# Research Papers — 2025-10 · bundle page 210 of 217

> Full-text markdown of papers #10451–10500 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/210
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/209.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/211.md)

### On the Role of Domain Experts in Creating Effective Tutoring Systems

Authors: Sarath Sreedharan, Kelsey Sikes, Nathaniel Blanchard, Lisa Mason, Nikhil Krishnaswamy, Jill Zarestky
Published: 2025-10-01
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.01432v1

The role that highly curated knowledge, provided by domain experts, could play in creating effective tutoring systems is often overlooked within the AI for education community. In this paper, we highlight this topic by discussing two ways such highly curated expert knowledge could help in creating novel educational systems. First, we will look at how one could use explainable AI (XAI) techniques to automatically create lessons. Most existing XAI methods are primarily aimed at debugging AI systems. However, we will discuss how one could use expert specified rules about solving specific problems along with novel XAI techniques to automatically generate lessons that could be provided to learners. Secondly, we will see how an expert specified curriculum for learning a target concept can help develop adaptive tutoring systems, that can not only provide a better learning experience, but could also allow us to use more efficient algorithms to create these systems. Finally, we will highlight the importance of such methods using a case study of creating a tutoring system for pollinator identification, where such knowledge could easily be elicited from experts.

---

### BioVERSE: Representation Alignment of Biomedical Modalities to LLMs for Multi-Modal Reasoning

Authors: Ching-Huei Tsou, Michal Ozery-Flato, Ella Barkan, Diwakar Mahajan, Ben Shapira
Published: 2025-10-01
Categories: q-bio.QM, cs.AI
arXiv: https://arxiv.org/abs/2510.01428v1

Recent advances in large language models (LLMs) and biomedical foundation models (BioFMs) have achieved strong results in biological text reasoning, molecular modeling, and single-cell analysis, yet they remain siloed in disjoint embedding spaces, limiting cross-modal reasoning. We present BIOVERSE (Biomedical Vector Embedding Realignment for Semantic Engagement), a two-stage approach that adapts pretrained BioFMs as modality encoders and aligns them with LLMs through lightweight, modality-specific projection layers. The approach first aligns each modality to a shared LLM space through independently trained projections, allowing them to interoperate naturally, and then applies standard instruction tuning with multi-modal data to bring them together for downstream reasoning. By unifying raw biomedical data with knowledge embedded in LLMs, the approach enables zero-shot annotation, cross-modal question answering, and interactive, explainable dialogue. Across tasks spanning cell-type annotation, molecular description, and protein function reasoning, compact BIOVERSE configurations surpass larger LLM baselines while enabling richer, generative outputs than existing BioFMs, establishing a foundation for principled multi-modal biomedical reasoning.

---

### A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining

Authors: Sipeng Zhang, Longfei Yun, Zilong Wang, Letian Peng, Jingbo Shang
Published: 2025-10-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.01427v4

At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language models (LLMs) excel at interpreting such instructions but are prohibitively expensive to deploy at scale, while traditional pipelines of classifiers and extractors remain efficient yet brittle and unable to generalize to new tasks. We introduce Falconer, a collaborative framework that combines the agentic reasoning of LLMs with lightweight proxy models for scalable knowledge mining. In Falconer, LLMs act as planners, decomposing user instructions into executable pipelines, and as annotators, generating supervision to train small proxies. The framework unifies classification and extraction into two atomic operations, get label and get span, enabling a single instruction-following model to replace multiple task-specific components. To evaluate the consistency between proxy models incubated by Falconer and annotations provided by humans and large models, we construct new benchmarks covering both planning and end-to-end execution. Experiments show that Falconer closely matches state-of-the-art LLMs in instruction-following accuracy while reducing inference cost by up to 90% and accelerating large-scale knowledge mining by more than 20x, offering an efficient and scalable foundation for Deep Research.

---

### DiffKnock: Diffusion-based Knockoff Statistics for Neural Networks Inference

Authors: Heng Ge, Qing Lu
Published: 2025-10-01
Categories: stat.ME, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.01418v1

We introduce DiffKnock, a diffusion-based knockoff framework for high-dimensional feature selection with finite-sample false discovery rate (FDR) control. DiffKnock addresses two key limitations of existing knockoff methods: preserving complex feature dependencies and detecting non-linear associations. Our approach trains diffusion models to generate valid knockoffs and uses neural network--based gradient and filter statistics to construct antisymmetric feature importance measures. Through simulations, we showed that DiffKnock achieved higher power than autoencoder-based knockoffs while maintaining target FDR, indicating its superior performance in scenarios involving complex non-linear architectures. Applied to murine single-cell RNA-seq data of LPS-stimulated macrophages, DiffKnock identifies canonical NF-$κ$B target genes (Ccl3, Hmox1) and regulators (Fosb, Pdgfb). These results highlight that, by combining the flexibility of deep generative models with rigorous statistical guarantees, DiffKnock is a powerful and reliable tool for analyzing single-cell RNA-seq data, as well as high-dimensional and structured data in other domains.

---

### Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting

Authors: Jiping Li, Rishi Sonthalia
Published: 2025-10-01
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.01414v1

This paper analyzes the generalization error of minimum-norm interpolating solutions in linear regression using spiked covariance data models. The paper characterizes how varying spike strengths and target-spike alignments can affect risk, especially in overparameterized settings. The study presents an exact expression for the generalization error, leading to a comprehensive classification of benign, tempered, and catastrophic overfitting regimes based on spike strength, the aspect ratio $c=d/n$ (particularly as $c \to \infty$), and target alignment. Notably, in well-specified aligned problems, increasing spike strength can surprisingly induce catastrophic overfitting before achieving benign overfitting. The paper also reveals that target-spike alignment is not always advantageous, identifying specific, sometimes counterintuitive, conditions for its benefit or detriment. Alignment with the spike being detrimental is empirically demonstrated to persist in nonlinear models.

---

### OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Models

Authors: Luca Cotti, Idilio Drago, Anisa Rula, Devis Bianchini, Federico Cerutti
Published: 2025-10-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.01409v2

System logs represent a valuable source of Cyber Threat Intelligence (CTI), capturing attacker behaviors, exploited vulnerabilities, and traces of malicious activity. Yet their utility is often limited by lack of structure, semantic inconsistency, and fragmentation across devices and sessions. Extracting actionable CTI from logs therefore requires approaches that can reconcile noisy, heterogeneous data into coherent and interoperable representations. We introduce OntoLogX, an autonomous Artificial Intelligence (AI) agent that leverages Large Language Models (LLMs) to transform raw logs into ontology-grounded Knowledge Graphs (KGs). OntoLogX integrates a lightweight log ontology with Retrieval Augmented Generation (RAG) and iterative correction steps, ensuring that generated KGs are syntactically and semantically valid. Beyond event-level analysis, the system aggregates KGs into sessions and employs a LLM to predict MITRE ATT&CK tactics, linking low-level log evidence to higher-level adversarial objectives. We evaluate OntoLogX on both logs from a public benchmark and a real-world honeypot dataset, demonstrating robust KG generation across multiple KGs backends and accurate mapping of adversarial activity to ATT&CK tactics. Results highlight the benefits of retrieval and correction for precision and recall, the effectiveness of code-oriented models in structured log analysis, and the value of ontology-grounded representations for actionable CTI extraction.

---

### Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction

Authors: Ethan G. Rogers, Cheng Wang
Published: 2025-10-01
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.01407v2

Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the complexity and large computational costs of the convolution-based decoders during data reconstruction. To address the decoder bottleneck in neural compression, we develop a new compression-reconstruction framework based on incorporating low-rank representation in an autoencoder with vector quantization. We demonstrated that performing a series of computationally efficient low-rank operations on the learned latent representation of images can efficiently reconstruct the data with high quality. Our approach dramatically reduces the computational overhead in the decoding phase of neural compression/reconstruction, essentially eliminating the decoder compute bottleneck while maintaining high fidelity of image outputs.

---

### Resolving the Identity Crisis in Text-to-Image Generation

Authors: Shubhankar Borse, Farzad Farhadzadeh, Munawar Hayat, Fatih Porikli
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01399v3

State-of-the-art text-to-image models suffer from a persistent identity crisis when generating scenes with multiple humans: producing duplicate faces, merging identities, and miscounting individuals. We present DisCo (Reinforcement with Diversity Constraints), a reinforcement learning framework that directly optimizes identity diversity both within images and across groups of generated samples. DisCo fine-tunes flow-matching models using Group-Relative Policy Optimization (GRPO), guided by a compositional reward that: (i) penalizes facial similarity within images, (ii) discourages identity repetition across samples, (iii) enforces accurate person counts, and (iv) preserves visual fidelity and prompt alignment via human preference scores. A single-stage curriculum stabilizes training as prompt complexity increases. Importantly, this method does not require any real data. On the DiverseHumans Testset, DisCo achieves 98.6% Unique Face Accuracy and near-perfect Global Identity Spread, outperforming open-source and proprietary models (e.g., Gemini, GPT-Image) while maintaining perceptual quality. Our results establish cross-sample diversity as a critical axis for resolving identity collapse, positioning DisCo as a scalable, annotation-free solution for multi-human image synthesis. Project page: https://qualcomm-ai-research.github.io/disco/

---

### Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model Agents

Authors: Yang Liu, Zaid Abulawi, Abhiram Garimidi, Doyeong Lim
Published: 2025-10-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.01398v1

Modern engineering increasingly relies on vast datasets generated by experiments and simulations, driving a growing demand for efficient, reliable, and broadly applicable modeling strategies. There is also heightened interest in developing data-driven approaches, particularly neural network models, for effective prediction and analysis of scientific datasets. Traditional data-driven methods frequently involve extensive manual intervention, limiting their ability to scale effectively and generalize to diverse applications. In this study, we propose an innovative pipeline utilizing Large Language Model (LLM) agents to automate data-driven modeling and analysis, with a particular emphasis on regression tasks. We evaluate two LLM-agent frameworks: a multi-agent system featuring specialized collaborative agents, and a single-agent system based on the Reasoning and Acting (ReAct) paradigm. Both frameworks autonomously handle data preprocessing, neural network development, training, hyperparameter optimization, and uncertainty quantification (UQ). We validate our approach using a critical heat flux (CHF) prediction benchmark, involving approximately 25,000 experimental data points from the OECD/NEA benchmark dataset. Results indicate that our LLM-agent-developed model surpasses traditional CHF lookup tables and delivers predictive accuracy and UQ on par with state-of-the-art Bayesian optimized deep neural network models developed by human experts. These outcomes underscore the significant potential of LLM-based agents to automate complex engineering modeling tasks, greatly reducing human workload while meeting or exceeding existing standards of predictive performance.

---

### Neural Network Surrogates for Free Energy Computation of Complex Chemical Systems

Authors: Wasut Pornpatcharapong
Published: 2025-10-01
Categories: cs.LG, cs.AI, cs.CE, physics.chem-ph, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.01396v1

Free energy reconstruction methods such as Gaussian Process Regression (GPR) require Jacobians of the collective variables (CVs), a bottleneck that restricts the use of complex or machine-learned CVs. We introduce a neural network surrogate framework that learns CVs directly from Cartesian coordinates and uses automatic differentiation to provide Jacobians, bypassing analytical forms. On an MgCl2 ion-pairing system, our method achieved high accuracy for both a simple distance CV and a complex coordination-number CV. Moreover, Jacobian errors also followed a near-Gaussian distribution, making them suitable for GPR pipelines. This framework enables gradient-based free energy methods to incorporate complex and machine-learned CVs, broadening the scope of biochemistry and materials simulations.

---

### Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence

Authors: Myra Cheng, Cinoo Lee, Pranav Khadpe, Sunny Yu, Dyllan Han, Dan Jurafsky
Published: 2025-10-01
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.01395v1

Both the general public and academic communities have raised concerns about sycophancy, the phenomenon of artificial intelligence (AI) excessively agreeing with or flattering users. Yet, beyond isolated media reports of severe consequences, like reinforcing delusions, little is known about the extent of sycophancy or how it affects people who use AI. Here we show the pervasiveness and harmful impacts of sycophancy when people seek advice from AI. First, across 11 state-of-the-art AI models, we find that models are highly sycophantic: they affirm users' actions 50% more than humans do, and they do so even in cases where user queries mention manipulation, deception, or other relational harms. Second, in two preregistered experiments (N = 1604), including a live-interaction study where participants discuss a real interpersonal conflict from their life, we find that interaction with sycophantic AI models significantly reduced participants' willingness to take actions to repair interpersonal conflict, while increasing their conviction of being in the right. However, participants rated sycophantic responses as higher quality, trusted the sycophantic AI model more, and were more willing to use it again. This suggests that people are drawn to AI that unquestioningly validate, even as that validation risks eroding their judgment and reducing their inclination toward prosocial behavior. These preferences create perverse incentives both for people to increasingly rely on sycophantic AI models and for AI model training to favor sycophancy. Our findings highlight the necessity of explicitly addressing this incentive structure to mitigate the widespread risks of AI sycophancy.

---

### Optimal Stopping vs Best-of-$N$ for Inference Time Optimization

Authors: Yusuf Kalayci, Vinod Raman, Shaddin Dughmi
Published: 2025-10-01
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.01394v1

Large language model (LLM) generation often requires balancing output quality against inference cost, especially when using multiple generations. We introduce a new framework for inference-time optimization based on the classical Pandora's Box problem. Viewing each generation as opening a costly "box" with random reward, we develop algorithms that decide when to stop generating without knowing the underlying reward distribution. Our first contribution is a UCB-style Pandora's Box algorithm, which achieves performance that is provably close to Weitzman's algorithm, the optimal strategy when the distribution is known. We further adapt this method to practical LLM settings by addressing reward scaling across prompts via a Bradley-Terry inspired transformation. This leads to an adaptive inference-time optimization method that normalizes rewards and learns stopping thresholds on the fly. Experiments on the AlpacaFarm and HH-RLHF datasets, using multiple LLM-reward model pairs, show that our adaptive strategy can obtain the same performance as non-adaptive Best-of-N sampling while requiring 15-35 percent fewer generations on average. Our results establish a principled bridge between optimal stopping theory and inference-time scaling, providing both theoretical performance bounds and practical efficiency gains for LLM deployment.

---

### TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting Strategies

Authors: Maithili Kadam, Francis Ferraro
Published: 2025-10-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.01391v1

Large language models (LLMs) excel at general language tasks but often struggle with event-based questions-especially those requiring causal or temporal reasoning. We introduce TAG-EQA (Text-And-Graph for Event Question Answering), a prompting framework that injects causal event graphs into LLM inputs by converting structured relations into natural-language statements. TAG-EQA spans nine prompting configurations, combining three strategies (zero-shot, few-shot, chain-of-thought) with three input modalities (text-only, graph-only, text+graph), enabling a systematic analysis of when and how structured knowledge aids inference. On the TORQUESTRA benchmark, TAG-EQA improves accuracy by 5% on average over text-only baselines, with gains up to 12% in zero-shot settings and 18% when graph-augmented CoT prompting is effective. While performance varies by model and configuration, our findings show that causal graphs can enhance event reasoning in LLMs without fine-tuning, offering a flexible way to encode structure in prompt-based QA.

---

### INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models

Authors: Ulas Berk Karli, Ziyao Shangguan, Tesca FItzgerald
Published: 2025-10-01
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.01389v2

Recent Vision-Language-Action (VLA) models show strong generalization capabilities, yet they lack introspective mechanisms for anticipating failures and requesting help from a human supervisor. We present \textbf{INSIGHT}, a learning framework for leveraging token-level uncertainty signals to predict when a VLA should request help. Using $π_0$-FAST as the underlying model, we extract per-token \emph{entropy}, \emph{log-probability}, and Dirichlet-based estimates of \emph{aleatoric and epistemic uncertainty}, and train compact transformer classifiers to map these sequences to help triggers. We explore supervision regimes for strong or weak supervision, and extensively compare them across in-distribution and out-of-distribution tasks. Our results show a trade-off: strong labels enable models to capture fine-grained uncertainty dynamics for reliable help detection, while weak labels, though noisier, still support competitive introspection when training and evaluation are aligned, offering a scalable path when dense annotation is impractical. Crucially, we find that modeling the temporal evolution of token-level uncertainty signals with transformers provides far greater predictive power than static sequence-level scores. This study provides the first systematic evaluation of uncertainty-based introspection in VLAs, opening future avenues for active learning and for real-time error mitigation through selective human intervention.

---

### VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation

Authors: Arthur Zhang, Xiangyun Meng, Luca Calliari, Dong-Ki Kim, Shayegan Omidshafiei, Joydeep Biswas, Ali Agha, Amirreza Shaban
Published: 2025-10-01
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.01388v1

Robots must adapt to diverse human instructions and operate safely in unstructured, open-world environments. Recent Vision-Language models (VLMs) offer strong priors for grounding language and perception, but remain difficult to steer for navigation due to differences in action spaces and pretraining objectives that hamper transferability to robotics tasks. Towards addressing this, we introduce VENTURA, a vision-language navigation system that finetunes internet-pretrained image diffusion models for path planning. Instead of directly predicting low-level actions, VENTURA generates a path mask (i.e. a visual plan) in image space that captures fine-grained, context-aware navigation behaviors. A lightweight behavior-cloning policy grounds these visual plans into executable trajectories, yielding an interface that follows natural language instructions to generate diverse robot behaviors. To scale training, we supervise on path masks derived from self-supervised tracking models paired with VLM-augmented captions, avoiding manual pixel-level annotation or highly engineered data collection setups. In extensive real-world evaluations, VENTURA outperforms state-of-the-art foundation model baselines on object reaching, obstacle avoidance, and terrain preference tasks, improving success rates by 33% and reducing collisions by 54% across both seen and unseen scenarios. Notably, we find that VENTURA generalizes to unseen combinations of distinct tasks, revealing emergent compositional capabilities. Videos, code, and additional materials: https://venturapath.github.io

---

### Learning to Play Multi-Follower Bayesian Stackelberg Games

Authors: Gerson Personnat, Tao Lin, Safwan Hossain, David C. Parkes
Published: 2025-10-01
Categories: cs.GT, cs.LG, econ.TH
arXiv: https://arxiv.org/abs/2510.01387v2

In a multi-follower Bayesian Stackelberg game, a leader plays a mixed strategy over $L$ actions to which $n\ge 1$ followers, each having one of $K$ possible private types, best respond. The leader's optimal strategy depends on the distribution of the followers' private types. We study an online learning version of this problem: a leader interacts for $T$ rounds with $n$ followers with types sampled from an unknown distribution every round. The leader's goal is to minimize regret, defined as the difference between the cumulative utility of the optimal strategy and that of the actually chosen strategies. We design learning algorithms for the leader under different feedback settings. Under type feedback, where the leader observes the followers' types after each round, we design algorithms that achieve $O\big(\sqrt{\min(L\log(nKA T), nK ) \cdot T} \big)$ regret for independent type distributions and $O\big(\sqrt{\min(L\log(nKA T), K^n ) \cdot T} \big)$ regret for general type distributions. Interestingly, those bounds do not grow with $n$ at a polynomial rate. Under action feedback, where the leader only observes the followers' actions, we design algorithms with $O( \min(\sqrt{ n^L K^L A^{2L} L T \log T}, K^n\sqrt{ T } \log T ) )$ regret. We also provide a lower bound of $Ω(\sqrt{\min(L, nK)T})$, almost matching the type-feedback upper bounds.

---

### Fine-Tuning Masked Diffusion for Provable Self-Correction

Authors: Jaeyeon Kim, Seunggeun Kim, Taekyun Lee, David Z. Pan, Hyeji Kim, Sham Kakade, Sitan Chen
Published: 2025-10-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01384v4

A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces, their capacity for self-correction remains poorly understood. Prior attempts to incorporate self-correction into MDMs either require overhauling MDM architectures/training or rely on imprecise proxies for token quality, limiting their applicability. Motivated by this, we introduce PRISM--Plug-in Remasking for Inference-time Self-correction of Masked Diffusions--a lightweight, model-agnostic approach that applies to any pretrained MDM. Theoretically, PRISM defines a self-correction loss that provably learns per-token quality scores, without RL or a verifier. These quality scores are computed in the same forward pass with MDM and used to detect low-quality tokens. Empirically, PRISM advances MDM inference across domains and scales: Sudoku; unconditional text (170M); and code with LLaDA (8B).

---

### Selective Underfitting in Diffusion Models

Authors: Kiwhan Song, Jaeyeon Kim, Sitan Chen, Yilun Du, Sham Kakade, Vincent Sitzmann
Published: 2025-10-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01378v1

Diffusion models have emerged as the principal paradigm for generative modeling across various domains. During training, they learn the score function, which in turn is used to generate samples at inference. They raise a basic yet unsolved question: which score do they actually learn? In principle, a diffusion model that matches the empirical score in the entire data space would simply reproduce the training data, failing to generate novel samples. Recent work addresses this question by arguing that diffusion models underfit the empirical score due to training-time inductive biases. In this work, we refine this perspective, introducing the notion of selective underfitting: instead of underfitting the score everywhere, better diffusion models more accurately approximate the score in certain regions of input space, while underfitting it in others. We characterize these regions and design empirical interventions to validate our perspective. Our results establish that selective underfitting is essential for understanding diffusion models, yielding new, testable insights into their generalization and generative performance.

---

### DeMuon: A Decentralized Muon for Matrix Optimization over Graphs

Authors: Chuan He, Shuyi Ren, Jingwei Mao, Erik G. Larsson
Published: 2025-10-01
Categories: math.OC, cs.AI, cs.LG, cs.MA, eess.SY
arXiv: https://arxiv.org/abs/2510.01377v2

In this paper, we propose DeMuon, a method for decentralized matrix optimization over a given communication topology. DeMuon incorporates matrix orthogonalization via Newton-Schulz iterations-a technique inherited from its centralized predecessor, Muon-and employs gradient tracking to mitigate heterogeneity among local functions. Under heavy-tailed noise conditions and additional mild assumptions, we establish the iteration complexity of DeMuon for reaching an approximate stochastic stationary point. This complexity result matches the best-known complexity bounds of centralized algorithms in terms of dependence on the target tolerance. To the best of our knowledge, DeMuon is the first direct extension of Muon to decentralized optimization over graphs with provable complexity guarantees. We conduct preliminary numerical experiments on decentralized transformer pretraining over graphs with varying degrees of connectivity. Our numerical results demonstrate a clear margin of improvement of DeMuon over other popular decentralized algorithms across different network topologies.

---

### Fine-tuning with RAG for Improving LLM Learning of New Skills

Authors: Humaid Ibrahim, Nikolai Rozanov, Marek Rei
Published: 2025-10-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.01375v1

Large language model (LLM) agents deployed for multi-step tasks frequently fail in predictable ways: attempting actions with unmet preconditions, issuing redundant commands, or mishandling environment constraints. While retrieval-augmented generation (RAG) can improve performance by providing runtime guidance, it requires maintaining external knowledge databases and adds computational overhead at every deployment. We propose a simple pipeline that converts inference-time retrieval into learned competence through distillation. Our approach: (1) extracts compact, reusable hints from agent failures, (2) uses these hints to generate improved teacher trajectories via one-shot retrieval at episode start, and (3) trains student models on these trajectories with hint strings removed, forcing internalization rather than memorization. Across two interactive benchmarks, ALFWorld (household tasks) and WebShop (online shopping), distilled students consistently outperform baseline agents, achieving up to 91% success on ALFWorld (vs. 79% for baselines) and improving WebShop scores to 72 (vs. 61 for baselines), while using 10-60% fewer tokens than retrieval-augmented teachers depending on the environment. The approach generalizes across model scales (7B/14B parameters) and agent architectures (ReAct/StateAct), demonstrating that retrieval benefits can be effectively internalized through targeted fine-tuning without permanent runtime dependencies.

---

### SPUS: A Lightweight and Parameter-Efficient Foundation Model for PDEs

Authors: Abu Bucker Siddik, Diane Oyen, Alexander Most, Michal Kucer, Ayan Biswas
Published: 2025-10-01
Categories: cs.CV, cs.AI, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.01370v1

We introduce Small PDE U-Net Solver (SPUS), a compact and efficient foundation model (FM) designed as a unified neural operator for solving a wide range of partial differential equations (PDEs). Unlike existing state-of-the-art PDE FMs-primarily based on large complex transformer architectures with high computational and parameter overhead-SPUS leverages a lightweight residual U-Net-based architecture that has been largely underexplored as a foundation model architecture in this domain. To enable effective learning in this minimalist framework, we utilize a simple yet powerful auto-regressive pretraining strategy which closely replicates the behavior of numerical solvers to learn the underlying physics. SPUS is pretrained on a diverse set of fluid dynamics PDEs and evaluated across 6 challenging unseen downstream PDEs spanning various physical systems. Experimental results demonstrate that SPUS using residual U-Net based architecture achieves state-of-the-art generalization on these downstream tasks while requiring significantly fewer parameters and minimal fine-tuning data, highlighting its potential as a highly parameter-efficient FM for solving diverse PDE systems.

---

### Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort

Authors: Xinpeng Wang, Nitish Joshi, Barbara Plank, Rico Angell, He He
Published: 2025-10-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.01367v4

Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's chain-of-thought (CoT), or implicit, where the CoT appears benign thus bypasses CoT monitors. To detect implicit reward hacking, we propose TRACE (Truncated Reasoning AUC Evaluation). Our key observation is that hacking occurs when exploiting the loophole is easier than solving the actual task. This means that the model is using less 'effort' than required to achieve high reward. TRACE quantifies effort by measuring how early a model's reasoning becomes sufficient to obtain the reward. We progressively truncate a model's CoT at various lengths, force the model to answer, and estimate the expected reward at each cutoff. A hacking model, which takes a shortcut, will achieve a high expected reward with only a small fraction of its CoT, yielding a large area under the accuracy-vs-length curve. TRACE achieves over 65% gains over our strongest 72B CoT monitor in math reasoning, and over 30% gains over a 32B monitor in coding. We further show that TRACE can discover unknown loopholes during training. Overall, TRACE offers a scalable unsupervised approach for oversight where current monitoring methods prove ineffective.

---

### RheOFormer: A generative transformer model for simulation of complex fluids and flows

Authors: Maedeh Saberi, Amir Barati Farimani, Safa Jamali
Published: 2025-10-01
Categories: cs.LG, physics.flu-dyn
arXiv: https://arxiv.org/abs/2510.01365v2

The ability to model mechanics of soft materials under flowing conditions is key in designing and engineering processes and materials with targeted properties. This generally requires solution of internal stress tensor, related to the deformation tensor through nonlinear and history-dependent constitutive models. Traditional numerical methods for non-Newtonian fluid dynamics often suffer from prohibitive computational demands and poor scalability to new problem instances. Developments in data-driven methods have mitigated some limitations but still require retraining across varied physical conditions. In this work, we introduce Rheological Operator Transformer (RheOFormer), a generative operator learning method leveraging self-attention to efficiently learn different spatial interactions and features of complex fluid flows. We benchmark RheOFormer across a range of different viscometric and non-viscometric flows with different types of viscoelastic and elastoviscoplastic mechanics in complex domains against ground truth solutions. Our results demonstrate that RheOFormer can accurately learn both scalar and tensorial nonlinear mechanics of different complex fluids and predict the spatio-temporal evolution of their flows, even when trained on limited datasets. Its strong generalization capabilities and computational efficiency establish RheOFormer as a robust neural surrogate for accelerating predictive complex fluid simulations, advancing data-driven experimentation, and enabling real-time process optimization across a wide range of applications.

---

### Retrieval-Augmented Framework for LLM-Based Clinical Decision Support

Authors: Leon Garza, Anantaa Kotal, Michael A. Grasso, Emre Umucu
Published: 2025-10-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.01363v1

The increasing complexity of clinical decision-making, alongside the rapid expansion of electronic health records (EHR), presents both opportunities and challenges for delivering data-informed care. This paper proposes a clinical decision support system powered by Large Language Models (LLMs) to assist prescribing clinicians. The system generates therapeutic suggestions by analyzing historical EHR data, including patient demographics, presenting complaints, clinical symptoms, diagnostic information, and treatment histories. The framework integrates natural language processing with structured clinical inputs to produce contextually relevant recommendations. Rather than replacing clinician judgment, it is designed to augment decision-making by retrieving and synthesizing precedent cases with comparable characteristics, drawing on local datasets or federated sources where applicable. At its core, the system employs a retrieval-augmented generation (RAG) pipeline that harmonizes unstructured narratives and codified data to support LLM-based inference. We outline the system's technical components, including representation representation alignment and generation strategies. Preliminary evaluations, conducted with de-identified and synthetic clinical datasets, examine the clinical plausibility and consistency of the model's outputs. Early findings suggest that LLM-based tools may provide valuable decision support in prescribing workflows when appropriately constrained and rigorously validated. This work represents an initial step toward integration of generative AI into real-world clinical decision-making with an emphasis on transparency, safety, and alignment with established practices.

---

### EvoStruggle: A Dataset Capturing the Evolution of Struggle across Activities and Skill Levels

Authors: Shijia Feng, Michael Wray, Walterio Mayol-Cuevas
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01362v1

The ability to determine when a person struggles during skill acquisition is crucial for both optimizing human learning and enabling the development of effective assistive systems. As skills develop, the type and frequency of struggles tend to change, and understanding this evolution is key to determining the user's current stage of learning. However, existing manipulation datasets have not focused on how struggle evolves over time. In this work, we collect a dataset for struggle determination, featuring 61.68 hours of video recordings, 2,793 videos, and 5,385 annotated temporal struggle segments collected from 76 participants. The dataset includes 18 tasks grouped into four diverse activities -- tying knots, origami, tangram puzzles, and shuffling cards, representing different task variations. In addition, participants repeated the same task five times to capture their evolution of skill. We define the struggle determination problem as a temporal action localization task, focusing on identifying and precisely localizing struggle segments with start and end times. Experimental results show that Temporal Action Localization models can successfully learn to detect struggle cues, even when evaluated on unseen tasks or activities. The models attain an overall average mAP of 34.56% when generalizing across tasks and 19.24% across activities, indicating that struggle is a transferable concept across various skill-based tasks while still posing challenges for further improvement in struggle detection. Our dataset is available at https://github.com/FELIXFENG2019/EvoStruggle.

---

### An Efficient Quality Metric for Video Frame Interpolation Based on Motion-Field Divergence

Authors: Conall Daly, Darren Ramsook, Anil Kokaram
Published: 2025-10-01
Categories: eess.IV, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.01361v2

Video frame interpolation is a fundamental tool for temporal video enhancement, but existing quality metrics struggle to evaluate the perceptual impact of interpolation artefacts effectively. Metrics like PSNR, SSIM and LPIPS ignore temporal coherence. State-of-the-art quality metrics tailored towards video frame interpolation, like FloLPIPS, have been developed but suffer from computational inefficiency that limits their practical application. We present $\text{PSNR}_{\text{DIV}}$, a novel full-reference quality metric that enhances PSNR through motion divergence weighting, a technique adapted from archival film restoration where it was developed to detect temporal inconsistencies. Our approach highlights singularities in motion fields which is then used to weight image errors. Evaluation on the BVI-VFI dataset (180 sequences across multiple frame rates, resolutions and interpolation methods) shows $\text{PSNR}_{\text{DIV}}$ achieves statistically significant improvements: +0.09 Pearson Linear Correlation Coefficient over FloLPIPS, while being 2.5$\times$ faster and using 4$\times$ less memory. Performance remains consistent across all content categories and are robust to the motion estimator used. The efficiency and accuracy of $\text{PSNR}_{\text{DIV}}$ enables fast quality evaluation and practical use as a loss function for training neural networks for video frame interpolation tasks. An implementation of our metric is available at www.github.com/conalld/psnr-div.

---

### Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks

Authors: Shoumik Saha, Jifan Chen, Sam Mayers, Sanjay Krishna Gouda, Zijian Wang, Varun Kumar
Published: 2025-10-01
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.01359v3

Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings. Prior evaluations emphasize refusal or harmful-text detection, leaving open whether agents compile and run malicious programs. We present JAWS-Bench (Jailbreaks Across WorkSpaces), a benchmark spanning three escalating workspace regimes mirroring attacker capability: empty (JAWS-0), single-file (JAWS-1), and multi-file (JAWS-M). We pair it with a hierarchical, executable-aware Judge Framework that tests (i) compliance, (ii) attack success, (iii) syntactic correctness, and (iv) runtime executability to measure deployable harm. Across seven LLM backends from five families, prompt-only attacks in JAWS-0 achieve 61% compliance; 58% are harmful, 52% parse, and 27% run end-to-end. In JAWS-1, compliance reaches ~100% for stronger models with a mean ASR (Attack Success Rate) ~71%; JAWS-M raises mean ASR to ~75%, with 32% runnable attack code. Wrapping an LLM in an agent increases ASR by 1.6$\times$, by overturning initial refusals during planning and tool use. Additional evaluations with SWE-Agent and OpenAI Codex exhibit similar trends, indicating that JAWS-Bench can be reused across multiple agent frameworks. Category analyses identify which attack classes are most vulnerable and deployable, motivating execution-aware defenses and refusal-preserving agent designs.

---

### A theoretical framework for M-posteriors: frequentist guarantees and robustness properties

Authors: Juraj Marusic, Marco Avella Medina, Cynthia Rush
Published: 2025-10-01
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.01358v1

We provide a theoretical framework for a wide class of generalized posteriors that can be viewed as the natural Bayesian posterior counterpart of the class of M-estimators in the frequentist world. We call the members of this class M-posteriors and show that they are asymptotically normally distributed under mild conditions on the M-estimation loss and the prior. In particular, an M-posterior contracts in probability around a normal distribution centered at an M-estimator, showing frequentist consistency and suggesting some degree of robustness depending on the reference M-estimator. We formalize the robustness properties of the M-posteriors by a new characterization of the posterior influence function and a novel definition of breakdown point adapted for posterior distributions. We illustrate the wide applicability of our theory in various popular models and illustrate their empirical relevance in some numerical examples.

---

### WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents

Authors: Yinuo Liu, Xilong Wang, Ruohan Xu, Yuqi Jia, Neil Zhenqiang Gong
Published: 2025-10-01
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.01354v2

Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this work, we bridge this gap by presenting the first comprehensive benchmark study on detecting prompt injection attacks targeting web agents. We begin by introducing a fine-grained categorization of such attacks based on the threat model. We then construct datasets containing both malicious and benign samples: malicious text segments generated by different attacks, benign text segments from four categories, malicious images produced by attacks, and benign images from two categories. Next, we systematize both text-based and image-based detection methods. Finally, we evaluate their performance across multiple scenarios. Our key findings show that while some detectors can identify attacks that rely on explicit textual instructions or visible image perturbations with moderate to high accuracy, they largely fail against attacks that omit explicit instructions or employ imperceptible perturbations. Our datasets and code are released at: https://github.com/Norrrrrrr-lyn/WAInjectBench.

---

### MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments

Authors: Darshan Deshpande, Varun Gangal, Hersh Mehta, Anand Kannappan, Rebecca Qian, Peng Wang
Published: 2025-10-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.01353v1

Recent works on context and memory benchmarking have primarily focused on conversational instances but the need for evaluating memory in dynamic enterprise environments is crucial for its effective application. We introduce MEMTRACK, a benchmark designed to evaluate long-term memory and state tracking in multi-platform agent environments. MEMTRACK models realistic organizational workflows by integrating asynchronous events across multiple communication and productivity platforms such as Slack, Linear and Git. Each benchmark instance provides a chronologically platform-interleaved timeline, with noisy, conflicting, cross-referring information as well as potential codebase/file-system comprehension and exploration. Consequently, our benchmark tests memory capabilities such as acquistion, selection and conflict resolution. We curate the MEMTRACK dataset through both manual expert driven design and scalable agent based synthesis, generating ecologically valid scenarios grounded in real world software development processes. We introduce pertinent metrics for Correctness, Efficiency, and Redundancy that capture the effectiveness of memory mechanisms beyond simple QA performance. Experiments across SoTA LLMs and memory backends reveal challenges in utilizing memory across long horizons, handling cross-platform dependencies, and resolving contradictions. Notably, the best performing GPT-5 model only achieves a 60\% Correctness score on MEMTRACK. This work provides an extensible framework for advancing evaluation research for memory-augmented agents, beyond existing focus on conversational setups, and sets the stage for multi-agent, multi-platform memory benchmarking in complex organizational settings

---

### Integrated Security Mechanisms for Weight Protection in Memristive Crossbar Arrays

Authors: Muhammad Faheemur Rahman, Wayne Burleson
Published: 2025-10-01
Categories: cs.CR, cs.AR, cs.ET, cs.NE, eess.SY
arXiv: https://arxiv.org/abs/2510.01350v1

Memristive crossbar arrays enable in-memory computing by performing parallel analog computations directly within memory, making them well-suited for machine learning, neural networks, and neuromorphic systems. However, despite their advantages, non-volatile memristors are vulnerable to security threats (such as adversarial extraction of stored weights when the hardware is compromised. Protecting these weights is essential since they represent valuable intellectual property resulting from lengthy and costly training processes using large, often proprietary, datasets. As a solution we propose two security mechanisms: Keyed Permutor and Watermark Protection Columns; where both safeguard critical weights and establish verifiable ownership (even in cases of data leakage). Our approach integrates efficiently with existing memristive crossbar architectures without significant design modifications. Simulations across 45nm, 22nm, and 7nm CMOS nodes, using a realistic interconnect model and a large RF dataset, show that both mechanisms offer robust protection with under 10% overhead in area, delay and power. We also present initial experiments employing the widely known MNIST dataset; further highlighting the feasibility of securing memristive in-memory computing systems with minimal performance trade-offs.

---

### To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking

Authors: Hannah Lawrence, Elyssa Hofgard, Vasco Portilheiro, Yuxuan Chen, Tess Smidt, Robin Walters
Published: 2025-10-01
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.01349v2

Symmetry-aware methods for machine learning, such as data augmentation and equivariant architectures, encourage correct model behavior on all transformations (e.g. rotations or permutations) of the original dataset. These methods can improve generalization and sample efficiency, under the assumption that the transformed datapoints are highly probable, or "important", under the test distribution. In this work, we develop a method for critically evaluating this assumption. In particular, we propose a metric to quantify the amount of symmetry breaking in a dataset, via a two-sample classifier test that distinguishes between the original dataset and its randomly augmented equivalent. We validate our metric on synthetic datasets, and then use it to uncover surprisingly high degrees of symmetry-breaking in several benchmark point cloud datasets, constituting a severe form of dataset bias. We show theoretically that distributional symmetry-breaking can prevent invariant methods from performing optimally even when the underlying labels are truly invariant, for invariant ridge regression in the infinite feature limit. Empirically, the implication for symmetry-aware methods is dataset-dependent: equivariant methods still impart benefits on some symmetry-biased datasets, but not others, particularly when the symmetry bias is predictive of the labels. Overall, these findings suggest that understanding equivariance -- both when it works, and why -- may require rethinking symmetry biases in the data.

---

### Image Generation Based on Image Style Extraction

Authors: Shuochen Chang
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01347v1

Image generation based on text-to-image generation models is a task with practical application scenarios that fine-grained styles cannot be precisely described and controlled in natural language, while the guidance information of stylized reference images is difficult to be directly aligned with the textual conditions of traditional textual guidance generation. This study focuses on how to maximize the generative capability of the pretrained generative model, by obtaining fine-grained stylistic representations from a single given stylistic reference image, and injecting the stylistic representations into the generative body without changing the structural framework of the downstream generative model, so as to achieve fine-grained controlled stylized image generation. In this study, we propose a three-stage training style extraction-based image generation method, which uses a style encoder and a style projection layer to align the style representations with the textual representations to realize fine-grained textual cue-based style guide generation. In addition, this study constructs the Style30k-captions dataset, whose samples contain a triad of images, style labels, and text descriptions, to train the style encoder and style projection layer in this experiment.

---

### Aristotle: IMO-level Automated Theorem Proving

Authors: Tudor Achim, Alex Best, Alberto Bietti, Kevin Der, Mathïs Fédérico, Sergei Gukov, Daniel Halpern-Leistner, Kirsten Henningsgard, Yury Kudryashov, Alexander Meiburg, Martin Michelsen, Riley Patterson et al.
Published: 2025-10-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.01346v2

We introduce Aristotle, an AI system that combines formal verification with informal reasoning, achieving gold-medal-equivalent performance on the 2025 International Mathematical Olympiad problems. Aristotle integrates three main components: a Lean proof search system, an informal reasoning system that generates and formalizes lemmas, and a dedicated geometry solver. Our system demonstrates state-of-the-art performance with favorable scaling properties for automated theorem proving.

---

### Self-Supervised Representation Learning as Mutual Information Maximization

Authors: Akhlaqur Rahman Sabby, Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu
Published: 2025-10-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01345v2

Self-supervised representation learning (SSRL) has demonstrated remarkable empirical success, yet its underlying principles remain insufficiently understood. While recent works attempt to unify SSRL methods by examining their information-theoretic objectives or summarizing their heuristics for preventing representation collapse, architectural elements like predictor networks, stop-gradient operations, and statistical regularizers are often viewed as empirically motivated additions. In this paper, we adopt a first-principles approach and investigate whether the learning objective of an SSRL algorithm dictates its possible optimization strategies and model design choices. In particular, by starting from a variational mutual information (MI) lower bound, we derive two training paradigms, namely Self-Distillation MI (SDMI) and Joint MI (JMI), each imposing distinct structural constraints and covering a set of existing SSRL algorithms. SDMI relies on alternating optimization, in which stop-gradient operations serve as a principled mechanism for realizing the alternating updates. In contrast, JMI admits joint optimization through symmetric architectures without such components. Under the proposed formulation, predictor networks in SDMI and statistical regularizers in JMI emerge as tractable surrogates for the MI objective. We show that many existing SSRL methods are specific instances or approximations of these two paradigms. This paper provides a theoretical explanation for the choices of different architectural components of existing SSRL methods, going beyond heuristic conveniences.

---

### LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video Restoration

Authors: Alessio Spagnoletti, Andrés Almansa, Marcelo Pereyra
Published: 2025-10-01
Categories: cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2510.01339v2

Computational imaging methods increasingly rely on powerful generative diffusion models to tackle challenging image restoration tasks. In particular, state-of-the-art zero-shot image inverse solvers leverage distilled text-to-image latent diffusion models (LDMs) to achieve unprecedented accuracy and perceptual quality with high computational efficiency. However, extending these advances to high-definition video restoration remains a significant challenge, due to the need to recover fine spatial detail while capturing subtle temporal dependencies. Consequently, methods that naively apply image-based LDM priors on a frame-by-frame basis often result in temporally inconsistent reconstructions. We address this challenge by leveraging recent advances in Video Consistency Models (VCMs), which distill video latent diffusion models into fast generators that explicitly capture temporal causality. Building on this foundation, we propose LVTINO, the first zero-shot or plug-and-play inverse solver for high definition video restoration with priors encoded by VCMs. Our conditioning mechanism bypasses the need for automatic differentiation and achieves state-of-the-art video reconstruction quality with only a few neural function evaluations, while ensuring strong measurement consistency and smooth temporal transitions across frames. Extensive experiments on a diverse set of video inverse problems show significant perceptual improvements over current state-of-the-art methods that apply image LDMs frame by frame, establishing a new benchmark in both reconstruction fidelity and computational efficiency. The code is available on GitHub.

---

### On the Identifiability of Latent Action Policies

Authors: Sébastien Lachapelle
Published: 2025-10-01
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.01337v1

We study the identifiability of latent action policy learning (LAPO), a framework introduced recently to discover representations of actions from video data. We formally describe desiderata for such representations, their statistical benefits and potential sources of unidentifiability. Finally, we prove that an entropy-regularized LAPO objective identifies action representations satisfying our desiderata, under suitable conditions. Our analysis provides an explanation for why discrete action representations perform well in practice.

---

### HiSpec: Hierarchical Speculative Decoding for LLMs

Authors: Avinash Kumar, Sujay Sanghavi, Poulami Das
Published: 2025-10-01
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.01336v2

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a 3B model speculates for a 70B target model), but most prior works focus only on accelerating drafting. $\textit{``Intermediate"}$ verification reduces verification time by discarding inaccurate draft tokens early, but existing methods incur substantial training overheads in incorporating the intermediate verifier, increase the memory footprint to orchestrate the intermediate verification step, and compromise accuracy by relying on approximate heuristics. We propose $\underline{\textit{Hi}}\textit{erarchical }\underline{\textit{Spec}}\textit{ulative Decoding (HiSpec)}$, a framework for high-throughput speculative decoding that exploits $\textit{early-exit (EE) models}$ for low-overhead intermediate verification. EE models allow tokens to exit early by skipping layer traversal and are explicitly trained so that hidden states at selected layers can be interpreted, making them uniquely suited for intermediate verification without drastically increasing compute and memory overheads. To improve resource-efficiency even further, we design a methodology that enables HiSpec to re-use key-value caches and hidden states between the draft, intermediate verifier, and target models. To maintain accuracy, HiSpec periodically validates the draft tokens accepted by the intermediate verifier against the target model. Our evaluations using various representative benchmarks and models show that HiSpec improves throughput by 1.28$\times$ on average and by up to 2.01$\times$ compared to the baseline single-layer speculation without compromising accuracy.

---

### HomID : Benchmarking Intrinsic Dimension Estimators on Homogenous Manifolds with Anisotropic Embeddings

Authors: Aritra Das, Joseph T. Iosue, Victor V. Albert
Published: 2025-10-01
Categories: cs.LG, cond-mat.dis-nn, math.MG, physics.data-an, quant-ph
arXiv: https://arxiv.org/abs/2510.01335v2

The manifold hypothesis suggests that data lies on manifolds with smaller intrinsic dimension (ID) than their ambient dimension. However there is no empirical agreement on the estimates for ID from different estimators for realistic datasets. Thus it is important to test ID estimators (IDEs) with targeted stressors. In this work, we consider the role of anisotropy. To this end, we propose HomID, a collection of homogeneous spaces with anisotropic embedding, for benchmarking ID estimators. We observe that methods that perform well on standard benchmarks systematically degrade on HomID under identical resource allocation. We further observe that anisotropic distortion of such benchmarks also results in performance degradation. Finally, we demonstrate that controlled anisotropic distortions induce systematic shifts in the distributions on which these methods rely, providing a concrete mechanism for the resulting estimation errors in two particular IDEs.

---

### Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

Authors: Huangjie Zheng, Shansan Gong, Ruixiang Zhang, Tianrong Chen, Jiatao Gu, Mingyuan Zhou, Navdeep Jaitly, Yizhe Zhang
Published: 2025-10-01
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.01329v1

Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing (MASK) token. This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost between denoising steps. We introduce Continuously Augmented Discrete Diffusion (CADD), a framework that augments the discrete state space with a paired diffusion in a continuous latent space. This yields graded, gradually corrupted states in which masked tokens are represented by noisy yet informative latent vectors rather than collapsed 'information voids'. At each reverse step, CADD may leverage the continuous latent as a semantic hint to guide discrete denoising. The design is clean and compatible with existing discrete diffusion training. At sampling time, the strength and choice of estimator for the continuous latent vector enables a controlled trade-off between mode-coverage (generating diverse outputs) and mode-seeking (generating contextually precise outputs) behaviors. Empirically, we demonstrate CADD improves generative quality over mask-based diffusion across text generation, image synthesis, and code modeling, with consistent gains on both qualitative and quantitative metrics against strong discrete baselines.

---

### Combining complex Langevin dynamics with score-based and energy-based diffusion models

Authors: Gert Aarts, Diaa E. Habibi, Lingxiao Wang, Kai Zhou
Published: 2025-10-01
Categories: hep-lat, cond-mat.dis-nn, cs.LG
arXiv: https://arxiv.org/abs/2510.01328v1

Theories with a sign problem due to a complex action or Boltzmann weight can sometimes be numerically solved using a stochastic process in the complexified configuration space. However, the probability distribution effectively sampled by this complex Langevin process is not known a priori and notoriously hard to understand. In generative AI, diffusion models can learn distributions, or their log derivatives, from data. We explore the ability of diffusion models to learn the distributions sampled by a complex Langevin process, comparing score-based and energy-based diffusion models, and speculate about possible applications.

---

### Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models

Authors: Yu Zeng, Wenxuan Huang, Shiting Huang, Xikun Bao, Yukun Qi, Yiming Zhao, Qiuchen Wang, Lin Chen, Zehui Chen, Huaian Chen, Wanli Ouyang, Feng Zhao
Published: 2025-10-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.01304v3

Although current large Vision-Language Models (VLMs) have advanced in multimodal understanding and reasoning, their fundamental perceptual and reasoning abilities remain limited. Specifically, even on simple jigsaw tasks, existing VLMs perform near randomly, revealing deficiencies in core perception and reasoning capabilities. While high-quality vision-language data can enhance these capabilities, its scarcity and limited scalability impose significant constraints. To address this, we propose AGILE, an Agentic jiGsaw Interaction Learning for Enhancing visual perception and reasoning in VLMs. AGILE formulates jigsaw solving as an interactive process, enabling the model to progressively engage with the environment. At each step, the model generates executable code to perform an action based on the current state, while the environment provides fine-grained visual feedback to guide task completion. Through this iterative cycle of observation and interaction, the model incrementally improves its perceptual and reasoning capabilities via exploration and feedback. Experimental results show that AGILE not only substantially boosts performance on jigsaw tasks of varying complexity (e.g., increasing accuracy from 9.5% to 82.8% under the 2 $\times$ 2 setting) but also demonstrates strong generalization across 9 general vision tasks, achieving an average improvement of 3.1%. These results indicate notable enhancements in both perceptual and reasoning abilities. This work opens a new avenue for advancing reasoning and generalization in multimodal models and provides an efficient, scalable solution to the scarcity of multimodal reinforcement learning data. The code and datasets is available at https://github.com/yuzeng0-0/AGILE .

---

### Low Rank Gradients and Where to Find Them

Authors: Rishi Sonthalia, Michael Murray, Guido Montúfar
Published: 2025-10-01
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.01303v1

This paper investigates low-rank structure in the gradients of the training loss for two-layer neural networks while relaxing the usual isotropy assumptions on the training data and parameters. We consider a spiked data model in which the bulk can be anisotropic and ill-conditioned, we do not require independent data and weight matrices and we also analyze both the mean-field and neural-tangent-kernel scalings. We show that the gradient with respect to the input weights is approximately low rank and is dominated by two rank-one terms: one aligned with the bulk data-residue , and another aligned with the rank one spike in the input data. We characterize how properties of the training data, the scaling regime and the activation function govern the balance between these two components. Additionally, we also demonstrate that standard regularizers, such as weight decay, input noise and Jacobian penalties, also selectively modulate these components. Experiments on synthetic and real data corroborate our theoretical predictions.

---

### Hybrid Predictive Modeling of Malaria Incidence in the Amhara Region, Ethiopia: Integrating Multi-Output Regression and Time-Series Forecasting

Authors: Kassahun Azezew, Amsalu Tesema, Bitew Mekuria, Ayenew Kassie, Animut Embiale, Ayodeji Olalekan Salau, Tsega Asresa
Published: 2025-10-01
Categories: q-bio.OT, cs.LG
arXiv: https://arxiv.org/abs/2510.01302v1

Malaria remains a major public health concern in Ethiopia, particularly in the Amhara Region, where seasonal and unpredictable transmission patterns make prevention and control challenging. Accurately forecasting malaria outbreaks is essential for effective resource allocation and timely interventions. This study proposes a hybrid predictive modeling framework that combines time-series forecasting, multi-output regression, and conventional regression-based prediction to forecast the incidence of malaria. Environmental variables, past malaria case data, and demographic information from Amhara Region health centers were used to train and validate the models. The multi-output regression approach enables the simultaneous prediction of multiple outcomes, including Plasmodium species-specific cases, temporal trends, and spatial variations, whereas the hybrid framework captures both seasonal patterns and correlations among predictors. The proposed model exhibits higher prediction accuracy than single-method approaches, exposing hidden patterns and providing valuable information to public health authorities. This study provides a valid and repeatable malaria incidence prediction framework that can support evidence-based decision-making, targeted interventions, and resource optimization in endemic areas.

---

### Domain-Specific Agents for Cherenkov Telescope Array Control Software and Gamma-Ray Data Analysis

Authors: Dmitriy Kostunin, Elisa Jones, Vladimir Sotnikov, Valery Sotnikov, Sergo Golovachev, Alexandre Strube
Published: 2025-10-01
Categories: astro-ph.IM, cs.AI
arXiv: https://arxiv.org/abs/2510.01299v3

We present domain-adapted large language model agents designed to support Cherenkov Telescope Array operation and data analysis. The agents combine contextual knowledge with automated validation and iterative correction to produce more reliable outputs. This approach reduces manual effort, improves consistency, and helps accelerate operational and scientific workflows. The results demonstrate the potential of agentic systems as practical assistants in specialized research environments.

---

### MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging

Authors: Berker Demirel, Marco Fumero, Theofanis Karaletsos, Francesco Locatello
Published: 2025-10-01
Categories: q-bio.QM, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.01298v2

Simulating in silico cellular responses to interventions is a promising direction to accelerate high-content image-based assays, critical for advancing drug discovery and gene editing. To support this, we introduce MorphGen, a state-of-the-art diffusion-based generative model for fluorescent microscopy that enables controllable generation across multiple cell types and perturbations. To capture biologically meaningful patterns consistent with known cellular morphologies, MorphGen is trained with an alignment loss to match its representations to the phenotypic embeddings of OpenPhenom, a state-of-the-art biological foundation model. Unlike prior approaches that compress multichannel stains into RGB images -- thus sacrificing organelle-specific detail -- MorphGen generates the complete set of fluorescent channels jointly, preserving per-organelle structures and enabling a fine-grained morphological analysis that is essential for biological interpretation. We demonstrate biological consistency with real images via CellProfiler features, and MorphGen attains an FID score over 35% lower than the prior state-of-the-art MorphoDiff, which only generates RGB images for a single cell type. Code is available at https://github.com/czi-ai/MorphGen.

---

### From 2D to 3D, Deep Learning-based Shape Reconstruction in Magnetic Resonance Imaging: A Review

Authors: Emma McMillian, Abhirup Banerjee, Alfonso Bueno-Orovio
Published: 2025-10-01
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.01296v1

Deep learning-based 3-dimensional (3D) shape reconstruction from 2-dimensional (2D) magnetic resonance imaging (MRI) has become increasingly important in medical disease diagnosis, treatment planning, and computational modeling. This review surveys the methodological landscape of 3D MRI reconstruction, focusing on 4 primary approaches: point cloud, mesh-based, shape-aware, and volumetric models. For each category, we analyze the current state-of-the-art techniques, their methodological foundation, limitations, and applications across anatomical structures. We provide an extensive overview ranging from cardiac to neurological to lung imaging. We also focus on the clinical applicability of models to diseased anatomy, and the influence of their training and testing data. We examine publicly available datasets, computational demands, and evaluation metrics. Finally, we highlight the emerging research directions including multimodal integration and cross-modality frameworks. This review aims to provide researchers with a structured overview of current 3D reconstruction methodologies to identify opportunities for advancing deep learning towards more robust, generalizable, and clinically impactful solutions.

---

### The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation

Authors: Zarreen Reza
Published: 2025-10-01
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.01295v1

As Large Language Models (LLMs) transition from static tools to autonomous agents, traditional evaluation benchmarks that measure performance on downstream tasks are becoming insufficient. These methods fail to capture the emergent social and cognitive dynamics that arise when agents communicate, persuade, and collaborate in interactive environments. To address this gap, we introduce a novel evaluation framework that uses multi-agent debate as a controlled "social laboratory" to discover and quantify these behaviors. In our framework, LLM-based agents, instantiated with distinct personas and incentives, deliberate on a wide range of challenging topics under the supervision of an LLM moderator. Our analysis, enabled by a new suite of psychometric and semantic metrics, reveals several key findings. Across hundreds of debates, we uncover a powerful and robust emergent tendency for agents to seek consensus, consistently reaching high semantic agreement (μ > 0.88) even without explicit instruction and across sensitive topics. We show that assigned personas induce stable, measurable psychometric profiles, particularly in cognitive effort, and that the moderators persona can significantly alter debate outcomes by structuring the environment, a key finding for external AI alignment. This work provides a blueprint for a new class of dynamic, psychometrically grounded evaluation protocols designed for the agentic setting, offering a crucial methodology for understanding and shaping the social behaviors of the next generation of AI agents. We have released the code and results at https://github.com/znreza/multi-agent-LLM-eval-for-debate.

---

### Cyber Academia-Chemical Engineering (CA-ChemE): A Living Digital Town for Self-Directed Research Evolution and Emergent Scientific Discovery

Authors: Zekun Jiang, Chunming Xu, Tianhang Zhou
Published: 2025-10-01
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.01293v1

The rapid advancement of artificial intelligence (AI) has demonstrated substantial potential in chemical engineering, yet existing AI systems remain limited in interdisciplinary collaboration and exploration of uncharted problems. To address these issues, we present the Cyber Academia-Chemical Engineering (CA-ChemE) system, a living digital town that enables self-directed research evolution and emergent scientific discovery through multi-agent collaboration. By integrating domain-specific knowledge bases, knowledge enhancement technologies, and collaboration agents, the system successfully constructs an intelligent ecosystem capable of deep professional reasoning and efficient interdisciplinary collaboration. Our findings demonstrate that knowledge base-enabled enhancement mechanisms improved dialogue quality scores by 10-15% on average across all seven expert agents, fundamentally ensuring technical judgments are grounded in verifiable scientific evidence. However, we observed a critical bottleneck in cross-domain collaboration efficiency, prompting the introduction of a Collaboration Agent (CA) equipped with ontology engineering capabilities. CA's intervention achieved 8.5% improvements for distant-domain expert pairs compared to only 0.8% for domain-proximate pairs - a 10.6-fold difference - unveiling the "diminished collaborative efficiency caused by knowledge-base gaps" effect. This study demonstrates how carefully designed multi-agent architectures can provide a viable pathway toward autonomous scientific discovery in chemical engineering.

---

### Network-Level Vehicle Delay Estimation at Heterogeneous Signalized Intersections

Authors: Xiaobo Ma, Hyunsoo Noh, James Tokishi, Ryan Hatch
Published: 2025-10-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01292v1

Accurate vehicle delay estimation is essential for evaluating the performance of signalized intersections and informing traffic management strategies. Delay reflects congestion levels and affects travel time reliability, fuel use, and emissions. Machine learning (ML) offers a scalable, cost-effective alternative; However, conventional models typically assume that training and testing data follow the same distribution, an assumption that is rarely satisfied in real-world applications. Variations in road geometry, signal timing, and driver behavior across intersections often lead to poor generalization and reduced model accuracy. To address this issue, this study introduces a domain adaptation (DA) framework for estimating vehicle delays across diverse intersections. The framework separates data into source and target domains, extracts key traffic features, and fine-tunes the model using a small, labeled subset from the target domain. A novel DA model, Gradient Boosting with Balanced Weighting (GBBW), reweights source data based on similarity to the target domain, improving adaptability. The framework is tested using data from 57 heterogeneous intersections in Pima County, Arizona. Performance is evaluated against eight state-of-the-art ML regression models and seven instance-based DA methods. Results demonstrate that the GBBW framework provides more accurate and robust delay estimates. This approach supports more reliable traffic signal optimization, congestion management, and performance-based planning. By enhancing model transferability, the framework facilitates broader deployment of machine learning techniques in real-world transportation systems.

---