# Research Papers — 2025-10 · bundle page 183 of 217

> Full-text markdown of papers #9101–9150 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/183
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/182.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/184.md)

### Improved probabilistic regression using diffusion models

Authors: Carlo Kneissl, Christopher Bülte, Philipp Scholl, Gitta Kutyniok
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04583v1

Probabilistic regression models the entire predictive distribution of a response variable, offering richer insights than classical point estimates and directly allowing for uncertainty quantification. While diffusion-based generative models have shown remarkable success in generating complex, high-dimensional data, their usage in general regression tasks often lacks uncertainty-related evaluation and remains limited to domain-specific applications. We propose a novel diffusion-based framework for probabilistic regression that learns predictive distributions in a nonparametric way. More specifically, we propose to model the full distribution of the diffusion noise, enabling adaptation to diverse tasks and enhanced uncertainty quantification. We investigate different noise parameterizations, analyze their trade-offs, and evaluate our framework across a broad range of regression tasks, covering low- and high-dimensional settings. For several experiments, our approach shows superior performance against existing baselines, while delivering calibrated uncertainty estimates, demonstrating its versatility as a tool for probabilistic prediction.

---

### Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Reference

Authors: Dang Anh, Rick Nouwen, Massimo Poesio
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04581v1

Our goal is to study how LLMs represent and interpret plural reference in ambiguous and unambiguous contexts. We ask the following research questions: (1) Do LLMs exhibit human-like preferences in representing plural reference? (2) Are LLMs able to detect ambiguity in plural anaphoric expressions and identify possible referents? To address these questions, we design a set of experiments, examining pronoun production using next-token prediction tasks, pronoun interpretation, and ambiguity detection using different prompting strategies. We then assess how comparable LLMs are to humans in formulating and interpreting plural reference. We find that LLMs are sometimes aware of possible referents of ambiguous pronouns. However, they do not always follow human reference when choosing between interpretations, especially when the possible interpretation is not explicitly mentioned. In addition, they struggle to identify ambiguity without direct instruction. Our findings also reveal inconsistencies in the results across different types of experiments.

---

### Strongly Solving 2048 4x3

Authors: Tomoyuki Kaneko, Shuhei Yamashita
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04580v1

2048 is a stochastic single-player game involving 16 cells on a 4 by 4 grid, where a player chooses a direction among up, down, left, and right to obtain a score by merging two tiles with the same number located in neighboring cells along the chosen direction. This paper presents that a variant 2048-4x3 12 cells on a 4 by 3 board, one row smaller than the original, has been strongly solved. In this variant, the expected score achieved by an optimal strategy is about $50724.26$ for the most common initial states: ones with two tiles of number 2. The numbers of reachable states and afterstates are identified to be $1,152,817,492,752$ and $739,648,886,170$, respectively. The key technique is to partition state space by the sum of tile numbers on a board, which we call the age of a state. An age is invariant between a state and its successive afterstate after any valid action and is increased two or four by stochastic response from the environment. Therefore, we can partition state space by ages and enumerate all (after)states of an age depending only on states with the recent ages. Similarly, we can identify (after)state values by going along with ages in decreasing order.

---

### Busemann Functions in the Wasserstein Space: Existence, Closed-Forms, and Applications to Slicing

Authors: Clément Bonet, Elsa Cazelles, Lucas Drumetz, Nicolas Courty
Published: 2025-10-06
Categories: cs.LG, math.MG, stat.ML
arXiv: https://arxiv.org/abs/2510.04579v2

The Busemann function has recently found much interest in a variety of geometric machine learning problems, as it naturally defines projections onto geodesic rays of Riemannian manifolds and generalizes the notion of hyperplanes. As several sources of data can be conveniently modeled as probability distributions, it is natural to study this function in the Wasserstein space, which carries a rich formal Riemannian structure induced by Optimal Transport metrics. In this work, we investigate the existence and computation of Busemann functions in Wasserstein space, which admits geodesic rays. We establish closed-form expressions in two important cases: one-dimensional distributions and Gaussian measures. These results enable explicit projection schemes for probability distributions on $\mathbb{R}$, which in turn allow us to define novel Sliced-Wasserstein distances over Gaussian mixtures and labeled datasets. We demonstrate the efficiency of those original schemes on synthetic datasets as well as transfer learning problems.

---

### Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers

Authors: Juncheng Wang, Chao Xu, Cheng Yu, Zhe Hu, Haoyu Xie, Guoqi Yu, Lei Shang, Shujun Wang
Published: 2025-10-06
Categories: cs.SD, cs.LG, cs.MM, eess.AS
arXiv: https://arxiv.org/abs/2510.04577v1

While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma underpinning this gap: incorporating more RVQ layers improves audio reconstruction fidelity but exceeds the generation capacity of conventional LMs. To address this, we first analyze RVQ dynamics and uncover two key limitations: 1) orthogonality of features across RVQ layers hinders effective LMs training, and 2) descending semantic richness in tokens from deeper RVQ layers exacerbates exposure bias during autoregressive decoding. Based on these insights, we propose Siren, a novel LM-based framework that employs multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning. Extensive experiments demonstrate that Siren outperforms both existing LM-based and diffusion-based T2A systems, achieving state-of-the-art results. By bridging the representational strengths of LMs with the fidelity demands of audio synthesis, our approach repositions LMs as competitive contenders against diffusion models in T2A tasks. Moreover, by aligning audio representations with linguistic structures, Siren facilitates a promising pathway toward unified multi-modal generation frameworks.

---

### SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator

Authors: Yuhta Takida, Satoshi Hayakawa, Takashi Shibuya, Masaaki Imaizumi, Naoki Murata, Bac Nguyen, Toshimitsu Uesaka, Chieh-Hsin Lai, Yuki Mitsufuji
Published: 2025-10-06
Categories: cs.LG, cs.AI, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2510.04576v1

Deep generative models have made significant advances in generating complex content, yet conditional generation remains a fundamental challenge. Existing conditional generative adversarial networks often struggle to balance the dual objectives of assessing authenticity and conditional alignment of input samples within their conditional discriminators. To address this, we propose a novel discriminator design that integrates three key capabilities: unconditional discrimination, matching-aware supervision to enhance alignment sensitivity, and adaptive weighting to dynamically balance all objectives. Specifically, we introduce Sum of Naturalness and Alignment (SONA), which employs separate projections for naturalness (authenticity) and alignment in the final layer with an inductive bias, supported by dedicated objective functions and an adaptive weighting mechanism. Extensive experiments on class-conditional generation tasks show that \ours achieves superior sample quality and conditional alignment compared to state-of-the-art methods. Furthermore, we demonstrate its effectiveness in text-to-image generation, confirming the versatility and robustness of our approach.

---

### Deep learning framework for predicting stochastic take-off and die-out of early spreading

Authors: Wenchao He, Tao Jia
Published: 2025-10-06
Categories: cs.SI, cs.AI, physics.soc-ph
arXiv: https://arxiv.org/abs/2510.04574v1

Large-scale outbreaks of epidemics, misinformation, or other harmful contagions pose significant threats to human society, yet the fundamental question of whether an emerging outbreak will escalate into a major epidemic or naturally die out remains largely unaddressed. This problem is challenging, partially due to inadequate data during the early stages of outbreaks and also because established models focus on average behaviors of large epidemics rather than the stochastic nature of small transmission chains. Here, we introduce the first systematic framework for forecasting whether initial transmission events will amplify into major outbreaks or fade into extinction during early stages, when intervention strategies can still be effectively implemented. Using extensive data from stochastic spreading models, we developed a deep learning framework that predicts early-stage spreading outcomes in real-time. Validation across Erdős-Rényi and Barabási-Albert networks with varying infectivity levels shows our method accurately forecasts stochastic spreading events well before potential outbreaks, demonstrating robust performance across different network structures and infectivity scenarios.To address the challenge of sparse data during early outbreak stages, we further propose a pretrain-finetune framework that leverages diverse simulation data for pretraining and adapts to specific scenarios through targeted fine-tuning. The pretrain-finetune framework consistently outperforms baseline models, achieving superior performance even when trained on limited scenario-specific data. To our knowledge, this work presents the first framework for predicting stochastic take-off versus die-out. This framework provides valuable insights for epidemic preparedness and public health decision-making, enabling more informed early intervention strategies.

---

### LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning

Authors: Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang, Nicklas Majamaki, Navdeep Jaitly, Yi-An Ma, Lianhui Qin
Published: 2025-10-06
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.04573v6

Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner, which can also lead to inefficient exploration for diverse solutions. In this paper, we propose LaDiR} (Latent Diffusion Reasoner), a novel reasoning framework that unifies the expressiveness of continuous latent representation with the iterative refinement capabilities of latent diffusion models for an existing LLM. We first construct a structured latent reasoning space using a Variational Autoencoder (VAE) that encodes text reasoning steps into blocks of thought tokens, preserving semantic information and interpretability while offering compact but expressive representations. Subsequently, we utilize a latent diffusion model that learns to denoise a block of latent thought tokens with a blockwise bidirectional attention mask, enabling longer horizon and iterative refinement with adaptive test-time compute. This design, combined with explicit diversity guidance during diffusion inference, enables the generation of multiple diverse reasoning trajectories that explore distinct regions of the latent space, rather than producing repetitive solutions as often occurs in standard autoregressive sampling. We conduct evaluations on a suite of mathematical reasoning, code generation and puzzle planning benchmarks. Empirical results show that LaDiR consistently improves accuracy, diversity, and interpretability over existing autoregressive, diffusion-based, and latent reasoning methods, revealing a new paradigm for text reasoning with latent diffusion.

---

### COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context

Authors: Naman Gupta, Shreeyash Gowaikar, Arun Iyer, Kirankumar Shiragur, Ramakrishna B Bairi, Rishikesh Maurya, Ritabrata Maiti, Sankarshan Damle, Shachee Mishra Gupta
Published: 2025-10-06
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.04568v1

Reasoning over very long inputs remains difficult for large language models (LLMs). Common workarounds either shrink the input via retrieval (risking missed evidence), enlarge the context window (straining selectivity), or stage multiple agents to read in pieces. In staged pipelines (e.g., Chain of Agents, CoA), free-form summaries passed between agents can discard crucial details and amplify early mistakes. We introduce COSMIR (Chain Orchestrated Structured Memory for Iterative Reasoning), a chain-style framework that replaces ad hoc messages with a structured memory. A Planner agent first turns a user query into concrete, checkable sub-questions. worker agents process chunks via a fixed micro-cycle: Extract, Infer, Refine, writing all updates to the shared memory. A Manager agent then Synthesizes the final answer directly from the memory. This preserves step-wise read-then-reason benefits while changing both the communication medium (structured memory) and the worker procedure (fixed micro-cycle), yielding higher faithfulness, better long-range aggregation, and auditability. On long-context QA from the HELMET suite, COSMIR reduces propagation-stage information loss and improves accuracy over a CoA baseline.

---

### GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

Authors: Weishuo Ma, Yanbo Wang, Xiyuan Wang, Lei Zou, Muhan Zhang
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04567v3

Graph Neural Networks (GNNs) are powerful tools for processing relational data but often struggle to generalize to unseen graphs, giving rise to the development of Graph Foundational Models (GFMs). However, current GFMs are challenged by the extreme heterogeneity of graph data, where each graph can possess a unique feature space, label set, and topology. To address this, two main paradigms have emerged. The first leverages Large Language Models (LLMs), but is fundamentally text-dependent, thus struggles to handle the numerical features in vast graphs. The second pre-trains a structure-based model, but the adaptation to new tasks typically requires a costly, per-graph tuning stage, creating a critical efficiency bottleneck. In this work, we move beyond these limitations and introduce \textbf{G}raph \textbf{I}n-context \textbf{L}earning \textbf{T}ransformer (GILT), a framework built on an LLM-free and tuning-free architecture. GILT introduces a novel token-based framework for in-context learning (ICL) on graphs, reframing classification tasks spanning node, edge and graph levels in a unified framework. This mechanism is the key to handling heterogeneity, as it is designed to operate on generic numerical features. Further, its ability to understand class semantics dynamically from the context enables tuning-free adaptation. Comprehensive experiments show that GILT achieves stronger few-shot performance with significantly less time than LLM-based or tuning-based baselines, validating the effectiveness of our approach. Our code is available at: https://github.com/yiming421/inductnode/.

---

### Conditional Representation Learning for Customized Tasks

Authors: Honglin Liu, Chao Sun, Peng Hu, Yunfan Li, Xi Peng
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04564v2

Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks. For instance, in animal habitat analysis, researchers prioritize scene-related features, whereas universal embeddings emphasize categorical semantics, leading to suboptimal results. As a solution, existing approaches resort to supervised fine-tuning, which however incurs high computational and annotation costs. In this paper, we propose Conditional Representation Learning (CRL), aiming to extract representations tailored to arbitrary user-specified criteria. Specifically, we reveal that the semantics of a space are determined by its basis, thereby enabling a set of descriptive words to approximate the basis for a customized feature space. Building upon this insight, given a user-specified criterion, CRL first employs a large language model (LLM) to generate descriptive texts to construct the semantic basis, then projects the image representation into this conditional feature space leveraging a vision-language model (VLM). The conditional representation better captures semantics for the specific criterion, which could be utilized for multiple customized tasks. Extensive experiments on classification and retrieval tasks demonstrate the superiority and generality of the proposed CRL. The code is available at https://github.com/XLearning-SCU/2025-NeurIPS-CRL.

---

### Stochastic Approximation Methods for Distortion Risk Measure Optimization

Authors: Jinyang Jiang, Bernd Heidergott, Jiaqiao Hu, Yijie Peng
Published: 2025-10-06
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.04563v1

Distortion Risk Measures (DRMs) capture risk preferences in decision-making and serve as general criteria for managing uncertainty. This paper proposes gradient descent algorithms for DRM optimization based on two dual representations: the Distortion-Measure (DM) form and Quantile-Function (QF) form. The DM-form employs a three-timescale algorithm to track quantiles, compute their gradients, and update decision variables, utilizing the Generalized Likelihood Ratio and kernel-based density estimation. The QF-form provides a simpler two-timescale approach that avoids the need for complex quantile gradient estimation. A hybrid form integrates both approaches, applying the DM-form for robust performance around distortion function jumps and the QF-form for efficiency in smooth regions. Proofs of strong convergence and convergence rates for the proposed algorithms are provided. In particular, the DM-form achieves an optimal rate of $O(k^{-4/7})$, while the QF-form attains a faster rate of $O(k^{-2/3})$. Numerical experiments confirm their effectiveness and demonstrate substantial improvements over baselines in robust portfolio selection tasks. The method's scalability is further illustrated through integration into deep reinforcement learning. Specifically, a DRM-based Proximal Policy Optimization algorithm is developed and applied to multi-echelon dynamic inventory management, showcasing its practical applicability.

---

### ContextNav: Towards Agentic Multimodal In-Context Learning

Authors: Honghao Fu, Yuan Ouyang, Kai-Wei Chang, Yiwei Wang, Zi Huang, Yujun Cai
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04560v1

Recent advances demonstrate that multimodal large language models (MLLMs) exhibit strong multimodal in-context learning (ICL) capabilities, enabling them to adapt to novel vision-language tasks from a few contextual examples. However, existing ICL approaches face challenges in reconciling scalability with robustness across diverse tasks and noisy contextual examples: manually selecting examples produces clean contexts but is labor-intensive and task-specific, while similarity-based retrieval improves scalability but could introduce irrelevant or structurally inconsistent samples that degrade ICL performance. To address these limitations, we propose ContextNav, the first agentic framework that integrates the scalability of automated retrieval with the quality and adaptiveness of human-like curation, enabling noise-robust and dynamically optimized contextualization for multimodal ICL. ContextNav unifies context management and noise-robust contextualization within a closed-loop workflow driven by graph-based orchestration. Specifically, it builds a resource-aware multimodal embedding pipeline, maintains a retrievable vector database, and applies agentic retrieval and structural alignment to construct noise-resilient contexts. An Operational Grammar Graph (OGG) further supports adaptive workflow planning and optimization, enabling the agent to refine its operational strategies based on downstream ICL feedback. Experimental results demonstrate that ContextNav achieves state-of-the-art performance across various datasets, underscoring the promise of agentic workflows for advancing scalable and robust contextualization in multimodal ICL.

---

### Challenger-Based Combinatorial Bandits for Subcarrier Selection in OFDM Systems

Authors: Mohsen Amiri, V Venktesh, Sindri Magnússon
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04559v1

This paper investigates the identification of the top-m user-scheduling sets in multi-user MIMO downlink, which is cast as a combinatorial pure-exploration problem in stochastic linear bandits. Because the action space grows exponentially, exhaustive search is infeasible. We therefore adopt a linear utility model to enable efficient exploration and reliable selection of promising user subsets. We introduce a gap-index framework that maintains a shortlist of current estimates of champion arms (top-m sets) and a rotating shortlist of challenger arms that pose the greatest threat to the champions. This design focuses on measurements that yield the most informative gap-index-based comparisons, resulting in significant reductions in runtime and computation compared to state-of-the-art linear bandit methods, with high identification accuracy. The method also exposes a tunable trade-off between speed and accuracy. Simulations on a realistic OFDM downlink show that shortlist-driven pure exploration makes online, measurement-efficient subcarrier selection practical for AI-enabled communication systems.

---

### Model Monitoring: A General Framework with an Application to Non-life Insurance Pricing

Authors: Alexej Brauer, Paul Menzel, Mario V. Wüthrich
Published: 2025-10-06
Categories: stat.ML, cs.LG, math.ST, q-fin.ST, stat.AP
arXiv: https://arxiv.org/abs/2510.04556v2

Maintaining the predictive performance of pricing models is challenging when insurance portfolios and data-generating mechanisms evolve over time. Focusing on non-life insurance, we adopt the concept-drift terminology from machine learning and distinguish virtual drift from real concept drift in an actuarial setting. Methodologically, we (i) formalize deviance loss and Murphy's score decomposition to assess global and local auto-calibration; (ii) study the Gini score as a rank-based performance measure, derive its asymptotic distribution, and develop a consistent bootstrap estimator of its asymptotic variance; and (iii) combine these results into a statistically grounded, model-agnostic monitoring framework that integrates a Gini-based ranking drift test with global and local auto-calibration tests. An application to a modified motor insurance portfolio with controlled concept-drift scenarios illustrates how the framework guides decisions on refitting or recalibrating pricing models.

---

### Tail-Safe Hedging: Explainable Risk-Sensitive Reinforcement Learning with a White-Box CBF--QP Safety Layer in Arbitrage-Free Markets

Authors: Jian'an Zhang
Published: 2025-10-06
Categories: cs.LG, q-fin.TR
arXiv: https://arxiv.org/abs/2510.04555v1

We introduce Tail-Safe, a deployability-oriented framework for derivatives hedging that unifies distributional, risk-sensitive reinforcement learning with a white-box control-barrier-function (CBF) quadratic-program (QP) safety layer tailored to financial constraints. The learning component combines an IQN-based distributional critic with a CVaR objective (IQN--CVaR--PPO) and a Tail-Coverage Controller that regulates quantile sampling through temperature tilting and tail boosting to stabilize small-$α$ estimation. The safety component enforces discrete-time CBF inequalities together with domain-specific constraints -- ellipsoidal no-trade bands, box and rate limits, and a sign-consistency gate -- solved as a convex QP whose telemetry (active sets, tightness, rate utilization, gate scores, slack, and solver status) forms an auditable trail for governance. We provide guarantees of robust forward invariance of the safe set under bounded model mismatch, a minimal-deviation projection interpretation of the QP, a KL-to-DRO upper bound linking per-state KL regularization to worst-case CVaR, concentration and sample-complexity results for the temperature-tilted CVaR estimator, and a CVaR trust-region improvement inequality under KL limits, together with feasibility persistence under expiry-aware tightening. Empirically, in arbitrage-free, microstructure-aware synthetic markets (SSVI $\to$ Dupire $\to$ VIX with ABIDES/MockLOB execution), Tail-Safe improves left-tail risk without degrading central performance and yields zero hard-constraint violations whenever the QP is feasible with zero slack. Telemetry is mapped to governance dashboards and incident workflows to support explainability and auditability. Limitations include reliance on synthetic data and simplified execution to isolate methodological contributions.

---

### Fast Witness Persistence for MRI Volumes via Hybrid Landmarking

Authors: Jorge Leonardo Ruiz Williams
Published: 2025-10-06
Categories: cs.CG, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.04553v1

We introduce a scalable witness-based persistent homology pipeline for full-brain MRI volumes that couples density-aware landmark selection with a GPU-ready witness filtration. Candidates are scored by a hybrid metric that balances geometric coverage against inverse kernel density, yielding landmark sets that shrink mean pairwise distances by 30-60% over random or density-only baselines while preserving topological features. Benchmarks on BrainWeb, IXI, and synthetic manifolds execute in under ten seconds on a single NVIDIA RTX 4090 GPU, avoiding the combinatorial blow-up of Cech, Vietoris-Rips, and alpha filtrations. The package is distributed on PyPI as whale-tda (installable via pip); source and issues are hosted at https://github.com/jorgeLRW/whale. The release also exposes a fast preset (mri_deep_dive_fast) for exploratory sweeps, and ships with reproducibility-focused scripts and artifacts for drop-in use in medical imaging workflows.

---

### Fine-grained auxiliary learning for real-world product recommendation

Authors: Mario Almagro, Diego Ortego, David Jimenez
Published: 2025-10-06
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.04551v1

Product recommendation is the task of recovering the closest items to a given query within a large product corpora. Generally, one can determine if top-ranked products are related to the query by applying a similarity threshold; exceeding it deems the product relevant, otherwise manual revision is required. Despite being a well-known problem, the integration of these models in real-world systems is often overlooked. In particular, production systems have strong coverage requirements, i.e., a high proportion of recommendations must be automated. In this paper we propose ALC , an Auxiliary Learning strategy that boosts Coverage through learning fine-grained embeddings. Concretely, we introduce two training objectives that leverage the hardest negatives in the batch to build discriminative training signals between positives and negatives. We validate ALC using three extreme multi-label classification approaches in two product recommendation datasets; LF-AmazonTitles-131K and Tech and Durables (proprietary), demonstrating state-of-the-art coverage rates when combined with a recent threshold-consistent margin loss.

---

### TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use

Authors: Pengfei He, Zhenwei Dai, Bing He, Hui Liu, Xianfeng Tang, Hanqing Lu, Juanhui Li, Jiayuan Ding, Subhabrata Mukherjee, Suhang Wang, Yue Xing, Jiliang Tang et al.
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04550v2

Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks. While existing works evaluate the LLMs' tool use capability, they largely focus on the final answers yet overlook the detailed tool usage trajectory, i.e., whether tools are selected, parameterized, and ordered correctly. We introduce TRAJECT-Bench, a trajectory-aware benchmark to comprehensively evaluate LLMs' tool use capability through diverse tasks with fine-grained evaluation metrics. TRAJECT-Bench pairs high-fidelity, executable tools across practical domains with tasks grounded in production-style APIs, and synthesizes trajectories that vary in breadth (parallel calls) and depth (interdependent chains). Besides final accuracy, TRAJECT-Bench also reports trajectory-level diagnostics, including tool selection and argument correctness, and dependency/order satisfaction. Analyses reveal failure modes such as similar tool confusion and parameter-blind selection, and scaling behavior with tool diversity and trajectory length where the bottleneck of transiting from short to mid-length trajectories is revealed, offering actionable guidance for LLMs' tool use.

---

### Learning Linear Regression with Low-Rank Tasks in-Context

Authors: Kaito Takanami, Takashi Takahashi, Yoshiyuki Kabashima
Published: 2025-10-06
Categories: cond-mat.dis-nn, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.04548v2

In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL operates in real-world applications where tasks have a common structure. In this work, we address this problem by analyzing a linear attention model trained on low-rank regression tasks. Within this setting, we precisely characterize the distribution of predictions and the generalization error in the high-dimensional limit. Moreover, we find that statistical fluctuations in finite pre-training data induce an implicit regularization. Finally, we identify a sharp phase transition of the generalization error governed by task structure. These results provide a framework for understanding how transformers learn to learn the task structure.

---

### Activation Quantization of Vision Encoders Needs Prefixing Registers

Authors: Seunghyeon Kim, Taesun Yeom, Jinho Kim, Wonpyo Park, Kyuyeun Kim, Jaeho Lee
Published: 2025-10-06
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.04547v5

Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models. Since these applications often demand real-time processing of massive visual data, reducing the inference cost of vision encoders is critical. Quantization offers a practical path, but it remains challenging even at 8-bit precision due to so-called outliers. In this work, we propose $\textit{RegCache}$, a training-free algorithm that mitigates outliers in large-scale pretrained vision encoders and serves as a plug-in module that can be applied on top of other quantization methods. RegCache introduces outlier-prone yet semantically meaningless prefix tokens to the vision encoder, which prevent other tokens from having outliers. Notably, we observe that outliers in vision encoders behave differently from those in language models, motivating two technical innovations: middle-layer prefixing and token deletion. Experimental results show that our method consistently improves quantized model performance across various vision encoders, particularly in extremely low-bit regimes (e.g., 4-bit).

---

### The Role of Feature Interactions in Graph-based Tabular Deep Learning

Authors: Elias Dubbeldam, Reza Mohammadi, Marit Schoonhoven, S. Ilker Birbil
Published: 2025-10-06
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.04543v2

Accurate predictions on tabular data rely on capturing complex, dataset-specific feature interactions. Attention-based methods and graph neural networks, referred to as graph-based tabular deep learning (GTDL), aim to improve predictions by modeling these interactions as a graph. In this work, we analyze how these methods model the feature interactions. Current GTDL approaches primarily focus on optimizing predictive accuracy, often neglecting the accurate modeling of the underlying graph structure. Using synthetic datasets with known ground-truth graph structures, we find that current GTDL methods fail to recover meaningful feature interactions, as their edge recovery is close to random. This suggests that the attention mechanism and message-passing schemes used in GTDL do not effectively capture feature interactions. Furthermore, when we impose the true interaction structure, we find that the predictive accuracy improves. This highlights the need for GTDL methods to prioritize accurate modeling of the graph structure, as it leads to better predictions.

---

### Code World Models for General Game Playing

Authors: Wolfgang Lehrach, Daniel Hennes, Miguel Lazaro-Gredilla, Xinghua Lou, Carter Wendelken, Zun Li, Antoine Dedieu, Jordi Grau-Moya, Marc Lanctot, Atil Iscen, John Schultz, Marcus Chiam et al.
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04542v1

Large Language Models (LLMs) reasoning abilities are increasingly being applied to classical board and card games, but the dominant approach -- involving prompting for direct move generation -- has significant drawbacks. It relies on the model's implicit fragile pattern-matching capabilities, leading to frequent illegal moves and strategically shallow play. Here we introduce an alternative approach: We use the LLM to translate natural language rules and game trajectories into a formal, executable world model represented as Python code. This generated model -- comprising functions for state transition, legal move enumeration, and termination checks -- serves as a verifiable simulation engine for high-performance planning algorithms like Monte Carlo tree search (MCTS). In addition, we prompt the LLM to generate heuristic value functions (to make MCTS more efficient), and inference functions (to estimate hidden states in imperfect information games). Our method offers three distinct advantages compared to directly using the LLM as a policy: (1) Verifiability: The generated CWM serves as a formal specification of the game's rules, allowing planners to algorithmically enumerate valid actions and avoid illegal moves, contingent on the correctness of the synthesized model; (2) Strategic Depth: We combine LLM semantic understanding with the deep search power of classical planners; and (3) Generalization: We direct the LLM to focus on the meta-task of data-to-code translation, enabling it to adapt to new games more easily. We evaluate our agent on 10 different games, of which 4 are novel and created for this paper. 5 of the games are fully observed (perfect information), and 5 are partially observed (imperfect information). We find that our method outperforms or matches Gemini 2.5 Pro in 9 out of the 10 considered games.

---

### C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editing

Authors: Zeng Tao, Zheng Ding, Zeyuan Chen, Xiang Zhang, Leizhi Li, Zhuowen Tu
Published: 2025-10-06
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2510.04539v2

Existing 2D-lifting-based 3D editing methods often encounter challenges related to inconsistency, stemming from the lack of view-consistent 2D editing models and the difficulty of ensuring consistent editing across multiple views. To address these issues, we propose C3Editor, a controllable and consistent 2D-lifting-based 3D editing framework. Given an original 3D representation and a text-based editing prompt, our method selectively establishes a view-consistent 2D editing model to achieve superior 3D editing results. The process begins with the controlled selection of a ground truth (GT) view and its corresponding edited image as the optimization target, allowing for user-defined manual edits. Next, we fine-tune the 2D editing model within the GT view and across multiple views to align with the GT-edited image while ensuring multi-view consistency. To meet the distinct requirements of GT view fitting and multi-view consistency, we introduce separate LoRA modules for targeted fine-tuning. Our approach delivers more consistent and controllable 2D and 3D editing results than existing 2D-lifting-based methods, outperforming them in both qualitative and quantitative evaluations.

---

### 3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG

Authors: Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Satoshi Ohshima, Takahiro Katagiri
Published: 2025-10-06
Categories: cs.GR, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.04536v1

This paper proposes "3Dify," a procedural 3D computer graphics (3D-CG) generation framework utilizing Large Language Models (LLMs). The framework enables users to generate 3D-CG content solely through natural language instructions. 3Dify is built upon Dify, an open-source platform for AI application development, and incorporates several state-of-the-art LLM-related technologies such as the Model Context Protocol (MCP) and Retrieval-Augmented Generation (RAG). For 3D-CG generation support, 3Dify automates the operation of various Digital Content Creation (DCC) tools via MCP. When DCC tools do not support MCP-based interaction, the framework employs the Computer-Using Agent (CUA) method to automate Graphical User Interface (GUI) operations. Moreover, to enhance image generation quality, 3Dify allows users to provide feedback by selecting preferred images from multiple candidates. The LLM then learns variable patterns from these selections and applies them to subsequent generations. Furthermore, 3Dify supports the integration of locally deployed LLMs, enabling users to utilize custom-developed models and to reduce both time and monetary costs associated with external API calls by leveraging their own computational resources.

---

### TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

Authors: Hyunmin Cho, Donghoon Ahn, Susung Hong, Jee Eun Kim, Seungryong Kim, Kyong Hwan Jin
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04533v2

Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time guidance methods rely on external signals or architectural modifications, adding computational overhead. We propose $\mathbf{T}$angential $\mathbf{A}$mplifying $\mathbf{G}$uidance $\mathbf{(TAG)}$, a training-free, architecture-agnostic, plug-and-play guidance method that operates purely on trajectory signals. TAG uses an intermediate sample as a projection basis and amplifies the tangential components of the estimated score to correct the sampling trajectory. A first-order Taylor analysis shows that this steers the state toward higher-probability regions of the data manifold, reducing inconsistencies and improving fidelity while adding negligible overhead to existing samplers. Code is available at our Project Page (https://hyeon-cho.github.io/TAG/).

---

### More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models

Authors: Xurui Song, Shuo Huai, JingJing Jiang, Jiayi Kong, Jun Luo
Published: 2025-10-06
Categories: cs.AI, cs.CL, cs.RO
arXiv: https://arxiv.org/abs/2510.04532v2

Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, whether planning is causally driven by this reasoning remains a critical but unverified assumption. To investigate this, we build DriveMind, a large-scale driving Visual Question Answering corpus with plan-aligned Chain-of-Thought (CoT), automatically generated from nuPlan. Our data generation process converts sensors and annotations into structured inputs and, crucially, separates priors from to-be-reasoned signals, enabling clean information ablations. Using DriveMind, we train representative VLM agents with Supervised Fine-Tuning and Group Relative Policy Optimization and evaluate them with nuPlan's metrics. Our results, unfortunately, indicate a consistent causal disconnect in reasoning-planning: removing ego/navigation priors causes large drops in planning scores, whereas removing CoT produces only minor changes. Attention analysis further shows that planning primarily focuses on priors rather than the CoT. Based on this evidence, we propose the Reasoning-Planning Decoupling Hypothesis, positing that the training-yielded reasoning is an ancillary byproduct rather than a causal mediator. To enable efficient diagnosis, we introduce a novel, training-free probe that measures an agent's reliance on priors by evaluating its planning robustness against minor input perturbations. In summary, we provide the community with a new dataset and a diagnostic tool to evaluate the causal fidelity of future models.

---

### Unified Threat Detection and Mitigation Framework (UTDMF): Combating Prompt Injection, Deception, and Bias in Enterprise-Scale Transformers

Authors: Santhosh KumarRavindran
Published: 2025-10-06
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.04528v1

The rapid adoption of large language models (LLMs) in enterprise systems exposes vulnerabilities to prompt injection attacks, strategic deception, and biased outputs, threatening security, trust, and fairness. Extending our adversarial activation patching framework (arXiv:2507.09406), which induced deception in toy networks at a 23.9% rate, we introduce the Unified Threat Detection and Mitigation Framework (UTDMF), a scalable, real-time pipeline for enterprise-grade models like Llama-3.1 (405B), GPT-4o, and Claude-3.5. Through 700+ experiments per model, UTDMF achieves: (1) 92% detection accuracy for prompt injection (e.g., jailbreaking); (2) 65% reduction in deceptive outputs via enhanced patching; and (3) 78% improvement in fairness metrics (e.g., demographic bias). Novel contributions include a generalized patching algorithm for multi-threat detection, three groundbreaking hypotheses on threat interactions (e.g., threat chaining in enterprise workflows), and a deployment-ready toolkit with APIs for enterprise integration.

---

### Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion

Authors: Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
Published: 2025-10-06
Categories: cs.LG, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2510.04525v3

Masked diffusion models have shown promising performance in generating high-quality samples in a wide range of domains, but accelerating their sampling process remains relatively underexplored. To investigate efficient samplers for masked diffusion, this paper theoretically analyzes the MaskGIT sampler for image modeling, revealing its implicit temperature sampling mechanism. Through this analysis, we show that MaskGIT is asymptotically equivalent to a choose-then-sample (CTS) formulation, instantiated as the "moment sampler," which explicitly separates index selection from token sampling. This CTS reformulation is essential: it yields unbiased token sampling and exposes an algorithmic design space for index selection, both of which are inaccessible in MaskGIT's original formulation. Regarding token sampling, we reveal that MaskGIT implicitly adopts a low-temperature sampler, which explains why MaskGIT often degrades with more sampling steps. The CTS reformulation of MaskGIT allows us to fix the temperature sampling to ensure unbiasedness. We also improve the index selection in CTS through two key innovations: a partial caching technique for transformers that approximates longer sampling trajectories without proportional computational cost, and a hybrid approach formalizing the exploration-exploitation trade-off in adaptive unmasking. Experiments in image and text domains demonstrate our theory as well as the efficiency of our proposed methods, advancing both theoretical understanding and practical implementation of masked diffusion samplers.

---

### Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction

Authors: Yisen Gao, Xingcheng Fu, Qingyun Sun, Jianxin Li, Xianxian Li
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04522v2

Graph diffusion models have made significant progress in learning structured graph data and have demonstrated strong potential for predictive tasks. Existing approaches typically embed node, edge, and graph-level features into a unified latent space, modeling prediction tasks including classification and regression as a form of conditional generation. However, due to the non-Euclidean nature of graph data, features of different curvatures are entangled in the same latent space without releasing their geometric potential. To address this issue, we aim to construt an ideal Riemannian diffusion model to capture distinct manifold signatures of complex graph data and learn their distribution. This goal faces two challenges: numerical instability caused by exponential mapping during the encoding proces and manifold deviation during diffusion generation. To address these challenges, we propose GeoMancer: a novel Riemannian graph diffusion framework for both generation and prediction tasks. To mitigate numerical instability, we replace exponential mapping with an isometric-invariant Riemannian gyrokernel approach and decouple multi-level features onto their respective task-specific manifolds to learn optimal representations. To address manifold deviation, we introduce a manifold-constrained diffusion method and a self-guided strategy for unconditional generation, ensuring that the generated data remains aligned with the manifold signature. Extensive experiments validate the effectiveness of our approach, demonstrating superior performance across a variety of tasks.

---

### Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph

Authors: Hanyu Wang, Ruohan Xie, Yutong Wang, Guoxiong Gao, Xintao Yu, Bin Dong
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04520v2

Accurate auto-formalization of theorem statements is essential for advancing automated discovery and verification of research-level mathematics, yet remains a major bottleneck for LLMs due to hallucinations, semantic mismatches, and their inability to synthesize new definitions. To tackle these issues, we present Aria (Agent for Retrieval and Iterative Autoformalization), a system for conjecture-level formalization in Lean that emulates human expert reasoning via a two-phase Graph-of-Thought process: recursively decomposing statements into a dependency graph and then constructing formalizations from grounded concepts. To ensure semantic correctness, we introduce AriaScorer, a checker that retrieves definitions from Mathlib for term-level grounding, enabling rigorous and reliable verification. We evaluate Aria on diverse benchmarks. On ProofNet, it achieves 91.6% compilation success rate and 68.5% final accuracy, surpassing previous methods. On FATE-X, a suite of challenging algebra problems from research literature, it outperforms the best baseline with 44.0% vs. 24.0% final accuracy. On a dataset of homological conjectures, Aria reaches 42.9% final accuracy while all other models score 0%.

---

### ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering

Authors: Rachneet Kaur, Nishan Srishankar, Zhen Zeng, Sumitra Ganesh, Manuela Veloso
Published: 2025-10-06
Categories: cs.AI, cs.CE, cs.CL, cs.CV, stat.ME
arXiv: https://arxiv.org/abs/2510.04514v3

Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts. To address this, we introduce ChartAgent, a novel agentic framework that explicitly performs visual reasoning directly within the chart's spatial domain. Unlike textual chain-of-thought reasoning, ChartAgent iteratively decomposes queries into visual subtasks and actively manipulates and interacts with chart images through specialized actions such as drawing annotations, cropping regions (e.g., segmenting pie slices, isolating bars), and localizing axes, using a library of chart-specific vision tools to fulfill each subtask. This iterative reasoning process closely mirrors human cognitive strategies for chart comprehension. ChartAgent achieves state-of-the-art accuracy on the ChartBench and ChartX benchmarks, surpassing prior methods by up to 16.07% absolute gain overall and 17.31% on unannotated, numerically intensive queries. Furthermore, our analyses show that ChartAgent is (a) effective across diverse chart types, (b) achieves the highest scores across varying visual and reasoning complexity levels, and (c) serves as a plug-and-play framework that boosts performance across diverse underlying LLMs. Our work is among the first to demonstrate visually grounded reasoning for chart understanding using tool-augmented multimodal agents.

---

### Quantum generative model on bicycle-sharing system and an application

Authors: Fumio Nemoto, Nobuyuki Koike, Daichi Sato, Yuuta Kawaai, Masayuki Ohzeki
Published: 2025-10-06
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.04512v2

Recently, bicycle-sharing systems have been implemented in numerous cities, becoming integral to daily life. However, a prevalent issue arises when intensive commuting demand leads to bicycle shortages in specific areas and at particular times. To address this challenge, we employ a novel quantum machine learning model that analyzes time series data by fitting quantum time evolution to observed sequences. This model enables us to capture actual trends in bicycle counts at individual ports and identify correlations between different ports. Utilizing the trained model, we simulate the impact of proactively adding bicycles to high-demand ports on the overall rental number across the system. Given that the core of this method lies in a Monte Carlo simulation, it is anticipated to have a wide range of industrial applications.

---

### Real-time Prediction of Urban Sound Propagation with Conditioned Normalizing Flows

Authors: Achim Eckerle, Martin Spitznagel, Janis Keuper
Published: 2025-10-06
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.04510v1

Accurate and fast urban noise prediction is pivotal for public health and for regulatory workflows in cities, where the Environmental Noise Directive mandates regular strategic noise maps and action plans, often needed in permission workflows, right-of-way allocation, and construction scheduling. Physics-based solvers are too slow for such time-critical, iterative "what-if" studies. We evaluate conditional Normalizing Flows (Full-Glow) for generating for generating standards-compliant urban sound-pressure maps from 2D urban layouts in real time per 256x256 map on a single RTX 4090), enabling interactive exploration directly on commodity hardware. On datasets covering Baseline, Diffraction, and Reflection regimes, our model accelerates map generation by >2000 times over a reference solver while improving NLoS accuracy by up to 24% versus prior deep models; in Baseline NLoS we reach 0.65 dB MAE with high structural fidelity. The model reproduces diffraction and interference patterns and supports instant recomputation under source or geometry changes, making it a practical engine for urban planning, compliance mapping, and operations (e.g., temporary road closures, night-work variance assessments).

---

### Wavelet Predictive Representations for Non-Stationary Reinforcement Learning

Authors: Min Wang, Xin Li, Ye He, Yao-Hui Li, Hasnaa Bennis, Riashat Islam, Mingzhong Wang
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04507v1

The real world is inherently non-stationary, with ever-changing factors, such as weather conditions and traffic flows, making it challenging for agents to adapt to varying environmental dynamics. Non-Stationary Reinforcement Learning (NSRL) addresses this challenge by training agents to adapt rapidly to sequences of distinct Markov Decision Processes (MDPs). However, existing NSRL approaches often focus on tasks with regularly evolving patterns, leading to limited adaptability in highly dynamic settings. Inspired by the success of Wavelet analysis in time series modeling, specifically its ability to capture signal trends at multiple scales, we propose WISDOM to leverage wavelet-domain predictive task representations to enhance NSRL. WISDOM captures these multi-scale features in evolving MDP sequences by transforming task representation sequences into the wavelet domain, where wavelet coefficients represent both global trends and fine-grained variations of non-stationary changes. In addition to the auto-regressive modeling commonly employed in time series forecasting, we devise a wavelet temporal difference (TD) update operator to enhance tracking and prediction of MDP evolution. We theoretically prove the convergence of this operator and demonstrate policy improvement with wavelet task representations. Experiments on diverse benchmarks show that WISDOM significantly outperforms existing baselines in both sample efficiency and asymptotic performance, demonstrating its remarkable adaptability in complex environments characterized by non-stationary and stochastically evolving tasks.

---

### GRACE: Generative Representation Learning via Contrastive Policy Optimization

Authors: Jiashuo Sun, Shixuan Liu, Zhaochen Su, Xianrui Zhong, Pengcheng Jiang, Bowen Jin, Peiran Li, Weijia Shi, Jiawei Han
Published: 2025-10-06
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.04506v1

Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and reasoning capabilities in favor of static embeddings. We introduce GRACE (Generative Representation Learning via Contrastive Policy Optimization), a novel framework that reimagines contrastive signals not as losses to be minimized, but as rewards that guide a generative policy. In GRACE, the LLM acts as a policy that produces explicit, human-interpretable rationales--structured natural language explanations of its semantic understanding. These rationales are then encoded into high-quality embeddings via mean pooling. Using policy gradient optimization, we train the model with a multi-component reward function that maximizes similarity between query positive pairs and minimizes similarity with negatives. This transforms the LLM from an opaque encoder into an interpretable agent whose reasoning process is transparent and inspectable. On MTEB benchmark, GRACE yields broad cross category gains: averaged over four backbones, the supervised setting improves overall score by 11.5% over base models, and the unsupervised variant adds 6.9%, while preserving general capabilities. This work treats contrastive objectives as rewards over rationales, unifying representation learning with generation to produce stronger embeddings and transparent rationales. The model, data and code are available at https://github.com/GasolSun36/GRACE.

---

### Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation

Authors: Zijing Hu, Yunze Tong, Fengda Zhang, Junkun Yuan, Jun Xiao, Kun Kuang
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04504v2

Diffusion models have achieved impressive results in generating high-quality images. Yet, they often struggle to faithfully align the generated images with the input prompts. This limitation is associated with synchronous denoising, where all pixels simultaneously evolve from random noise to clear images. As a result, during generation, the prompt-related regions can only reference the unrelated regions at the same noise level, failing to obtain clear context and ultimately impairing text-to-image alignment. To address this issue, we propose asynchronous diffusion models -- a novel framework that allocates distinct timesteps to different pixels and reformulates the pixel-wise denoising process. By dynamically modulating the timestep schedules of individual pixels, prompt-related regions are denoised more gradually than unrelated regions, thereby allowing them to leverage clearer inter-pixel context. Consequently, these prompt-related regions achieve better alignment in the final images. Extensive experiments demonstrate that our asynchronous diffusion models can significantly improve text-to-image alignment across diverse prompts. The code repository for this work is available at https://github.com/hu-zijing/AsynDM.

---

### P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs

Authors: Shuai Zhao, Xinyi Wu, Shiqian Zhao, Xiaobao Wu, Zhongliang Guo, Yanhao Jia, Anh Tuan Luu
Published: 2025-10-06
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.04503v2

During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited generalization: they only work on specific attack types or task settings. In this study, we propose Poison-to-Poison (P2P), a general and effective backdoor defense algorithm. P2P injects benign triggers with safe alternative labels into a subset of training samples and fine-tunes the model on this re-poisoned dataset by leveraging prompt-based learning. This enforces the model to associate trigger-induced representations with safe outputs, thereby overriding the effects of original malicious triggers. Thanks to this robust and generalizable trigger-based fine-tuning, P2P is effective across task settings and attack types. Theoretically and empirically, we show that P2P can neutralize malicious backdoors while preserving task performance. We conduct extensive experiments on classification, mathematical reasoning, and summary generation tasks, involving multiple state-of-the-art LLMs. The results demonstrate that our P2P algorithm significantly reduces the attack success rate compared with baseline models. We hope that the P2P can serve as a guideline for defending against backdoor attacks and foster the development of a secure and trustworthy LLM community.

---

### Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation

Authors: Yue Que, Yingyi Zhang, Xiangyu Zhao, Chen Ma
Published: 2025-10-06
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.04502v1

Graph-based recommender systems leverage neighborhood aggregation to generate node representations, which is highly sensitive to popularity bias, resulting in an echo effect during information propagation. Existing graph-based debiasing solutions refine the aggregation process with attempts such as edge reconstruction or weight adjustment. However, these methods remain inadequate in fully alleviating popularity bias. Specifically, this is because 1) they provide no insights into graph aggregation rationality, thus lacking an optimality guarantee; 2) they fail to well balance the training and debiasing process, which undermines the effectiveness. In this paper, we propose a novel approach to mitigate popularity bias through rational modeling of the graph aggregation process. We reveal that graph aggregation is a special form of backdoor adjustment in causal inference, where the aggregation weight corresponds to the historical interaction likelihood distribution. Based on this insight, we devise an encoder-decoder architecture, namely Causality-aware Graph Aggregation Weight Estimator for Debiasing (CAGED), to approximate the unbiased aggregation weight by optimizing the evidence lower bound of the interaction likelihood. In order to enhance the debiasing effectiveness during early training stages, we further design a momentum update strategy that incrementally refines the aggregation weight matrix. Extensive experiments on three datasets demonstrate that CAGED outperforms existing graph-based debiasing methods. Our implementation is available at https://github.com/QueYork/CAGED.

---

### Expand Neurons, Not Parameters

Authors: Linghao Kong, Inimai Subramanian, Yonadav Shavit, Micah Adler, Dan Alistarh, Nir Shavit
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04500v3

This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves performance. We show that this gain corresponds with a decrease in interference between multiple features that would otherwise share the same neurons. On symbolic Boolean tasks, splitting each neuron into sparser sub-neurons with knowledge of the clauses systematically reduces polysemanticity metrics and yields higher task accuracy. Notably, even random splits of neuron weights approximate these gains, indicating that reduced collisions, not precise assignment, are a primary driver. Consistent with the superposition hypothesis, the benefits of this framework grow with increasing interference: when polysemantic load is high, accuracy improvements are the largest. Transferring these insights to more realistic models, including classifiers over CLIP embeddings, convolutional neural networks, and deeper multilayer networks, we find that widening networks while maintaining a constant non-zero parameter count consistently increases accuracy. These results identify an interpretability-grounded mechanism to leverage width against superposition, improving performance without increasing the number of non-zero parameters. Such a direction is well matched to modern accelerators, where memory movement of non-zero parameters, rather than raw compute, is often a dominant bottleneck.

---

### GenQuest: An LLM-based Text Adventure Game for Language Learners

Authors: Qiao Wang, Adnan Labib, Robert Swier, Michael Hofmeyr, Zheng Yuan
Published: 2025-10-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.04498v1

GenQuest is a generative text adventure game that leverages Large Language Models (LLMs) to facilitate second language learning through immersive, interactive storytelling. The system engages English as a Foreign Language (EFL) learners in a collaborative "choose-your-own-adventure" style narrative, dynamically generated in response to learner choices. Game mechanics such as branching decision points and story milestones are incorporated to maintain narrative coherence while allowing learner-driven plot development. Key pedagogical features include content generation tailored to each learner's proficiency level, and a vocabulary assistant that provides in-context explanations of learner-queried text strings, ranging from words and phrases to sentences. Findings from a pilot study with university EFL students in China indicate promising vocabulary gains and positive user perceptions. Also discussed are suggestions from participants regarding the narrative length and quality, and the request for multi-modal content such as illustrations.

---

### Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents

Authors: Muyu He, Anand Kumar, Tsach Mackey, Meghana Rajeev, James Zou, Nazneen Rajani
Published: 2025-10-06
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.04491v3

Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more impatient, incoherent, or skeptical, can cause sharp drops in agent performance, revealing how brittle current AI agents are. Today's benchmarks fail to capture this fragility: agents may perform well under standard evaluations but degrade spectacularly in more realistic and varied settings. We address this robustness testing gap by introducing TraitBasis, a lightweight, model-agnostic method for systematically stress testing AI agents. TraitBasis learns directions in activation space corresponding to steerable user traits (e.g., impatience or incoherence), which can be controlled, scaled, composed, and applied at inference time without any fine-tuning or extra data. Using TraitBasis, we extend $τ$-Bench to $τ$-Trait, where user behaviors are altered via controlled trait vectors. We observe on average a 2%-30% performance degradation on $τ$-Trait across frontier models, highlighting the lack of robustness of current AI agents to variations in user behavior. Together, these results highlight both the critical role of robustness testing and the promise of TraitBasis as a simple, data-efficient, and compositional tool. By powering simulation-driven stress tests and training loops, TraitBasis opens the door to building AI agents that remain reliable in the unpredictable dynamics of real-world human interactions. We have open-sourced $τ$-Trai across four domains: airline, retail, telecom, and telehealth, so the community can systematically QA their agents under realistic, behaviorally diverse intents and trait scenarios: https://github.com/collinear-ai/tau-trait.

---

### Deep vs. Shallow: Benchmarking Physics-Informed Neural Architectures on the Biharmonic Equation

Authors: Akshay Govind Srinivasan, Vikas Dwivedi, Balaji Srinivasan
Published: 2025-10-06
Categories: cs.CE, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2510.04490v1

Partial differential equation (PDE) solvers are fundamental to engineering simulation. Classical mesh-based approaches (finite difference/volume/element) are fast and accurate on high-quality meshes but struggle with higher-order operators and complex, hard-to-mesh geometries. Recently developed physics-informed neural networks (PINNs) and their variants are mesh-free and flexible, yet compute-intensive and often less accurate. This paper systematically benchmarks RBF-PIELM, a rapid PINN variant-an extreme learning machine with radial-basis activations-for higher-order PDEs. RBF-PIELM replaces PINNs' time-consuming gradient descent with a single-shot least-squares solve. We test RBF-PIELM on the fourth-order biharmonic equation using two benchmarks: lid-driven cavity flow (streamfunction formulation) and a manufactured oscillatory solution. Our results show up to $(350\times)$ faster training than PINNs and over $(10\times)$ fewer parameters for comparable solution accuracy. Despite surpassing PINNs, RBF-PIELM still lags mature mesh-based solvers and its accuracy degrades on highly oscillatory solutions, highlighting remaining challenges for practical deployment.

---

### Multi-Agent Collaborative Intelligence: Dual-Dial Control for Reliable LLM Reasoning

Authors: Edward Y. Chang, Ethan Y. Chang
Published: 2025-10-06
Categories: cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2510.04488v1

Multi-agent debate often wastes compute by using a fixed adversarial stance, aggregating without deliberation, or stopping on heuristics. We introduce MACI, an active controller with two independent dials that decouple information from behavior: an information dial that gates evidence by quality, and a behavior dial that schedules contentiousness from exploration to consolidation. A moderator tracks disagreement, overlap, evidence quality, and argument quality, and halts when gains plateau. We provide theory-lite guarantees for nonincreasing dispersion and provable termination, with a budget-feasible scheduler. Across clinical diagnosis and news-bias tasks, MACI improves accuracy and calibration while reducing tokens, and converts residual uncertainty into precision RAG plans that specify what to retrieve next. We use a cross-family LLM judge (CRIT) as a conservative soft weight and stop signal, validated for order invariance and judge-swap stability; stability depends on using high-capability judges. MACI turns debate into a budget-aware, measurable, and provably terminating controller.

---

### Forking-Sequences: Statistically and Computationally Efficient Multi-Horizon Forecasting with Reduced Volatility

Authors: Willa Potosnak, Malcolm Wolff, Mengfei Cao, Ruijun Ma, Tatiana Konstantinova, Dmitry Efimov, Michael W. Mahoney, Boris Oreshkin, Kin G. Olivares
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04487v5

While accuracy is a critical requirement for time series forecasting, an equally important desideratum is reasonable forecast volatility across forecast creation dates (FCDs). Even highly accurate models can produce erratic revisions between FCDs, undermining trust and disrupting downstream decision-making. To improve the volatility of forecast revisions, state-of-the-art models like MQCNN, MQT, and SPADE employ a powerful yet underexplored neural network architectural design: forking-sequences. This architectural design jointly encodes and decodes the entire time series across all FCDs, producing an entire multi-horizon forecast grid in a single forward pass. This approach contrasts with conventional neural forecasting methods that process FCDs independently, generating only a single multi-horizon forecast per forward pass. In this work, we formalize the forking-sequences design and motivate its broader adoption by introducing a metric for quantifying excess volatility in forecast revisions and by providing theoretical and empirical analysis. We theoretically motivate three key benefits of forking-sequences: (i) reduced forecast volatility through ensembling; (ii) gradient variance reduction, improving the statistical efficiency of the training procedure; and (iii) improved inference computational efficiency. We validate the benefits of forking-sequences compared to baseline window-sampling on the M-series benchmark, using 16 datasets from the M1, M3, M4, and Tourism competitions. We observe median sCRPS improvements across datasets of 46.2%, 49.3%, 28.6%, 24.7%, and 6.4% for RNN, LSTM, CNN, Transformer, and State Space-based architectures, respectively. We then show that forecast ensembling during inference can reduce median forecast volatility by 13.2%, 13.0%, 10.9%, 10.2%, and 11.2% for these respective models trained with forking-sequences, while maintaining accuracy.

---

### Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness

Authors: Amin Banayeeanzade, Ala N. Tak, Fatemeh Bahrani, Anahita Bolourani, Leonardo Blas, Emilio Ferrara, Jonathan Gratch, Sai Praneeth Karimireddy
Published: 2025-10-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.04484v2

The ability to control LLMs' emulated emotional states and personality traits is an essential step in enabling rich, human-centered interactions in socially interactive settings. We introduce PsySET, a Psychologically-informed benchmark to evaluate LLM Steering Effectiveness and Trustworthiness across the emotion and personality domains. Our study spans four models from different LLM families paired with various steering strategies, including prompting, fine-tuning, and representation engineering. Our results indicate that prompting is consistently effective but limited in intensity control, whereas vector injections achieve finer controllability while slightly reducing output quality. Moreover, we explore the trustworthiness of steered LLMs by assessing safety, truthfulness, fairness, and ethics, highlighting potential side effects and behavioral shifts. Notably, we observe idiosyncratic effects; for instance, even a positive emotion like joy can degrade robustness to adversarial factuality, lower privacy awareness, and increase preferential bias. Meanwhile, anger predictably elevates toxicity yet strengthens leakage resistance. Our framework establishes the first holistic evaluation of emotion and personality steering, offering insights into its interpretability and reliability for socially interactive applications.

---

### TBStar-Edit: From Image Editing Pattern Shifting to Consistency Enhancement

Authors: Hao Fang, Zechao Zhan, Weixin Feng, Ziwei Huang, Xubin Li, Tiezheng Ge
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04483v3

Recent advances in image generation and editing technologies have enabled state-of-the-art models to achieve impressive results in general domains. However, when applied to e-commerce scenarios, these general models often encounter consistency limitations. To address this challenge, we introduce TBStar-Edit, an new image editing model tailored for the e-commerce domain. Through rigorous data engineering, model architecture design and training strategy, TBStar-Edit achieves precise and high-fidelity image editing while maintaining the integrity of product appearance and layout. Specifically, for data engineering, we establish a comprehensive data construction pipeline, encompassing data collection, construction, filtering, and augmentation, to acquire high-quality, instruction-following, and strongly consistent editing data to support model training. For model architecture design, we design a hierarchical model framework consisting of a base model, pattern shifting modules, and consistency enhancement modules. For model training, we adopt a two-stage training strategy to enhance the consistency preservation: first stage for editing pattern shifting, and second stage for consistency enhancement. Each stage involves training different modules with separate datasets. Finally, we conduct extensive evaluations of TBStar-Edit on a self-proposed e-commerce benchmark, and the results demonstrate that TBStar-Edit outperforms existing general-domain editing models in both objective metrics (VIE Score) and subjective user preference.

---

### FourierCSP: Differentiable Constraint Satisfaction Problem Solving by Walsh-Fourier Expansion

Authors: Yunuo Cen, Zixuan Wang, Jintao Zhang, Zhiwei Zhang, Xuanyao Fong
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04480v2

The Constraint-satisfaction problem (CSP) is fundamental in mathematics, physics, and theoretical computer science. Continuous local search (CLS) solvers, as recent advancements, can achieve highly competitive results on certain classes of Boolean satisfiability (SAT) problems. Motivated by these advances, we extend the CLS framework from Boolean SAT to general CSP with finite-domain variables and expressive constraint formulations. We present FourierCSP, a continuous optimization framework that generalizes the Walsh-Fourier transform to CSP, allowing for transforming versatile constraints to compact multilinear polynomials, thereby avoiding the need for auxiliary variables and memory-intensive encodings. We employ projected subgradient and mirror descent algorithms with provable convergence guarantees, and further combine them to accelerate gradient-based optimization. Empirical results on benchmark suites demonstrate that FourierCSP is scalable and competitive, significantly broadening the class of problems that can be efficiently solved by differentiable CLS techniques and paving the way toward end-to-end neurosymbolic integration.

---

### VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery

Authors: Nonghai Zhang, Zeyu Zhang, Jiazi Wang, Yang Zhao, Hao Tang
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04479v2

Vision-Language Models (VLMs) have achieved significant progress in multimodal understanding tasks, demonstrating strong capabilities particularly in general tasks such as image captioning and visual reasoning. However, when dealing with specialized cultural heritage domains like 3D vase artifacts, existing models face severe data scarcity issues and insufficient domain knowledge limitations. Due to the lack of targeted training data, current VLMs struggle to effectively handle such culturally significant specialized tasks. To address these challenges, we propose the VaseVQA-3D dataset, which serves as the first 3D visual question answering dataset for ancient Greek pottery analysis, collecting 664 ancient Greek vase 3D models with corresponding question-answer data and establishing a complete data construction pipeline. We further develop the VaseVLM model, enhancing model performance in vase artifact analysis through domain-adaptive training. Experimental results validate the effectiveness of our approach, where we improve by 12.8% on R@1 metrics and by 6.6% on lexical similarity compared with previous state-of-the-art on the VaseVQA-3D dataset, significantly improving the recognition and understanding of 3D vase artifacts, providing new technical pathways for digital heritage preservation research. Code: https://github.com/AIGeeksGroup/VaseVQA-3D. Website: https://aigeeksgroup.github.io/VaseVQA-3D.

---

### MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models

Authors: Soo Yong Kim, Suin Cho, Vincent-Daniel Yun, Gyeongyeon Hwang
Published: 2025-10-06
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.04477v1

Bridging clinical diagnostic reasoning with AI remains a central challenge in medical imaging. We introduce MedCLM, an automated pipeline that converts detection datasets into large-scale medical visual question answering (VQA) data with Chain-of-Thought (CoT) reasoning by linking lesion boxes to organ segmentation and structured rationales. These contextual signals enable medical vision-language models to generate question-answer pairs with step-by-step reasoning. To utilize this data effectively, we propose an Integrated CoT-Curriculum Strategy composed of an Easy stage with explicit lesion boxes for visual grounding, a Medium stage that encourages implicit localization, and a Hard stage for weakly supervised reasoning. Experimental results demonstrate that MedCLM attains state-of-the-art performance on several medical VQA benchmarks, providing a scalable framework for developing clinically aligned medical vision-language models.

---