# Research Papers — 2026-08 · bundle page 70 of 240

> Full-text markdown of papers #3451–3500 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-08/page/70
[← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/69.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-08/page/71.md)

### Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missions

Authors: Yue Li, Sudip Bhujel, Cameron Lira, Ning Wang, Yang Xiao
Published: 2026-08-23
Categories: cs.DC, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2608.22552v1

Decentralized federated learning (DFL) is a promising paradigm for autonomous nodes to collaboratively train AI models without relying on a central server. However, existing DFL solutions do not guarantee global model consistency, a critical requirement for collaborative mission-critical scenarios where model divergence undermines decision uniformity and safety. This lack of consistency also amplifies vulnerability to Byzantine adversaries, who exploit the decentralized network topology and weak synchrony to perform equivocation and model poisoning attacks against individual victims. This paper introduces DFL-C, a novel Byzantine-resilient DFL architecture that enables decentralized nodes to perform collaborative training with global model consistency. At its core, DFL-C integrates an asynchronous common subset (ACS) consensus protocol into the DFL workflow to ensure all nodes aggregate a uniform set of model updates to establish global model consistency, despite individual Byzantine equivocation. DFL-C further implements a dual-domain trust scoring mechanism to provide resilience against data-domain Byzantine manipulations including model poisoning attacks. This mechanism complements the consensus protocol, significantly reducing the latter's runtime. Our experimental results demonstrate that DFL-C maintains model accuracy while achieving global model consistency under Byzantine behaviors with moderate consensus overhead. Notably, when compared with the state-of-the-art DFL solution BALANCE (Fang et al.) that does not provide model consistency, DFL-C achieves better model accuracy against untargeted model poisoning attacks and comparable resilience against backdoor attacks, with the advantage widened under non-IID scenarios.

---

### Scaling Curriculum Learning For Autonomous Driving

Authors: Cevahir Koprulu, David Paz, Feng Tao, Yuliang Guo, Xinyu Huang, Ufuk Topcu, Liu Ren
Published: 2026-08-23
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.22549v1

Batched simulators for autonomous driving have recently enabled training reinforcement learning (RL) agents at scale, encompassing thousands of traffic scenarios and billions of interactions within a matter of days. Although such high-throughput feeds RL algorithms faster than ever, their sample-efficiency has not kept pace: As the standard training scheme, domain randomization uniformly samples scenarios, thereby consuming a vast number of interactions on cases that contribute little to learning. Curriculum learning offers a remedy by adaptively prioritizing scenarios that matter most to policy improvement. We present CL4AD, the first integration of curriculum learning into batched autonomous driving simulators by framing scenario selection as an unsupervised environment design problem. We introduce utility functions that shape curricula based on success rates and the realism of the agent's behavior, in addition to existing regret-estimation functions. Large-scale experiments in GPUDRIVE demonstrate that curriculum learning achieves a 99% success rate a billion steps earlier than domain randomization, reducing wall-clock time by 77%, and outperforms heuristic curricula with static and dynamic attributes, with only one exception at the largest scale. An ablation under limited compute shows that curriculum learning improves sample efficiency by 67%. We also investigate how utility functions behave at scale, and how prioritized scenarios evolve during training. We release an implementation of CLForAD in GPUDRIVE.

---

### STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control

Authors: Mengxi Luo, Changjia Chen, An Cao, Zirong Huang, Wanyi Dai
Published: 2026-08-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.22538v2

Policy-governed agents must interpret case evidence while reliably following authorized procedures. We present STAGE, an executable-graph framework that confines model judgment to policy-scoped nodes while placing procedural control in deterministic code. We evaluate STAGE on three public policy-following benchmarks and Smart Dispute, a proprietary banking benchmark. Compared with monolithic full-policy execution, STAGE improves task success and repeated-run reliability, with its largest observed gains on the deeper workflows. On $τ^2$-bench Telecom and Smart Dispute, $\mathrm{Pass}^{3}$ improves by up to 55.0 and 65.7 percentage points, respectively. These results demonstrate the value of combining localized policy reasoning with deterministic procedural control for enterprise use.

---

### CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories

Authors: Zheyuan Deng, Binghang Lu, Hanqi Feng, Shirley Huang, Dianzhuo Wang, Yuanda Xu, Zhiwei Zhang, Yige Sun, Changhong Mou, Runyu Zhang, Yuexing Hao, Barnabas Poczos et al.
Published: 2026-08-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.22533v1

Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and verifier-sensitive writes, yet they remain prone to procedural failures: misreading application state, tool semantics, or task progress. Procedural memory promises more consistent decisions and less redundant exploration, but constructing high-quality memory without model training remains challenging. We introduce CONTRAMEM, a source-flexible, training-free framework for self-evolving procedural memory that treats same-task outcome variation as supervision: differences in correctness, efficiency, recovery, and failure modes expose outcome-relevant procedural distinctions, distilled into a compact bank of app-level Function Cards and task-level Skill Cards that evolves through localized curation rather than append-only accumulation or whole-bank rewriting. On held-out GAIA2/ARE computer-use tasks, CONTRAMEM more than doubles the success rate across the three source-model targets (26.2% to 55.3%), with consistent per-model gains (GPT-5.5: 27.5 to 61.0; Claude Sonnet 4.6: 28.0 to 52.5; DeepSeek V4 Pro: 23.0 to 52.5). The same bank transfers unchanged to the unseen Qwen3.7 Plus (18.5 to 35.5), indicating transferable procedural knowledge rather than model-specific behavior. The same construction carries over unchanged to AppWorld, beating both no memory and its own single-source self-memory variant for all three mid-tier agents on both public test splits. Under a matched trajectory budget, heterogeneous multi-model trajectories yield stronger memory than self- or same-model multi-rollout memory: the margin comes from contrastive behavioral diversity, not stronger source agents or more sampling.

---

### SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation in Medical Image Segmentation

Authors: Tal Grossman, Noa Cahan, Hayit Greenspan
Published: 2026-08-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.22532v1

Domain shift across imaging modalities and acquisition sites remains a significant barrier to the clinical deployment of segmentation models. Source-free unsupervised domain adaptation (SFUDA) addresses this by adapting a pretrained model to an unlabeled target domain without requiring access to sensitive source data. We introduce a novel SFUDA framework built on Symmetrical Flow Matching, a unified generative model that segments an input image and synthesizes a source-like image from a mask within the same learned flow. By initializing inference from a domain-agnostic Gaussian origin, the model preserves structural consistency across domains and grounds predictions in learned anatomy rather than shifted texture statistics. Our pipeline leverages this symmetry to generate reliable pseudo-labels and corresponding source-like synthetic images from unlabeled target data, creating a generative replay buffer that anchors source knowledge during a generative self-training stage that fine-tunes on a joint set of real target and synthetic source-like images. We evaluate on abdominal multi-organ and cardiac segmentation, covering cross-modality MRI<->CT shifts, and multi-site prostate segmentation. Our approach outperforms SFUDA baselines and is competitive with conventional UDA methods.

---

### Stress Testing Unlearning Algorithms

Authors: Noam Diamant, Neta Glazer, Ethan Fetaya
Published: 2026-08-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.22527v2

Recently, machine unlearning, the removal of specific training data influence from a model, has gained increasing attention. In large language models (LLMs), unlearning is particularly challenging due to the ambiguity of inputs and outputs. Con- sequently, rigorous evaluation is critical for assessing both safety and utility, and for driving progress in unlearning meth- ods. We identify two key shortcomings in existing unlearning benchmarks: (1) they do not actively test whether unlearned information can still be forcibly extracted, and (2) they fail to evaluate performance preservation on boundary questions, be- nign queries that are semantically close to the unlearned con- tent. Here we introduce WMDP++, an extension of WMDP that addresses these gaps by incorporating targeted extrac- tion of unlearned information and systematic evaluation on boundary questions. WMDP++ provides a more stringent and informative benchmark for evaluating unlearning in LLMs.

---

### RS$^3$-Prune: Read-Sparse, Store-Sparse Token Pruning for Video Object Segmentation

Authors: Avilasha Mandal, Sarvesh Shashikumar
Published: 2026-08-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.22526v1

We introduce RS$^3$-Prune, a training-free token-pruning recipe that instantiates as a small set of inference time hooks atop existing video object segmentation (VOS) networks. Modern VOS models have converged on a common, expensive design: an image encoder produces a dense token grid for every frame, and a memory bank accumulates these tokens across all previously processed frames to condition future predictions. As a video grows longer, the resulting token budget governs both per-frame latency and peak GPU memory. Hence these models break on use cases such as --- long-form video or real-time deployment on memory-bounded accelerators. In this work we argue that the right axis along which to compress memory-bank VOS is the token budget itself. RS$^3$-Prune operates in two precise locations within an arbitrary memory-bank VOS pipeline: at the boundary between the image encoder and the memory-attention readout, where we restrict the queries that participate in the cross-frame attention to only a small, geometrically informed subset; and at the boundary between the memory encoder and the memory bank, where we restrict which tokens are ever permitted to enter the bank to those that lie within the object's spatial extent. Over various established benchmarks, RS$^3$-Prune delivers up to $38.8\%$ FPS speedup and reduces $13.1\%$ peak memory usage, while preserving a competitive $\mathcal{J}$&$\mathcal{F}$ compared to the unmodified VOS networks.

---

### From Detrimental to Beneficial: Dynamic Influence-based Valuation and Editing

Authors: Adrian Nyakairu, Hongfu Liu
Published: 2026-08-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.22522v1

Data valuation is a cornerstone of data-centric learning, where prior efforts primarily focus on designing algorithms to classify training samples as either beneficial or detrimental for the learning task. However, leveraging these valuation estimates for subsequent data intervention remains underexplored; conventional approaches typically discard or downweight harmful samples, thereby underutilizing available data resources. In this paper, we present Dynamic Influence-based Valuation and Editing (DIVE), a novel and efficient framework that dynamically estimates sample values at the batch level and transforms detrimental data into beneficial contributions. Rather than altering the raw data, DIVE operates at the optimization level by strategically reversing the gradient directions of harmful samples during training, ensuring seamless integration with standard learning procedures with minimal overhead. Extensive empirical evaluations demonstrate that DIVE consistently improves classification performance, maximizes data efficiency, stabilizes optimization, and effectively generalizes to large language model fine-tuning.

---

### VISTA: Test-Time Compositional Alignment for Visual Autoregressive Generation

Authors: Hossein Shahabadi, Niki Sepasian, Mahdieh Soleymani Baghshah
Published: 2026-08-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.22521v1

Visual autoregressive (VAR) models have emerged as a fast, high-quality alternative to diffusion for text-to-image generation, but like diffusion models they exhibit persistent compositional failures, producing images that violate the attribute bindings and spatial relations specified in the prompt. While a rich line of test-time alignment methods has developed for diffusion, no comparable approach exists for next-scale VAR generation, whose stateful, discrete, multi-resolution sampling process makes existing techniques inapplicable. We close this gap with \textbf{VISTA} (\textbf{Vi}sual Autoregressive \textbf{S}emantic \textbf{T}est-time \textbf{A}lignment), the first gradient-based test-time alignment framework for next-scale autoregressive image generation. Built on Infinity, VISTA intervenes directly in the generation process, optimizing intermediate representations through the frozen transformer to steer visual predictions toward compositional constraints, without modifying model parameters or requiring additional training. VISTA introduces the mechanisms needed to make such optimization stable across scales, together with an extensible objective space that any differentiable constraint on cross-attention can plug into. Across two benchmarks and two model scales, VISTA improves every targeted compositional category, raising the mean targeted score by nearly 20\% on a 2B backbone and almost 6\% on an 8B backbone, with the largest gains on spatial relations. Image quality is preserved: an independent preference model VISTA never optimizes scores its outputs nearly 20\% higher. Notably, the 2B model with VISTA surpasses a backbone four times its size, indicating that a substantial part of the compositional gap between model scales is recoverable at test time.

---

### TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding

Authors: Pengyiang Liu, Junbo Niu, Xiaoyang Hu, Zhongyue Shi, Zitian Wang, Linjiang Huang, Si Liu
Published: 2026-08-23
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2608.22516v1

A long-video answer is evidence-supported only when the frames decoded from the video cover every event the answer depends on. Existing evaluations score final-answer correctness or predicted evidence intervals, but the frames a method decodes before answering are rarely audited, so correct answers can still rest on incomplete observation. We introduce VES-Bench, a 600-question benchmark of Temporal Ordering and Event Counting items over 348 public long videos. Each item carries a jointly necessary set of evidence intervals, letting us audit at three strictness levels whether a method's decoded frames cover every one of them. We also propose TRACE, a training-free agent that grounds answers in raw visual clips, builds an evidence bundle round by round, and stops only when the answer stabilises as the bundle grows and a final pass over the same clips returns the same answer. Under a same-backbone audit, TRACE answers 50.7% of questions correctly with at least two decoded frames inside every evidence interval, at 98.7 frames per question: over 10 points above uniform decoding at 128 frames (40.2%), and within 2.6 points of uniform decoding at 256 frames at 0.39x its frame cost, while reaching the highest answer accuracy in the audit (63.5%). TRACE also stays competitive on Video-MME (86.1), LVBench (75.6), and LongVideoBench (75.1).

---

### Interpretable statistical feature engineering for early disruption prediction in the short pulse ADITYA tokamak

Authors: Jyoti Agarwal, Kavit Patel, Bhaskar Chaudhury, Abhishek Sharma, Shrichand Jakhar, Manika Sharma
Published: 2026-08-23
Categories: physics.plasm-ph, cs.LG, physics.data-an
arXiv: https://arxiv.org/abs/2608.22515v1

Reliable early disruption prediction is critical for the safe operation and real-time control of tokamaks. However, machine learning based prediction frameworks have predominantly targeted medium and long pulse devices, with comparatively limited attention given to short pulse tokamaks where available warning time is inherently constrained. In this work, an interpretable machine learning framework is developed for feature engineering and early prediction of disruptions in the ADITYA using the initial plasma evolution information, prior to the activation of the negative converter of the ohmic transformer power supply. Statistical descriptors comprising the mean, variance, skewness, kurtosis and wavelet energy entropy are extracted from routinely available plasma diagnostics over different operation time windows. Decision tree based feature selection is employed to identify physically meaningful disruption precursors and to reduce feature dimensionality. These selected features are used to train a random forest classifier. The proposed framework achieves stable predictive performance across different analysis windows, with a maximum ROC-AUC of 0.87 for 0-35 ms and 0-40 ms windows. Comparable and in some cases improved, performance is obtained using the reduced feature set, demonstrating that the selected statistical descriptors retain the essential information required for disruption prediction. The proposed methodology provides an interpretable and computationally efficient framework for real time disruption prediction in short pulse tokamaks and establishes that carefully engineered statistical descriptors can effectively replace raw time series inputs for early disruption prediction, thereby offering a practical pathway toward real time plasma control in short pulse tokamaks similar to ADITYA and ADITYA-U.

---

### From Symmetry to Invariance: Learning Galois Equivalent Representations in Finite Fields

Authors: Zheng Zhang, Na Zhang
Published: 2026-08-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.22513v1

Neural networks can learn algebraic operations from finite examples, but it remains unclear whether this ability transfers across mathematically equivalent representations of the same operation. We study this question through multiplication in finite fields under changes of basis. The Galois action organizes basis representations into orbits, and bases in the same orbit induce the same coordinate multiplication map. This structure allows us to separate learning multiplication from transferring it to basis representations that are not used for training. We examine several ways of providing or recovering the relevant orbit structure, including invariant labels, basis matrices, orbit recognition, and algebraic decomposition. Our main approach trains a model to predict the Galois action between basis representations. Repeated applications of the learned transformation are then used to construct a canonical representative for each orbit, which supports multiplication on held-out bases through exact canonical matching. This provides a concrete mechanism for converting a learned algebraic symmetry into an invariant representation that can be used for transfer.

---

### HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems

Authors: Christos Sardianos, Iliana Pla, Vasilis Efthymiou, Iraklis Varlamis, Thomas Lagkas, Panagiotis Sarigiannidis, Georgios Th. Papadopoulos
Published: 2026-08-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.22512v1

Autonomous multi-agent systems nowadays act in finance, software supply chains, and security operations. Already, the first largely AI-orchestrated intrusion campaigns have been reported. Yet, when such a system causes harm, no method can robustly establish what happened, what caused it, or who is accountable. This is because provenance forensics works at the wrong abstraction, formal causality assumes the causal model, and agent auditing trusts self-recording. The target failure mode is, thus, attribution laundering, i.e., spreading an act across redundant agents until none is a but-for cause. Worse, the record is produced by the suspects, which comprises the assumption adopted throughout this work. Agents may therefore anticipate the investigation and the part of logging infrastructure may itself collude. In this paper, HANSARD is proposed, a reference architecture treating accountability as a life-cycle property. First, a readiness profile sealed before operation bounds what later findings may claim. Second, capturing at five choke points beyond the agents' reach makes omissions detectable, not only tampering. Third, a typed PROV-DM-aligned causal graph accrues as the system runs, and three indicators read it live to gate oversight without adjudicating. Fourth, post-incident replay yields contingent effects under the modified Halpern-Pearl definition, together with a compensation-set size. Finally, a synergy residual measures harm due to the combination rather than to individuals, making laundering visible. Cause, responsibility and accountability are then reported separately, each capped by an evidentiary tier, while a future research agenda is also provided.

---

### ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts

Authors: YuanHang Xiao
Published: 2026-08-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.22510v1

Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated: the proper unit is a declared model-plus-runtime configuration whose failures can occur in evidence acquisition, runtime routing, safety boundaries, or repeated execution. We present ClawProBench, a trace-aware benchmark for runtime-native agent evaluation instantiated on OpenClaw, a live agent runtime with workspace tools and native surfaces for browsing, memory, messaging, scheduling, skills, and subagents. ClawProBench defines two tracks: a 102-scenario full profile with live workspace and native-runtime routing tasks, and a frozen 68-scenario holdout with closed-world JSON output contracts for robust ranking. Trials are scored from execution traces via a safety-gated formula combining correctness, process quality, and efficiency, preserving failure evidence for audit. Our anonymous artifact includes benchmark definitions, scoring code, manifests and sanitized traces. We evaluate 68 configurations on the full profile and 37 on holdout. The top safety-gated average trace score is 0.7671. Native-runtime tasks underperform workspace-live tasks (0.5238 vs. 0.6415). On holdout, pass@k-any outperforms strict three-trial pass (0.6638 vs. 0.2890), while full-profile and holdout rankings show weak alignment (Spearman 0.1300). Rankings based purely on correctness differ substantially from process-aware, safety-gated and strict-pass views. Final-answer leaderboards may hide native-surface weaknesses, one-off successes and trace-local agent failure modes.

---

### Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification

Authors: Jérémie Dentan, Alexi Canesse, Mahammed El Sharkawy, Sonia Vanier
Published: 2026-08-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.22506v1

Claim-level Uncertainty Quantification (UQ) aims to mitigate the lack of reliability of Large Language Models (LLMs) by evaluating the factuality of each claim in their outputs. We introduce Kernel Token Contradiction (KTC), a lightweight approach to compute claim-level UQ under realistic white-box conditions. KTC represents the candidate tokens involved in LLM generation as a positive semi-definite kernel that integrates both the LLM's conditional distribution and a token contradiction score. We then use the Von Neumann entropy to quantify the uncertainty of this kernel. To estimate token contradiction, we develop a new approach based on frequency statistics from the Wikipedia corpus. Although CPU-only, our approach achieves over an 8.2x speedup compared to state-of-the-art GPU-accelerated methods based on cross-encoders, and over a 65x speedup compared to CPU-only methods with comparable performance. Our evaluation spans two benchmarks across four European languages and 16 different models. KTC not only matches the average performance of existing methods but also outperforms them in high-precision regimes. This combination of computational efficiency and accuracy makes real-time monitoring of LLM outputs practical in production.

---

### When Does AI for PDEs Yield Scientific Evidence?

Authors: Wenshuo Wang
Published: 2026-08-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.22504v1

Existing AI-for-PDE benchmarks primarily assess models in terms of predictive or approximation accuracy. In physics research, however, AI outputs often serve as evidence for scientific claims. These two objectives are not equivalent: the former measures an output's agreement with a reference target or satisfaction of governing constraints; the latter asks whether, given a specified object of study, scientific claim, assumptions, and evidence standard, the output provides sufficient evidence for that claim. To bridge this gap, we extend a widely used PDE-simulation benchmark and a comprehensive benchmark for PDE inverse problems to enable, for the first time in AI for PDEs, evaluation of whether and to what extent model outputs support specified scientific claims. Our results show that numerical accuracy and evidential support can rank models differently, explain when and why they do so, and reveal that existing benchmarks can favor methods whose outputs provide weaker support for the scientific claims of interest. Together, we formalize, empirically demonstrate, and explain this evaluation--use mismatch in AI for PDEs.

---

### Learning Sample-wise Rank-aware Interpolation Weights for Composed Visual Data Retrieval

Authors: Boseung Jeong, Taegyu Park, Donghyeon Kwon, Hyunsouk Cho, Suha Kwak
Published: 2026-08-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.22500v1

At the heart of composed visual data retrieval is the fusion of a reference visual input and a textual modification into a single query. While current state-of-the-art methods utilize multimodal large language models for this fusion, their complexity introduces prohibitive querytime latency, limiting their scalability. We instead revisit the efficacy of simple linear interpolation within an embedding space, and introduce SRAIN, the first framework that dynamically predicts query-specific interpolation weights. The key challenge lies in the fact that the quality of an interpolation weight should be measured by the interpolated embedding's discriminability from negatives as well as its proximity to true targets; this makes collecting and predicting optimal weights intractable. We overcome this bottleneck through two key innovations: batch-wise rank-aware weight estimation during training, and a compact memory bank that synthesizes hard negatives during inference. SRAIN achieves the best in composed video retrieval and matches the current state of the art in composed image retrieval, all while substantially reducing querytime latency compared to MLLM-based alternatives.

---

### Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages

Authors: Chanwoong Yoon, Jungsoo Park, Alan Ritter
Published: 2026-08-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.22490v1

Safety alignment helps models adhere to human values, but it often reduces response utility. We ask a critical but understudied question: Does safety alignment impose the cost equally across language groups? To answer this, we introduce a rigorous protocol to measure the utility loss imposed solely by safety alignment, which we term Safety Cost. Through direct pairwise comparisons between safety-aligned models and their unaligned counterparts, we find a systematic inequity: non-English users consistently bear a higher Safety Cost than English users. We further identify three underlying patterns. First, multiple languages lie in a double-penalty zone, experiencing both weaker safety protection and larger utility loss. Second, certain languages exhibit apparent utility gains that are in fact a consequence of safety filters failing to engage. Third, even high-resource languages pay a larger Safety Cost than English to reach the same level of safety. We show that these disparities arise from both explicit refusals and implicit qualitative differences across multiple dimensions. By accurately measuring the disparate effects of safety alignment, our findings expose a systematic disparity in current safety alignment practices.

---

### HeatTok: Enhancing Remote Sensing Image Understanding via Thermodiffusion-based Tokenization

Authors: Yingying Yan, Jiaqi Tang, Wei Wei, Qianzhou Wang, Jinjian Wu, Botong Geng, Jianmin Chen, Yuyang Xia, Lei Zhang
Published: 2026-08-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.22485v1

Current visual tokenizers in Multimodal Large Language Models (MLLMs) predominantly rely on patch-based partitioning, which causes severe semantic mixture and object fragmentation in remote sensing imagery due to the irregular contours of geo-objects. Moreover, existing adaptive methods struggle to extract precise object-level tokens and lack dedicated geometric positional encodings for irregular regions. In this paper, we propose HeatTok, a semantic-aware tokenizer driven by thermodiffusion aggregation. Inspired by the physical principles of heat conduction, HeatTok adaptively merges adjacent homogeneous regions to generate semantically independent, object-aligned irregular tokens. To enable MLLMs to perceive these irregular shapes, we design the Gaussian Multimodal Rotary Positional Embedding (G-MRoPE), which models token spatial distributions via 2D Gaussians and explicitly injects center, scale, and orientation cues. Extensive evaluations on the VRSBench and EarthVQA datasets demonstrate that HeatTok effectively preserves object-level semantic integrity and achieves state-of-the-art performance under a reasonable token budget. The code is available: https://github.com/YingyingYan1/HeatTok.

---

### Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models

Authors: Toghrul Abbasli, Kentaroh Toyoda, Yuan Wang, Li Chen
Published: 2026-08-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.22483v1

Large Language Models (LLMs) increasingly support decision-making in high-stakes domains, but they often hallucinate and express confidence that is misaligned with factual correctness. Response-level confidence is a coarse signal: a single generation can mix correct and incorrect statements, so a single number is not actionable for users that must accept, reject, or verify individual pieces of information. We study claim-level confidence calibration as a decision-relevant uncertainty signal: each response is decomposed into atomic, verifiable claims, and each claim is assigned a calibrated confidence using inference-time signals from consistency across samples and self-verification. Our framework operates in closed-box settings (no logits, no fine-tuning) and applies post-hoc calibration directly at the claim level, enabling selective intervention such as evidence retrieval or human review for low-confidence claims. Across TriviaQA and TruthfulQA we evaluate seven baselines on six recent models (Llama-3.1, Mistral, Qwen2.5, DeepSeek-R1, GPT-4, GPT-4o), and show that claim-level decomposition combined with post-hoc calibration reduces expected calibration error on factual questions while exposing failure modes on adversarial false-premise questions where decision-makers most need reliable uncertainty estimates.

---

### GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning

Authors: Jun Chen, Yongchao Liu, Pengyu Qiu, Jiajun Zheng, Juelu Zhang, Yujie Zeng, Qin Zhang, Ziyue Qiao, Xiao Luo
Published: 2026-08-23
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.22479v2

Retrieval-augmented generation (RAG) enables LLMs to access external knowledge for answering knowledge-intensive questions. For complex multi-hop questions, multi-turn retrieval-augmented reasoning extends RAG into an iterative process that repeatedly searches for and integrates evidence across documents. However, existing reinforcement-learning (RL) approaches for agentic RAG are typically optimized with final-answer rewards, which provide sparse supervision and overlook whether the model actually retrieves the required evidence chain. We present \textsc{GTA-RAG}, a graph-trajectory-augmented RL framework for multi-turn retrieval-augmented reasoning. From an entity--document graph, we sample connected document paths, synthesize multi-hop QA trajectories, and validate them with the deployed retriever to obtain executable trajectory-level supervision. We then optimize the retrieval policy with Group Relative Policy Optimization (GRPO) and a trajectory-guided reward that encourages both accurate answers and acquisition of target evidence documents, followed by answer-reward training on natural QA instances. Experiments on three multi-hop and two simple QA benchmarks show that \method{} consistently outperforms RL-based RAG baselines with both Qwen2.5-3B and Qwen2.5-7B backbones, while substantially improving evidence-chain coverage. Our code is available at https://github.com/cjcj46262/GTA-RAG.

---

### Arbitrage-Aware Multi-Step Forecasting of Implied Volatility Surfaces: Modelling Surface Trajectories Using Latent Diffusion

Authors: Dominik Manuel Buchegger, Lukas Gonon
Published: 2026-08-23
Categories: q-fin.MF, cs.LG
arXiv: https://arxiv.org/abs/2608.22478v1

Implied volatility surfaces summarise the option market and are central to many financial applications. Forecasting their future evolution requires modelling two-dimensional geometry, temporal dependence, and predictive uncertainty while preserving economic admissibility. We propose a conditional latent diffusion framework for generating joint 30-step trajectories of implied volatility surfaces and underlying returns. An arbitrage-aware autoencoder learns a low-dimensional surface representation, while the diffusion model captures the conditional joint evolution. Evaluated on SPX surfaces, the framework generates realistic probabilistic multi-step scenarios while also outperforming the persistence benchmark in point forecasting.

---

### Quantum-Inspired Hybrid Neural Networks for Neural Decoding: A Controlled Ablation Study of Learnable Quantum Sidecar Integration

Authors: Diana Legziel Levy, Menachem Finkelstein, Peter Chin, Eilon Vaadia, Sarel Cohen
Published: 2026-08-23
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2608.22475v1

We study parameterized quantum circuits (PQCs) integrated as residual sidecar modules within a ResNet-50 backbone for 31-class neural population decoding---imagined handwriting classification from multi-neuron spike rasters. Under strictly controlled conditions (fixed data splits, seeds, and optimizer), we compare four model variants: baseline, quantum sidecar with frozen input projection, quantum sidecar with backbone-gradient-trained projection, and a measurement-guided variant that aligns angle encodings with circuit measurement outcomes. The backbone-gradient variant improves accuracy in 3/4 seeds (+0.19% mean, 95% CI (-1.10%, +1.48%)) and consistently reduces Linear CKA similarity to baseline features ($Δ=-0.025$, 4/4 seeds), indicating genuine structural reorganization of representations. A nine-variant ablation identifies simple shallow architectures as the most effective and reproducible configuration. Measurement-guided training consistently improves representation geometry without reducing accuracy. All results use noiseless statevector simulation on 4 qubits, a regime chosen to reflect the practical constraints of current near-term superconducting hardware; no quantum computational advantage over classical methods is claimed.

---

### Small Reasoning Models are Instruction Followers in Function Calling

Authors: Yalda Taheri, Mohammad Hassan Heydari, Erfan Naaman, Afsaneh Fatemi
Published: 2026-08-23
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2608.22472v1

Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-calling accuracy through fine-tuning, reinforcement learning (RL), and multi-agent frameworks, particularly for native function-calling LLMs. This work demonstrates that LLMs achieve superior accuracy in function calling in instruction-following contexts (i.e., standard user-assistant interactions) rather than a tool calling context. We introduce Instruction-Followed Function Calling (IFFC), a novel framework that decouples function-calling logic from the primary LLM and delegates it to a dedicated smaller model operating within the instruction-following paradigm. Our method consistently outperforms both native function calling (NFC) and prompt-based function calling (PFC) baselines, with particularly strong gains on reasoning-oriented LLMs. Furthermore, we demonstrate that IFFC maintains robust performance under aggressive quantization, enabling efficient on-device deployment without significant accuracy degradation. This work establishes a new paradigm for reliable, resource-efficient function calling in edge-computing scenarios.

---

### The Variance of Thought: Policy Variance, Critical Forks, and Local Credit Assignment

Authors: Yingru Li
Published: 2026-08-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.22467v1

Long-horizon language-model tasks --- multi-step reasoning and tool-using agents alike --- are limited by credit assignment. We analyze it through the policy variance $σ_π^2(s)=\operatorname{Var}_{a\simπ}(Q_π(s,a))$, which in a deterministic MDP is the sole source of return variance and is injected in discrete pulses at states we call critical forks. Three results follow. (i) Policy variance is a discovery budget: observing an action of advantage $c$ requires $Ω(c^2/σ_π^2(s))$ draws, a bound that is exact on the canonical two-point fork. (ii) Policy variance is bounded by the policy's Gini dispersion, $σ_π^2(s)\le 1-\|π(\cdot|s)\|_2^2$, a rollout-free necessary condition for criticality computable from logits alone. (iii) The remaining horizon sets the estimation cost: at a fork whose downstream success probability is $P$, the Monte Carlo advantage estimate has signal-to-noise ratio of order $\sqrt{P}$, so its sample cost scales as $1/P$ --- a cost that branched sampling shares. Bootstrapping removes it by converting a product of survival probabilities into a sum, provided the value representation is multiplicatively accurate, which argues for log-value parameterization.

---

### M$^3$ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compression

Authors: Xinhui Liu, Lei Liu, Zhenghao Chen, Lebin Zhou, Wei Wang, Wei Jiang
Published: 2026-08-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.22465v1

High-fidelity free-viewpoint video (FVV) and interactive rendering increasingly rely on explicit Gaussian representations, yet practical deployment remains constrained by representation size, dynamic updates, and computational cost. Existing multi-view video benchmarks provide valuable real-captured content, but they make it difficult to isolate the effects of controlled camera geometry, representation efficiency, and temporal redundancy. We introduce M$^3$ISR, a controlled synthetic benchmark for 3D and 4D Gaussian Splatting (3DGS/4DGS). The benchmark contains 25 scenes from five indoor and outdoor scene groups, two camera/motion configurations, six synchronized 1080p views, and dense ground-truth annotations including RGB, camera parameters, depth, semantic and instance segmentation, and static--dynamic masks. The shared-center camera design intentionally isolates angular view variation and enables controlled evaluation of novel-view synthesis and representation efficiency. We organize M$^3$ISR into five complementary tracks covering 3DGS synthesis, 4DGS synthesis, 4DGS streaming, 3DGS compression, and 4DGS compression. Representative baseline results show small differences in static reconstruction quality but substantial differences in representation storage, while the evaluated streaming methods exhibit substantially higher reported training or reconstruction cost than the corresponding offline dynamic reconstruction baselines. We further define feedforward compression tasks for 3DGS and 4DGS and provide reference rate--distortion formulations and preliminary baseline evaluations. The benchmark is intended as a controlled and complementary testbed for systematic study of Gaussian-based FVV reconstruction, compression, and streaming.

---

### Functional compatibility as a determinant of persistent neural learning

Authors: Hossein Javidnia
Published: 2026-08-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.22462v3

Neural networks can acquire new capabilities while damaging existing ones, but what determines whether new learning persists remains unclear. We identify functional compatibility, the extent to which incoming learning can coexist with behaviour that must be preserved, as an experimentally manipulable causal determinant of persistence. From identical neural states, we vary compatibility while matching unrestricted learning opportunity and imposing a common retention requirement. Persistent learning increases with compatibility across independent directions, convolutional and transformer architectures, vision and text, and a ten-seed replication. Learning rules and retention constraints determine how much compatible opportunity is retained, whereas nonlinear geometry limits the matched intervention at larger update norms. Functional compatibility therefore reframes stability-plasticity from preventing forgetting to determining which new learning can coexist with existing function and persist.

---

### MASH-Bench: Diagnosing Cross-Source Failure in Mass-Shooting Risk Classification

Authors: Neha Sharma, Ritesh Sharma
Published: 2026-08-23
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2608.22460v1

Public mass-shooting databases differ substantially in coverage, feature availability, and reporting practices, creating challenges for machine-learning models that must generalize across data sources. We introduce MASH-Bench, a harmonized benchmark of 6,968 incidents from four U.S. databases: Kaggle, Mother Jones, Stanford MSA, and the Gun Violence Archive (GVA). We evaluate cross-source risk classification using leave-one-dataset-out (LODO) evaluation. Random Forest, XGBoost, and LightGBM achieve VeryHigh-risk recall of 0.68-0.89 on the curated sources but generalize poorly to GVA, where mean recall drops to 0.20 and precision to 0.0004. To investigate the source of this degradation, we conduct a controlled feature-masking ablation that removes the five features unavailable in GVA from the curated sources. The resulting recall collapse to zero provides evidence that feature completeness is a major contributor to the observed cross-source failure. We further evaluate three domain-adaptation approaches: DANN, CORAL, and importance weighting. DANN improves VeryHigh-risk recall on GVA by 0.282 (95% CI (0.11, 0.47), p = 0.003), although precision remains low, whereas CORAL and importance weighting yield zero recall. Oracle prior-shift recalibration likewise fails to recover VeryHigh-risk predictions, indicating that label-side correction alone is insufficient under the observed feature deficiencies. A per-group audit further identifies substantial disparities associated with media-attributed mental-health labels. Overall, these results indicate that, in MASH-Bench, cross-source generalization is constrained more by feature completeness and label prevalence than by classifier choice. The benchmark provides a controlled setting for diagnosing these effects in cross-source risk classification.

---

### KPI-Conditioned Generative Design of Automotive Hood Inner Panels: A Two-Stage Retrieval-Generation Pipeline with Surrogate-Based Performance Estimation

Authors: Sudeep Chavare
Published: 2026-08-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.22457v1

An inner hood panel must meet a deflection target, stay below a stress limit, and hit a mass target. Machine-learned surrogates have made the forward direction, geometry to performance, fast and routine. The inverse direction, producing geometry from a stated requirement, remains largely unaddressed for industrial parts whose design space is organized into discrete topology families rather than a continuous parameterization. This work presents a two-stage pipeline for that inverse problem. A reachability stage determines which topology families can satisfy a given requirement vector. A conditional variational autoencoder then generates point-cloud geometry within a selected family, and a neural-operator surrogate estimates the performance of each candidate. The pipeline is built entirely from public data and freely available compute, and is deployed as an interactive tool. The pipeline works, with qualifications that are reported as primary findings rather than caveats. The surrogate is accurate in aggregate, but its error is comparable to the performance differences it is asked to discriminate, which bounds what can be claimed for any individual generated design. That ratio of surrogate error to within-class signal is argued to be the quantity that determines whether a pipeline of this kind can work at all.

---

### Geometric Structures on Graphs: a Holonomy-Based Discretization of Curvature

Authors: Hao Li, Yuhan Peng, Junwen Dong
Published: 2026-08-23
Categories: cs.LG, math.DG
arXiv: https://arxiv.org/abs/2608.22453v1

We propose a holonomy-based framework for discretizing curvature on graphs equipped with local symmetric positive-definite metrics. Each vertex carries a fibre metric \(g_i\), and each directed edge carries a reversible metric-compatible transport \(F_{ij}\). The ordered product around an oriented triangular loop \(\mathcal C\) gives a holonomy \(H_{\mathcal C}\), whose normalized logarithm \(Ω_{\mathcal C}=-s_{\mathcal C}^{-1}\operatorname{Log}(H_{\mathcal C})\) is used as a finite-loop curvature observation. Thus the construction discretizes the geometric principle that infinitesimal holonomy is controlled by curvature, rather than treating holonomy as a heuristic feature. Since \(Ω_{\mathcal C}\) lies in the \(g_i\)-orthogonal Lie algebra, it is not itself a velocity of an SPD metric. We therefore introduce two aggregation mechanisms: a commutator with a symmetric response matrix, producing symmetric Ricci-type metric responses, and an incidence-aware covariant divergence of curvature-induced edge fluxes, reflecting the relation between trace and covariant divergence. The resulting responses are locally orthogonal-gauge equivariant and can drive exponential updates that preserve positive definiteness. We also give a reversible metric-compatible parametrization of edge transports, allowing orthogonal edge factors, loop scales, weights, and response matrices to be learned while respecting the graph geometry. Known-geometry calibrations on the unit sphere test the holonomy--curvature relation, curvature preservation under nontrivial local metric representations, and the empirical recovery of edge transports from local observations.

---

### From Exposure to Expectation: Frequency, Surprisal, and Language Across Development in Spanish

Authors: Francisco Portillo López
Published: 2026-08-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.22452v1

Surprisal, the negative log-probability a language model assigns to a word given its preceding context, reliably predicts adult reading times. Does it contribute as much to explaining when children acquire individual words? Frequency reflects a learner's cumulative exposure to a word, whereas surprisal reflects how predictable a single occurrence is given its context. We investigate this question across two corpus-based studies of Spanish. In Study 1, we modeled age of acquisition (AoA) for 225 Spanish nouns using lexical frequency and contextual diversity from child-directed speech, plus surprisal from three language models differing in architecture and training language (BETO, BERTIN, mGPT). Frequency strongly predicted AoA (r=-.597, p<.001); surprisal added little beyond frequency and word length, including in a naturalistic-context analysis. In Study 2, we modeled adult fixation durations in the Chilean Spanish subsample of the Multilingual Eye-movement Corpus (MECO Wave 2), using mGPT surprisal alongside two independent frequency measures. Surprisal robustly predicted longer fixation durations after controlling for frequency and word length, consistent across both frequency sources. A matched word-type-level comparison showed the surprisal-behavior association was stronger in reading than in acquisition (z=3.63, p<.001). The findings suggest cumulative lexical exposure and contextual predictability play different roles across the language trajectory: frequency is particularly informative about when early lexical representations are acquired, whereas surprisal captures moment-to-moment processing difficulty in an already-established linguistic system. We discuss this pattern in relation to usage-based and entrenchment-based accounts of lexical development and to the evaluation of language models as models of human language behavior.

---

### EMPIRE: Explicit Manipulation Planning as a Learnable Intermediate Representation for Egocentric Hand-Motion Forecasting

Authors: Wen Wang, Ruibing Hou, Hong Chang, Shiguang Shan, Xilin Chen
Published: 2026-08-23
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2608.22449v1

Forecasting dexterous hand motions from egocentric observations is fundamental to intelligent interactive systems. Existing VLM-based methods typically map observations directly to future motions, overlooking the underlying manipulation process that governs hand-object interactions. Moreover, end-to-end optimization couples manipulation learning with motion synthesis, causing motion-generation gradients to interfere with the pre-learned manipulation-aware representations. To overcome these limitations, we propose EMPIRE, a two-stage framework that introduces Explicit Manipulation Planning as an Intermediate Representation for Egocentric hand-motion forecasting. Stage I: Learn to Plan. EMPIRE first learns explicit manipulation plans from multimodal context to capture the progression of hand-object interactions. Stage II: Learn to Act. A motion generator synthesizes future bimanual hand motions conditioned on frozen planner representations, preventing motion-generation gradients from affecting manipulation planning. To support our method, we further construct EMPIRE-651K, a bimanual hand-motion forecasting dataset comprising 650,910 training windows across 111 tasks, each paired with an explicit per-hand manipulation plan. Under identical training and evaluation protocols, EMPIRE achieves state-of-the-art forecasting accuracy, with an MPJPE of 84.53 mm and a finger-relative error of 38.97mm. We release the code and dataset at https://github.com/wangwen-banban/EMPIRE.

---

### Figurative Justice: Detecting metaphors in Hindi judgements with qualitative assessment and transformers

Authors: Bhumika Bhattacharyya, Shouvik Kumar Guha, Indranil Dutta
Published: 2026-08-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.22446v1

Metaphors are figurative use of words for conceptual mapping. Metaphor detection in the legal context has been crucial as metaphors are persuasive juridical means of creating legal meaning and concepts resulting in significant consequences. Metaphorical framing in legal discourse by judges, lawyers, and legislators brings about real-time implications upon individuals and influences judicial decision-making, argumentation and interpretation of laws. This is crucial in Human Rights infringement cases where language determines severity of punishment, public perception and judicial outcomes. While automatic metaphor detection in major languages like English, Spanish, Polish, Lithuanian have aided in understanding inherent intentions of metaphorical use of language, there is no such attempt in low-resource languages like Hindi. The dearth of annotated legal corpora in Hindi makes it difficult to develop NLP models and detect metaphors in judicial proceedings. In the Indian context, Convolutional Neural Networks (CNNs) have been used for classification of bail judgements, however there are no existing models designed for metaphor detection. We present a Hindi Legal Metaphor Corpus (HiLeMe) by isolating judgements from Hindi Legal Data Corpus (HLDC). Legal experts annotated HiLeMe to classify metaphorical constructions using the MIPVU schema. We downstreamed an mBERT on Hindi legal metaphor detection task. We built a transformer-based architecture for metaphor detection that are known to outperform traditional models in legal classification tasks. This model provides insights into the judicial psyche for decoding judicial decisions. Our research contributes to advancing automated models in legal discourse in low-resource languages like Hindi and envisages adoption into 22 Indian schedule languages.

---

### Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent Populations

Authors: Isotta Magistrali, Chen Shani
Published: 2026-08-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.22444v2

The unit of AI safety evaluation is still the individual model, yet language-model agents are increasingly deployed in interacting populations that read and write one another's decisions. This raises a question no single-agent audit can answer: an agent that is well-calibrated on its own may still be pulled toward a different decision by the agents around it. We study this on a security-triage task, where populations of language-model monitors decide whether to escalate or dismiss alerts, and into which we can inject a committed minority that always pushes one way. We find that two alerts a single agent judges almost identically on its own can drive collective behavior far apart, so auditing any one member need not reveal what the population will do. Yet that collective behavior can be predicted in advance. From a population's benign, adversary-free operation alone, we calibrate a response function that forecasts, before any attack is run, how far a committed minority will later move it. We then ask what shifts the outcome and find that letting agents see each other's reasoning neutralizes a weak attack, while only delaying it against a strong one, turning the question from whether the population converges on the adversaries' choice into when. Finally, we exclude the hypothesis of capture being an irreversible trap: once the committed agents are removed, the population drifts back toward where it began, so capture is a temporary state. Alignment in isolation is not alignment in a population, yet what a population will do under attack can be read in advance, from how it behaves before any adversary arrives.

---

### When Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion Sensing

Authors: Taehyeon An, Jaehyeong Park, Donghyuk Shin
Published: 2026-08-23
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2608.22438v1

Persona-conditioned large language models (LLMs) are increasingly used to simulate survey responses across diverse domains. However, apparent response variation can reflect unconditioned model priors or token sampling noise rather than systematic persona conditioning. We argue that persona-conditioned variation is informative when semantically similar personas exhibit concordant response shifts. To operationalize this principle, we introduce Persona-Conditioned Informativeness (PCI), an unsupervised diagnostic metric that measures whether semantically similar personas deviate in concordant directions relative to item-level sample baselines. By modeling personas as a similarity graph, PCI uses Local Moran's I to quantify local spatial coherence and extract compact persona subsets without using construct labels. To evaluate PCI without external human benchmarks, we test its ability to recover established latent value structure using the 57-item Portrait Values Questionnaire-Revised (PVQ-RR). Confirmatory factor analysis (CFA) shows that a PCI-selected 10% subset substantially improves overall construct recovery relative to response-stability and random selection. These findings support PCI as a principled internal diagnostic for screening synthetic respondents in survey pipelines.

---

### Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering Calibrator

Authors: Alhasan Mahmood, Samir Abdaljalil, Hasan Kurban
Published: 2026-08-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.22432v2

Multilingual LLM judges produce different evaluator-backbone rankings depending on the prompt language: on an eight-language Agent-as-a-Judge benchmark, the top-ranked backbone alternates across English, Arabic, Chinese, Hindi, Japanese, Spanish, Turkish, and Swahili, and 7 of 15 backbone pairs show statistically significant pairwise rank reversal. We treat this as a measurement problem. The multilingual judge score decomposes additively into task difficulty, backbone skill, and a language-backbone interaction term, the last of which is recoverable without human labels by double-centering the cell-mean score matrix. We make this estimator (\textbf{Consensus-Based Calibration}, CBC) explicit, give an $O(1/\sqrt{n})$ finite-sample concentration bound with variance constant $(1-\tfrac{1}{m})(1-\tfrac{1}{k})$, and show that it is unbiased even when task-language interactions are present. Across 7{,}920 judge runs (6 backbones, 8 languages, 55 tasks, 3 frameworks), CBC raises held-out cross-task rank consistency $τ$ from 0.650 to 0.902 and agrees with the held-out additive-model oracle in 100\% of per-language decisions versus 68.5\% raw; these are consistency diagnostics, not human-grounded correctness measures. On a separately collected M-RewardBench panel (7 languages, 1{,}500 items per language, 10{,}500 language-item instances, 5 evaluators), panel agreement with the public human gold preferences rises from 68.7\% to 76.6\% (gain 7.9 percentage points, 95\% CI $(6.0, 9.9)$), our strongest external evidence of downstream usefulness. The estimator is the standard two-way ANOVA interaction-recovery operation under sum-to-zero contrasts; our contribution is its application as a label-free post-hoc calibrator for multilingual LLM judges, an explicit finite-sample concentration bound, and an unbiasedness result that holds even under task-language misspecification.

---

### Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular Understanding

Authors: Changjiang Jiang, Qiannian Zhao, Lei Xin, Jinxiang Xie, Preslav Nakov, Zhuohan Xie
Published: 2026-08-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.22429v1

Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this reliance introduces significant inference latency and fails to effectively resolve the spatial-structural gap-a fundamental challenge in text-dense and structurally relational visuals (e.g., charts and visual tables) where strict relative spatial arrangements bind textual elements. Without external tools, standard MLLMs struggle with such fine-grained visual reasoning tasks. To address these issues, we propose Think with Structured Grounding (TwSG), a novel fine-grained image perception framework designed to internalize complex images's tool-use capabilities within the model. TwSG distills the benefits of multi-step reasoning and micro-cropping into a single efficient forward pass during inference. Specifically, we use an MLLM to identify key regions guided by ground-truth answers, and then prompt a teacher model to generate high-quality visual question-answering (VQA) data. These fine-grained, region-based supervisory signals are subsequently distilled back into the full-image representation. Our training pipeline consists of two stages: (1) a cold-start supervised fine-tuning (SFT) phase using multi-turn data with focused area descriptions to foster complex reasoning and error recovery; and (2) a reinforcement fine-tuning (RFT) phase driven by a novel process reward mechanism, TL-GRPO, which encourages strategic reasoning. Extensive experiments across various MLLM architectures demonstrate that TwSG reduces inference latency while substantially improving accuracy and robustness, endowing models with native fine-grained region description and flexible reasoning capabilities.

---

### All four leading LLMs talk more than they listen to personality-verified synthetic help-seekers

Authors: Pablo A. Fonseca, Raquel Rodríguez-Carvajal, Rafael A. Calvo
Published: 2026-08-23
Categories: cs.HC, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2608.22425v1

Large language models are increasingly consulted at moments of distress, yet single-turn benchmarks neither test sustained exchanges nor distinguish between users. We built a personality-aware evaluation in which four widely used models advised several synthetic help-seekers, each given a psychometrically specified profile, in an acute crisis: a caregiver learning of a relative's dementia diagnosis. Auditors blind to the profile prompt recovered the specified bands from dialogue alone with high agreement on every instrument (ICC(2,4) = 0.91; 0.79-0.96 by instrument; band-score r = 0.78), as expected for the Big Five but equally for coping style, coping self-efficacy, resilience and reactance, which the lexical approach never covered. Such evaluation therefore reaches beyond the Five Factor Model to motivational, regulatory and self-appraisal dispositions. The four models were not distinguishable on emotion stabilisation and failed alike, sharing three modes: verbosity, a talk-to-listen ratio above one, and problem-solving before the situation had been explored.

---

### Where World Models Break: Natural-Input Failure Discovery

Authors: Zhanpeng Shi, Zi Liang, Rong Feng, Shiqin Tang, Xuyang Chen, Hongzong Li
Published: 2026-08-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.22421v1

World models predict action-conditioned futures and serve as critical internal simulators for downstream planning and control. However, catastrophic prediction failures of world models could dangerously propagate through the control pipeline, as subsequent agent or model training and decision-making depend heavily on the continuous environment evolution forecasted by these world models. Existing evaluations overlook this systemic risk: by aggregating average errors over benign generations from general queries, they fail to stress-test the model against catastrophic collapses under rare or unobserved condition-action combinations. To bridge this gap, we formalize the natural-input failure discovery problem: under a finite query budget, finding environment-valid conditions and action prefixes that induce severe prediction risk, verifying whether these failures reproduce on fresh seeds, and testing their persistence under nearby valid edits. Discovering such critical failures is computationally challenging, as valid condition-action combinations explode exponentially, rendering exhaustive search or standard sampling infeasible given the high cost of noisy rollouts. To tackle this, we propose BasinLens, which exploits the underlying structure of valid inputs, where each coordinate possesses environment-defined semantic types and admissible domains, by pairing uncertainty-guided global search with typed local replacements. Across diverse benchmarks and world-model families, BasinLens exposes reproducible and locally persistent failure modes that conventional evaluations fail to reveal, showing that average-case benchmarks can mask important vulnerabilities in world-model-driven control.

---

### Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings

Authors: Aoke Zhang, Bo Wang, Xihong Wu, Heping Cheng, Jing Chen
Published: 2026-08-23
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2608.22420v1

Decoding perceived speech from non-invasive brain recordings has garnered significant attention in recent years due to its wide range of potential applications. However, existing methods face considerable challenges in cross-subject decoding, primarily due to limited generalizability and the absence of explicit mechanisms for extracting subject-consistent information. These limitations result in high training costs and suboptimal decoding performance. To address these challenges, we propose an innovative Cross-Subject Perceived Speech Decoding (CPSD) framework, which comprises two training stages: source model pre-training and personal specialization. In the source model pre-training stage, contrastive learning is employed to capture shared representations across multiple source subjects. Subsequently, personal specialization initializes the model for the target subject by extracting consistent components from the source model and fine-tuning it using target subject data. Additionally, we introduce the Positional Encoding-based Spatial Attention (PESA) module, which remaps MEG/EEG data into a standardized reference space, thereby enhancing cross-subject consistency and facilitating model training. We evaluate the proposed CPSD framework on three perceived speech neural datasets encompassing different modalities and languages. The results demonstrate that our framework outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top-10 accuracy on the Armeni 2022, PKUEEG 2025, and Broderick 2018 datasets, respectively. Further analyses confirm the effectiveness, efficiency, and robustness of the proposed approach.

---

### Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking

Authors: Dongzhou Cheng, Ziang Li, Yixiao Zhou, Haojuan Li, Jinghao Zhang, Lei Lei, Minjing Dong, Jie Gui, Jiaqi Wang
Published: 2026-08-23
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2608.22419v1

Query-based Vision-Language-Action (VLA) models offer low-latency inference that is attractive for bimanual robotic manipulation, but we observe that they can still exhibit discontinuous actions and execution failures in complex dual-arm tasks. We hypothesize that unstable multi-view and language fusion is one contributing factor in these failures, often coinciding with attention spreading to distracting regions. To improve robustness, we introduce the Modality Masking Mechanism (M3), an embarrassingly simple, training-only strategy that requires no architectural changes or large-scale robot pretraining. M3 stochastically masks subsets of modality channels during training, exposing the policy to controlled partial observations and encouraging it to rely less on distracting cues and more on evidence that remains reliable. We evaluate M3 on ten bimanual tasks from RoboTwin 2.0 and on three long-horizon real-world tasks. Compared with the Adapter baseline, M3 improves average success by 21.7% in the Clean setting and 11.4% in Clean2Rand, where policies are trained on clean demonstrations and evaluated on randomized scenes, while also improving averaged real-world full-task success by over 30%. These results suggest that structured training-time masking is a practical way to improve the robustness of query-based VLA policies for bimanual manipulation.

---

### LLMs for Survey Text Analysis - A Performance Comparison Between Humans and GPT-5 on Inductive Content Analysis

Authors: Leonardo Bergmann, Renata Gheorghiu, Ana Gvritishvili, Alex Mican, Chris Stewart, Topias Tolonen-Weckström
Published: 2026-08-23
Categories: cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2608.22417v1

Large language models (LLMs) are increasingly used to support text analysis in qualitative research, yet evidence on their performance in inductive content analysis remains limited. This study compares human and LLM-based inductive coding of open-ended survey responses from 903 answers across six variables from a European PhD student survey. Five human coders performed inductive content analysis following a standardized coding scheme, while an LLM (GPT-5.4) conducted the same task using an established prompting procedure. Agreement between human and LLM outputs was assessed using the Adjusted Rand Index (ARI). Results showed an alignment between humans and the LLM, with ARI values of 0.61 for coding and 0.54 for theme generation. These values were close to the internal consistency of coding and theme results within humans (ARI = 0.68) and the LLM (ARI = 0.76). Agreement varied widely across variables, with low within-entity consistency consistently linked to low between-entity agreement, underscoring the role of data characteristics and individual performance in reliability. Overall, the findings suggest that LLMs can approximate human coding in this case-specific setting, particularly at the coding level, and may serve as a scalable support tool for inductive qualitative analysis.

---

### Don' t Box Me In: Dynamic Cultural Adaptation and Cognitive Tracking for Social Understanding

Authors: Chongyuan Dai, Yaling Shen, Shengeng Tang, Hui Ma, Jinpeng Hu
Published: 2026-08-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.22411v2

Social interaction increasingly takes place in multicultural settings, where individuals may draw on multiple cultural influences and adapt their communicative behavior across contexts. Despite recent advances in equipping Large Language Models (LLMs) with social understanding capabilities, existing approaches often model culture as a static demographic attribute, limiting their ability to accommodate hybrid and dynamically expressed communicative preferences. Therefore, in this paper, we propose \textbf{DyCAC}, a training-free framework that achieves fluid social alignment by incorporating \underline{Dy}namic \underline{C}ultural \underline{A}daptation with continuous \underline{C}ognitive tracking. Rather than inferring a fixed cultural identity, DyCAC models culturally relevant communicative preferences as a time-varying mixture of population-level cultural reference profiles. This reference-based representation is further calibrated using dialogue-style signals observed in the ongoing interaction, enabling the model to capture both composite cultural influences and turn-level shifts in communicative behavior. In parallel, a memory module driven by Theory of Mind (ToM) continuously tracks the cognitive states of the interlocutor. Extensive experiments on interactive social and cultural benchmarks demonstrate the superiority of our approach. The proposed framework outperforms existing baselines, exhibiting enhanced social intelligence and broad adaptability across varied multicultural contexts.

---

### Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation

Authors: Guan-Hua Wen, Hou-Chiang Tseng, Kuan-Yu Chen
Published: 2026-08-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.22399v2

Conversational speech emotion recognition must reconcile acoustic evidence across temporal scales with two interaction processes: cross-speaker contextual influence and within-speaker emotion evolution. We propose DSSM-CRF, an audio-only architecture that explicitly separates these processes. Bidirectional state-space models encode fused self-supervised speech representations at frame and dialogue scales, so each utterance representation captures local prosody and context from all speakers. The decoder then orders each speaker's utterances into an independent dynamic conditional random field chain. Consecutive utterances in a speaker's chain form a transition pair whose score combines a corpus-level transition matrix with a residual predicted from the two contextualized utterances. An auxiliary objective supervises whether each pair changes emotion but does not participate in Viterbi inference. Thus, interlocutor turns affect contextual emotion scores without being treated as transitions in another speaker's emotion trajectory. DSSM-CRF achieves 75.81% UA and 74.90% WA on IEMOCAP, and 54.72% WA and 49.31% WF1 on MELD. Matched controls demonstrate complementary gains from speaker-wise factorization and CRF modeling.

---

### MotionDLO: Hybrid Event- and Frame-Based Tracking of Deformable Linear Objects

Authors: Annalena Hartmann, Priyamvada Ajithkumar, Patrick Bründl, Jörg Franke
Published: 2026-08-23
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2608.22398v1

Reliably tracking moving deformable linear objects (DLOs) while simultaneously ensuring robustness, accuracy, and temporally consistent state estimation remains a fundamental challenge in robot perception. We introduce MotionDLO, a real-time tracking framework specifically designed to overcome these limitations in temporal continuity and latency. The method exploits the high temporal resolution and sparsity of event-based cameras and combines segmentation with the Coherent Point Drift (CPD) algorithm under the principles of Motion Coherence Theory. This integration enables temporally consistent shape estimation while maintaining a low computational overhead. Existing event-based tracking methods are typically computationally efficient but exhibit reduced accuracy compared to frame-based approaches, or alternatively compromise event sparsity to achieve competitive performance. To resolve this trade-off, we propose a hybrid event- and frame-based tracking architecture that preserves the complementary strengths of both sensing modalities. The event stream ensures high-frequency motion updates, while frame-based information stabilizes spatial accuracy and object identity. We demonstrate that the proposed framework reliably associates DLO instances across video sequences, enabling robust perception for robotic manipulation tasks. Experimental results validate real-time performance at 12 ms update rates and accurate shape tracking with an point-to-curve error as measurement of accuracy of up to 0.43 mm, supporting dynamic path adaptation during manipulation. The source code and demonstration datasets are publicly available.

---

### SchemaGUI: A Schema-Driven Benchmark for Controllable GUI Generation Evaluation

Authors: Jiarui Dong, Yin Cai, Zhouhong Gu, Chenmou Wu, Ci Tao, Yiran Chen, Jialing Li, Xiaoran Shi, Juntao Zhang, Zhijun Fang
Published: 2026-08-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.22390v1

Large language models (LLMs) have demonstrated strong potential in graphical user interface (GUI) generation, but reliable evaluation remains challenging due to uncontrolled data distributions, noisy annotations, and limited layout scenario coverage. To address this, we propose SchemaGUI, a template-based benchmark for controllable GUI generation evaluation. By synthesizing paired natural language instructions and deterministic function-call references from parameterized interface schemas, SchemaGUI can generate thousands of deterministically annotated tasks in seconds without human labeling. Based on 1,000 evaluated instances per scenario and language across six representative bilingual scenarios, we benchmark five mainstream models, including the Qwen3.5 family, Qwen3-Coder-30B, and DeepSeek-R1. Our extensive analysis reveals three key insights. First, precise geometric spatial control remains an important bottleneck; while scaling Qwen3.5 from 4B to 27B improves Schema Feasibility from 91.56% to 99.63%, the Geometry score improves more modestly (from 67.05% to 75.30%). Second, generation difficulty is highly sensitive to layout complexity, with current LLMs excelling at simple sequential arrangements but suffering severe coordinate drift in dense grids and multi-region compositions. Third, thinking mode increases token consumption while generally reducing GUI Score, particularly for smaller models.

---

### KONTOGRAPH: Verified Point-in-Time Feature Consistency and Amortised Explanation for Real-Time Anti-Money Laundering under a 200 ms Decision Budget

Authors: Ahmed Abolfadl
Published: 2026-08-23
Categories: cs.CR, cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2608.22389v1

Regulation (EU) 2024/886 obliges European payment service providers to settle euro credit transfers in under ten seconds, around the clock. This removes both the overnight batch window in which anti-money-laundering (AML) analytics traditionally ran and the settlement delay that made recovery possible, forcing detection, explanation and decision inside a single-digit-second envelope. We present KONTOGRAPH, an end-to-end AML pipeline for the SEPA Instant rail built under a self-imposed 200 ms 99th-percentile budget, and report an empirical study on 1,562,860 simulated payments with injected typologies and deliberately incomplete labels. Three findings are of interest beyond the system itself. First, a temporal graph network with per-node memory improves PR-AUC over a gradient-boosted tabular baseline from 0.0053 to 0.1717, a paired day-blocked bootstrap difference of +0.166 with 95% CI (0.105, 0.241); per-node memory alone more than doubles the score. Second, expressing each feature once and compiling it to three execution backends, with equivalence enforced by property-based tests that perturb the future, surfaced three point-in-time violations that code review had passed--each of which would have inflated reported performance. Third, and most consequential for practice, exporting the deployed tree ensemble to ONNX changed only $7.4 \times 10^{-8}$ in mean score yet altered 0.26% of decisions and inflated the alert volume by 12%, because 32-bit accumulation perturbs scores across a cost-optimal threshold of $3.98 \times 10^{-4}$. We argue that a serving-format conversion must be treated as a model change until measured, and that fidelity metrics for subgraph explainers can be vacuous when candidate neighbourhoods are small--a null result we report in full.

---

### ProBel: Propaganda Detection with Techniques, Spans, and Explanations

Authors: Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Elisa Sartori, Giovanni Da San Martino, Firoj Alam
Published: 2026-08-23
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.22388v1

Propaganda detection includes several related prediction levels, ranging from sentence-level decisions to technique classification and span identification. However, it remains unclear how supervision at these levels interacts when learned jointly across Arabic and English. We present ProBel, an Arabic and English resource that aligns binary labels, multi-label annotations over 23 propaganda techniques grouped into six coarse categories, technique-labeled spans, and reference explanations for the same news sentences. It includes a substantially larger English collection and supports matched binary, coarse-grained, multi-label, and span-level tasks in both languages. We evaluate zero-shot prompting, task-specific fine-tuning, and joint training under a shared setup. A single bilingual multi-task model achieves the best overall performance and remains competitive across tasks and languages. Cross-task analysis shows that transfer depends on the supervision level. Joint classification training preserves binary performance, whereas span-only training can weaken sentence-level prediction. Joint bilingual training yields the most stable results, while monolingual fine-tuning can reduce transfer to the other language. We will release the data, code, and evaluation scripts.

---

### Self-Supervised Graph Representation Learning for In-The-Wild Wearable and Smartphone based Emotion Recognition

Authors: Ioannis N. Ziogas, Leontios J. Hadjileontiadis, Ahsan H. Khandoker, Aamna Al Shehhi
Published: 2026-08-23
Categories: cs.LG, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2608.22387v1

Wearable and smartphone-based emotion recognition (WER) remains a challenging setting in affective computing, due to the notorious difficulty and bias associated with in-the-wild label collection. The high inter-and intra-subject emotional variability motivates us to explore WER modeling through graph node classification in a limited resources learning scheme powered by Self-Supervised Learning (SSL) graph masking augmentation tasks. We employ a subgraph sampling approach during training, utilizing labeled and unlabeled data, along with supervised, semi-supervised, and SSL mechanisms in a multi-task inductive graph neural network architecture. Our evaluations on K-EmoPhone through leave-one-group-out cross-validation in the binary arousal and valence tasks yield average accuracy gains of 4.3% and 7.8%, compared to the full resource setting, utilizing only 20% and 25% of the labels, respectively. Our model analysis sheds light on the relation of SSL graph augmentations to emotional arousal and valence and justifies the approach of SSL-driven subgraph training for in-the-wild WER.

---

### GRAFT: Graph-Distilled Generative Retrieval for Facet-Aware Scientific Literature Exploration

Authors: Italo Luis da Silva, Hanqi Yan, Yujing Wang, Jiangnan Ye, Lin Gui, Yulan He
Published: 2026-08-23
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2608.22381v1

Scientific papers may relate by problem, method, result, or contribution, but document-level retrievers collapse these into a single similarity score without saying why they are related. Citation- and similarity-based retrieval alone also confines search to the neighbourhood of what is already known, whereas generative retrieval generates document identifiers directly, enabling the exploratory retrieval that scientific discovery depends on. We connect papers in a graph whose edges are typed by these four facets, derived from facet items and citation signals, and distil it into a generative retriever whose identifiers are the papers' own facet text. Two graph properties do not survive naive distillation. First, because every training pair is an edge, naive enumeration indexes just 84% of the corpus. Coverage-aware distillation makes every paper learnable through a reverse-neighbour fallback, a minimum-coverage threshold, and edge-importance weighting. Second, constrained decoding guarantees that every generated identifier is a valid paper, but not that the graph connects it to the query. Graph-weighted reciprocal rank fusion scales each candidate's rank term by its query-candidate edge weight, dropping unsupported ones. On LitWeave, our constructed corpus of 11,359 NLP papers, Graft recovers 91% of its graph teacher's Recall@20 with no nearest-neighbour index or encoder at inference, and outperforms the graph teacher on query papers outside the corpus. It reproduces the graph's own facet labels at 0.922 precision, so every returned paper arrives labelled with the facet that surfaced it rather than an opaque score.

---