem. This thesis introduces MALBO (Multi-Agent LLM Bayesian Optimization), a systematic framework designed to automate the efficient composition of LLM-based agent teams. We formalize the assignment challenge as a multi-objective optimization problem, aiming to identify the Pareto front of configurations between task accuracy and inference cost. The methodology employs multi-objective Bayesian Optimization (MOBO) with independent Gaussian Process surrogate models. By searching over a continuous feature-space representation of the LLMs, this approach performs a sample-efficient exploration guided by the expected hypervolume improvement. The primary contribution is a principled and automated methodology that yields a Pareto front of optimal team configurations. Our results demonstrate that the Bayesian optimization phase, compared to an initial random search, maintained a comparable average performance while reducing the average configuration cost by over 45%. Furthermore, MALBO identified specialized, heterogeneous teams that achieve cost reductions of up to 65.8% compared to homogeneous baselines, all while maintaining maximum performance. The framework thus provides a data-driven tool for deploying cost-effective and highly specialized multi-agent AI systems.

---

### Towards Mitigating Systematics in Large-Scale Surveys via Few-Shot Optimal Transport-Based Feature Alignment

Authors: Sultan Hassan, Sambatra Andrianomena, Benjamin D. Wandelt
Published: 2025-11-14
Categories: astro-ph.IM, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.11787v1

Systematics contaminate observables, leading to distribution shifts relative to theoretically simulated signals-posing a major challenge for using pre-trained models to label such observables. Since systematics are often poorly understood and difficult to model, removing them directly and entirely may not be feasible. To address this challenge, we propose a novel method that aligns learned features between in-distribution (ID) and out-of-distribution (OOD) samples by optimizing a feature-alignment loss on the representations extracted from a pre-trained ID model. We first experimentally validate the method on the MNIST dataset using possible alignment losses, including mean squared error and optimal transport, and subsequently apply it to large-scale maps of neutral hydrogen. Our results show that optimal transport is particularly effective at aligning OOD features when parity between ID and OOD samples is unknown, even with limited data-mimicking real-world conditions in extracting information from large-scale surveys. Our code is available at https://github.com/sultan-hassan/feature-alignment-for-OOD-generalization.

---

### NegBLEURT Forest: Leveraging Inconsistencies for Detecting Jailbreak Attacks

Authors: Lama Sleem, Jerome Francois, Lujun Li, Nathan Foucher, Niccolo Gentile, Radu State
Published: 2025-11-14
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.11784v2

Jailbreak attacks designed to bypass safety mechanisms pose a serious threat by prompting LLMs to generate harmful or inappropriate content, despite alignment with ethical guidelines. Crafting universal filtering rules remains difficult due to their inherent dependence on specific contexts. To address these challenges without relying on threshold calibration or model fine-tuning, this work introduces a semantic consistency analysis between successful and unsuccessful responses, demonstrating that a negation-aware scoring approach captures meaningful patterns. Building on this insight, a novel detection framework called NegBLEURT Forest is proposed to evaluate the degree of alignment between outputs elicited by adversarial prompts and expected safe behaviors. It identifies anomalous responses using the Isolation Forest algorithm, enabling reliable jailbreak detection. Experimental results show that the proposed method consistently achieves top-tier performance, ranking first or second in accuracy across diverse models using the crafted dataset, while competing approaches exhibit notable sensitivity to model and data variations.

---

### Coordinate Descent for Network Linearization

Authors: Vlad Rakhlin, Amir Jevnisek, Shai Avidan
Published: 2025-11-14
Categories: cs.LG, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2511.11781v1

ReLU activations are the main bottleneck in Private Inference that is based on ResNet networks. This is because they incur significant inference latency. Reducing ReLU count is a discrete optimization problem, and there are two common ways to approach it. Most current state-of-the-art methods are based on a smooth approximation that jointly optimizes network accuracy and ReLU budget at once. However, the last hard thresholding step of the optimization usually introduces a large performance loss. We take an alternative approach that works directly in the discrete domain by leveraging Coordinate Descent as our optimization framework. In contrast to previous methods, this yields a sparse solution by design. We demonstrate, through extensive experiments, that our method is State of the Art on common benchmarks.

---

### CATCHFed: Efficient Unlabeled Data Utilization for Semi-Supervised Federated Learning in Limited Labels Environments

Authors: Byoungjun Park, Pedro Porto Buarque de Gusmão, Dongjin Ji, Minhoe Kim
Published: 2025-11-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.11778v2

Federated learning is a promising paradigm that utilizes distributed client resources while preserving data privacy. Most existing FL approaches assume clients possess labeled data, however, in real-world scenarios, client-side labels are often unavailable. Semi-supervised Federated learning, where only the server holds labeled data, addresses this issue. However, it experiences significant performance degradation as the number of labeled data decreases. To tackle this problem, we propose \textit{CATCHFed}, which introduces client-aware adaptive thresholds considering class difficulty, hybrid thresholds to enhance pseudo-label quality, and utilizes unpseudo-labeled data for consistency regularization. Extensive experiments across various datasets and configurations demonstrate that CATCHFed effectively leverages unlabeled client data, achieving superior performance even in extremely limited-label settings.

---

### Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy

Authors: Vinit Mehta, Charu Sharma, Karthick Thiyagarajan
Published: 2025-11-14
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2511.11777v2

With the rapid advancement of artificial intelligence and robotics, the integration of Large Language Models (LLMs) with 3D vision is emerging as a transformative approach to enhancing robotic sensing technologies. This convergence enables machines to perceive, reason and interact with complex environments through natural language and spatial understanding, bridging the gap between linguistic intelligence and spatial perception. This review provides a comprehensive analysis of state-of-the-art methodologies, applications and challenges at the intersection of LLMs and 3D vision, with a focus on next-generation robotic sensing technologies. We first introduce the foundational principles of LLMs and 3D data representations, followed by an in-depth examination of 3D sensing technologies critical for robotics. The review then explores key advancements in scene understanding, text-to-3D generation, object grounding and embodied agents, highlighting cutting-edge techniques such as zero-shot 3D segmentation, dynamic scene synthesis and language-guided manipulation. Furthermore, we discuss multimodal LLMs that integrate 3D data with touch, auditory and thermal inputs, enhancing environmental comprehension and robotic decision-making. To support future research, we catalog benchmark datasets and evaluation metrics tailored for 3D-language and vision tasks. Finally, we identify key challenges and future research directions, including adaptive model architectures, enhanced cross-modal alignment and real-time processing capabilities, which pave the way for more intelligent, context-aware and autonomous robotic sensing systems.

---

### On the Measure of a Model: From Intelligence to Generality

Authors: Ruchira Dhar, Ninell Oldenburg, Anders Soegaard
Published: 2025-11-14
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.11773v1

Benchmarks such as ARC, Raven-inspired tests, and the Blackbird Task are widely used to evaluate the intelligence of large language models (LLMs). Yet, the concept of intelligence remains elusive- lacking a stable definition and failing to predict performance on practical tasks such as question answering, summarization, or coding. Optimizing for such benchmarks risks misaligning evaluation with real-world utility. Our perspective is that evaluation should be grounded in generality rather than abstract notions of intelligence. We identify three assumptions that often underpin intelligence-focused evaluation: generality, stability, and realism. Through conceptual and formal analysis, we show that only generality withstands conceptual and empirical scrutiny. Intelligence is not what enables generality; generality is best understood as a multitask learning problem that directly links evaluation to measurable performance breadth and reliability. This perspective reframes how progress in AI should be assessed and proposes generality as a more stable foundation for evaluating capability across diverse and evolving tasks.

---

### Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents

Authors: Chenyu Zhang, Xiaohang Luo
Published: 2025-11-14
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2511.11772v2

Formative feedback is widely recognized as one of the most effective drivers of student learning, yet it remains difficult to implement equitably at scale. In large or low-resource courses, instructors often lack the time, staffing, and bandwidth required to review and respond to every student reflection, creating gaps in support precisely where learners would benefit most. This paper presents a theory-grounded system that uses five coordinated role-based LLM agents (Evaluator, Equity Monitor, Metacognitive Coach, Aggregator, and Reflexion Reviewer) to score learner reflections with a shared rubric and to generate short, bias-aware, learner-facing comments. The agents first produce structured rubric scores, then check for potentially biased or exclusionary language, add metacognitive prompts that invite students to think about their own thinking, and finally compose a concise feedback message of at most 120 words. The system includes simple fairness checks that compare scoring error across lower and higher scoring learners, enabling instructors to monitor and bound disparities in accuracy. We evaluate the pipeline in a 12-session AI literacy program with adult learners. In this setting, the system produces rubric scores that approach expert-level agreement, and trained graders rate the AI-generated comments as helpful, empathetic, and well aligned with instructional goals. Taken together, these results show that multi-agent LLM systems can deliver equitable, high-quality formative feedback at a scale and speed that would be impossible for human graders alone. More broadly, the work points toward a future where feedback-rich learning becomes feasible for any course size or context, advancing long-standing goals of equity, access, and instructional capacity in education.

---

### Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction

Authors: Floris Vossebeld, Shenghui Wang
Published: 2025-11-14
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.11770v1

Generating complex, logically-sound SPARQL queries for multi-hop questions remains a critical bottleneck for Knowledge Graph Question Answering, as the brittle nature of one-shot generation by Large Language Models (LLMs) hinders reliable interaction with structured data. Current methods lack the adaptive policies needed to dynamically debug queries based on real-time execution feedback. This paper introduces a novel agentic framework where an LLM learns a resilient policy for the sequential process of iterative SPARQL construction. We show that a compact 3B-parameter model, trained exclusively via outcome-driven Reinforcement Learning (GRPO) without supervised fine-tuning, can learn effective policies for this task, discovering how to systematically recover from execution errors and refine its queries toward a correct answer. On a curated, executable single-answer subset of LC-QuAD 2.0, our agent achieves 49.7\% accuracy post-entity-linking, a significant 17.5 percentage point improvement over the strongest iterative zero-shot baseline. Further analysis reveals that while the agent's capability is driven by RL, its performance is enhanced by an explicit deliberative reasoning step that acts as a cognitive scaffold to improve policy precision. This work presents a generalizable blueprint for teaching agents to master formal, symbolic tools through interaction, bridging the gap between probabilistic LLMs and the structured world of Knowledge Graphs.

---

### Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules

Authors: Xiangru Wang, Zekun Jiang, Heng Yang, Cheng Tan, Xingying Lan, Chunming Xu, Tianhang Zhou
Published: 2025-11-14
Categories: physics.chem-ph, cs.LG, q-bio.QM, stat.ME
arXiv: https://arxiv.org/abs/2511.11769v1

Molecular property prediction is fundamental to chemical engineering applications such as solvent screening. We present Socrates-Mol, a framework that transforms language models into empirical Bayesian reasoners through context engineering, addressing cold start problems without model fine-tuning. The system implements a reflective-prediction cycle where initial outputs serve as priors, retrieved molecular cases provide evidence, and refined predictions form posteriors, extracting reusable chemical rules from sparse data. We introduce ranking tasks aligned with industrial screening priorities and employ cross-model self-consistency across five language models to reduce variance. Experiments on amine solvent LogP prediction reveal task-dependent patterns: regression achieves 72% MAE reduction and 112% R-squared improvement through self-consistency, while ranking tasks show limited gains due to systematic multi-model biases. The framework reduces deployment costs by over 70% compared to full fine-tuning, providing a scalable solution for molecular property prediction while elucidating the task-adaptive nature of self-consistency mechanisms.

---

### Learning Fair Representations with Kolmogorov-Arnold Networks

Authors: Amisha Priyadarshini, Sergio Gago-Masague
Published: 2025-11-14
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2511.11767v4

Despite recent advances in fairness-aware machine learning, predictive models often exhibit discriminatory behavior towards marginalized groups. Such unfairness might arise from biased training data, model design, or representational disparities across groups, posing significant challenges in high-stakes decision-making domains such as college admissions. While existing fair learning models aim to mitigate bias, achieving an optimal trade-off between fairness and accuracy remains a challenge. Moreover, the reliance on black-box models hinders interpretability, limiting their applicability in socially sensitive domains. To circumvent these issues, we propose integrating Kolmogorov-Arnold Networks (KANs) within a fair adversarial learning framework. Leveraging the adversarial robustness and interpretability of KANs, our approach facilitates stable adversarial learning. We derive theoretical insights into the spline-based KAN architecture that ensure stability during adversarial optimization. Additionally, an adaptive fairness penalty update mechanism is proposed to strike a balance between fairness and accuracy. We back these findings with empirical evidence on two real-world admissions datasets, demonstrating the proposed framework's efficiency in achieving fairness across sensitive attributes while preserving predictive performance.

---

### Demystify, Use, Reflect: Preparing students to be informed LLM-users

Authors: Nikitha Donekal Chandrashekar, Sehrish Basir Nizamani, Margaret Ellis, Naren Ramakrishnan
Published: 2025-11-14
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2511.11764v1

We transitioned our post-CS1 course that introduces various subfields of computer science so that it integrates Large Language Models (LLMs) in a structured, critical, and practical manner. It aims to help students develop the skills needed to engage meaningfully and responsibly with AI. The course now includes explicit instruction on how LLMs work, exposure to current tools, ethical issues, and activities that encourage student reflection on personal use of LLMs as well as the larger evolving landscape of AI-assisted programming. In class, we demonstrate the use and verification of LLM outputs, guide students in the use of LLMs as an ingredient in a larger problem-solving loop, and require students to disclose and acknowledge the nature and extent of LLM assistance. Throughout the course, we discuss risks and benefits of LLMs across CS subfields. In our first iteration of the course, we collected and analyzed data from students pre and post surveys. Student understanding of how LLMs work became more technical, and their verification and use of LLMs shifted to be more discerning and collaborative. These strategies can be used in other courses to prepare students for the AI-integrated future.

---

### Sumudu Neural Operator for ODEs and PDEs

Authors: Ben Zelenskiy, Saibilila Abudukelimu, George Flint, Kevin Zhu, Sunishchal Dev
Published: 2025-11-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.11762v1

We introduce the Sumudu Neural Operator (SNO), a neural operator rooted in the properties of the Sumudu Transform. We leverage the relationship between the polynomial expansions of transform pairs to decompose the input space as coefficients, which are then transformed into the Sumudu Space, where the neural operator is parameterized. We evaluate the operator in ODEs (Duffing Oscillator, Lorenz System, and Driven Pendulum) and PDEs (Euler-Bernoulli Beam, Burger's Equation, Diffusion, Diffusion-Reaction, and Brusselator). SNO achieves superior performance to FNO on PDEs and demonstrates competitive accuracy with LNO on several PDE tasks, including the lowest error on the Euler-Bernoulli Beam and Diffusion Equation. Additionally, we apply zero-shot super-resolution to the PDE tasks to observe the model's capability of obtaining higher quality data from low-quality samples. These preliminary findings suggest promise for the Sumudu Transform as a neural operator design, particularly for certain classes of PDEs.

---

### Optimizing Mixture of Block Attention

Authors: Guangxuan Xiao, Junxian Guo, Kasra Mazaheri, Song Han
Published: 2025-11-14
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2511.11571v2

Mixture of Block Attention (MoBA) (Lu et al., 2025) is a promising building block for efficiently processing long contexts in LLMs by enabling queries to sparsely attend to a small subset of key-value blocks, drastically reducing computational cost. However, the design principles governing MoBA's performance are poorly understood, and it lacks an efficient GPU implementation, hindering its practical adoption. In this paper, we first develop a statistical model to analyze MoBA's underlying mechanics. Our model reveals that performance critically depends on the router's ability to accurately distinguish relevant from irrelevant blocks based on query-key affinities. We derive a signal-to-noise ratio that formally connects architectural parameters to this retrieval accuracy. Guided by our analysis, we identify two key pathways for improvement: using smaller block sizes and applying a short convolution on keys to cluster relevant signals, which enhances routing accuracy. While theoretically better, small block sizes are inefficient on GPUs. To bridge this gap, we introduce FlashMoBA, a hardware-aware CUDA kernel that enables efficient MoBA execution even with the small block sizes our theory recommends. We validate our insights by training LLMs from scratch, showing that our improved MoBA models match the performance of dense attention baselines. FlashMoBA achieves up to 14.7x speedup over FlashAttention-2 for small blocks, making our theoretically-grounded improvements practical. Code is available at: https://github.com/mit-han-lab/flash-moba.

---

### Private Frequency Estimation Via Residue Number Systems

Authors: Héber H. Arcolezi
Published: 2025-11-14
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.11569v2

We present \textsf{ModularSubsetSelection} (MSS), a new algorithm for locally differentially private (LDP) frequency estimation. Given a universe of size $k$ and $n$ users, our $\varepsilon$-LDP mechanism encodes each input via a Residue Number System (RNS) over $\ell$ pairwise-coprime moduli $m_0, \ldots, m_{\ell-1}$, and reports a randomly chosen index $j \in (\ell)$ along with the perturbed residue using the statistically optimal \textsf{SubsetSelection} (SS) (Wang et al. 2016). This design reduces the user communication cost from $Θ\bigl(ω\log_2(k/ω)\bigr)$ bits required by standard SS (with $ω\approx k/(e^\varepsilon+1)$) down to $\lceil \log_2 \ell \rceil + \lceil \log_2 m_j \rceil$ bits, where $m_j < k$. Server-side decoding runs in $Θ(n + r k \ell)$ time, where $r$ is the number of LSMR (Fong and Saunders 2011) iterations. In practice, with well-conditioned moduli (\textit{i.e.}, constant $r$ and $\ell = Θ(\log k)$), this becomes $Θ(n + k \log k)$. We prove that MSS achieves worst-case MSE within a constant factor of state-of-the-art protocols such as SS and \textsf{ProjectiveGeometryResponse} (PGR) (Feldman et al. 2022) while avoiding the algebraic prerequisites and dynamic-programming decoder required by PGR. Empirically, MSS matches the estimation accuracy of SS, PGR, and \textsf{RAPPOR} (Erlingsson, Pihur, and Korolova 2014) across realistic $(k, \varepsilon)$ settings, while offering faster decoding than PGR and shorter user messages than SS. Lastly, by sampling from multiple moduli and reporting only a single perturbed residue, MSS achieves the lowest reconstruction-attack success rate among all evaluated LDP protocols.

---

### Estimating Total Effects in Bipartite Experiments with Spillovers and Partial Eligibility

Authors: Albert Tan, Mohsen Bayati, James Nordlund, Roman Istomin
Published: 2025-11-14
Categories: stat.ME, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.11564v1

We study randomized experiments in bipartite systems where only a subset of treatment-side units are eligible for assignment while all units continue to interact, generating interference. We formalize eligibility-constrained bipartite experiments and define estimands aligned with full deployment: the Primary Total Treatment Effect (PTTE) on eligible units and the Secondary Total Treatment Effect (STTE) on ineligible units. Under randomization within the eligible set, we give identification conditions and develop interference-aware ensemble estimators that combine exposure mappings, generalized propensity scores, and flexible machine learning. We further introduce a projection that links treatment- and outcome-level estimands; this mapping is exact under a Linear Additive Edges condition and enables estimation on the (typically much smaller) treatment side with deterministic aggregation to outcomes. In simulations with known ground truth across realistic exposure regimes, the proposed estimators recover PTTE and STTE with low bias and variance and reduce the bias that could arise when interference is ignored. Two field experiments illustrate practical relevance: our method corrects the direction of expected interference bias for a pre-specified metric in both studies and reverses the sign and significance of the primary decision metric in one case.

---

### LARM: A Large Articulated-Object Reconstruction Model

Authors: Sylvia Yuan, Ruoxi Shi, Xinyue Wei, Xiaoshuai Zhang, Hao Su, Minghua Liu
Published: 2025-11-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.11563v1

Modeling 3D articulated objects with realistic geometry, textures, and kinematics is essential for a wide range of applications. However, existing optimization-based reconstruction methods often require dense multi-view inputs and expensive per-instance optimization, limiting their scalability. Recent feedforward approaches offer faster alternatives but frequently produce coarse geometry, lack texture reconstruction, and rely on brittle, complex multi-stage pipelines. We introduce LARM, a unified feedforward framework that reconstructs 3D articulated objects from sparse-view images by jointly recovering detailed geometry, realistic textures, and accurate joint structures. LARM extends LVSM a recent novel view synthesis (NVS) approach for static 3D objects into the articulated setting by jointly reasoning over camera pose and articulation variation using a transformer-based architecture, enabling scalable and accurate novel view synthesis. In addition, LARM generates auxiliary outputs such as depth maps and part masks to facilitate explicit 3D mesh extraction and joint estimation. Our pipeline eliminates the need for dense supervision and supports high-fidelity reconstruction across diverse object categories. Extensive experiments demonstrate that LARM outperforms state-of-the-art methods in both novel view and state synthesis as well as 3D articulated object reconstruction, generating high-quality meshes that closely adhere to the input images. project page: https://sylviayuan-sy.github.io/larm-site/

---

### PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning

Authors: Afra Feyza Akyürek, Advait Gosai, Chen Bo Calvin Zhang, Vipul Gupta, Jaehwan Jeong, Anisha Gunjal, Tahseen Rabbani, Maria Mazzone, David Randolph, Mohammad Mahmoudi Meymand, Gurshaan Chattha, Paula Rodriguez et al.
Published: 2025-11-14
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2511.11562v1

Frontier model progress is often measured by academic benchmarks, which offer a limited view of performance in real-world professional contexts. Existing evaluations often fail to assess open-ended, economically consequential tasks in high-stakes domains like Legal and Finance, where practical returns are paramount. To address this, we introduce Professional Reasoning Bench (PRBench), a realistic, open-ended, and difficult benchmark of real-world problems in Finance and Law. We open-source its 1,100 expert-authored tasks and 19,356 expert-curated criteria, making it, to our knowledge, the largest public, rubric-based benchmark for both legal and finance domains. We recruit 182 qualified professionals, holding JDs, CFAs, or 6+ years of experience, who contributed tasks inspired by their actual workflows. This process yields significant diversity, with tasks spanning 114 countries and 47 US jurisdictions. Our expert-curated rubrics are validated through a rigorous quality pipeline, including independent expert validation. Subsequent evaluation of 20 leading models reveals substantial room for improvement, with top scores of only 0.39 (Finance) and 0.37 (Legal) on our Hard subsets. We further catalog associated economic impacts of the prompts and analyze performance using human-annotated rubric categories. Our analysis shows that models with similar overall scores can diverge significantly on specific capabilities. Common failure modes include inaccurate judgments, a lack of process transparency and incomplete reasoning, highlighting critical gaps in their reliability for professional adoption.

---

### A Unified Convergence Analysis for Semi-Decentralized Learning: Sampled-to-Sampled vs. Sampled-to-All Communication

Authors: Angelo Rodio, Giovanni Neglia, Zheng Chen, Erik G. Larsson
Published: 2025-11-14
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2511.11560v2

In semi-decentralized federated learning, devices primarily rely on device-to-device communication but occasionally interact with a central server. Periodically, a sampled subset of devices uploads their local models to the server, which computes an aggregate model. The server can then either (i) share this aggregate model only with the sampled clients (sampled-to-sampled, S2S) or (ii) broadcast it to all clients (sampled-to-all, S2A). Despite their practical significance, a rigorous theoretical and empirical comparison of these two strategies remains absent. We address this gap by analyzing S2S and S2A within a unified convergence framework that accounts for key system parameters: sampling rate, server aggregation frequency, and network connectivity. Our results, both analytical and experimental, reveal distinct regimes where one strategy outperforms the other, depending primarily on the degree of data heterogeneity across devices. These insights lead to concrete design guidelines for practical semi-decentralized FL deployments.

---

### Human-AI collaborative autonomous synthesis with pulsed laser deposition for remote epitaxy

Authors: Asraful Haque, Daniel T. Yimam, Jawad Chowdhury, Ralph Bulanadi, Ivan Vlassiouk, John Lasseter, Sujoy Ghosh, Christopher M. Rouleau, Kai Xiao, Yongtao Liu, Eva Zarkadoula, Rama K. Vasudevan et al.
Published: 2025-11-14
Categories: cond-mat.mtrl-sci, cs.AI
arXiv: https://arxiv.org/abs/2511.11558v1

Autonomous laboratories typically rely on data-driven decision-making, occasionally with human-in-the-loop oversight to inject domain expertise. Fully leveraging AI agents, however, requires tightly coupled, collaborative workflows spanning hypothesis generation, experimental planning, execution, and interpretation. To address this, we develop and deploy a human-AI collaborative (HAIC) workflow that integrates large language models for hypothesis generation and analysis, with collaborative policy updates driving autonomous pulsed laser deposition (PLD) experiments for remote epitaxy of BaTiO$_3$/graphene. HAIC accelerated the hypothesis formation and experimental design and efficiently mapped the growth space to graphene-damage. In situ Raman spectroscopy reveals that chemistry drives degradation while the highest energy plume components seed defects, identifying a low-O$_2$ pressure low-temperature synthesis window that preserves graphene but is incompatible with optimal BaTiO$_3$ growth. Thus, we show a two-step Ar/O$_2$ deposition is required to exfoliate ferroelectric BaTiO$_3$ while maintaining a monolayer graphene interlayer. HAIC stages human insight with AI reasoning between autonomous batches to drive rapid scientific progress, providing an evolution to many existing human-in-the-loop autonomous workflows.

---

### Multistability of Self-Attention Dynamics in Transformers

Authors: Claudio Altafini
Published: 2025-11-14
Categories: cs.LG, eess.SY, math.DS
arXiv: https://arxiv.org/abs/2511.11553v1

In machine learning, a self-attention dynamics is a continuous-time multiagent-like model of the attention mechanisms of transformers. In this paper we show that such dynamics is related to a multiagent version of the Oja flow, a dynamical system that computes the principal eigenvector of a matrix corresponding for transformers to the value matrix. We classify the equilibria of the ``single-head'' self-attention system into four classes: consensus, bipartite consensus, clustering and polygonal equilibria. Multiple asymptotically stable equilibria from the first three classes often coexist in the self-attention dynamics. Interestingly, equilibria from the first two classes are always aligned with the eigenvectors of the value matrix, often but not exclusively with the principal eigenvector.

---

### DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding

Authors: Dawei Zhu, Rui Meng, Jiefeng Chen, Sujian Li, Tomas Pfister, Jinsung Yoon
Published: 2025-11-14
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2511.11552v1

Comprehending long visual documents, where information is distributed across extensive pages of text and visual elements, is a critical but challenging task for modern Vision-Language Models (VLMs). Existing approaches falter on a fundamental challenge: evidence localization. They struggle to retrieve relevant pages and overlook fine-grained details within visual elements, leading to limited performance and model hallucination. To address this, we propose DocLens, a tool-augmented multi-agent framework that effectively ``zooms in'' on evidence like a lens. It first navigates from the full document to specific visual elements on relevant pages, then employs a sampling-adjudication mechanism to generate a single, reliable answer. Paired with Gemini-2.5-Pro, DocLens achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts. The framework's superiority is particularly evident on vision-centric and unanswerable queries, demonstrating the power of its enhanced localization capabilities.

---

### Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping

Authors: Dena Mujtaba, Brian Hu, Anthony Hoogs, Arslan Basharat
Published: 2025-11-14
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.11551v3

The deployment of decision-making AI agents presents a critical challenge in maintaining alignment with human values or guidelines while operating in complex, dynamic environments. Agents trained solely to achieve their objectives may adopt harmful behavior, exposing a key trade-off between maximizing the reward function and maintaining alignment. For pre-trained agents, ensuring alignment is particularly challenging, as retraining can be a costly and slow process. This is further complicated by the diverse and potentially conflicting attributes representing the ethical values for alignment. To address these challenges, we propose a test-time alignment technique based on model-guided policy shaping. Our method allows precise control over individual behavioral attributes, generalizes across diverse reinforcement learning (RL) environments, and facilitates a principled trade-off between ethical alignment and reward maximization without requiring agent retraining. We evaluate our approach using the MACHIAVELLI benchmark, which comprises 134 text-based game environments and thousands of annotated scenarios involving ethical decisions. The RL agents are first trained to maximize the reward in their respective games. At test time, we apply policy shaping via scenario-action attribute classifiers to ensure decision alignment with ethical attributes. We compare our approach against prior training-time methods and general-purpose agents, as well as study several types of ethical violations and power-seeking behavior. Our results demonstrate that test-time policy shaping provides an effective and scalable solution for mitigating unethical behavior across diverse environments and alignment attributes.

---

### Generalizing Fair Clustering to Multiple Groups: Algorithms and Applications

Authors: Diptarka Chakraborty, Kushagra Chatterjee, Debarati Das, Tien-Long Nguyen
Published: 2025-11-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.11539v1

Clustering is a fundamental task in machine learning and data analysis, but it frequently fails to provide fair representation for various marginalized communities defined by multiple protected attributes -- a shortcoming often caused by biases in the training data. As a result, there is a growing need to enhance the fairness of clustering outcomes, ideally by making minimal modifications, possibly as a post-processing step after conventional clustering. Recently, Chakraborty et al. (COLT'25) initiated the study of \emph{closest fair clustering}, though in a restricted scenario where data points belong to only two groups. In practice, however, data points are typically characterized by many groups, reflecting diverse protected attributes such as age, ethnicity, gender, etc. In this work, we generalize the study of the \emph{closest fair clustering} problem to settings with an arbitrary number (more than two) of groups. We begin by showing that the problem is NP-hard even when all groups are of equal size -- a stark contrast with the two-group case, for which an exact algorithm exists. Next, we propose near-linear time approximation algorithms that efficiently handle arbitrary-sized multiple groups, thereby answering an open question posed by Chakraborty et al. (COLT'25). Leveraging our closest fair clustering algorithms, we further achieve improved approximation guarantees for the \emph{fair correlation clustering} problem, advancing the state-of-the-art results established by Ahmadian et al. (AISTATS'20) and Ahmadi et al. (2020). Additionally, we are the first to provide approximation algorithms for the \emph{fair consensus clustering} problem involving multiple (more than two) groups, thus addressing another open direction highlighted by Chakraborty et al. (COLT'25).

---

### Volumetric Ergodic Control

Authors: Jueun Kwon, Max M. Sun, Todd Murphey
Published: 2025-11-14
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2511.11533v3

Ergodic control synthesizes optimal coverage behaviors over spatial distributions for nonlinear systems. However, existing formulations model the robot as a non-volumetric point, whereas in practice a robot interacts with the environment through its body and sensors with physical volume. In this work, we introduce a new ergodic control formulation that optimizes spatial coverage using a volumetric state representation. Our method preserves the asymptotic coverage guarantees of ergodic control, adds minimal computational overhead for real-time control, and supports arbitrary sample-based volumetric models. We evaluate our method across search and manipulation tasks -- with multiple robot dynamics and end-effector geometries or sensor models -- and show that it improves coverage efficiency by more than a factor of two while maintaining a 100% task completion rate across all experiments, outperforming the standard ergodic control method. Finally, we demonstrate the effectiveness of our method on a robot arm performing mechanical erasing tasks. Project website: https://murpheylab.github.io/vec/

---

### Bridging Hidden States in Vision-Language Models

Authors: Benjamin Fein-Ashley, Jacob Fein-Ashley
Published: 2025-11-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.11526v1

Vision-Language Models (VLMs) are a new family of models that align image content with natural language. Existing approaches typically fuse either (a) early: by mixing tokens/features inside the encoders, or (b) late: by comparing pooled embeddings. Many methods also tie fusion to an autoregressive decoder. However, the hidden states of both modalities already carry rich, modality-specific structure (spatial layout in vision; syntax and semantics in text), so directly aligning these states is a natural way to match what the two modalities "think". We propose a lightweight fusion module: a few cross-only, bidirectional attention layers placed near the top of both encoders. Each layer projects the vision and text encoder hidden-state sequences into a shared space, attends across modalities, and sends gated residual updates back, with simple stabilizers to improve alignment. The encoders remain non-causal and strong for understanding, while generation stays cleanly decoupled via an optional decoder. Across standard retrieval, VQA, and visual reasoning benchmarks, BRIDGE outperforms comparable VLMs while preserving the bi-encoder efficiency of contrastive models. We make our code publicly available at https://github.com/jfeinashley/BRIDGE.

---

### CVChess: A Deep Learning Framework for Converting Chessboard Images to Forsyth-Edwards Notation

Authors: Luthira Abeykoon, Ved Patel, Gawthaman Senthilvelan, Darshan Kasundra
Published: 2025-11-14
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.11522v3

Chess has experienced a large increase in viewership since the pandemic, driven largely by the accessibility of online learning platforms. However, no equivalent assistance exists for physical chess games, creating a divide between analog and digital chess experiences. This paper presents CVChess, a deep learning framework for converting chessboard images to Forsyth-Edwards Notation (FEN), which is later input into online chess engines to provide you with the best next move. Our approach employs a convolutional neural network (CNN) with residual layers to perform piece recognition from smartphone camera images. The system processes RGB images of a physical chess board through a multistep process: image preprocessing using the Hough Line Transform for edge detection, projective transform to achieve a top-down board alignment, segmentation into 64 individual squares, and piece classification into 13 classes (6 unique white pieces, 6 unique black pieces and an empty square) using the residual CNN. Residual connections help retain low-level visual features while enabling deeper feature extraction, improving accuracy and stability during training. We train and evaluate our model using the Chess Recognition Dataset (ChessReD), containing 10,800 annotated smartphone images captured under diverse lighting conditions and angles. The resulting classifications are encoded as an FEN string, which can be fed into a chess engine to generate the most optimal move

---

### CVChess: A Deep Learning Framework for Converting Chessboard Images to Forsyth-Edwards Notation

Authors: Luthira Abeykoon, Ved Patel, Gawthaman Senthilvelan, Darshan Kasundra
Published: 2025-11-14
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.11522v1

Chess has experienced a large increase in viewership since the pandemic, driven largely by the accessibility of online learning platforms. However, no equivalent assistance exists for physical chess games, creating a divide between analog and digital chess experiences. This paper presents CVChess, a deep learning framework for converting chessboard images to Forsyth-Edwards Notation (FEN), which is later input into online chess engines to provide you with the best next move. Our approach employs a convolutional neural network (CNN) with residual layers to perform piece recognition from smartphone camera images. The system processes RGB images of a physical chess board through a multistep process: image preprocessing using the Hough Line Transform for edge detection, projective transform to achieve a top-down board alignment, segmentation into 64 individual squares, and piece classification into 13 classes (6 unique white pieces, 6 unique black pieces and an empty square) using the residual CNN. Residual connections help retain low-level visual features while enabling deeper feature extraction, improving accuracy and stability during training. We train and evaluate our model using the Chess Recognition Dataset (ChessReD), containing 10,800 annotated smartphone images captured under diverse lighting conditions and angles. The resulting classifications are encoded as an FEN string, which can be fed into a chess engine to generate the most optimal move

---

### Experience-Guided Adaptation of Inference-Time Reasoning Strategies

Authors: Adam Stein, Matthew Trager, Benjamin Bowman, Michael Kleinman, Aditya Chattopadhyay, Wei Xia, Stefano Soatto
Published: 2025-11-14
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.11519v1

Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a memory at inference time have been proposed, existing designs only steer the system by modifying textual input to a language model or agent, which means that they cannot change sampling parameters, remove tools, modify system prompts, or switch between agentic and workflow paradigms. On the other hand, systems that adapt more flexibly require offline optimization and remain static once deployed. We present Experience-Guided Reasoner (EGuR), which generates tailored strategies -- complete computational procedures involving LLM calls, tools, sampling parameters, and control logic -- dynamically at inference time based on accumulated experience. We achieve this using an LLM-based meta-strategy -- a strategy that outputs strategies -- enabling adaptation of all strategy components (prompts, sampling parameters, tool configurations, and control logic). EGuR operates through two components: a Guide generates multiple candidate strategies conditioned on the current problem and structured memory of past experiences, while a Consolidator integrates execution feedback to improve future strategy generation. This produces complete, ready-to-run strategies optimized for each problem, which can be cached, retrieved, and executed as needed without wasting resources. Across five challenging benchmarks (AIME 2025, 3-SAT, and three Big Bench Extra Hard tasks), EGuR achieves up to 14% accuracy improvements over the strongest baselines while reducing computational costs by up to 111x, with both metrics improving as the system gains experience.

---

### W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search

Authors: Zhenyu Ding, Yuhao Wang, Tengyue Xiao, Haoying Wang, Caigui Jiang, Ning Ding
Published: 2025-11-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.11518v2

Large Language Models (LLMs) demonstrate impressive capabilities, yet their outputs often suffer from misalignment with human preferences due to the inadequacy of weak supervision and a lack of fine-grained control. Training-time alignment methods like Reinforcement Learning from Human Feedback (RLHF) face prohibitive costs in expert supervision and inherent scalability limitations, offering limited dynamic control during inference. Consequently, there is an urgent need for scalable and adaptable alignment mechanisms. To address this, we propose W2S-AlignTree, a pioneering plug-and-play inference-time alignment framework that synergistically combines Monte Carlo Tree Search (MCTS) with the Weak-to-Strong Generalization paradigm for the first time. W2S-AlignTree formulates LLM alignment as an optimal heuristic search problem within a generative search tree. By leveraging weak model's real-time, step-level signals as alignment proxies and introducing an Entropy-Aware exploration mechanism, W2S-AlignTree enables fine-grained guidance during strong model's generation without modifying its parameters. The approach dynamically balances exploration and exploitation in high-dimensional generation search trees. Experiments across controlled sentiment generation, summarization, and instruction-following show that W2S-AlignTree consistently outperforms strong baselines. Notably, W2S-AlignTree raises the performance of Llama3-8B from 1.89 to 2.19, a relative improvement of 15.9 on the summarization task.

---

### W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search

Authors: Zhenyu Ding, Yuhao Wang, Tengyue Xiao, Haoying Wang, Guojun Ma, Mingyang Wan, Caigui Jiang, Ning Ding
Published: 2025-11-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.11518v1

Large Language Models (LLMs) demonstrate impressive capabilities, yet their outputs often suffer from misalignment with human preferences due to the inadequacy of weak supervision and a lack of fine-grained control. Training-time alignment methods like Reinforcement Learning from Human Feedback (RLHF) face prohibitive costs in expert supervision and inherent scalability limitations, offering limited dynamic control during inference. Consequently, there is an urgent need for scalable and adaptable alignment mechanisms. To address this, we propose W2S-AlignTree, a pioneering plug-and-play inference-time alignment framework that synergistically combines Monte Carlo Tree Search (MCTS) with the Weak-to-Strong Generalization paradigm for the first time. W2S-AlignTree formulates LLM alignment as an optimal heuristic search problem within a generative search tree. By leveraging weak model's real-time, step-level signals as alignment proxies and introducing an Entropy-Aware exploration mechanism, W2S-AlignTree enables fine-grained guidance during strong model's generation without modifying its parameters. The approach dynamically balances exploration and exploitation in high-dimensional generation search trees. Experiments across controlled sentiment generation, summarization, and instruction-following show that W2S-AlignTree consistently outperforms strong baselines. Notably, W2S-AlignTree raises the performance of Llama3-8B from 1.89 to 2.19, a relative improvement of 15.9 on the summarization task.

---

### Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities

Authors: Yiyun Zhou, Mingjing Xu, Jingwei Shi, Quanjiang Li, Jingyuan Chen
Published: 2025-11-14
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2511.11512v5

Tactile sensing offers rich and complementary information to vision and language, enabling robots to perceive fine-grained object properties. However, existing tactile sensors lack standardization, leading to redundant features that hinder cross-sensor generalization. Moreover, existing methods fail to fully integrate the intermediate communication among tactile, language, and vision modalities. To address this, we propose TLV-CoRe, a CLIP-based Tactile-Language-Vision Collaborative Representation learning method. TLV-CoRe introduces a Sensor-Aware Modulator to unify tactile features across different sensors and employs tactile-irrelevant decoupled learning to disentangle irrelevant tactile features. Additionally, a Unified Bridging Adapter is introduced to enhance tri-modal interaction within the shared representation space. To fairly evaluate the effectiveness of tactile models, we further propose the RSS evaluation framework, focusing on Robustness, Synergy, and Stability across different methods. Experimental results demonstrate that TLV-CoRe significantly improves sensor-agnostic representation learning and cross-modal alignment, offering a new direction for multimodal tactile representation.

---