# Research Papers — 2026-04 · bundle page 87 of 233 > Full-text markdown of papers #4301–4350 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/87 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/86.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/88.md) ### STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering Authors: Wei Chen, Lili Zhao, Zhi Zheng, HuiJun Hou, Tong Xu Published: 2026-04-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17405v1 Multi-hop question answering (MHQA) enables accurate answers to complex queries by retrieving and reasoning over evidence dispersed across multiple documents. Existing MHQA approaches mainly rely on iterative retrieval-augmented generation, which suffer from the following two major issues. 1) Existing methods prematurely commit to surface-level entities rather than underlying reasoning structures, making question decomposition highly vulnerable to lexical ambiguity. 2) Existing methods overlook the logical dependencies among reasoning steps, resulting in uncoordinated execution. To address these issues, we propose STRIDE, a framework that separates strategic planning, dynamic control, and grounded execution. At its core, a Meta-Planner first constructs an entity-agnostic reasoning skeleton to capture the abstract logic of the query, thereby deferring entity grounding until after the reasoning structure is established, which mitigates disambiguation errors caused by premature lexical commitment. A Supervisor then orchestrates sub-question execution in a dependency-aware manner, enabling efficient parallelization where possible and sequential coordination when necessary. By dynamically deciding whether to retrieve new evidence or infer from existing facts, it avoids redundant queries and error propagation, while fusing cross-branch information and reformulating failed queries to enhance robustness. Grounded fact extraction and logical inference are delegated to specialized execution modules, ensuring faithfulness through explicit separation of retrieval and reasoning. We further propose STRIDE-FT, a modular fine-tuning framework that uses self-generated execution trajectories from STRIDE, requiring neither human annotations nor stronger teacher models. Experiments show that STRIDE achieves robust and accurate reasoning, while STRIDE-FT effectively enhances open-source LLMs. --- ### On the Generalization Bounds of Symbolic Regression with Genetic Programming Authors: Masahiro Nomura, Ryoki Hamano, Isao Ono Published: 2026-04-19 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2604.17402v2 Symbolic regression (SR) with genetic programming (GP) aims to discover interpretable mathematical expressions directly from data. Despite its strong empirical success, the theoretical understanding of why GP-based SR generalizes beyond the training data remains limited. In this work, we provide a learning-theoretic analysis of SR models represented as expression trees. We derive a generalization bound for GP-style SR under constraints on tree size, depth, and learnable constants. Our result decomposes the generalization gap into two interpretable components: a structure-selection term, reflecting the combinatorial complexity of choosing an expression-tree structure, and a constant-fitting term, capturing the complexity of optimizing numerical constants within a fixed structure. This decomposition provides a theoretical perspective on several widely used practices in GP, including parsimony pressure, depth limits, numerically stable operators, and interval arithmetic. In particular, our analysis shows how structural restrictions reduce hypothesis-class growth while stability mechanisms control the sensitivity of predictions to parameter perturbations. By linking these practical design choices to explicit complexity terms in the generalization bound, our work offers a principled explanation for commonly observed empirical behaviors in GP-based SR and contributes towards a more rigorous understanding of its generalization properties. --- ### Phase-Scheduled Multi-Agent Systems for Token-Efficient Coordination Authors: Mohit Dubey Published: 2026-04-19 Categories: cs.AI, math.AT arXiv: https://arxiv.org/abs/2604.17400v1 Multi-agent systems (MAS) powered by large language models suffer from severe token inefficiency arising from two compounding sources: (i) unstructured parallel execution, where all agents activate simultaneously irrespective of input readiness; and (ii) unrestricted context sharing, where every agent receives the full accumulated context regardless of relevance. Existing mitigation strategies - static pruning, hierarchical decomposition, and learned routing - treat coordination as a structural allocation problem and fundamentally ignore its temporal dimension. We propose Phase-Scheduled Multi-Agent Systems (PSMAS), a framework that reconceptualizes agent activation as continuous control over a shared attention space modeled on a circular manifold. Each agent i is assigned a fixed angular phase theta_i in the range (0, 2*pi), derived from the task dependency topology; a global sweep signal phi(t) rotates at velocity omega, activating only agents within an angular window epsilon. Idle agents receive compressed context summaries, reducing per-step token consumption. We implement PSMAS on LangGraph, evaluate on four structured benchmarks (HotPotQA-MAS, HumanEval-MAS, ALFWorld-Multi, WebArena-Coord) and two unstructured conversational settings, and prove stability, convergence, and optimality results for the sweep dynamics. PSMAS achieves a mean token reduction of 27.3 percent (range 21.4-34.8 percent) while maintaining task performance within 2.1 percentage points of a fully activated baseline (p < 0.01, n = 500 per configuration), and outperforms the strongest learned routing baseline by 5.6 percentage points in token reduction with 2.0 percentage points less performance drop. Crucially, we show that scheduling and compression are independent sources of gain: scheduling alone accounts for 18-20 percentage points of reduction, robust to compression degradation up to alpha = 0.40. --- ### Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning Authors: Ziqing Zhuang, Linhai Zhang, Jiasheng Si, Deyu Zhou, Yulan He Published: 2026-04-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17399v1 Large language models (LLMs) have demonstrated strong reasoning capabilities, and as existing approaches for enhancing LLM reasoning continue to mature, increasing attention has shifted toward meta-reasoning as a promising direction for further improvement. However, most existing meta-reasoning methods remain episodic: they focus on executing complex meta-reasoning routines within individual instances, but ignore the accumulation of reusable meta-reasoning skills across instances, leading to recurring failure modes and repeatedly high metacognitive effort. In this paper, we introduce Metacognitive Consolidation, a novel framework in which a model consolidates metacognitive experience from past reasoning episodes into reusable knowledge that improves future meta-reasoning. We instantiate this framework by structuring instance-level problem solving into distinct roles for reasoning, monitoring, and control to generate rich, attributable meta-level traces. These traces are then consolidated through a hierarchical, multi-timescale update mechanism that gradually forms evolving meta-knowledge. Experimental results demonstrate consistent performance gains across benchmarks and backbone models, and show that performance improves as metacognitive experience accumulates over time. --- ### Contrastive Analysis of Linguistic Representations in Large Language Model Outputs through Structured Synthetic Data Generation and Abstracted N-gram Associations Authors: S. A. Desimone, L. Alonso Alemany Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17398v1 We present a methodological framework to discover linguistic and discursive patterns associated to different social groups through contrastive synthetic text generation and statistical analysis. In contrast with previous approaches, we aim to characterize subtle expressions of bias, instead of diagnosing bias through a pre-determined list of words or expressions. We are also working with contextualized data instead of isolated words or sentences. Our methodology applies to textual productions in any genre, encompassing narrative, task-oriented or dialogic. Contextualized data are generated using controlled combinations of situational scenarios and group markers, creating minimal pairs of texts that differ only in the referenced group while maintaining comparable narrative conditions. To facilitate robust analysis, linguistic forms are generalized and associations between linguistic abstractions and groups are quantified using a variant of pointwise mutual information to detect expressions that appear disproportionately across groups. A fragment-ranking strategy then prioritizes text segments with a high concentration of biased linguistic signals, which allows for experts to assess the harmful potential of linguistic expressions in context, bridging quantitative analysis and qualitative interpretation. --- ### Speculative Decoding for Autoregressive Video Generation Authors: Yuezhou Hu, Jintao Zhang Published: 2026-04-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.17397v1 Autoregressive video diffusion is emerging as a promising paradigm for streaming video synthesis, with step distillation serving as the primary means of accelerating inference. Whether speculative decoding, the dominant acceleration strategy for large language models, can be effectively adapted to autoregressive video generation remains an open question, because video blocks are continuous spatiotemporal tensors with no token-level distribution for exact rejection sampling. We introduce SDVG, which brings speculative decoding to block-based autoregressive video diffusion by replacing token verification with an image-quality router. A 1.3B drafter proposes candidate blocks via four denoising steps; each block is VAE-decoded and scored by ImageReward using worst-frame aggregation--taking the minimum per-frame reward to catch single-frame artifacts that averaging would mask. Blocks scoring above a fixed threshold tau are accepted into the 14B target's KV cache; the rest are regenerated by the target. Two additional design choices prove critical: the first block is always force-rejected to anchor scene composition, and tau serves as a single knob that traces a smooth quality-speed Pareto frontier. On 1003 MovieGenVideoBench prompts (832x480), SDVG retains 98.1% of target-only VisionReward quality (0.0773 vs. 0.0788) at a 1.59x speedup with tau=-0.7, and reaches 2.09x at 95.7% quality retention--while consistently outperforming draft-only generation by over +17%. The framework is training-free, requires no architectural changes, and can be seamlessly integrated into existing autoregressive video generation pipelines. --- ### Representation-Guided Parameter-Efficient LLM Unlearning Authors: Zeguan Xiao, Lang Mo, Yun Chen, Lei Yang, Jiehui Zhao, Lili Yang, Guanhua Chen Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17396v1 Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning methods have shown promise, they still struggle with the forget-retain trade-off. This can be attributed to their reliance on parameter importance metrics to identify parameters that are important exclusively for the forget set, which is fundamentally limited by the superposition phenomenon. Due to the polysemantic nature of LLM parameters, such an importance metric may struggle to disentangle parameters associated with the forget and retain sets. In this work, we propose Representation-Guided Low-rank Unlearning (REGLU), a novel approach that leverages the geometric properties of representation spaces to achieve robust and precise unlearning. First, we develop a representation-guided initialization for LoRA that identifies the optimal subspace for selective forgetting. Second, we introduce a regularization loss that constrains the outputs of the LoRA update to lie in the orthogonal complement of the retain set's representation subspace, thereby minimizing interference with the model's performance on the retain set. We evaluate REGLU on the TOFU and WMDP benchmarks across multiple models. Our results demonstrate that REGLU consistently outperforms state-of-the-art baselines, achieving superior unlearning quality while maintaining higher model utility. --- ### Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains Authors: Finn Schmidt, Jan Philip Wahle, Terry Ruas, Bela Gipp Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17393v2 Automatic evaluation metrics are central to the development of machine translation systems, yet their robustness under domain shift remains unclear. Most metrics are developed on the Workshop on Machine Translation (WMT) benchmarks, raising concerns about their robustness to unseen domains. Prior studies that analyze unseen domains vary translation systems, annotators, or evaluation conditions, confounding domain effects with human annotation noise. To address these biases, we introduce a systematic multi-annotator Cross-Domain Error-Span-Annotation dataset (CD-ESA), comprising 18.8k human error span annotations across three language pairs, where we fix annotators within each language pair and evaluate translations of the same six translation systems across one seen news domain and two unseen technical domains. Using this dataset, we first find that automatic metrics appear surprisingly robust to domain-shifts at the segment level (up to 0.69 agreement), but this robustness largely disappears once we account for human label variation. Averaging annotations increases inter-annotator agreement by up to +0.11. Metrics struggle on the unseen chemical domain compared to humans (inter-annotator agreement of 0.78-0.83 vs. 0.96). We recommend comparing metric-human agreement against inter-annotator agreement, rather than comparing raw metric-human agreement alone, when evaluating across different domains. --- ### RISC-V Functional Safety for Autonomous Automotive Systems: An Analytical Framework and Research Roadmap for ML-Assisted Certification Authors: Nick Andreasyan, Mikhail Struve, Alexey Popov, Maksim Nikolaev, Vadim Vashkelis Published: 2026-04-19 Categories: cs.SE, cs.AR, cs.LG arXiv: https://arxiv.org/abs/2604.17391v1 RISC-V is emerging as a viable platform for automotive-grade embedded computing, with recent ISO 26262 ASIL-D certifications demonstrating readiness for safety-critical deployment in autonomous driving systems. However, functional safety in automotive systems is fundamentally a certification problem rather than a processor problem. The dominant costs arise from diagnostic coverage analysis, toolchain qualification, fault injection campaigns, safety-case generation, and compliance with ISO 26262, ISO 21448 (SOTIF), and ISO/SAE 21434. This paper analyzes the role of RISC-V in automotive functional safety, focusing on ISA openness, formal verifiability, custom extension control, debug transparency, and vendor-independent qualification. We examine autonomous driving safety requirements and map them to RISC-V architectural challenges such as lockstep execution, safety islands, mixed-criticality isolation, and secure debug. Rather than proposing a single algorithmic breakthrough, we present an analytical framework and research roadmap centered on certification economics as the primary optimization objective. We also discuss how selected ML methods, including LLM-assisted FMEDA generation, knowledge-graph-based safety case automation, reinforcement learning for fault injection, and graph neural networks for diagnostic coverage, can support certification workflows. We argue that the strongest outcome is not a faster core, but an ASIL-D-ready certifiable RISC-V platform. --- ### MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Textures Authors: Vasileios Toulatzis, Sofia Theodoridou, Ioannis Fudos Published: 2026-04-19 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2604.17390v2 Ancient inscriptions frequently suffer missing or corrupted regions from fragmentation, erosion, or other damage, hindering reading, and analysis. We review prior image restoration methods and their applicability to inscription image recovery, then introduce MESA (Multi-Exemplar, Style-Aware) -an image-level restoration method that uses well-preserved exemplar inscriptions (from the same epigraphic monument, material, or similar letterforms) to guide reconstruction of damaged text. MESA encodes VGG19 convolutional features as Gram matrices to capture exemplar texture, style, and stroke structure; for each neural network layer it selects the exemplar minimizing Mean-Squared Displacement (MSD) to the damaged input. Layer-wise contribution weights are derived from Optical Character Recognition-estimated character widths in the exemplar set to bias filters toward scales matching letter geometry, and a training mask preserves intact regions so synthesis is restricted to damaged areas. We also summarize prior network architectures and exemplar and single-image synthesis, inpainting, and Generative Adversarial Network (GAN) approaches, highlighting limitations that MESA addresses. Comparative experiments demonstrate the advantages of MESA. Finally, we provide a practical roadmap for choosing restoration strategies given available exemplars and metadata. --- ### Deep learning based Non-Rigid Volume-to-Surface Registration for Brain Shift compensation Using Point Cloud Authors: Eashrat Jahan Muniya, Gernot Kronreif, Ander Biguri, Wolfgang Birkfellner, Sepideh Hatamikia Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17389v1 Soft-tissue deformation remains a major limitation in image-guided neurosurgery, where intra-operative anatomy can deviate substantially from pre-operative imaging due to brain shift, compromising navigation accuracy and surgical safety. Existing compensation methods often rely on intra-operative MRI, CT, or ultrasound, which are disruptive and difficult to integrate repeatedly into the surgical workflow. In contrast, partial 3D cortical surfaces can be reconstructed as point clouds from stereoscopic microscopes or laser range scanners (LRS), capturing only a limited portion of the exposed cortex. This makes point cloud registration a practical alternative without interrupting surgery; however, such partial and noisy observations make deformation estimation highly challenging. In this study, we propose a deep learning-based framework for non-rigid volume-to-surface registration, enabling dense displacement field estimation from sparse intra-operative surface observations without explicit point correspondences or volumetric intra-operative imaging. The network leverages multi-scale point-based feature extraction and a hierarchical deformation decoder to capture both global and local deformations. The key contribution lies in integrating partial intra-operative surface information into the full pre-operative point cloud domain, enabling implicit correspondence learning and dense deformation recovery under limited visibility. Quantitative results demonstrate accurate recovery of fine-scale deformations, achieving an Endpoint Error (EPE) of 1.13 +/- 0.75 mm and RMSE of 1.33 +/- 0.81 mm under challenging partial-surface conditions. The proposed approach supports automatic, workflow-compatible brain-shift compensation from sparse surface observations. --- ### Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection Authors: Kadir-Kaan Özer, René Ebeling, Markus Enzweiler Published: 2026-04-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.17388v3 Time series anomaly detectors have grown steadily more complex, incorporating attention mechanisms, adversarial training, and stochastic latent variables. Yet, it is unclear how much of this machinery detection actually requires. We test this question with JuRe (Just Repair), a deliberately minimal detector: a single depthwise-separable convolutional residual block trained to repair Gaussian-corrupted, channel-masked windows, scored at inference by a fixed structural discrepancy function with no learned parameters. JuRe ranks second on the TSB-AD multivariate benchmark (AUC-PR 0.404 over 180 series) and second on the UCR univariate archive (AUC-PR 0.201 over 250 series), where it leads all neural baselines. On TSB-AD, JuRe runs roughly $20\times$ faster than AxonAD, one of the top-ranked methods on that benchmark. Full-benchmark ablations show that removing Gaussian corruption reduces AUC-PR by 0.046, whereas AUC-PR across the evaluated architecture variants spans at most 0.017. A synthetic linear-manifold experiment provides partial evidence for this geometric interpretation: anomaly scores correlate with true off-manifold distance (Pearson $r=0.725$), and repair directions align increasingly with the true projection as anomaly magnitude grows. Wilcoxon signed-rank tests with Holm correction find significant differences against 20 of 25 baselines, although dependence among series limits dataset-level interpretation. Code is available at https://github.com/iis-esslingen/JuRe. --- ### SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning Authors: Yian Li, Yang Jiao, Bin Zhu, Tianwen Qian, Shaoxiang Chen, Jingjing Chen, Yu-Gang Jiang Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17385v1 Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language models. Despite promising performance, recent multimodal large language models (MLLMs) often exhibit fragile reasoning traces in spatial intelligence tasks that involve consistent spatial state recognition. We argue that these failures stem from a mismatch between the spatial recognition mechanism and the text-only reasoning behavior of these MLLMs. Effective spatial reasoning requires low-level geometric structure to be faithfully preserved and updated throughout the reasoning process, whereas textual representations tend to abstract away precisely these critical details. To address this issue, we propose SpatialImaginer, a unified multimodal generation framework that integrates textual reasoning with visual imagination. Our framework adopts a divide-and-conquer strategy, using text chain-of-thought for high-level semantic planning and the visual imagination for geometry-sensitive state transformation and consistency preservation. To support this capability, we further introduce a difficulty-aware data engine with closed-loop verification to train the model to invoke visual imagination selectively when stable spatial state tracking is required. Extensive experiments on diverse spatial intelligence benchmarks show that SpatialImaginer achieves state-of-the-art performance and substantially improves robustness on complex multi-step spatial reasoning tasks. --- ### Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion Authors: Ou Wu Published: 2026-04-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17384v1 Large language model optimization has historically bifurcated into isolated data-centric and model-centric paradigms: the former manipulates involved samples through selection, augmentation, or poisoning, while the latter tunes model weights via masking, quantization, or low-rank adaptation. This paper establishes a unified \emph{data-parameter correspondence} revealing these seemingly disparate operations as dual manifestations of the same geometric structure on the statistical manifold $\mathcal{M}$. Grounded in the Fisher-Rao metric $g_{ij}(θ)$ and Legendre duality between natural ($θ$) and expectation ($η$) parameters, we identify three fundamental correspondences spanning the model lifecycle: 1. Geometric correspondence: data pruning and parameter sparsification equivalently reduce manifold volume via dual coordinate constraints; 2. Low-rank correspondence: in-context learning (ICL) and LoRA adaptation explore identical subspaces on the Grassmannian $\mathcal{G}(r,d)$, with $k$-shot samples geometrically equivalent to rank-$r$ updates; 3. Security-privacy correspondence: adversarial attacks exhibit cooperative amplification between data poisoning and parameter backdoors, whereas protective mechanisms follow cascading attenuation where data compression multiplicatively enhances parameter privacy. Extending from training through post-training compression to inference, this framework provides mathematical formalization for cross-community methodology transfer, demonstrating that cooperative optimization integrating data and parameter modalities may outperform isolated approaches across efficiency, robustness, and privacy dimensions. --- ### StrEBM: A Structured Latent Energy-Based Model for Blind Source Separation Authors: Yuan-Hao Wei Published: 2026-04-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.17381v1 This paper proposes StrEBM, a structured latent energy-based model for source-wise structured representation learning. The framework is motivated by a broader goal of promoting identifiable and decoupled latent organization by assigning different latent dimensions their own learnable structural biases, rather than constraining the entire latent representation with a single shared energy. In this sense, blind source separation is adopted here as a concrete and verifiable testbed, through which the evolution of latent dimensions toward distinct underlying components can be directly examined. In the proposed framework, latent trajectories are optimized directly together with an observation-generation map and source-wise structural parameters. Each latent dimension is associated with its own energy-based formulation, allowing different latent components to gradually evolve toward distinct source-like roles during training. In the present study, this source-wise energy design is instantiated using Gaussian-process-inspired energies with learnable length-scales, but the framework itself is not restricted to Gaussian processes and is intended as a more general structured latent EBM formulation. Experiments on synthetic multichannel signals under linear and nonlinear mixing settings show that the proposed model can recover source components effectively, providing an initial empirical validation of the framework. At the same time, the study reveals important optimization characteristics, including slow late-stage convergence and reduced stability under nonlinear observation mappings. These findings not only clarify the practical behavior of the current GP-based instantiation, but also establish a basis for future investigation of richer source-wise energy families and more robust nonlinear optimization strategies. --- ### Study and Improvement of Search Algorithms in Multi-Player Perfect-Information Games Authors: Quentin Cohen-Solal Published: 2026-04-19 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2604.17378v1 In this article, we generalize Unbounded Minimax, the state-of-the-art search algorithm for zero sums two-player games with perfect information to the framework of multiplayer games with perfect information. We experimentally show that this generalized algorithm also achieves better performance than the main multiplayer search algorithms. --- ### AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models Authors: Zhanyu Shen, Sijie Cheng, Zhicheng Guo, Weiqin Wang, Yile Wang, Hui Huang Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17377v1 While large language models have achieved remarkable performance in complex tasks, they still need a memory system to utilize historical experience in long-term interactions. Existing memory methods (e.g., A-Mem, Mem0) place excessive emphasis on organizing interactions by frequently rewriting them, however, this heavy reliance on summarization risks diluting essential contextual nuances and obscuring key retrieval features. To bridge this gap, we introduce AnchorMem, a novel memory framework inspired by the Proust Phenomenon in cognitive science, where a specific anchor triggers a holistic recollection. We propose a method that decouples the retrieval unit from the generation context. AnchorMem extracts atomic facts from interaction history to serve as retrieval anchors, while preserving the original context as the immutable context. To reveal implicit narrative cues, we construct an associative event graph that uses higher-order event links that bind sets of related facts into shared event representations, strengthening cross-memory integration without relying on generic entities as bridges. During retrieval, the system anchors queries to specific facts and events to locate relevant memories, but reconstructs the context using the associated raw chunks and events. Our method reconciles fine-grained retrieval with the contextual integrity of interactions. Experiments across three closed-source and open-source models on the LoCoMo benchmark demonstrate that AnchorMem significantly outperforms baselines. Code is available at https://github.com/RayNeo-AI-2025/AnchorMem. --- ### Towards Generalizable Deepfake Image Detection with Vision Transformers Authors: Kaliki V Srinanda, M Manvith Prabhu, Hemanth K Mogilipalem, Jayavarapu S Abhinai, Vaibhav Santhosh, Aryan Herur, Deepu Vijayasenan Published: 2026-04-19 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2604.17376v2 In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods. In this paper, we use an ensemble of fine-tuned vision transformers like DINOv2, AIMv2 and OpenCLIP's ViT-L/14 to create generalizable method to detect deepfakes. We use the DF-Wild dataset released as part of the IEEE SP Cup 2025, because it uses a challenging and diverse set of manipulations and generation techniques. We started our experiments with CNN classifiers trained on spatial features. Experimental results show that our ensemble outperforms individual models and strong CNN baselines, achieving an AUC of 96.77% and an Equal Error Rate (EER) of just 9% on the DF-Wild test set, beating the state-of-the-art deepfake detection algorithm Effort by 7.05% and 8% in AUC and EER respectively. This was the winning solution for SP Cup, presented at ICASSP 2025. --- ### When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models Authors: Cui Yakun, Xingqun Qi, TianTian Geng, Yuyao Zhang, Sirui Han, Yike Guo Published: 2026-04-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.17375v1 Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning temporal, action, object, and spatial understanding. However, we identify a critical yet overlooked issue: when embedded on-screen text contradicts the visual scene, existing VLMs systematically hallucinate, prioritizing overlay textual semantics over the actual visual content. We define this phenomenon as Text Overlay-Induced Hallucination (TOIH). In this work, we propose VisualTextTrap, the first comprehensive benchmark, including large-scale human-validated samples with specifically designed evaluation metrics. In particular, we construct VisualTextTrap from widely-used public datasets using a scalable hybrid pipeline of VLMs assisted text generation and rigorous manual verification. The benchmark features 6,057 samples annotated across 88 fine-grained attributes within four dimensions, with hallucination intensity quantified on a five-level scale (L1--L5) that reflects the semantic contradiction between overlay text and visual reality. Moreover, we propose Visual Text Hallucination Mitigation Mixture-of-Experts (VTHM-MoE), a novel Vision-Text Disentanglement framework that employs a dual-encoder architecture. Concretely, four dimension-specialized expert modules spanning Temporal, Action, Object, and Spatial reasoning are first pre-trained to identify and leverage cross-modal discrepancies between textual semantics and actual video content. We develop an Adaptive Token Routing Strategy to enable dynamic expert allocation, conferring robust resistance to TOIH while preserving performance on uncontaminated videos. Extensive experiments conducted on our VisualTextTrap benchmark verify the effectiveness of VTHM-MoE, outperforming state-of-the-art counterparts with diverse video question answering tasks. --- ### Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer Authors: Anis Hamadouche, Mathini Sellathurai Published: 2026-04-19 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2604.17371v1 This paper investigates communication-efficient neural network transmission by exploiting structured symmetry constraints in convolutional kernels. Instead of transmitting all model parameters, we propose a degrees-of-freedom (DoF) based codec that sends only the unique coefficients implied by a chosen symmetry group, enabling deterministic reconstruction of the full weight tensor at the receiver. The proposed framework is evaluated under quantization and noisy channel conditions across multiple symmetry patterns, signal-to-noise ratios, and bit-widths. To improve robustness against transmission impairments, a projection step is further applied at the receiver to enforce consistency with the symmetry-invariant subspace, effectively denoising corrupted parameters. Experimental results on MNIST and CIFAR-10 using a DeepCNN architecture demonstrate that DoF-based transmission achieves substantial bandwidth reduction while preserving significantly higher accuracy than pruning-based baselines, which often suffer catastrophic degradation. Among the tested symmetries, \textit{central-skew symmetry} consistently provides the best accuracy-compression tradeoff, confirming that structured redundancy can be leveraged for reliable and efficient neural model delivery over constrained links. --- ### ArgBench: Benchmarking LLMs on Computational Argumentation Tasks Authors: Yamen Ajjour, Carlotta Quensel, Nedim Lipka, Henning Wachsmuth Published: 2026-04-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.17366v1 Argumentation skills are an essential toolkit for large language models (LLMs). These skills are crucial in various use cases, including self-reflection, debating collaboratively for diverse answers, and countering hate speech. In this paper, we create the first benchmark for a standardized evaluation of LLM-based approaches to computational argumentation, encompassing 33 datasets from previous work in unified form. Using the benchmark, we evaluate the generalizability of five LLM families across 46 computational argumentation tasks that cover mining arguments, assessing perspectives, assessing argument quality, reasoning about arguments, and generating arguments. On the benchmark, we conduct an extensive systematic analysis of the contribution of few-shot examples, reasoning steps, model size, and training skills to the performance of LLMs on the computational argumentation tasks in the benchmark. --- ### LLM-Guided Strategy Synthesis for Scalable Equality Saturation Authors: Chenyun Yin, Youwei Xiao, Yuze Luo, Yuyang Zou, Yun Liang Published: 2026-04-19 Categories: cs.AI, cs.MA, cs.PL arXiv: https://arxiv.org/abs/2604.17364v1 Equality saturation (EqSat) is a powerful optimization paradigm that compactly represents many equivalent programs in an e-graph and delays commitment until extraction selects a lowest-cost program. Making EqSat effective, therefore, requires not only domain-specific rewrite rules but also domain-specific strategies. Today, much of this strategy design is still manual, making it a major obstacle to automating e-graph-based compilers. Recent rule-synthesis frameworks can automatically infer large rewrite vocabularies from semantic specifications, but they also enlarge the rewrite space and further exacerbate e-graph explosion. Although large language models (LLMs) make automated strategy synthesis plausible, directly evolving backend code remains ineffective in practice. The search lacks reusable strategy abstractions and actionable feedback, and can easily trigger e-graph explosion or converge to poor designs. We present EggMind, an LLM-guided, end-to-end framework for synthesizing reusable EqSat strategies. At its core, EggMind introduces a domain-specific language, EqSatL, to represent EqSat strategies as explicit and inspectable artifacts. It then proposes an LLM-guided agentic workflow, equipped with novel techniques including proof-derived rewrite motif caching and tractability guidance, to search efficiently for high-quality strategies while keeping synthesis stable under e-graph growth. Evaluation shows that EggMind substantially improves the resource-quality trade-off on vectorization benchmarks, reducing final cost by 45.1% and peak RAM by 69.1% relative to full EqSat. We further show that the same methodology transfers effectively to an XLA-based tensor compiler, and demonstrate its practical potential in a logic-synthesis case study with augmented rewrite spaces. --- ### T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classification Authors: Zixuan Tang, Shen Zhao Published: 2026-04-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17360v1 Fine-grained medical image classification is challenged by subtle inter-class variations and visually ambiguous cases, where confidence estimates often exhibit uncertainty rather than being overconfident. In such scenarios, purely discriminative classifiers may achieve high overall accuracy yet still fail to distinguish between highly similar categories, leading to miscalibrated predictions. We propose T-DuMpRa, a teacher-guided dual-path multi-prototype retrieval-augmented framework, where discriminative classification and multi-prototype retrieval jointly drive both training and prediction. During training, we jointly optimize cross-entropy and supervised contrastive objectives to learn a cosine-compatible embedding geometry for reliable prototype matching. We further employ an exponential moving average (EMA) teacher to obtain smoother representations and build a multi-prototype memory bank by clustering teacher embeddings in the teacher embedding space. Our framework is plug-and-play: it can be easily integrated into existing classification models by constructing a compact prototype bank, thereby improving performance on visually ambiguous cases. At inference, we combine the classifier's predicted distribution with a similarity-based distribution computed via cosine matching to prototypes, and apply a conservative confidence-gated fusion that activates retrieval only when the classifier's prediction is uncertain and the retrieval evidence is decisive and conflicting, otherwise keeping confident predictions unchanged. On HAM10000 and ISIC2019, our method yields 0.68%-0.21% and 0.44%-2.69% improvements on 5 different backbones. And visualization analysis proves our model can enhance the model's ability to handle visually ambiguous cases. --- ### Plausible Patients, Impossible Populations: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations Authors: Patrick Keough Published: 2026-04-19 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.17359v2 Language models asked to simulate psychiatric patients produce cases that survive inspection one at a time and populations that match no real one. We gave GPT-4o-mini, Gemini-3-Flash, DeepSeek-V3 and GLM-4.7 each of 120 demographic cohorts under two framings, one written as a clinician enters a patient and one as a person describes themselves, and scored all 28,800 responses against survey-weighted PHQ-8 anchors derived from NHANES microdata. Case by case the output holds up: 97.3% of elevated presentations satisfy the DSM-5 gateway rule, violating it at 2.68% against a chance null of 10.4%. As populations, four things fail at once. Every benchmarkable group returns inflated by 2.8 to 5.5 PHQ-8 points, and 18.2% of simulated patients screen at the treatment threshold against 7.5% of adults. Population Black-White and Hispanic-White disparities do not survive the simulation, with two models attenuating each gap and two flattening or inverting it. Symptom covariance reorganizes by cohort, putting the error beyond any recalibration, and demographic offsets do not stack, so a correction fitted on marginals misses the cells by about 0.4 points either way. And the answer does not hold still: at the decoding a deployment inherits, a third of patients change severity category between two draws of one prompt and one in five crosses the line from watchful waiting to treatment. We read the four together as one failure, and name the gap between case-level plausibility and population-level failure the coherence-fidelity dissociation. Individual cases clear a formal rule a case review would apply; the populations they compose fail every comparison we can construct against a real one. Gender identity carries an extreme on both symptom structure and regeneration stability, and no federal benchmark exists to check any of it. The patients look right. They do not represent real populations. --- ### Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions Authors: Dongwook Lee, Eunwoo Song, Che Hyun Lee, Heeseung Kim, Sungroh Yoon Published: 2026-04-19 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2604.17358v1 While recent Spoken Language Models (SLMs) have been actively deployed in real-world scenarios, they lack the capability to discern Third-Party Interruptions (TPI) from the primary user's ongoing flow, leaving them vulnerable to contextual failures. To bridge this gap, we introduce TPI-Train, a dataset of 88K instances designed with speaker-aware hard negatives to enforce acoustic cue prioritization for interruption handling, and TPI-Bench, a comprehensive evaluation framework designed to rigorously measure the interruption-handling strategy and precise speaker discrimination in deceptive contexts. Experiments demonstrate that our dataset design mitigates semantic shortcut learning-a critical pitfall where models exploit semantic context while neglecting acoustic signals essential for discerning speaker changes. We believe our work establishes a foundational resource for overcoming text-dominated unimodal reliance in SLMs, paving the way for more robust multi-party spoken interaction. The code for the framework is publicly available at https://tpi-va.github.io --- ### More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage Authors: Wei He Published: 2026-04-19 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2604.17354v1 Vision-Language Models (VLMs) excel at photorealistic generation, yet often struggle to represent abstract meaning such as idiomatic interpretations of noun compounds. To study whether high visual fidelity interferes with idiomatic compositionality under visual abstraction, we introduce DIVA, a controlled benchmark that replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings. We further propose Semantic Alignment Gap ($Δ$), an architecture-agnostic metric that quantifies divergence between literal and idiomatic visual grounding. We additionally introduce a directional signed bias $b(t)$ to separately measure the direction and strength of literal preference. Evaluating 8 recent VLMs, we reveal a consistent Literal Superiority Bias: model scale alone does not resolve literal preference, and increased visual fidelity is associated with weaker symbolic alignment, suggesting cognitive interference from hyper-realistic imagery. Our findings suggest that improving compositional understanding requires iconographic abstraction of visual input and anchoring interpretation and generation in intended meaning. --- ### Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling Authors: Zizhang Luo, Yuhao Luo, Youwei Xiao, Yansong Xu, Runlin Guo, Yun Liang Published: 2026-04-19 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2604.17353v1 Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely unaddressed, constraining the full potential of agentic systems. At the algorithm level, allocating additional inference-time computation can enhance workflow capacity but introduces cross-path redundancy: overlapping computations across multiple reasoning branches. At the task level, complex tasks can be decomposed into subproblems and delegated across multiple agents for improved scalability and parallelism. However, existing infrastructures' scheduling is unaware of the existence of multiple agents, missing opportunities to optimize resource allocation. We propose Hive, a multi-agent infrastructure that enables algorithm- and task-level scaling. Hive features a description frontend that captures per-agent behavior and supports test-time scaling algorithms. Leveraging this specification, our backend introduces two key mechanisms: Logits Cache that reuses intermediate logits across redundant sampling paths to mitigate cross-path redundancy at the algorithm level, and Agent-Aware Scheduling that efficiently allocates compute and KV-cache resources according to agent contributions at the task level. Experiments show that Logits Cache achieves an average speedup of $1.11\times$-$1.76\times$ for re-sampling, and Agent-Aware Scheduling reduces the hotspot miss rate by $33\%$-$51\%$. --- ### SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization Authors: Yuncheng Hua, Sion Weatherhead, Mehdi Jafari, Hao Xue, Flora D. Salim Published: 2026-04-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17351v1 Automated simulator construction requires distributional fidelity, distinguishing it from generic code generation. We identify two failure modes in long-horizon LLM agents: contextual drift and optimization instability arising from conflating structural and parametric errors. We propose SOCIA-EVO, a dual-anchored evolutionary framework. SOCIA-EVO introduces: (1) a static blueprint to enforce empirical constraints; (2) a bi-level optimization to decouple structural refinement from parameter calibration; and (3) a self-curating Strategy Playbook that manages remedial hypotheses via Bayesian-weighted retrieval. By falsifying ineffective strategies through execution feedback, SOCIA-EVO achieves robust convergence, generating simulators that are statistically consistent with observational data. The code and data of SOCIA-EVO are available here: https://github.com/cruiseresearchgroup/SOCIA/tree/evo. --- ### SPaRSe-TIME: Saliency-Projected Low-Rank Temporal Modeling for Efficient and Interpretable Time Series Prediction Authors: K. A. Shahriar Published: 2026-04-19 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2604.17350v1 Time series forecasting is traditionally dominated by sequence-based architectures such as recurrent neural networks and attention mechanisms, which process all time steps uniformly and often incur substantial computational cost. However, real-world temporal signals typically exhibit heterogeneous structure, where informative patterns are sparsely distributed and interspersed with redundant observations. This work introduces \textbf{SPaRSe-TIME}, a structured and computationally efficient framework that models time series through a decomposition into three complementary components: saliency, memory, and trend. The proposed approach reformulates temporal modeling as a projection onto informative subspaces, where saliency acts as a data-dependent sparsification operator, memory captures dominant low-rank temporal patterns, and trend encodes low-frequency dynamics. These components are integrated through a lightweight, adaptive mapping that enables simplified, selective, and interpretable temporal reasoning. Extensive experiments on diverse real-world datasets demonstrate that SPaRSe-TIME achieves competitive predictive performance compared to recurrent and attention-based architectures, while significantly reducing computational complexity. The model is particularly effective in structured time series with clear temporal components and provides explicit interpretability through component-wise contributions. Furthermore, analysis reveals both the strengths and limitations of decomposition-based modeling, highlighting challenges in highly stochastic and complex multivariate settings. Overall, SPaRSe-TIME offers a principled alternative to monolithic sequence models, bridging efficiency, interpretability, and performance, and providing a scalable framework for time series learning. --- ### Formal Foundations of Agentic Business Process Management Authors: Giuseppe De Giacomo, Timotheus Kampik, Lukas Kirchdorfer, Marco Montali, Christoph Weinhuber Published: 2026-04-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17347v1 Just like traditional BPM systems, agentic BPM systems are built around a specification of the process under consideration. Their distinguishing feature, however, is that the execution of the process is driven by multiple autonomous decision-makers, referred to as agents. Since such agents cannot be fully controlled, the process specification is augmented with explicit objectives, or goals, assigned to the participating agents. Agents then pursue these goals, at least to the best of their efforts, under suitable assumptions on the behavior of others, by adopting appropriate strategies. Centrally, the organization enacting the process can use these specifications to provide guardrails on the decision-making capabilities of agents at the strategy level. This paper sets up the mathematical foundations of such systems in three key settings and analyzes four foundational problems of agentic BPM. --- ### Logical Computational Linguistics Authors: Glyn V. Morrill, Oriol Valentín Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17346v1 In this book we promote logical computational linguistics as opposed to statistical computational linguistics. In particular, we provide a logical semantic interface. This book assembles more than twenty years of research work on type logical grammar, and adds new ideas and material. Chains of statistical dependencies of less than one hundred per cent confidence tend monotonically to zero. Chains of logical dependencies of any length maintain one hundred per cent confidence end to end. We aspire to enable perfect syntactic and semantic processing in life-critical NLP applications. --- ### FLARE: Task-agnostic embedding model evaluation through a normalization process Authors: Jingzhou Jiang, Yixuan Tang, Yi Yang, Kar Yan Tam Published: 2026-04-19 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.17344v1 When task-specific labels are not available, it becomes difficult to select an embedding model for a specific target corpus. Existing labelless measures based on kernel estimators or Gaussian mixes fail in high-dimensional space, resulting in unstable rankings. We propose a flow-based labelless representation embedding evaluation (FLARE), which utilizes normalized streams to estimate information sufficiency directly from log-likelihood and avoid distance-based density estimation. We give a finite sample boundary, indicating that the estimation error depends on the intrinsic dimension of the data manifold rather than the original embedding dimension. On 11 datasets and 8 embedders, FLARE reached Spearman's $ρ$ of 0.90 under the supervised benchmark and remained stable in high-dimensional embeddings ($d \geq 3{,}584$) as the existing labelless baseline collapsed. --- ### Monotone but Exciting: On Evolving Monotone Boolean Functions with High Nonlinearity Authors: Claude Carlet, Marko Čupić, Marko Ðurasevic, Domagoj Jakobovic, Luca Mariot, Stjepan Picek Published: 2026-04-19 Categories: cs.NE, cs.CR arXiv: https://arxiv.org/abs/2604.17342v1 Monotone Boolean functions are a structurally important class of Boolean functions, but their restricted form imposes strong limitations on achievable nonlinearity. In this paper, we investigate whether evolutionary computation can evolve monotone Boolean functions with high nonlinearity, both in the balanced and imbalanced settings. We consider three solution encodings: the standard truth table representation, a balanced truth table encoding that preserves Hamming weight, and a symbolic tree-based genetic programming representation. To guide the search toward monotone increasing functions, we introduce a non-monotonicity penalty and combine it with fitness functions targeting balancedness and nonlinearity. Experimental results are reported for dimensions from $n=5$ to $n=14$. The results show that evolutionary search can discover monotone Boolean functions with nonlinearities clearly exceeding those of majority functions, and in several cases approaching the best currently known values for monotone functions. At the same time, the experiments reveal substantial differences between encodings: the balanced truth table encoding performs poorly for larger dimensions, while the standard truth table and genetic programming encodings remain competitive, with genetic programming becoming especially relevant in the largest tested dimensions. --- ### Dual-Resolution Attention-Gated Deep Learning with Ordinal Regression for Diabetic Retinopathy Grading: A Quantified Assessment of Cross-Domain Generalization Authors: Afshan Hashmi Published: 2026-04-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.17341v2 Diabetic retinopathy (DR) is a leading cause of preventable blindness, and automated grading could extend screening capacity. However, most reported DR models are validated only on the dataset they were trained on, leaving their behaviour under real screening variability unmeasured. This study presents a dual-resolution grading framework and quantifies how far performance falls when the imaging domain shifts. Two EfficientNet backbones process complementary views of each fundus image: B0 receives Ben Graham-normalised input at 224x224, emphasising vascular structure, while B3 receives CLAHE-enhanced input at 300x300, emphasising focal lesions. A learnable attention gate fuses the branches per image, and an ordinal binary-decomposition head models severity as an ordered scale rather than as unordered categories. Training used a combined set of 4,149 images (APTOS 2019, n = 2,929; Messidor-2 training portion, n = 1,220); evaluation used a held-out APTOS split (n = 733) and a Messidor-2 test set (n = 524) excluded from training and from all model selection. Quadratic weighted kappa was 0.882 (95% CI 0.853-0.906) on APTOS and 0.679 (95% CI 0.613-0.735) on Messidor-2 for this run, a significant gap of 0.202 (95% CI 0.142-0.273); across three random seeds the held-out kappa was 0.689 +/- 0.021. Critically, accuracy fell 19.3 points while 93.7% of predictions stayed within one grade of reference: ordering survives domain shift, threshold placement does not. Referable-DR sensitivity fell from 0.879 to 0.620. --- ### Neuro-Symbolic Resolution of Recommendation Conflicts in Multimorbidity Clinical Guidelines Authors: Shiyao Xie, Jian Du Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17340v1 Clinical guidelines, typically developed by independent specialty societies, inherently exhibit substantial fragmentation, redundancy, and logical contradiction. These inconsistencies, particularly when applied to patients with multimorbidity, not only cause cognitive dissonance for clinicians but also introduce catastrophic noise into AI systems, rendering the standard Retrieval-Augmented Generation (RAG) system fragile and prone to hallucination. To address this fundamental reliability crisis, we introduce a Neuro-Symbolic framework that automates the detection of recommendation redundancies and conflicts. Our pipeline employs a multi-agent system to translate unstructured clinical natural language into rigorous symbolic logic language, which is then verified by a Satisfiability (SAT) solver. By formulating a hierarchical taxonomy of logical rule interactions, we identify a critical category termed Local Conflict - a decision conflict arising from the intersection of comorbidities. Evaluating our system on a curated benchmark of 12 authoritative SGLT2 inhibitor guidelines, we reveal that 90.6% of conflicts are Local, a structural complexity that single-disease guidelines fail to address. While state-of-the-art LLMs fail in detecting these conflicts, our neuro-symbolic approach achieves an F1 score of 0.861. This work demonstrates that logical verification must precede retrieval, establishing a new technical standard for automated knowledge coordination in medical AI. --- ### Precise Debugging Benchmark: Is Your Model Debugging or Regenerating? Authors: Wang Bill Zhu, Miaosen Chai, Shangshang Wang, Yejia Liu, Song Bian, Honghua Dong, Willie Neiswanger, Robin Jia Published: 2026-04-19 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2604.17338v4 Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise debugging, we introduce the Precise Debugging Benchmark (PDB) framework, which automatically converts any coding dataset into a debugging benchmark with precision-aware evaluation. PDB generates buggy programs by synthesizing verified atomic bugs and composing them into multi-bug programs. We define two novel metrics, edit-level precision and bug-level recall, which measures how many necessary edits are made and how many bugs are resolved. We release two evaluation benchmarks: PDB-Single-Hard on single-line bugs, and PDB-Multi on multi-line bugs. Experiments show that frontier models, such as GPT-5.1-Codex and DeepSeek-V3.2-Thinking, achieve unit-test pass rates above 76% but exhibit precision below 45%, even when explicitly instructed to perform minimal debugging. Finally, we show that iterative and agentic debugging strategies do not substantially improve precision or recall, highlighting the need to rethink post-training pipelines for coding models. --- ### AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning Authors: Jingbo Sun, Wenyue Chong, Songjun Tu, Qichao Zhang, Yaocheng Zhang, Jiajun Chai, Xiaohan Wang, Wei Lin, Guojun Yin, Dongbin Zhao Published: 2026-04-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17337v1 Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant search steps, incurring substantial computational cost and latency. Prior work limits search depth (i.e., the number of search steps) to reduce cost, but this often leads to underexploration of complex questions. To address this, we first investigate how search depth affects accuracy and find a minimal sufficient search depth that defines an accuracy-efficiency trade-off, jointly determined by question complexity and the agent's capability. Furthermore, we propose AutoSearch, a reinforcement learning (RL) framework that evaluates each search step via self-generated intermediate answers. By a self-answering mechanism, AutoSearch identifies the minimal sufficient search depth and promotes efficient search by rewarding its attainment while penalizing over-searching. In addition, reward mechanisms are introduced to stabilize search behavior and improve answer quality on complex questions. Extensive experiments on multiple benchmarks show that AutoSearch achieves a superior accuracy-efficiency trade-off, alleviating over-searching while preserving search quality. --- ### Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction Authors: Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang, Sibo wang, Linglin Liao Published: 2026-04-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.17328v2 This paper investigates the length problem in sequence-level relative reinforcement learning. We observe that, although existing methods partially alleviate length-related phenomena, a more fundamental issue remains insufficiently characterized: the comparison units used during training lack inherent comparability. Building on this observation, we propose a new perspective: the length problem should not be viewed merely as a loss-scaling or normalization bias, but rather as a \emph{comparison unit construction} problem. We further establish a sample-construction-based training framework that, instead of applying post-hoc corrections to unequal-length responses, proactively constructs equal-length, alignable, and comparable training segments during generation. Within this framework, we propose EqLen, a concrete method applicable to group-relative comparison algorithms such as GRPO, GSPO, and RLOO. Through dual-track synchronous generation, prefix inheritance, and segment masking, EqLen efficiently collects effective equal-length training segments and enables stable --- ### Signal or Noise in Multi-Agent LLM-based Stock Recommendations? Authors: George Fatouros, Kostas Metaxas Published: 2026-04-19 Categories: q-fin.PM, cs.AI, q-fin.ST arXiv: https://arxiv.org/abs/2604.17327v1 We present the first portfolio-level validation of MarketSenseAI, a deployed multi-agent LLM equity system. All signals are generated live at each observation date, eliminating look-ahead bias. The system routes four specialist agents (News, Fundamentals, Dynamics, and Macro) through a synthesis agent that issues a monthly equity thesis and recommendation for each stock in its coverage universe, and we ask two questions: do its buy recommendations add value over both passive benchmarks and random selection, and what does the internal agent structure reveal about the source of the edge? On the S&P 500 cohort (19 months) the strong-buy equal-weight portfolio earns +2.18%/month against a passive equal-weight benchmark of +1.15% (approximating RSP), a +25.2% compound excess, and ranks at the 99.7th percentile of 10,000 Monte Carlo portfolios (p=0.003). The S&P 100 cohort (35 months) delivers a +30.5% compound excess over EQWL with consistent direction but formal significance not reached, limited by the small average selection of ~10 stocks per month. Non-negative least-squares projection of thesis embeddings onto agent embeddings reveals an adaptive-integration mechanism. Agent contributions rotate with market regime (Fundamentals leads on S&P 500, Macro on S&P 100, Dynamics acts as an episodic momentum signal) and this agent rotation moves in lockstep with both the sector composition of strong-buy selections and identifiable macro-calendar events, three independent views of the same underlying adaptation. The recommendation's cross-sectional Information Coefficient is statistically significant on S&P 500 (ICIR=+0.489, p=0.024). These results suggest that multi-agent LLM equity systems can identify sources of alpha beyond what classical factor models capture, and that the buy signal functions as an effective universe-filter that can sit upstream of any portfolio-construction process. --- ### Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation Authors: Jiaang Li, Zhendong Mao, Quan Wang, Yuning Wan, Yongdong Zhang Published: 2026-04-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17325v1 Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts, favoring fluent but hallucinated generated content over factually grounded yet disorganized retrieved evidence. This phenomenon reveals that the utility of retrieved information is bottlenecked by its presentation. To bridge this gap, we propose QREAM, a style-controlled rewriter that aligns retrieved documents with a question-oriented style while preserving facts, better for LLM readers to utilize. Our framework consists of two stages: (1) QREAM-ICL, which uses stylistic seeds to guide iterative rewriting exploration; and (2) QREAM-FT, a lightweight student model distilled from denoised ICL outputs. QREAM-FT employs dual-criteria rejection sampling, filtering based on answer correctness and factual consistency to ensure high-quality supervision. QREAM seamlessly integrates into existing RAG pipelines as a plug-and-play module. Experiments demonstrate that QREAM consistently enhances advanced RAG pipelines, yielding up to 8% relative improvement with negligible latency overhead, effectively balancing question relevance with factual grounding. --- ### Capacity-Controlled Global Attention for Graph Transformers Authors: Yang Liu, Dongxin Guo, Tom Zheng, Siu Ming Yiu, Liam Ning, Jikun Wu Published: 2026-04-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.17324v2 Global self-attention drives modern graph transformers, yet the softmax at its core imposes a structural constraint rarely examined directly: every attention row is non-negative and sums to one, so each per-head output is a mass-conserving convex combination of value vectors. A node can never "attend to nothing." We argue this conservation constraint is a single root cause behind three pathologies usually studied in isolation: the collapse of node representations with depth (over-smoothing), a low-rank bottleneck on per-head outputs, and brittle optimization in deep stacks. Drawing on how sigmoid gating removes analogous attention sinks in language models, we introduce SigGate-GT, a graph transformer that applies a learned, per-head, input-conditioned sigmoid gate to the attention output inside the GraphGPS framework. The gate is a smooth, per-dimension "volume control" that can drive head outputs toward zero, relaxing the constraint without abandoning attention's probabilistic interpretation. Analytically and through synthetic experiments, we show the gate strictly increases the stable rank of per-head outputs, and connect this rank gain to all three manifestations. On five molecular and long-range benchmarks, SigGate-GT matches the prior best on ZINC (0.059 MAE), records the strongest result among the graph-transformer baselines we evaluate on ogbg-molhiv (82.47% ROC-AUC), and is competitive on ogbg-molpcba and the Long-Range Graph Benchmark, with statistically significant gains over GraphGPS on all five datasets (p < 0.05). Mechanism analyses confirm the diagnosis: gating slows over-smoothing (a 30% mean relative gain in representation diversity across 4-16 layers), keeps attention entropy from collapsing, and stabilizes training across a 10x learning-rate range, at about 1% parameter overhead on OGB and under 3% wall-clock cost. --- ### A Universal Avoidance Method for Diverse Multi-branch Generation Authors: Kyeongman Park, Minha Jhang, Kyomin Jung Published: 2026-04-19 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.17323v1 Modern generative models still lack human-level creativity, particularly in multi-branch diversity. Prior approaches to address this problem often incur heavy computation or strong dependency on model architecture. Therefore, we introduce UAG(Universal Avoidance Generation), a model-agnostic and computationally efficient generation strategy that penalizes similarity among previously generated outputs. Thus, UAG can enhance multi-branch diversity across both diffusion and transformer models, with minimal additional computation. In experiments, our method achieves up to 1.9 times higher diversity, runs 4.4 times faster, and requires only 1/64 of the FLOPs compared to state-of-the-art methods. The full code is https://anonymous.4open.science/r/2026_ACL_Universal/. --- ### R-FLoRA: Residual-Statistic-Gated Low-Rank Adaptation for Single-Image Face Morphing Attack Detection Authors: Raghavendra Ramachandra Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17321v1 Face morphing attacks pose a substantial risk to the reliability of face recognition systems used in passport issuance, border control, and digital identity verification. Detecting morphing attacks from a single facial image remains challenging owing to the lack of a trusted reference and the diversity of attack generation methods. This paper presents a new Single-Image Face Morphing Attack Detection (S-MAD) framework that integrates high-frequency Laplacian residual statistics with representations from a frozen, foundation-scale vision transformer. The approach employs residual-statistic-gated low-rank adapters (R-FLoRA) and feature-wise residual fusion (Res-FiLM) to enhance sensitivity to local morphing artefacts while preserving the semantic context of the backbone. A novel residual-contrastive alignment loss further regularises the fused token space, improving discrimination under unseen morphing conditions. Comprehensive experiments on four ICAO-compliant datasets, encompassing seven morph generation techniques, demonstrate that the proposed method consistently surpasses nine recent state-of-the-art S-MAD algorithms in detection accuracy and cross-domain (or dataset) generalisation. With a frozen backbone and minimal trainable parameters, the model achieves real-time efficiency and interpretability, making it suitable for real-life scenarios in biometric verification systems. --- ### Towards Joint Quantization and Token Pruning of Vision-Language Models Authors: Xinqing Li, Xin He, Xindong Zhang, Ming-Ming Cheng, Lei Zhang, Yun Liu Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17320v1 Deploying Vision-Language Models (VLMs) under aggressive low-bit inference remains challenging because inference cost is dominated by the long visual-token prefix during prefill and the growing KV cache during autoregressive decoding. Token pruning and low-bit quantization are complementary for reducing these costs, yet naive stage-wise combinations are often brittle due to a mismatch between quantization calibration and pruning execution. We present a collaborative quantization-and-pruning framework that unifies low-bit inference and deterministic visual-token pruning in a single deployable pipeline. The framework introduces the \textbf{Q}uantization \textbf{U}nified \textbf{O}ffline \textbf{T}oken \textbf{A}llocator (\textbf{QUOTA}), which converts low-bit calibration signals into a layer-wise token allocation schedule and materializes it as a pruning recipe. Token importance is evaluated under deployed W4A4 operators with a quantized KV cache by combining activation magnitude, attention cues, and an explicit low-bit risk signal, enabling consistent budgeted top-$k$ selection. Experiments on standard VLM benchmarks show improved robustness over stage-wise baselines under the same low-bit regime, achieving 95.65\% average retention while retaining only 30\% of visual tokens, compared with about 94.3\% retention for representative stage-wise combinations. The code will be released. --- ### E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition Authors: Meng Zhang, Jinzhong Ning, Xiaolong Wu, Hongfei Lin, Yijia Zhang Published: 2026-04-19 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.17319v1 Grounded Multimodal Named Entity Recognition (GMNER) aims to jointly identify named entity mentions in text, predict their semantic types, and ground each entity to a corresponding visual region in an associated image. Existing approaches predominantly adopt pipeline-based architectures that decouple textual entity recognition and visual grounding, leading to error accumulation and suboptimal joint optimization. In this paper, we propose E2E-GMNER, a fully end-to-end generative framework that unifies entity recognition, semantic typing, visual grounding, and implicit knowledge reasoning within a single multimodal large language model. We formulate GMNER as an instruction-tuned conditional generation task and incorporate chain-of-thought reasoning to enable the model to adaptively determine when visual evidence or background knowledge is informative, reducing reliance on noisy cues. To further address the instability of generative bounding box prediction, we introduce Gaussian Risk-Aware Box Perturbation (GRBP), which replaces hard box supervision with probabilistically perturbed soft targets to improve robustness against annotation noise and discretization errors. Extensive experiments on the Twitter-GMNER and Twitter-FMNERG benchmarks demonstrate that E2E-GMNER achieves highly competitive performance compared with state of the art methods, validating the effectiveness of unified end-to-end optimization and noise-aware grounding supervision. Code is available at:https://github.com/Finch-coder/E2E-GMNER --- ### When Background Matters: Breaking Medical Vision Language Models by Transferable Attack Authors: Akash Ghosh, Subhadip Baidya, Sriparna Saha, Xiuying Chen Published: 2026-04-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17318v1 Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model stealing or adversarial fine-tuning, while transferable attacks from natural images introduce visible distortions that clinicians can easily detect. To address this, we propose MedFocusLeak, a highly transferable black-box multimodal attack that induces incorrect yet clinically plausible diagnoses while keeping perturbations imperceptible. The method injects coordinated perturbations into non-diagnostic background regions and employs an attention distraction mechanism to shift the model's focus away from pathological areas. Extensive evaluations across six medical imaging modalities show that MedFocusLeak achieves state-of-the-art performance, generating misleading yet realistic diagnostic outputs across diverse VLMs. We further introduce a unified evaluation framework with novel metrics that jointly capture attack success and image fidelity, revealing a critical weakness in the reasoning capabilities of modern clinical VLMs. --- ### Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA Authors: Alberto Testoni, Iacer Calixto Published: 2026-04-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.17316v1 Safe clinical deployment of Large Language Models (LLMs) requires not only high accuracy but also robust uncertainty calibration to ensure models defer to clinicians when appropriate. Our paper investigates how social descriptors of a patient (specifically sexual orientation and religious affiliation) distort these uncertainty signals and model accuracy. Evaluating nine general-purpose and biomedical LLMs on 2,364 medical questions and their counterfactual variants, we demonstrate that identity markers cause a "calibration crisis". "Homosexual" markers consistently trigger performance drops, and intersectional identities produce idiosyncratic, non-additive harms to calibration. Moreover, a clinician-validated case study in an open-ended generation setting confirms that these failures are not an artifact of the multiple-choice format. Our results demonstrate that the presence of social identity cues does not merely shift predictions; it affects the reliability of confidence signals, posing a significant risk to equitable care and safe deployment in confidence-based clinical workflows. --- ### A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions Authors: Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang et al. Published: 2026-04-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.17312v1 Reinforcement learning (RL) has emerged as a powerful post-training paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, reinforcement learning for LLMs faces substantial data scarcity challenges, including the limited availability of high-quality external supervision and the constrained volume of model-generated experience. These limitations make data-efficient reinforcement learning a critical research direction. In this survey, we present the first systematic review of reinforcement learning for LLMs under data scarcity. We propose a bottom-up hierarchical framework built around three complementary perspectives: the data-centric perspective, the training-centric perspective, and the framework-centric perspective. We develop a taxonomy of existing methods, summarize representative approaches in each category, and analyze their strengths and limitations. Our taxonomy aims to provide a clear conceptual foundation for understanding the design space of data-efficient RL for LLMs and to guide researchers working in this emerging area. We hope this survey offers a comprehensive roadmap for future research and inspires new directions toward more efficient and scalable reinforcement learning post-training for LLMs. --- ### Interpolating Discrete Diffusion Models with Controllable Resampling Authors: Marcel Kollovieh, Sirine Ayadi, Stephan Günnemann Published: 2026-04-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17310v1 Discrete diffusion models form a powerful class of generative models across diverse domains, including text and graphs. However, existing approaches face fundamental limitations. Masked diffusion models suffer from irreversible errors due to early unmasking, while uniform diffusion models, despite enabling self-correction, often yield low-quality samples due to their strong reliance on intermediate latent states. We introduce IDDM, an Interpolating Discrete Diffusion Model, that improves diffusion by reducing dependence on intermediate latent states. Central to IDDM is a controllable resampling mechanism that partially resets probability mass to the marginal distribution, mitigating error accumulation and enabling more effective token corrections. IDDM specifies a generative process whose transitions interpolate between staying at the current state, resampling from a prior, and flipping toward the target state, while enforcing marginal consistency and fully decoupling training from inference. We benchmark our model against state-of-the-art discrete diffusion models across molecular graph generation as well as text generation tasks, demonstrating competitive performance. --- ### Knows: Agent-Native Structured Research Representations Authors: Guangsheng Yu, Xu Wang Published: 2026-04-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17309v1 Research artifacts are distributed primarily as reader-oriented documents like PDFs. This creates a bottleneck for increasingly agent-assisted and agent-native research workflows, in which LLM agents need to infer fine-grained, task-relevant information from lengthy full documents, a process that is expensive, repetitive, and unstable at scale. We introduce Knows, a lightweight companion specification that binds structured claims, evidence, provenance, and verifiable relations to existing research artifacts in a form LLM agents can consume directly. Knows addresses the gap with a thin YAML sidecar (KnowsRecord) that coexists with the original PDF, requiring no changes to the publication itself, and validated by a deterministic schema linter. We evaluate Knows on 140 comprehension questions across 20 papers spanning 14 academic disciplines, comparing PDF-only, sidecar-only, and hybrid conditions across six LLM agents of varying capacity. Weak models (0.8B--2B parameters) improve from 19--25\% to 47--67\% accuracy (+29 to +42 percentage points) when reading sidecar instead of PDF, while consuming 29--86\% fewer input tokens; an LLM-as-judge re-scoring confirms that weak-model sidecar accuracy (75--77\%) approaches stronger-model PDF accuracy (78--83\%). Beyond this controlled evaluation, a community sidecar hub at https://knows.academy/ has already indexed over ten thousand publications and continues to grow daily, providing independent evidence that the format is adoption-ready at scale. ---