# Research Papers — 2026-05 · bundle page 216 of 326 > Full-text markdown of papers #10751–10800 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/216 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/215.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/217.md) ### More Than Meets the Eye: A Semantics-Aware Traffic Augmentation Framework for Generalizable Website Fingerprinting Authors: Youquan Xian, Xueying Zeng, Lingjia Meng, Lei Cui, Runhan Song, Wei Wang, Zhengquan Ding, Peng Liu, Zhiyu Hao Published: 2026-05-12 Categories: cs.LG, cs.CR, cs.NI arXiv: https://arxiv.org/abs/2605.11402v1 Deep learning-based website fingerprinting has emerged as an effective technique for inferring the websites users visit. Although existing methods achieve strong performance on closed-world datasets, they often fail to generalize to real-world environments, especially under geographic and temporal shifts. This limitation fundamentally stems from the coupled effects of two key challenges: application-layer resource composition variability and observable feature instability induced by cross-layer encapsulation. Intertwined, these factors induce systematic shifts between underlying application semantics and observable traffic features. To address the above challenges, we propose SATA , a semantics-aware traffic augmentation framework. Specifically, SATA first performs application-layer semantic augmentation based on protocol rules, expanding the resource composition patterns within each flow and frame sequence patterns under protocol constraints. Based on these augmented frame sequences, we further introduce a cross-layer feature alignment mechanism via knowledge distillation. It aligns frame sequence with packet-length sequence features, enabling cross-layer feature alignment between enhanced semantics and observable sequences. Extensive experiments show that SATA successfully generates traffic patterns that are absent from the training set but genuinely exist in the test set, and significantly improves the performance of mainstream models across diverse and complex scenarios. In particular, in open-world settings, SATA improves ACC by 90.81% and AUROC by 48.37%. The source code of the prototype system is available at https://anonymous.4open.science/r/SATA-B6C2/. --- ### AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment Authors: Robin Linzmayer, Georgianna Lin, Di Coneybeare, Jason Chu, Trudi Cloyd, Manish Garg, Miles Gordon, Elizabeth Hartofilis, Benjamin Hong, Ashraf Hussain, Eugene Y. Kim, Oluchi Iheagwara King et al. Published: 2026-05-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.11398v2 We introduce AcuityBench, a benchmark for evaluating whether language models identify the appropriate urgency of care from user medical presentations. Existing health benchmarks emphasize medical question answering, broad health interactions, or narrow workflow-specific triage tasks, but they do not offer a unified evaluation of acuity identification across these settings. AcuityBench addresses this gap by harmonizing five public datasets spanning user conversations, online forum posts, clinical vignettes, and patient portal messages under a shared four-level acuity framework ranging from home monitoring to immediate emergency care. The benchmark contains 914 cases, including 697 consensus cases for standard accuracy evaluation and 217 physician-confirmed ambiguous cases for uncertainty-aware evaluation. It supports two complementary task formats: explicit four-way classification in a QA setting, and free-form conversational responses evaluated with a rubric-based judge anchored to the same framework. Across 12 frontier proprietary and open-weight models, we find substantial variation in clear-case acuity accuracy and error direction. Comparing task formats reveals a systematic tradeoff: conversational responses reduce over-triage but increase under-triage relative to QA, especially in higher-acuity cases. In ambiguous cases, no model closely matches the distribution of physician judgments, and model predictions are more concentrated than expert clinical uncertainty. We also compare expert and model adjudication on a subset of maximally ambiguous cases, using those cases to examine the role of clinical uncertainty in label disagreement. Together, these results position acuity identification as a distinct safety-critical capability and show that AcuityBench enables systematic comparison and stress-testing of how well models guide users to the right level of care in real-world health use. --- ### AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment Authors: Robin Linzmayer, Georgianna Lin, Di Coneybeare, Jason Chu, Trudi Cloyd, Manish Garg, Miles Gordon, Elizabeth Hartofilis, Benjamin Hong, Ashraf Hussain, Eugene Y. Kim, Oluchi Iheagwara King et al. Published: 2026-05-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.11398v1 We introduce AcuityBench, a benchmark for evaluating whether language models identify the appropriate urgency of care from user medical presentations. Existing health benchmarks emphasize medical question answering, broad health interactions, or narrow workflow-specific triage tasks, but they do not offer a unified evaluation of acuity identification across these settings. AcuityBench addresses this gap by harmonizing five public datasets spanning user conversations, online forum posts, clinical vignettes, and patient portal messages under a shared four-level acuity framework ranging from home monitoring to immediate emergency care. The benchmark contains 914 cases, including 697 consensus cases for standard accuracy evaluation and 217 physician-confirmed ambiguous cases for uncertainty-aware evaluation. It supports two complementary task formats: explicit four-way classification in a QA setting, and free-form conversational responses evaluated with a rubric-based judge anchored to the same framework. Across 12 frontier proprietary and open-weight models, we find substantial variation in clear-case acuity accuracy and error direction. Comparing task formats reveals a systematic tradeoff: conversational responses reduce over-triage but increase under-triage relative to QA, especially in higher-acuity cases. In ambiguous cases, no model closely matches the distribution of physician judgments, and model predictions are more concentrated than expert clinical uncertainty. We also compare expert and model adjudication on a subset of maximally ambiguous cases, using those cases to examine the role of clinical uncertainty in label disagreement. Together, these results position acuity identification as a distinct safety-critical capability and show that AcuityBench enables systematic comparison and stress-testing of how well models guide users to the right level of care in real-world health use. --- ### MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization Authors: Yupeng Su, Ruijie Zhang, Ziyue Liu, Yequan Zhao, Zheng Zhang Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.11396v2 The Muon optimizer has emerged as a compelling alternative to Adam for training large language models, achieving remarkable computational savings through gradient orthogonalization. However, Muon's optimizer state is more sensitive to quantization errors: because the orthogonalization discards the magnitudes of singular values and retains only directional information, even small quantization errors in singular vector directions are amplified in the update. In this work, we propose MuonQ, a low-bit Muon training framework built on the principle of directional fidelity optimization. First, we apply a pre-quantization normalization so that each step introduces quantization errors of the same magnitude, preventing the accumulated error from developing a preferred direction. Second, we introduce a structural decomposition that separately quantizes the dominant singular components via power iteration, ensuring that quantization errors perturb only singular value magnitudes rather than rotating singular vector directions. Third, we adopt $μ$-law companding quantization to allocate higher resolution to densely packed momentum values, shifting the quantization objective from outlier preservation to dense-region distinguishability. Together, these techniques enable stable 4-bit quantization of Muon's optimizer states. Pre-training experiments on GPT-style and LLaMA-style models demonstrate that MuonQ at 4-bit precision recovers most of full-precision Muon's training loss and downstream accuracy while reducing optimizer-state memory by up to 7.3$\times$, offering a favorable point on the accuracy-memory trade-off. Our code is available at https://github.com/YupengSu/MuonQ. --- ### Spatial Adapter: Structured Spatial Decomposition and Closed-Form Covariance for Frozen Predictors Authors: Wen-Ting Wang, Wei-Ying Wu, Hao-Yun Huang, Xuan-Chun Wang Published: 2026-05-12 Categories: stat.ML, cs.AI, cs.LG, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2605.11394v1 We present the Spatial Adapter, a parameter-efficient post-hoc layer that equips any frozen first-stage predictor with a structured spatial representation of its residual field and an induced closed-form spatial covariance. The adapter operates as a cascade second stage on residuals, jointly learning a spatially regularized orthonormal basis and per-sample scores via a tractable mini-batch ADMM procedure, without modifying any first-stage parameter. Because the first-stage parameters are frozen, the adapter does not retrain the backbone; its role is to supply a compressed distributional summary of the residual field. Smoothness, sparsity, and orthogonality together turn a generic low-rank factorization into an identifiable spatial representation whose induced residual covariance admits a closed-form low-rank-plus-noise estimator; the effective rank is determined data-adaptively by spectral thresholding, while the nominal rank K is an optimization-side upper bound only. This covariance enables kriging-style spatial prediction at unobserved locations, with plug-in uncertainty quantification as a secondary downstream use. Across synthetic data, Weather2K for spatial-holdout prediction, and GWHD patch grids as a basis-transferability diagnostic, the adapter recovers residual spatial structure when paired with frozen first stages from linear models to deep spatiotemporal and vision backbones; the added representation uses fewer than K(N+T) parameters alongside a compact residual-trend network. --- ### Transformer Interpretability from Perspective of Attention and Gradient Authors: Yongjin Cui, Xiaohui Fan, Huajun Chen Published: 2026-05-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.11392v1 Although researchers' attention is more focused on the performance of Transformer models, the interpretation of Transformer can never be ignored. Gradient is widely utilized in Transformer interpretation. From the perspective of attention and gradient, we conduct an in-depth study of Transformer interpretation and propose a method to achieve it by guiding the gradient direction, or more precisely, the attention direction. The method enables more comprehensive interpretation of feature regions, offers detail interpretation, and helps to better understand Transformer mechanism. Leveraging the difference in how Vision Transformer (ViT) and humans perceive images, we alter the class of an image in a way that is almost imperceptible to the human eye. This class rewriting phenomenon may potentially pose security risks in certain scenarios. --- ### Deep Reasoning in General Purpose Agents via Structured Meta-Cognition Authors: Dean Light, Michael Theologitis, Kshitish Ghate, Shuyue Stella Li, Benjamin Newman, Chirag Shah, Aylin Caliskan, Pang Wei Koh, Dan Suciu, Yulia Tsvetkov Published: 2026-05-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.11388v1 Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems. Current LLM agents lack this flexibility, as their scaffolds hard-code such reasoning decisions in advance. These scaffolds are effective when their prescribed structure matches the task, but brittle when solving the task requires adapting the structure of reasoning itself. We introduce Deep Reasoning -- an inference-time approach for constructing task-specific scaffolds through structured meta-reasoning. Deep Reasoning uses a formal language that represents meta-reasoning as executable decompositions over associative inference, formal computation, and recursive subproblem solving, enabling decomposition principles to be encoded as in-context examples that guide test-time scaffold construction. We instantiate this approach in a general-purpose agent (DOLORES) that distributes complex tasks across more controlled reasoning threads. We evaluate it against state-of-the-art scaffolding methods across four hard benchmarks: multi-hop reasoning, long-chain question answering, long-context aggregation, and deep research-style information seeking. DOLORES outperforms all evaluated scaffolds across three model sizes and two model families, improving over the strongest evaluated scaffold baseline by 24.8% on average. DOLORES distributes cognition across structured, lower-load reasoning threads, thereby reducing premature termination and hallucinations. This advantage can even bridge the scaling gap, with an 8B version surpassing all evaluated 32B baselines from the same family in more than half the settings. These results point toward future agentic systems that treat scaffolding as adaptive reasoning, constructing the structure each task requires just-in-time. --- ### Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies Authors: Alberta Longhini, David Emukpere, Jean-Michel Renders, Seungsu Kim Published: 2026-05-12 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.11387v1 We address the problem of fine-tuning pre-trained generative policies with reinforcement learning (RL) while preserving the multimodality of their action distributions. Existing methods for RL fine-tuning of generative policies (e.g., diffusion policies) improve task performance but often collapse diverse behaviors into a single reward-maximizing mode. To mitigate this issue, we propose an unsupervised mode discovery framework that uncovers latent behavioral modes within generative policies. The discovered modes enable the use of mutual information as an intrinsic reward, regularizing RL fine-tuning to enhance task success while maintaining behavioral diversity. Experiments on robotic manipulation tasks demonstrate that our method consistently outperforms conventional fine-tuning approaches, achieving higher success rates and preserving richer multimodal action distributions. --- ### Revisiting Privacy Preservation in Brain-Computer Interfaces: Conceptual Boundaries, Risk Pathways, and a Protection-Strength Grading Framework Authors: Lei Sun, Xiuqing Mao, Shuai Zhang, Qingyu Zeng, Min Zhao, Jiyuan Li, Wenle Dong Published: 2026-05-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.11386v1 Brain-computer interfaces (BCIs) are moving rapidly from laboratory research into clinical, edge, and real-world settings. Under ISO/IEC 8663:2025, a BCI is a direct communication link between central nervous system activity and external software or hardware systems. This link expands privacy risk beyond raw neural-signal leakage: neural data, derived representations, model assets, and decoded outputs can be re-associated with individuals across collection, transmission, storage, training, inference, and feedback, or used to infer information beyond what a task requires. Starting from the general BCI paradigm, this review deffnes privacy-protection boundaries, protection objects, and the relationship between user data privacy and model privacy within a shared risk pathway. It then proposes a three-dimensional framework - protection object, lifecycle stage, and dominant protection-strength level - to classify existing work into four levels of protection strength. Finally, mental privacy and neuroethical risks are treated as open issues, emphasizing that BCI privacy protection should not only obscure data but also disentangle task-irrelevant sensitive information while preserving downstream utility. Keywords: Brain-computer interface, Neural data privacy, User data privacy, Model privacy, Disentanglement of task-irrelevant sensitive information, Protection-strength grading, Neuroethical risks --- ### JACoP: Joint Alignment for Compliant Multi-Agent Prediction Authors: Qingze Liu, Alen Mrdovic, Danrui Li, Mathew Schwartz, Sejong Yoon, Mubbasir Kapadia Published: 2026-05-12 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.11385v1 Stochastic Human Trajectory Prediction (HTP) using generative modeling has emerged as a significant area of research. Although state-of-the-art models excel in optimizing the accuracy of individual agents, they often struggle to generate predictions that are collectively compliant, leading to output trajectories marred by social collisions and environmental violations, thus rendering them impractical for real-world applications. To bridge this gap, we present JACoP: Joint Alignment for Compliant Multi-Agent Prediction, an innovative multi-stage framework that ensures scene-level plausibility. JACoP incorporates an Anchor-Based Agent-Centric Profiler for effective initial compliance filtering and employs a Markov Random Field (MRF) based aligner to formalize the joint selection for scene predictions. By representing inter-agent spatial and social costs as MRF energy potentials, we successfully infer and sample from the joint trajectory distribution, achieving prediction with optimal scene compliance. Comprehensive experiments show that JACoP not only achieves competitive accuracy, but also sets a new standard in reducing both environmental violations and social collisions, thereby confirming its ability to produce collectively feasible and practically applicable trajectory predictions. --- ### HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels Authors: Ningkang Peng, Jingyang Mao, Qianfeng Yu, Xiaoqian Peng, Peirong Ma, Yanhui Gu Published: 2026-05-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.11383v1 In large-scale visual recognition and data mining tasks, the presence of noisy labels severely undermines the generalization capability of deep neural networks (DNNs). Prevalent sample selection methods rely primarily on training loss or prediction confidence for passive screening. However, within a feature space degraded by noise, decision boundaries undergo systematic boundary collapse. This phenomenon hinders the ability of the model to distinguish between hard clean samples and noisy samples at the decision margins, thereby creating a significant performance bottleneck. This study is the first to emphasize the pivotal importance of active boundary restoration for noise-robust learning. We propose HamBR, a novel paradigm based on Hamiltonian dynamics. The core approach leverages the Spherical Hamiltonian Monte Carlo (Spherical HMC) mechanism to actively probe inter-class ambiguous regions within the representation space and synthesize high-quality virtual outliers. By imposing explicit repulsion constraints via energy-based modeling, these synthesized samples establish robust energy barriers at the decision boundaries. This mechanism forces real samples to move from dispersed overlapping regions toward their respective class centers, thereby restoring the discriminative sharpness of the decision boundaries. HamBR demonstrates exceptional versatility and can be integrated as a plug-and-play defense module into existing semi-supervised noisy label learning frameworks. Empirical evaluations show that the proposed paradigm significantly enhances the discriminative accuracy of hard boundary samples, achieving state-of-the-art (SOTA) performance on CIFAR-10/100 and real-world noise benchmarks. Furthermore, it exhibits superior convergence efficiency and reliable robustness, while improving significantly the capability of the model for Out-of-Distribution (OOD) detection. --- ### TRACE: Temporal Routing with Autoregressive Cross-channel Experts for EEG Representation Learning Authors: Fan Ma, Qier An, Peng Chen, Lingfei Qian, Xiang Lan, Mingyang Jiang, Zhiling Gu, Xenophon Papademetris, Hua Xu Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.11380v1 Learning transferable representations for electroencephalography (EEG) remains challenging because EEG signals are inherently multi-channel and non-stationary. Channels observed at the same time provide coupled measurements of neural activity, while the relevant temporal dynamics vary across contexts. This structure is poorly matched by architectures that apply uniform computation across time or route each channel patch independently. To this end, we propose TRACE, an autoregressive EEG pre-training framework that predicts future EEG patches from causal context while performing temporally adaptive and cross-channel coherent computation. At each temporal step, TRACE derives an expert routing decision from the causal cross-channel history and applies it jointly to all channels at that step. This preserves instantaneous cross-channel coherence while allowing different temporal regimes to activate different computation. Since routing is defined over the available channel set and causal temporal context, TRACE is compatible with heterogeneous pre-training across corpora with different channel counts, montages, sequence lengths, and recording domains. Across eight downstream EEG benchmarks, TRACE is evaluated in both settings: when downstream domains are seen only as unlabeled pre-training data and when downstream datasets are completely unseen during pre-training. It obtains the best results on several benchmarks while remaining competitive on motor imagery and clinical event classification tasks, with ablations supporting the importance of cross-channel temporal routing. --- ### An Empirical Study of Automating Agent Evaluation Authors: Kang Zhou, Sangmin Woo, Haibo Ding, Kiran Ramnath, Subramanian Chidambaram, Aosong Feng, Vinayak Arannil, Muhyun Kim, Ishan Singh, Darren Wang, Zhichao Xu, Megha Gandhi et al. Published: 2026-05-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.11378v3 Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this evaluation process? Our study shows that simply prompting coding assistants is insufficient for this task. Without domain-specific evaluation knowledge, frontier coding assistants achieve only a 30% execution success rate and produce over-engineered evaluations averaging 12+ metrics per agent, indicating that strong coding ability does not automatically translate to reliable agent evaluation. We introduce EvalAgent, an AI assistant that automates the end-to-end agent evaluation pipeline. EvalAgent encodes evaluation domain expertise as evaluation skills (procedural instructions, reusable code and templates, and dynamically retrieved API documentation) that compose into a trace-based pipeline producing complete evaluation artifacts including metrics, executable code, and reports. To systematically assess generated evaluations, we introduce a meta-evaluation framework alongside AgentEvalBench, a benchmark comprising 20 agents, each paired with evaluation requirements and test scenarios. We further propose the Eval@1 metric to measure whether generated evaluation code both executes and yields meaningful results on the first run. Our experiments show that EvalAgent produces focused evaluations, improving Eval@1 from 17.5% to 65%, and achieving 79.5% human expert preference over baseline approaches. Further ablation studies show that evaluation skills are critical for handling complex evaluation: removing them causes Eval@1 to drop significantly from 65% to 30%. --- ### An Empirical Study of Automating Agent Evaluation Authors: Kang Zhou, Sangmin Woo, Haibo Ding, Kiran Ramnath, Subramanian Chidambaram, Aosong Feng, Vinayak Arannil, Muhyun Kim, Ishan Singh, Darren Wang, Zhichao Xu, Megha Gandhi et al. Published: 2026-05-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.11378v2 Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this evaluation process? Our study shows that simply prompting coding assistants is insufficient for this task. Without domain-specific evaluation knowledge, frontier coding assistants achieve only a 30% execution success rate and produce over-engineered evaluations averaging 12+ metrics per agent, indicating that strong coding ability does not automatically translate to reliable agent evaluation. We introduce EvalAgent, an AI assistant that automates the end-to-end agent evaluation pipeline. EvalAgent encodes evaluation domain expertise as evaluation skills (procedural instructions, reusable code and templates, and dynamically retrieved API documentation) that compose into a trace-based pipeline producing complete evaluation artifacts including metrics, executable code, and reports. To systematically assess generated evaluations, we introduce a meta-evaluation framework alongside AgentEvalBench, a benchmark comprising 20 agents, each paired with evaluation requirements and test scenarios. We further propose the Eval@1 metric to measure whether generated evaluation code both executes and yields meaningful results on the first run. Our experiments show that EvalAgent produces focused evaluations, improving Eval@1 from 17.5% to 65%, and achieving 79.5% human expert preference over baseline approaches. Further ablation studies show that evaluation skills are critical for handling complex evaluation: removing them causes Eval@1 to drop significantly from 65% to 30%. --- ### LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents Authors: Giuliano Lorenzoni, Paulo Alencar, Donald Cowan Published: 2026-05-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.11376v1 We propose a personal-LLM exchange (LLM-X), a scalable negotiation-oriented environment that enables direct, structured communication across populations of personal agents (LLMs), each representing an individual user. Unlike existing tool-centric protocols that focus on agent-API interaction, LLM-X introduces a message bus and routing substrate for LLM-to-LLM coordination with guarantees around schema validity and policy enforcement. We contribute: (1) an architecture for LLM-X comprising federated gateways, topic-based routing, and policy enforcement; (2) a typed message protocol supporting capability negotiation and contract-net-style coordination; and (3) the first empirical evaluation of LLM-based multi-agent negotiation at scale. Experiments span 5, 9, and 12 agents, under distinct negotiation policies (Low, Medium, High), and across both short-run (minutes) and long-run (2h, 12h) load conditions. Results highlight clear policy-performance trade-offs: stricter policies improve robustness and fairness but increase latencies and message volume. Extended runs confirm that LLM-X remains stable under sustained load, with bounded latency drift. --- ### Test-Time Compute for Frozen Embedding Models through Agentic Program Search Authors: Han Xiao Published: 2026-05-12 Categories: cs.LG, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2605.11374v5 Test-time compute is widely believed to benefit only large reasoning models, leaving small models with nothing to gain. We argue the opposite for dense retrieval, since modern small embedding models are distilled or adapted from large language model backbones and can inherit their latent test-time-compute potential. We ask how much retrieval quality a frozen embedding model gains at inference alone, with no auxiliary model and no parameters trained at deployment. An agentic loop in which a large language model writes programs over a frozen encoder API explores 144 candidates and yields twelve Pareto-optimal programs that trade inference compute for quality across cost ratios from $c{=}1.2$ to $14.7$, every one improving nDCG@10 on all 14 discovery tasks. The programs use no trainable parameters and recover classical retrieval primitives, among them reciprocal rank fusion, the Fisher linear discriminant, Rocchio pseudo-relevance feedback, and sentence-level MaxSim. Applied unmodified to nineteen held-out tasks and three unseen encoder families, a single fixed program improves the majority of tasks, with a positive median $Δ$nDCG@10 and a 54 to 57% win-rate at $c{\ge}4$, and the gains are largest on encoder families never seen during discovery. A matched-budget learned projection head trained on the same tasks does not transfer this way, improving in-domain retrieval by $+0.20$ to $+0.25$ nDCG@10 yet falling below baseline on every held-out encoder. Small embedding models therefore inherit usable test-time-compute potential, and a frozen encoder converts inference compute into retrieval gains that transfer to new corpora and encoders with no per-domain labels. --- ### Causal Algorithmic Recourse: Foundations and Methods Authors: Drago Plecko, Collin Wang, Elias Bareinboim Published: 2026-05-12 Categories: cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.11373v1 The trustworthiness of AI decision-making systems is increasingly important. A key feature of such systems is the ability to provide recommendations for how an individual may reverse a negative decision, a problem known as algorithmic recourse. Existing approaches treat recourse outcomes as counterfactuals of a fixed unit, ignoring that real-world recourse involves repeated decisions on the same individual under possibly different latent conditions. We develop a causal framework that models recourse as a process over pre- and post-intervention outcomes, allowing for partial stability and resampling of latent variables. We introduce post-recourse stability conditions that enable reasoning about recourse from observational data alone, and develop a copula-based algorithm for inferring the effects of recourse under these conditions. For settings where paired observations of the same individual before and after intervention are available (called recourse data), we develop methods for inferring copula parameters and performing goodness-of-fit testing. When the copula model is rejected, we provide a distribution-free algorithm for learning recourse effects directly from recourse data. We demonstrate the value of the proposed methods on real and semi-synthetic datasets. --- ### Dynamic Full-body Motion Agent with Object Interaction via Blending Pre-trained Modular Controllers Authors: Sanghyeok Nam, Byoungjun Kim, Daehyung Park, Tae-Kyun Kim Published: 2026-05-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.11369v1 Generating physically plausible dynamic motions of human-object interaction (HOI) remains challenging, mainly due to existing HOI datasets limited to static interactions, and pretrained agents capable of either dynamic full-body motions without objects or static HOI motions. Recent works such as InsActor and CLoSD generate HOI motions in planning and execution stages, are yet limited to either static or short-term contacts e.g. striking. In this work, we propose a framework that fulfills dynamic and long-term interaction motions such as running while holding a table, by combining pretrained motion priors and imitation agents in planning and execution stages. In the planning stage, we augment HOI datasets with dynamic priors from a pretrained human motion diffusion model, followed by object trajectory generation. This plans dynamic HOI sequences. In the execution stage, a composer network blends actions of pretrained imitation agents specialized either for dynamic human motions or static HOI motions, enabling spatio-temporal composition of their complementary skills. Our method over relevant prior-arts consistently improves success rates while maintaining interaction for dynamic HOI tasks. Furthermore, blending pretrained experts with our composer achieves competitive performance in significantly reduced training time. Ablation studies validate the effectiveness of our augmentation and composer blending. --- ### LPDP: Inference-Time Reward Control for Variable-Length DNA Generation with Edit Flows Authors: Jeongchan Kim, Yunkyung Ko, Jong Chul Ye Published: 2026-05-12 Categories: cs.LG, cs.AI, q-bio.GN arXiv: https://arxiv.org/abs/2605.11368v1 We study the application of recent Edit Flows for inference-time reward control for DNA sequence generation. Unlike most reward-guided DNA generation frameworks, which operate on fixed-length sequence spaces, Edit Flows have a potential to generate variable-length DNA through biologically plausible insertion, deletion, and substitution operations. In particular, we propose Local Perturbation Discrete Programming (LPDP), a training-free, intermediate-state and action-aware local re-solving operator for variable-length DNA edit-action generators at inference time. More specifically, at each guided rollout step, LPDP scores one-step root edits, retains a near-best root band, and re-ranks each retained root by solving a bounded local discrete program around its child sequence. This local program uses the typed geometry of edit actions to focus on coherent substitution, insertion, or deletion subgraphs, and aggregates local continuations with either a hard Max backup or a soft log-sum-exponential (LSE) backup. We instantiate LPDP in two regimes: front-loaded reward tilting for enhancer optimization, where early edits are critical for establishing global regulatory sequence structure, and back-loaded reward tilting for exon-intron-exon inpainting, where late edits fine-tune splice-boundary contexts. --- ### 3D-Belief: Embodied Belief Inference via Generative 3D World Modeling Authors: Yifan Yin, Zehao Wen, Suyu Ye, Jieneng Chen, Zehan Zheng, Nanru Dai, Haojun Shi, Aydan Huang, Zheyuan Zhang, Alan Yuille, Jianwen Xie, Ayush Tewari et al. Published: 2026-05-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.11367v2 Recent advances in visual generative models have highlighted the promise of learning generative world models. However, most existing approaches frame world modeling as novel-view synthesis or future-frame prediction, emphasizing visual realism rather than the structured uncertainty required by embodied agents acting under partial observability. In this work, we propose a different perspective: world modeling as embodied belief inference in 3D space. From this view, a world model should not merely render what may be seen, but maintain and update an agent's belief about the unobserved 3D world as new observations are acquired. We identify several key capabilities for such models, including spatially consistent scene memory, multi-hypothesis belief sampling, sequential belief updating, and semantically informed prediction of unseen regions. We instantiate these ideas in 3D-Belief, a generative 3D world model that infers explicit, actionable 3D beliefs from partial observations and updates them online over time. Unlike prior visual prediction models, 3D-Belief represents uncertainty directly in 3D, enabling embodied agents to imagine plausible scene completions and reason over partially observed environments. We evaluate 3D-Belief on 2D visual quality for scene memory and unobserved-scene imagination, object- and scene-level 3D imagination using our proposed 3D-CORE benchmark, and challenging object navigation tasks in both simulation and the real world. Experiments show that 3D-Belief improves 2D and 3D imagination quality and downstream embodied task performance compared to state-of-the-art methods. --- ### Causal Bias Detection in Generative Artificial Intelligence Authors: Drago Plecko Published: 2026-05-12 Categories: cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.11365v2 Automated systems built on artificial intelligence (AI) are increasingly deployed across high-stakes domains, raising critical concerns about fairness and the perpetuation of demographic disparities that exist in the world. In this context, causal inference provides a principled framework for reasoning about fairness, as it links observed disparities to underlying mechanisms and aligns naturally with human intuition and legal notions of discrimination. Prior work on causal fairness primarily focuses on the standard machine learning setting, where a decision-maker constructs a single predictive mechanism $f_{\widehat Y}$ for an outcome variable $Y$, while inheriting the causal mechanisms of all other covariates from the real world. The generative AI setting, however, is markedly more complex: generative models can sample from arbitrary conditionals over any set of variables, implicitly constructing their own beliefs about all causal mechanisms rather than learning a single predictive function. This fundamental difference requires new developments in causal fairness methodology. We formalize the problem of causal fairness in generative AI and unify it with the standard ML setting under a common theoretical framework. We then derive new causal decomposition results that enable granular quantification of fairness impacts along both (a) different causal pathways and (b) the replacement of real-world mechanisms by the generative model's mechanisms. We establish identification conditions and introduce efficient estimators for causal quantities of interest, and demonstrate the value of our methodology by analyzing race and gender bias in large language models across different datasets. --- ### PresentAgent-2: Towards Generalist Multimodal Presentation Agents Authors: Wei Wu, Ziyang Xu, Zeyu Zhang, Yang Zhao, Hao Tang Published: 2026-05-12 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2605.11363v1 Presentation generation is moving beyond static slide creation toward end-to-end presentation video generation with research grounding, multimodal media, and interactive delivery. We introduce PresentAgent-2, an agentic framework for generating presentation videos from user queries. Given an open-ended user query and a selected presentation mode, PresentAgent-2 first summarizes the query into a focused topic and performs deep research over presentation-friendly sources to collect multimodal resources, including relevant text, images, GIFs, and videos. It then constructs presentation slides, generates mode-specific scripts, and composes slides, audio, and dynamic media into a complete presentation video. PresentAgent-2 supports three independent presentation modes within a unified framework: Single Presentation, which generates a single-speaker narrated presentation video; Discussion, which creates a multi-speaker presentation with structured speaker roles, such as for asking guiding questions, explaining concepts, clarifying details, and summarizing key points; and Interaction, which independently supports answering audience questions grounded in the generated slides, scripts, retrieved evidence, and presentation context. To evaluate these capabilities, we build a multimodal presentation benchmark covering single presentation, discussion, and interaction scenarios, with task-specific evaluation criteria for content quality, media relevance, dynamic media use, dialogue naturalness, and interaction grounding. Overall, PresentAgent-2 extends presentation generation from document-dependent slide creation to query-driven, research-grounded presentation video generation with multimodal media, dialogue, and interaction. Code: https://github.com/AIGeeksGroup/PresentAgent-2. Website: https://aigeeksgroup.github.io/PresentAgent-2. --- ### Causal Fairness for Survival Analysis Authors: Drago Plecko Published: 2026-05-12 Categories: cs.LG, cs.AI, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2605.11362v1 In the data-driven era, large-scale datasets are routinely collected and analyzed using machine learning (ML) and artificial intelligence (AI) to inform decisions in high-stakes domains such as healthcare, employment, and criminal justice, raising concerns about the fairness behavior of these systems. Existing works in fair ML cover tasks such as bias detection, fair prediction, and fair decision-making, but largely focus on static settings. At the same time, fairness in temporal contexts, particularly survival/time-to-event (TTE) analysis, remains relatively underexplored, with current approaches to fair survival analysis adopting statistical fairness definitions, which, even with unlimited data, cannot disentangle the causal mechanisms that generate disparities. To address this gap, we develop a causal framework for fairness in TTE analysis, enabling the decomposition of disparities in survival into contributions from direct, indirect, and spurious pathways. This provides a human-understandable explanation of why disparities arise and how they evolve over time. Our non-parametric approach proceeds in four steps: (1) formalizing the necessary assumptions about censoring and lack of confounding using a graphical model; (2) recovering the conditional survival function given covariates; (3) applying the Causal Reduction Theorem to reframe the problem in a form amenable to causal pathway decomposition; (4) estimating the effects efficiently. Finally, our approach is used to analyze the temporal evolution of racial disparities in outcome after admission to an intensive care unit (ICU). --- ### The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives Authors: Ankur Moitra, Andrej Risteski, Dhruv Rohatgi Published: 2026-05-12 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2605.11361v1 Inference-time reward alignment asks how to turn a pre-trained diffusion model with base law $p$ into a sampler that favors a reward $r$ while remaining close to $p$. Since there is no canonical distributional distance for this closeness constraint, different choices lead to different "reward-aligned" laws and, just as importantly, different algorithmic problems. We develop a primitive-based approach to reward alignment: rather than assuming arbitrary reward-aligned laws can be sampled, we ask which simple algorithmic primitives suffice to implement alignment for non-trivial reward classes. If closeness is measured in KL distance, the target law is $q(x) \propto p(x) \exp(λ^{-1}r(x))$. For this setting, we show that linear exponential tilts of the form $q(x)\propto p(x)\exp(\langle θ, x \rangle)$ -- which according to recent work (MRR26) can be efficiently sampled from -- are a sufficient primitive for aligning to a very broad class of convex low-dimensional rewards. If closeness is measured in Wasserstein distance, the corresponding primitive is a proximal transport oracle: given $x$, solve $\mbox{argmax}_y \{r(y)- λc(x,y)\}$. This oracle can be efficiently implemented for concave or low-dimensional Lipschitz rewards $r(x)=f(Ax)$. Together, these results illustrate that the choice of distribution distance for alignment affects the computational primitive and the tractable reward class. --- ### Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization Authors: Ying Li, Yanju Chen, Peiran Wang, Issac Khabra, Faysal Hossain Shezan, Yu Feng, Yuan Tian Published: 2026-05-12 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.11360v1 As Model Context Protocol adoption grows, securing tool invocations via meaningful user consent has become a critical challenge, as existing methods, broad always allow toggles or opaque LLM-based decisions, fail to account for dangerous call arguments and often lead to consent fatigue. In this work, we present Conleash, a client-side middleware that enforces boundary-scoped authorization by utilizing a risk lattice to auto-permit safe calls within known boundaries while escalating risks, a policy engine for user-defined invariants, and a refinement loop that converts user decisions into reusable rules. Evaluated on 984 real-world traces, Conleash achieved 98.2% accuracy, caught 99.4% of escalations, and added only 8.2 ms of overhead for policy verification; furthermore, in a user study where N=16, participants significantly preferred Conleash scoped permissions over traditional methods, citing higher trust and reduced prompting. --- ### CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing Authors: Ming Du, Xiangyu Yin, Yanqi Luo, Dishant Beniwal, Songyuan Tang, Hemant Sharma, Mathew J. Cherukara Published: 2026-05-12 Categories: cs.AI, physics.data-an arXiv: https://arxiv.org/abs/2605.11359v3 Scientific data processing often requires task-specific algorithms or AI models, creating a barrier for domain scientists who need to analyze their data but may not have extensive computing or image-processing expertise. This barrier is especially pronounced when data are noisy, have a high dynamic range, are sparsely labeled, or are only loosely specified. We introduce CVEvolve, an autonomous agentic harness with a zero-code interface for scientific data-processing algorithm discovery. CVEvolve combines a multi-round search strategy with tools for code execution, evaluation implementation, history management, holdout testing, and optional inspection of scientific data and visual outputs. The search alternates between discovery and improvement actions, and uses lineage-aware stochastic candidate sampling to balance exploration and exploitation. We demonstrate CVEvolve on X-ray fluorescence microscopy image registration, Bragg peak detection, high-energy diffraction microscopy image segmentation, and hybrid analytical-learning-based affine registration. Across these tasks, CVEvolve discovers algorithms that improve over baseline methods, while holdout test tracking helps identify candidates that generalize better than later over-optimized alternatives. These results show that zero-code, autonomous LLM-powered algorithm development can help domain scientists turn unstructured scientific image data into practical algorithms and downstream scientific discoveries. --- ### gym-invmgmt: An Open Benchmarking Framework for Inventory Management Methods Authors: Reza Barati, Qinmin Vivian Hu Published: 2026-05-12 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2605.11355v1 Inventory-policy comparisons are often difficult to interpret because performance depends on the evaluation contract as much as on the policy itself. Differences in topology, demand regime, information access, feasibility constraints, shortage treatment, and Key Performance Indicator (KPI) definitions can change method rankings. We present gym-invmgmt, a Gymnasium-compatible extension of the OR-Gym inventory-management lineage for auditable cross-paradigm evaluation. The benchmark evaluates optimization, heuristic, and learned controllers under a shared CoreEnv transition, reward, action-bound, and KPI contract, while varying stress conditions through a 22-scenario core grid plus four supplemental MARL-mode rows. Within these released scenarios, informed stochastic programming provides the strongest non-oracle reference, reflecting the value of scenario hedging under forecast access, but at substantially higher online computational cost. Among learned controllers, the Proximal Policy Optimization Transformer variant (PPO-Transformer) achieves the strongest learned-policy quality at fast inference, while Residual Reinforcement Learning (Residual RL) provides competitive hybrid performance. The graph neural network variant (PPO-GNN) is highly competitive on the default divergent topology but less robust on the serial topology. Imitation learning performs well in stationary regimes but degrades under demand shift, and the bounded Large Language Model (LLM) policy-parameter baseline is best interpreted as a diagnostic controller rather than an autonomous inventory optimizer. Overall, the benchmark identifies scenario-conditioned leaders while showing that performance depends jointly on information access, demand shift, topology, and policy representation. --- ### Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction Authors: Haoyu Zhang, Zeyu Zhang, Zedong Zhou, Yang Zhao, Hao Tang Published: 2026-05-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.11354v1 Transformer-based 3D reconstruction has emerged as a powerful paradigm for recovering geometry and appearance from multi-view observations, offering strong performance across challenging visual conditions. As these models scale to larger backbones and higher-resolution inputs, improving their efficiency becomes increasingly important for practical deployment. However, modern 3D transformer pipelines face two coupled challenges: dense multi-view attention creates substantial token-mixing overhead, and low-precision execution can destabilize geometry-sensitive representations and degrade depth, pose, and 3D consistency. To address the first challenge, we propose Lite3R, a model-agnostic teacher-student framework that replaces dense attention with Sparse Linear Attention to preserve important geometric interactions while reducing attention cost. To address the second challenge, we introduce a parameter-efficient FP8-aware quantization-aware training (FP8-aware QAT) strategy with partial attention distillation, which freezes the vast majority of pretrained backbone parameters and trains only lightweight linear-branch projection layers, enabling stable low-precision deployment while retaining pretrained geometric priors. We further evaluate Lite3R on two representative backbones, VGGT and DA3-Large, over BlendedMVS and DTU64, showing that it substantially reduces latency (1.7-2.0x) and memory usage (1.9-2.4x) while preserving competitive reconstruction quality overall. These results demonstrate that Lite3R provides an effective algorithm-system co-design approach for practical transformer-based 3D reconstruction. Code: https://github.com/AIGeeksGroup/Lite3R. Website: https://aigeeksgroup.github.io/Lite3R. --- ### Human-AI Productivity Paradoxes: Modeling the Interplay of Skill, Effort, and AI Assistance Authors: Ali Aouad, Thodoris Lykouris, Huiying Zhong Published: 2026-05-12 Categories: cs.GT, cs.AI, econ.TH arXiv: https://arxiv.org/abs/2605.11350v1 Generative Artificial Intelligence (AI) tools are rapidly adopted in the workplace and in education, yet the empirical evidence on AI's impact remains mixed. We propose a model of human-AI interaction to better understand and analyze several mechanisms by which AI affects productivity. In our setup, human agents with varying skill levels exert utility-maximizing effort to produce certain task outcomes with AI assistance. We find that incorporating either endogeneity in skill development or in AI unreliability can induce a productivity paradox: increased levels of AI assistance may degrade productivity, leading to potentially significant shortfalls. Moreover, we examine the long-term distributional effect of AI on skill, and demonstrate that skill polarization can emerge in steady state when accounting for heterogeneity in AI literacy -- the agent's capability to identify and adapt to inaccurate AI outputs. Our results elucidate several mechanisms that may explain the emergence of human-AI productivity paradoxes and skill polarization, and identify simple measures that characterize when they arise. --- ### Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence Authors: Ujun Jeong, Saketh Vishnubhatla, Bohan Jiang, Andre Harrison, Adrienne Raglin, Huan Liu Published: 2026-05-12 Categories: cs.CL, cs.AI, cs.IR, cs.SI arXiv: https://arxiv.org/abs/2605.11348v1 During disasters, extracting causal relations from social media can strengthen situational awareness by identifying factors linked to casualties, physical damage, infrastructure disruption, and cascading impacts. However, disaster-related posts are often informal, fragmented, and context-dependent, and they may describe personal experiences rather than explicit causal relations. In this work, we examine whether Large Language Models (LLMs) can effectively extract causal relations from disaster-related social media posts. To this end, we (1) propose an expert-grounded evaluation framework that compares LLM-generated causal graphs with reference graphs derived from disaster-specific reports and (2) assess whether the extracted relations are supported by post-event evidence or instead reflect model priors. Our findings highlight both the potential and risks of using LLMs for causal relation extraction in disaster decision-support systems. --- ### Gradient-Free Noise Optimization for Reward Alignment in Generative Models Authors: Jeongsol Kim, Hongeun Kim, Jian Wang, Jong Chul Ye Published: 2026-05-12 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.11347v2 Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making them difficult to extend to deterministic generators. A natural alternative is noise-space optimization, but existing approaches require backpropagation through the generator and reward pipeline, limiting applicability to differentiable settings. To address this, here we present ZeNO (Zeroth-order Noise Optimization), a gradient-free framework that formulates noise optimization as a path-integral control problem, estimable from zeroth-order reward evaluations alone. When instantiated with an Ornstein--Uhlenbeck reference process, the update connects to Langevin dynamics implicitly targeting a reward-tilted distribution. ZeNO enables effective inference-time scaling and demonstrates strong performance across diverse generators and reward functions, including a protein structure generation task where backpropagation is infeasible. --- ### QFoldAgent: An Autonomous Quantum Optimization Multi-Agent System for Protein Structure Prediction Authors: Winson Chen, Yuqi Zhang, Sixu Chen, Nuo Xu, Qiang Guan, Caiwen Ding Published: 2026-05-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22549v1 Hybrid quantum-classical protein structure prediction depends strongly on Hamiltonian penalty weights, yet existing lattice-based workflows typically fix these coefficients by hand and evaluate only very short fragments in simulation. We present QFoldAgent, a closed-loop multi-agent framework for 5-residue tetrahedral-lattice folding in which a design agent proposes sequence-conditioned penalties, a VQE-based quantum-classical pipeline optimizes the resulting Hamiltonian under Qiskit Aer noise, and a feedback agent uses energy-landscape diagnostics and MolProbity validation signals to refine penalties across cycles. Ground-truth metrics such as RMSD are never exposed to the agents and are used only for evaluation. We study the framework on two complementary datasets: 55 QDockBank-derived fragments with known structures and 100 coverage-optimized unseen sequences. On the QDockBank benchmark, QFoldAgent reduces median RMSD from 3.64 Å to 3.20 Å, with the largest gains on the hardest targets. On unseen sequences, the closed loop raises structural validity from 87.5% to 98.7%, recovers 87% of initially invalid cases, and the strongest controller improves cycle-3 energy on 87% of sequences while maintaining 96% Ramachandran-favored geometry. These results show that iterative agent control can systematically improve optimization behavior and reduce failure cases in a 5-residue quantum setting. --- ### SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series Authors: Giovanni B. Esposito, Francesco Antici, Daniele Cesarini, Andrea Bartolini Published: 2026-05-11 Categories: cs.AI, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2607.22548v1 Data centers and their compute nodes require accurate and flexible digital twins capable of modeling the complex interplay of workloads, environmental parameters, and physical metrics. Current machine learning approaches for HPC and its telemetry typically rely on a static subset of anonymous, fixed-position sensor variables tailored to single tasks. Consequently, these models become obsolete when target tasks change or sensor metrics vary. We propose SeT-Diff, the first foundational model for compute node telemetry and time-series. Unlike rigid architectures, our diffusion-based approach conditions the generative process on each sensor's semantic description, decoupling the system dynamics from the structure of the dataset. Experiments on a real-world supercomputer dataset demonstrate a Mean Absolute Error (MAE) of 0.0470 on reconstruction tasks. SeT-Diff exhibits zero-shot permutation stability, maintaining accuracy with negligible degradation even when sensors are shuffled. A single pre-trained model effectively performs data imputation, forecasting, and virtual sensing - achieving a 0.033 MAE in thermal inference - making SeT-Diff an effective data-driven digital twin for HPC systems. --- ### Transferable Latency Prediction for Fast LLM Screening on Heterogeneous Edge Devices Authors: Xiaolong Tu, Vinod K. Mishra, Venkat R. Dasari, Anu G. Bourgeois, Haoxin Wang Published: 2026-05-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.21602v1 Accurate latency prediction is critical for deploying large language models (LLMs) on heterogeneous edge devices, where inference latency is affected by model architecture, prompt behavior, runtime backend, hardware utilization, dynamic voltage and frequency scaling (DVFS), and thermal variation. This paper presents a runtime-aware latency prediction framework for deployment-oriented LLM selection. The framework represents each inference request as a hardware-runtime-model-prompt configuration, separates inference into prefill and decode phases, and adaptively fuses static descriptors with dynamic hardware telemetry through a gated prediction model. We evaluate the framework using Pixel mobile devices and validate the profiling pipeline on Jetson Nano, Orange Pi 5 Pro, and an RTX 3090-class GPU platform. On Pixel 8, the full predictor improves total-latency R-squared from 0.953 to 0.960 and decode-latency R-squared from 0.957 to 0.973 over a static-only baseline. On Pixel 8 Pro, it improves prefill-latency R-squared from -1.383 to 0.966. For cross-device transfer, calibration improves Pixel 8 Pro to Pixel 8 total-latency R-squared from -0.974 to 0.940 and decode-latency R-squared from -1.085 to 0.927. Heterogeneous profiling further shows that latency is highly device- and runtime-dependent: the same SmolLM2 model family reaches 8.42 tokens/s on Orange Pi 5 Pro but 64.38 tokens/s on an RTX 3090-class GPU. These results demonstrate that runtime-aware prediction with lightweight calibration can reduce profiling cost and support latency-aware LLM deployment across heterogeneous edge platforms. --- ### TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG Authors: Chahana Dahal, Zuobin Xiong Published: 2026-05-11 Categories: cs.CL, cs.CR, cs.IR arXiv: https://arxiv.org/abs/2607.20437v1 Production Retrieval Augmented Generation (RAG) systems rely on aggregating multiple external documents to answer complex queries. However, the retrieved documents introduce a new threat surface that can be exploited to launch split-knowledge attacks. In this attack, the adversary injects documents that are individually benign but create false associations when combined and fed to language models. This paper shows that the new attack is structurally invisible to existing per-document filters, like LlamaGuard. To address this issue in RAG, this work introduces TopoGuard, a family of graph theory-based methods specifically targeting the split-knowledge attacks by building a semantic similarity graph from retrieved documents and detecting contexts with malicious topology. Grounded on the theoretical analysis, the TopoGuard family has been proven to be effective and robust even with noisy inputs. Extensive experiments are conducted on two retrieval datasets and compared with multiple baseline methods. Specifically, the TopoGuard-$λ_2$+Entity catches 21$\times$ more attacks than LlamaGuard-2-8B at 1\% FPR (32.6\% vs 1.5\% recall) on the HotpotQA dataset. Compared with production RAG detection systems using large language models, the proposed TopoGuard variants run efficiently at sub-millisecond latency and stay robust under adaptive adversaries and benign cross-domain queries. --- ### Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models Authors: Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz Published: 2026-05-11 Categories: cs.CL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.20436v1 Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption. A checkpoint can appear fixed under evaluation-style prompts while the same behavior persists under ordinary-use prompts. Output scores reveal this mismatch but do not locate it. We investigate whether the distinction is encoded in a stable internal site and introduce an approach that fits a paired activation contrast at a path-patching-informed mid-depth window, then modifies the resulting coordinate on held-out prompts. The intervention closes the evaluation-to-deployment gap in ten of twelve model--behavior settings (six of the eight settings with $n{\geq}120$ paired questions) across four full-matrix instruction-tuned model instances; a fifth model supports localization and edit-provenance checks, and deployment-framed rates change by at most $6.1$pp. The two flat cells, both sycophancy, indicate that a single-coordinate audit is not sufficient when the installed distinction is higher-rank or missed by the depth heuristic. The audit is a diagnostic for fine-tuned checkpoints, not a training-time defense or a guarantee of deployment safety. --- ### Making Open-Source Text LLM Watermarks Durable Against Merging Authors: Luisa Scharff, Thibaud Gloaguen, Robin Staab, Martin Vechev Published: 2026-05-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.20435v1 Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly into their weights. Yet, OSMs are subject to post-training modifications, which has been shown to remove the watermark. Model merging in particular, a prominent method used for combining expert knowledge and preventing catastrophic forgetting, strongly removes such OSM watermarks. A key question is how to enable OSM watermarks that survive subsequent merging. In this work, we show for the first time how to design an OSM watermark that is durable against model merging. We propose Merge-Adversarial Training, an adversarial training algorithm to distill text watermarks into model weights while being robust to subsequent model merging. Our approach consistently outperforms all baselines (e.g. with SLERP up to +51 percentage points (pp) TPR@1%FPR with +25 pp on average) while preserving downstream capabilities. We also for the first time evaluate OSM watermarks against realistic merge scenarios, representing common use-cases such as combining expert capabilities or preventing catastrophic forgetting, and with 3 prominent merging algorithms. More broadly, our findings suggest that adversarial training is a reliable approach for increasing OSM watermark durability against post-training modifications. --- ### Break Through the Compression Bottleneck: From Theory to Practice Authors: Xiusheng Huang, Lu Wang, Yequan Wang, Jun Zhao, Kang Liu Published: 2026-05-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.20434v1 As the parameter size of language models continues to grow, effective model compression is required to reduce their computational and memory overhead. Existing compression methods suffer from bottleneck issues: when the compression ratio is increased, performance degrades significantly. Low-rank decomposition and quantization are two prominent compression methods that have been proven to significantly reduce the computational and memory requirements of Large Language Models (LLMs) while maintaining model accuracy. Evidently, combining these two methods will break through the existing compression bottleneck. However, how these two methods interact when combined remains a critical question for developers, as many assume they are orthogonal, meaning their combination would not introduce additional errors beyond those independently introduced by each method. This paper provides the first mathematical proof that low-rank decomposition and quantization are non-orthogonal. We validate these findings through a series of experiments on large language models. Our results demonstrate that these methods are non-orthogonal, and their combination leads to significant performance degradation. Importantly, we propose a novel approach Diagonal Adhesive Method (DAM), which can effectively combine the two methods and mitigate the performance loss. Our research provides deep insights into model compression and lays a solid theoretical and experimental foundation for future related studies. --- ### A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges Authors: Wen Liang, Li Siyan, Zackary Rackauckas, Julia Hirschberg Published: 2026-05-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.27380v1 Automated coaching for oral presentations sits at the intersection of computer-assisted pronunciation training (CAPT), prosody modeling, and speech synthesis, yet no prior work has systematically surveyed and compared existing systems along these dimensions. This survey reviews and categorizes automated presentation coaching systems, spanning pronunciation tutors, fluency and prosody coaches, multimodal trainers, and conference Q&A practice tools. We introduce a five-dimensional task taxonomy - covering segmental pronunciation, lexical stress, suprasegmental prosody, pacing, and content faithfulness - and explicitly map surveyed systems onto it to reveal coverage gaps. We further review the core technical methods these systems employ: TTS-based exemplar generation and diagnostic methods for pronunciation, prosody, and fluency assessment. Key open challenges include the scarcity of annotated presentation corpora, achieving accent-fair feedback across diverse L1 backgrounds, and delivering low-latency diagnostics for real-time rehearsal. --- ### Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents Authors: Chibuzor Okocha, Christan Grant Published: 2026-05-11 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2606.11219v1 Audio language models (ALMs) are increasingly used for speech-based understanding, yet their ability to perform semantic reasoning beyond transcription, Text-to-Audio Retrieval, Captioning, and Question-Answering accuracy remains insufficiently benchmarked. In particular, the effects of accent variation, domain shift, and semantic over-inference on audio reasoning are poorly understood. We evaluate audio language models across five semantic and paralinguistic reasoning tasks: entailment, consistency, plausibility, accent drift, and accent restraint. Collectively, these tasks assess a model's ability to reason over spoken audio as the primary evidence source, including whether a textual hypothesis can be inferred, contradicted, or left undetermined by the audio, whether statements align or conflict with spoken content, whether claims are plausible given the discourse, and whether model predictions remain stable or appropriately constrained across accent variation. These findings highlight critical limitations in current audio reasoning evaluations and hope to provide guidance for more robust and equitable ALM design and assessment --- ### LLM-Based Code Documentation Generation and Multi-Judge Evaluation Authors: Ikbel Ghrab, Mohamed Dhieb, Ismail Khenissi, Ines Abdeljaoued-Tej Published: 2026-05-11 Categories: cs.HC, cs.AI, cs.CL, cs.LG, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2606.09852v1 High-quality source code documentation is vital yet often neglected, especially in critical domains like healthcare where reliability and maintainability are essential. We presented an AI powered framework that automates documentation generation from code and repositories using eight state of the art Large Language Models (LLMs), including GPT, Gemini, Qwen, and LLaMA variants. Built on the PocketFlow orchestration framework, the system applies modular pipelines and advanced prompt engineering to produce structured, context aware documentation. To ensure quality and guide model selection, we introduced a MultiLLMasJudges evaluation framework, where four independent LLMs assess outputs across nine criteria, such as Completeness, Clarity, and Faithfulness. Experiments conducted on an open-source medical physics library, demonstrated showed a 42% performance gap between top and bottom models. By combining diverse model outputs, optimized prompting, and rigorous evaluation, our approach enhances documentation quality and reduces manual effort, especially in safety critical healthcare software. --- ### Temporal Preference Concepts and their Functions in a Large Language Model Authors: Ian Rios-Sialer, Shantanu Darveshi, Shuai Jiang, Avigya Paudel, Anastasiia Pronina, Ipshita Bandyopadhyay, Justin Shenk Published: 2026-05-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.05194v2 Large Language Models (LLMs) are increasingly being deployed to make decisions that require trading off near-term gains against long-term consequences, yet little is known about how they internally represent or resolve these tradeoffs. In this work, we causally localize an underlying subgraph for temporal preference in a distilled LLM (Qwen3-4B-Instruct-2507), identifying mid-to-upper-layer nodes through converging evidence from gradient-based attribution and activation patching. We find that the geometry of time horizon is encoded in the residual stream at the expected localized layers. A behavioral analysis reveals that unintervened LLMs discount the future several times less steeply than humans, yet this preference is unstable across contexts, motivating explicit control rather than implicit reliance on training. Finally, we find suggestive evidence that steering vectors can shift temporal preference. Our work demonstrates how mechanistic interpretability can bring us closer to reliable control over how LLMs plan and reason --- ### AI in the Enterprise: How People Use M365 Copilot Chat Authors: Scott Counts, Yan Chen, Jing Dong, Himanshu Sharma, Andrey Zaikin, Rui Hu, Alperen Kok, Gorkem Ozer Yilmaz, Siddharth Suri, Kiran Tomlinson, Sonia Jaffe, Will Wang Published: 2026-05-11 Categories: cs.CY, cs.AI, econ.GN arXiv: https://arxiv.org/abs/2605.23958v1 M365 Copilot is used every week by millions of people across more than a million companies around the world as part of their workflows. Uniquely positioned in the AI landscape given its near-exclusive use for work purposes, M365 Copilot can offer a clear picture of how people use AI for work and where that usage may expand next. This paper characterizes that usage through direct classification of user interactions with M365 Copilot Chat. Based on an anonymized and privacy-preserving analysis of a sample of approximately 5.5 million sessions, we combine a learned classification of user intent with a classification of O*NET work activities done with M365 Copilot Chat. We find that M365 Copilot is emerging as an everyday assistant for knowledge work: writing dominates, but users also rely on it for information retrieval, analysis, decision making and strategizing, and evaluating and diagnosing programs and systems, among others. Information seeking tasks remain common, but time trends suggest a relative shift away from ``chat as search'' and toward content and communication-related work. Comparisons across occupational groupings and to work done in the labor market further show that usage is broad but uneven, where the relative share of work done with M365 Copilot Chat cuts across jobs in some cases and is occupation-specific in others. Areas of relative underrepresentation in the labor market suggest the next frontier for enterprise AI adoption. --- ### Low-Cost Labels, Reliable Choices: Rollout-Calibrated Hyper-Heuristics for Job Shop Scheduling Authors: Junhao Wei, Yanxiao Li, Yifu Zhao, Zhenhong Peng, Baili Lu, Dexing Yao, Haochen Li, Qinbin He, Sio-Kei Im, Yapeng Wang, Xu Yang Published: 2026-05-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23957v1 Learning-assisted hyper-heuristics can select among dispatching rules while preserving the feasibility and interpretability of constructive Job Shop Scheduling Problem (JSSP) heuristics. Their main computational cost lies in label generation rather than model fitting, since each supervised label usually requires rolling out candidate rules from a partial schedule. We study this label-cost problem together with a reliability problem: a learned selector should not switch away from a strong default rule unless the predicted gain is credible. The proposed selector uses regret-normalized rollout labels, a contextual KNN uncertainty estimate, and a gate that acts only when the predicted improvement exceeds an uncertainty-adjusted margin. We also vary rollout depth and breadth to measure the cost-quality trade-off. On synthetic JSSP instances, the gated selector achieves the lowest mean RPD among learned selectors, remains close to the best fixed dispatching rule, and reduces Random-HH mean RPD by more than an order of magnitude. --- ### QUIVER: A Formal Framework for Quantifying Perturbation Propagation and Bifurcation in Compound AI Systems Authors: Prashanti Nilayam, Sankalp Nayak Published: 2026-05-11 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2605.23956v1 Compound AI systems that chain multiple LLM calls into directed computation graphs are now the dominant architecture for production AI. Although these architectures leverage heterogeneous nodes with mixed-mode outputs, no existing framework quantifies how perturbations propagate through such pipelines, where nodes are stochastic and execution paths can diverge structurally. We introduce QUIVER, a formal framework for measuring perturbation propagation in graph-structured LLM pipelines. The framework defines: (1) a sensitivity matrix with type-dispatched distance metrics that classifies edges as amplifiers, absorbers, or threshold-sensitive, complemented by occurrence-lift; (2) trajectory divergence decomposing variation into value drift, structural path divergence, and iteration count divergence; (3) bifurcation thresholds identifying the smallest perturbation that causes structural execution path changes; and (4) distribution faithfulness, quantifying when per node evaluation datasets diverge from production distributions. We validate on two production enterprise pipelines and a public DSPy multihop QA pipeline, three structurally distinct architectures. Across 8,200+ instrumented traces (32,000+ pair comparisons), we demonstrate that QUIVER reveals distinct sensitivity profiles across architectures, distinguishes mechanistically different cascade patterns producing identical divergence rates, predicts nodes prone to trajectory bifurcation from observational data alone, and localizes stale evaluation artifacts to specific node-field categories that aggregate metrics cannot surface. --- ### From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems Authors: Ruizhe Zhou, Xiaoyang Liu, Gaoyuan Du, Yi Zheng, Shouxi Ren, Deepayan Chakrabarti, Dengdu Jiang Published: 2026-05-11 Categories: cs.AI, cs.DC, cs.LG, cs.SI, q-fin.CP arXiv: https://arxiv.org/abs/2605.23955v4 Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabilities in algorithmic reproducibility. While early financial ML addressed statistical challenges such as backtest overfitting, deep neural networks and Generative AI have introduced mechanical nondeterminism rooted in hardware and architecture. This survey provides a systems perspective on reproducibility failures across three modalities now dominant in financial AI: tabular models (post-hoc explanation variance), graph networks (stochastic sampling and temporal asynchrony), and LLM-based agentic workflows (batch-dependent divergence and trajectory drift). We supplement the literature analysis with first-party experiments on public financial datasets -- quantifying explanation rank instability in credit scoring, prediction flip rates in GNN-based fraud detection, and tensor-parallel-induced output divergence in LLM entity extraction. We propose a layered evaluation framework linking modality-specific metrics (RBO, D_cos, TDI, PSD) to audit readiness, and report where these measures overlap rather than complement one another. --- ### From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems Authors: Ruizhe Zhou, Xiaoyang Liu, Gaoyuan Du, Yi Zheng, Shouxi Ren, Deepayan Chakrabarti, Dengdu Jiang Published: 2026-05-11 Categories: cs.AI, cs.DC, cs.LG, cs.SI, q-fin.CP arXiv: https://arxiv.org/abs/2605.23955v2 Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabilities in algorithmic reproducibility. While early financial ML addressed statistical challenges such as backtest overfitting, deep neural networks and Generative AI have introduced mechanical nondeterminism rooted in hardware and architecture. This survey provides a systems perspective on reproducibility failures across three modalities now dominant in financial AI: tabular models (post-hoc explanation variance), graph networks (stochastic sampling and temporal asynchrony), and LLM-based agentic workflows (batch-dependent divergence and trajectory drift). We supplement the literature analysis with first-party experiments on public financial datasets -- quantifying explanation rank instability in credit scoring, prediction flip rates in GNN-based fraud detection, and tensor-parallel-induced output divergence in LLM entity extraction. We propose a layered evaluation framework linking modality-specific metrics (RBO, D_cos, TDI, PSD) to audit readiness, and empirically validate the complementarity of logit-level and semantic-level determinism measures. --- ### EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs Authors: Liang Lin, Chunxi Luo, Kaiwen Luo, Jie Zhang, Jin Wang, Yuanhe Zhang, Cai Yuchen, Qiankun Li, Gongli Xi, Zhenhong Zhou, Kun Wang, Junhao Dong Published: 2026-05-11 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2605.23954v1 Audio Large Language Models (ALLMs) are highly vulnerable to real-world noise, which often induces severe semantic drift and hallucinations. Existing robustness methods primarily rely on waveform-level acoustic enhancement, answer-level supervision, or the internal suppression of noise representations. To address these issues, we propose echodistill, an alignment-based noisy-to-clean self-distillation framework. Echodistill leverages a frozen clean-audio teacher to provide semantic references for an inference-time noisy-audio student. Specifically, the student samples candidate responses under noisy conditions to expose its test-time behavior. These trajectories are then optimized via group-relative policy optimization (GRPO), where the token-level consistency with the teacher acts as a reward bonus. By aligning the noisy student's candidate responses with clean semantic evidence, and applying audio-aware reward shaping, our method encourages reasoning trajectories that are both correct and genuinely acoustically grounded. Echodistill significantly improves the semantic reliability and task performance of Audio LLMs under complex noise, without introducing any additional inference costs. Extensive experiments show that: (I) Compared with the strongest baseline, echodistill achieves average improvements of 4.18\%$\uparrow$ in GSR under strong noise. (II) Ablation results on Qwen-Omni further show that echodistill improves over the GRPO-only variant by 3.02\%$\uparrow$ in Acc, 3.89\%$\uparrow$ in Noisy, and 4.53\%$\uparrow$ in GSR on average. Our codes are available at https://anonymous.4open.science/r/echodistill-10DE. --- ### Game-Theoretic Modeling of Heterogeneous Investor Interactions for Stock Price Forecasting Authors: Yong Zhang, Xinxiao Wu, Yunde Jia, Che Sun Published: 2026-05-11 Categories: q-fin.TR, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2605.23953v1 Accurate stock price forecasting has consistently remained a pivotal yet challenging FinTech task that underpins quantitative trading and investment decision making. Recent efforts have been dedicated to modeling various complex relationships among stocks in the stock market toward more reliable stock price forecasting.These methods depend heavily on strong static prior assumptions by modeling either temporal dependencies within individual stocks or spatial dependencies across different stocks based on predefined structures, while the complex market dynamics that drive stock price movements remain unexplored. To alleviate this issue, we propose a novel game-theoretic modeling method that captures heterogeneous investor interactions for stock price forecasting. The core idea is to embed game-theoretic mechanisms into the heterogeneous graph structure to finely model the dynamic strategic interactions among heterogeneous investors with respect to target stocks. Additionally, temporal positional encoding is adopted to reflect the differentiated influences of each game event at different time steps within the time window on future stock price movements. Leveraging heterogeneous graph networks, we proxy the intricate dynamics of the stock market through investor games and enable real-time information propagation and node updates among all nodes. Extensive experiments conducted on two real-world benchmark dataset demonstrate that our method effectively outperforms state-of-the-art stock price forecasting methods. --- ### Strategic Coercion Within Alliances: The Greenland Sovereignty Game as an AI Stress Test Authors: Rommin Adl, Peyton Williams Published: 2026-05-11 Categories: physics.soc-ph, cs.AI, cs.CL, cs.GT, cs.MA, econ.GN arXiv: https://arxiv.org/abs/2605.22841v1 What happens when the strongest alliance member pressures a weaker member over territory and strategic control? We examine the Greenland sovereignty crisis as a stress test for LLM geopolitics, centered on the 2019-2026 U.S. push to acquire Greenland from the Kingdom of Denmark. The crisis nests two collective-action problems: Arctic strategic control and whether NATO can enforce alliance norms against the dominant member. We develop three games (asymmetric coercion; a NATO assurance game with a critical-mass tipping point; a triadic extensive-form game with social preferences) and test them with a multi-agent simulation in which eight frontier LLMs play six geopolitical roles (United States, Denmark, Greenland, NATO, Russia, Canada) across 3,604 completed games and 108,120 action observations. Using inverse game theory, we recover each model's structural utility parameters (alpha, beta, gamma, delta, eta) for material self-interest, reciprocity, inequality aversion, norm respect, and commitment consistency. Three findings stand out. First, all eight models become more escalatory under coercion framing (four-action escalation rises from 10.7% to 28.6%). Second, Chinese-origin models show systematically different power-weight profiles from Western-origin models when playing the U.S. role. Third, peaceful US acquisition emerges in only 1.9% of clean games and only 3 of 8 frontier models ever achieve it, most prominently DeepSeek V3.2, which executes a stable five-round playbook through the metropole. Prompts emphasizing jus cogens and self-determination reduce escalation back near baseline in the English-only confirmatory sample; multilingual contrasts are reported as exploratory sensitivity checks. We position this as a structural benchmark for LLM geopolitical behavior, complementing action-frequency benchmarks. ---