# Research Papers — 2026-04 · bundle page 6 of 233 > Full-text markdown of papers #251–300 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/6 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/5.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/7.md) ### Geometry-Calibrated Conformal Abstention for Language Models Authors: Rui Xu, Yi Chen, Sihong Xie, Hui Xiong Published: 2026-04-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.27914v1 When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about the answer. Retraining models to reward admitting ignorance can lead to overly conservative behaviors and poor generalization due to scarce evaluation benchmarks. We propose a post hoc framework, Conformal Abstention (CA), adapted from conformal prediction (CP) to determine whether to abstain from answering a query. CA provides finite-sample guarantees on both the probability of participation (i.e., not abstaining) and the probability that the generated response is correct. Importantly, the abstention decision relies on prediction confidence rather than the non-conformity scores used in CP, which are intractable for open-ended generation. To better align prediction confidence with the model's ignorance, we introduce a calibration strategy using representation geometry within the model to measure knowledge involvement in shaping the response. Experiments demonstrate that we improve selective answering significantly with 75 percent conditional correctness. --- ### Physical Foundation Models: Fixed hardware implementations of large-scale neural networks Authors: Logan G Wright, Tianyu Wang, Tatsuhiro Onodera, Peter L. McMahon Published: 2026-04-30 Categories: cs.LG, cs.ET, cs.NE arXiv: https://arxiv.org/abs/2604.27911v1 Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks -- text and code generation, question answering, summarization, image classification, and so on. The philosophy of foundation models is to put effort into a single, large (${\sim}10^{12}$-parameter) general-purpose model that can be adapted to many downstream tasks with no or minimal additional training. We argue that the rise of foundation models presents an opportunity for hardware engineers: in contrast to when different models were used for different tasks, it now makes sense to build special-purpose, fixed hardware implementations of neural networks, manufactured and released at the roughly 1-year cadence of major new foundation-model versions. Beyond conventional digital-electronic inference hardware with read-only weight memory, we advocate a more radical re-thinking: hardware in which the neural network is realized directly at the level of the physical design and operates via the hardware's natural physical dynamics -- \textit{Physical Foundation Models} (PFMs). PFMs could enable orders-of-magnitude advantages in energy efficiency, speed, and parameter density. For ${\sim}10^{12}$-parameter models, this would both reduce the high energy burden of AI in datacenters and enable AI in edge devices that today are power-constrained to far smaller models. PFMs could also enable inference hardware for models much larger than current ones: $10^{15}$- or even $10^{18}$-parameter PFMs seem plausible by some measures. We present back-of-the-envelope calculations illustrating PFM scaling using an optical example -- a 3D nanostructured glass medium -- and discuss prospects in nanoelectronics and other physical platforms. We conclude with the major research challenges that must be resolved for trillion-parameter PFMs and beyond to become reality. --- ### From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction Authors: Alex Petrov, Alexander Gusak, Denis Mukha, Dima Korolev Published: 2026-04-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.27906v3 Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This design is useful for thematic recall, but it is mismatched to the kinds of memory that agents need in production: exact facts, current state, updates and deletions, aggregation, relations, negative queries, and explicit unknowns. These operations require memory to behave less like search and more like a system of record. This paper argues that reliable external AI memory must be schema-grounded. Schemas define what must be remembered, what may be ignored, and which values must never be inferred. We present an iterative, schema-aware write path that decomposes memory ingestion into object detection, field detection, and field-value extraction, with validation gates, local retries, and stateful prompt control. The result shifts interpretation from the read path to the write path: reads become constrained queries over verified records rather than repeated inference over retrieved prose. We evaluate this design on structured extraction and end-to-end memory benchmarks. On the extraction benchmark, the judge-in-the-loop configuration reaches 90.42% object-level accuracy and 62.67% output accuracy, above all tested frontier structured-output baselines. On our end-to-end memory benchmark, xmemory reaches 97.10% F1, compared with 80.16%-87.24% across the third-party baselines. On the application-level task, xmemory reaches 95.2% accuracy, outperforming specialised memory systems, code-generated Markdown harnesses, and customer-facing frontier-model application harnesses. The results show that, for memory workloads requiring stable facts and stateful computation, architecture matters more than retrieval scale or model strength alone. --- ### From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction Authors: Alex Petrov, Alexander Gusak, Denis Mukha, Dima Korolev Published: 2026-04-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.27906v2 Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This design is useful for thematic recall, but it is mismatched to the kinds of memory that agents need in production: exact facts, current state, updates and deletions, aggregation, relations, negative queries, and explicit unknowns. These operations require memory to behave less like search and more like a system of record. This paper argues that reliable external AI memory must be schema-grounded. Schemas define what must be remembered, what may be ignored, and which values must never be inferred. We present an iterative, schema-aware write path that decomposes memory ingestion into object detection, field detection, and field-value extraction, with validation gates, local retries, and stateful prompt control. The result shifts interpretation from the read path to the write path: reads become constrained queries over verified records rather than repeated inference over retrieved prose. We evaluate this design on structured extraction and end-to-end memory benchmarks. On the extraction benchmark, the judge-in-the-loop configuration reaches 90.42% object-level accuracy and 62.67% output accuracy, above all tested frontier structured-output baselines. On our end-to-end memory benchmark, xmemory reaches 97.10% F1, compared with 80.16%-87.24% across the third-party baselines. On the application-level task, xmemory reaches 95.2% accuracy, outperforming specialised memory systems, code-generated Markdown harnesses, and customer-facing frontier-model application harnesses. The results show that, for memory workloads requiring stable facts and stateful computation, architecture matters more than retrieval scale or model strength alone. --- ### HiMix: Hierarchical Artifact-aware Mixup for Generalized Synthetic Image Detection Authors: Shuchang Zhou, Kaiwen Shen, Jiwei Wei, Yuyang Zhou, Peng Wang, Yang Yang Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27903v1 The rapid evolution of generative models has enabled the creation of highly realistic and diverse synthetic images, posing significant challenges to reliable and generalizable Synthetic Image Detection (SID). However, existing detectors are typically trained on limited and biased datasets, resulting in poor generalization to unseen generators. To address this issue, we propose HiMix, a unified framework that enhances generalization by expanding the training distribution and promoting artifact-aware representations. Specifically, the Mixup-driven Distributional Augmentation (MDA) module constructs continuous transitional samples between real and fake images, improving coverage of low-confidence regions and exposing the model to more challenging samples, while the pixel-wise mixup operation smoothly perturbs semantics to enhance sensitivity to low-level artifacts. Moreover, the Hierarchical Artifact-aware Representation (HAR) module aggregates artifact information from both global and local levels through cross-layer integration and coarse-to-fine feature fusion, enabling the extraction of discriminative forgery representations under diverse distributions. Extensive experiments across multiple benchmarks demonstrate that HiMix achieves state-of-the-art performance, establishing well-separated logits for improved generalization to unseen forgeries. --- ### Simulating clinical interventions with a generative multimodal model of human physiology Authors: Guy Lutsker, Gal Sapir, Jordi Merino, Smadar Shilo, Anastasia Godneva, Eli Meirom, Shie Mannor, Hagai Rossman, Gal Chechik, Eran Segal Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27899v1 Understanding how human health changes over time, and why responses to interventions vary between individuals, remains a central challenge in medicine. Here we present HealthFormer, a decoder-only transformer that models the human physiological trajectory generatively, by training on data from the Human Phenotype Project, a multi-visit cohort of over 15,000 deeply phenotyped individuals. We tokenise each participant's health trajectory across 667 measurements spanning seven domains: blood biomarkers, body composition, sleep physiology, continuous glucose monitoring, gut microbiome, wearable-derived physiology, and behaviour and medication exposure. We train HealthFormer to forecast individual physiological trajectories across these domains, and from this single generative objective a range of clinically relevant tasks can be expressed as queries on the model. We show that, without task-specific training, HealthFormer transfers to four independent cohorts and improves prediction for 27 of 30 incident-disease and mortality endpoints, exceeding established clinical risk scores in every comparison. We further show that the model can simulate interventions in silico: in a held-out personalised-nutrition trial, intervention-conditioned predictions recover individual six-month biomarker changes (e.g., Pearson r = 0.78 for diastolic blood pressure). Across 41 randomised intervention-outcome comparisons drawn from published trials, our results show that the predicted direction of effect agrees in every case, and the predicted mean falls within the reported 95% confidence interval in 30 cases. We position HealthFormer as an initial health world model, from which forecasting, risk stratification, and intervention-conditioned simulation arise as queries, providing a basis for clinical digital twins. --- ### Graph World Models: Concepts, Taxonomy, and Future Directions Authors: Jiawei Liu, Senqiao Yang, Mingjun Wang, Yu Wang, Bei Yu Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27895v1 As one of the mainstream models of artificial intelligence, world models allow agents to learn the representation of the environment for efficient prediction and planning. However, classical world models based on flat tensors face several key problems, including noise sensitivity, error accumulation and weak reasoning. To address these limitations, many recent studies use graph structure to decompose the environment into entity nodes and interactive edges, and model virtual environments in a structured space. This paper systematically formalizes and unifies these emerging graph-based works under the concept of graph world models (GWMs). To the best of our knowledge, GWMs have not yet been explicitly defined and surveyed as a unified research paradigm. Furthermore, we propose a taxonomy based on relational inductive biases (RIB), categorizing GWMs by the specific structural priors they inject: (1) spatial RIB for topological abstraction; (2) physical RIB for dynamic simulation; and (3) logical RIB for causal and semantic reasoning. For each model category, we outline the key design principles, summarize representative models, and conduct comparative analyses. We further discuss open challenges and future directions, including dynamic graph adaptation, probabilistic relational dynamics, multi-granularity inductive biases, and the need for dedicated benchmarks and evaluation metrics for GWMs. --- ### Prediction-powered Inference by Mixture of Experts Authors: Yanwu Gu, Linglong Kong, Dong Xia Published: 2026-04-30 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2604.27892v1 The rapidly expanding artificial intelligence (AI) industry has produced diverse yet powerful prediction tools, each with its own network architecture, training strategy, data-processing pipeline, and domain-specific strengths. These tools create new opportunities for semi-supervised inference, in which labeled data are limited and expensive to obtain, whereas unlabeled data are abundant and widely available. Given a collection of predictors, we treat them as a mixture of experts (MOE) and introduce an MOE-powered semi-supervised inference framework built upon prediction-powered inference (PPI). Motivated by the variance reduction principle underlying PPI, the proposed framework seeks the mixture of experts that achieves the smallest possible variance. Compared with standard PPI, the MOE-powered inference framework adapts to the unknown performance of individual predictors, benefits from their collective predictive power, and enjoys a best-expert guarantee. The framework is flexible and applies to mean estimation, linear regression, quantile estimation, and general M-estimation. We develop non-asymptotic theory for the MOE-powered inference framework and establish upper bounds on the coverage error of the resulting confidence intervals. Numerical experiments demonstrate the practical effectiveness of MOE-powered inference and corroborate our theoretical findings. --- ### In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks Authors: Simon Dennis, Michael Diamond, Rivaan Patil, Kevin Shabahang, Hao Guo Published: 2026-04-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.27891v2 Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking state and injecting routing instructions at every turn. We present a controlled comparison showing that for procedural tasks, this architecture is dominated by a simpler alternative: putting the entire procedure in the system prompt and letting the model self-orchestrate. Across three domains -- travel booking (14 nodes), Zoom technical support (14 nodes), and insurance claims processing (55 nodes) -- we evaluate 200 conversations per condition using LLM-as-judge scoring on five quality criteria. The in-context approach scores 4.53--5.00 on a 5-point scale while a LangGraph orchestrator using the same model scores 4.17--4.84. The orchestrated system fails on 24% of travel, 9% of Zoom, and 17% of insurance conversations, compared to 11.5%, 0.5%, and 5% for the in-context baseline. While external orchestration may have been necessary for earlier models, advances in frontier model capabilities have made it unnecessary for multi-turn conversations following a defined procedure. --- ### Noise2Map: End-to-End Diffusion Model for Semantic Segmentation and Change Detection Authors: Ali Shibli, Andrea Nascetti, Yifang Ban Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27889v1 Semantic segmentation and change detection are two fundamental challenges in remote sensing, requiring models to capture either spatial semantics or temporal differences from satellite imagery. Existing deep learning models often struggle with temporal inconsistencies or in capturing fine-grained spatial structures, require extensive pretraining, and offer limited interpretability - especially in real-world remote sensing scenarios. Recent advances in diffusion models show that Gaussian noise can be systematically leveraged to learn expressive data representations through denoising. Motivated by this, we investigate whether the noise process in diffusion models can be effectively utilized for discriminative tasks. We propose Noise2Map, a unified diffusion-based framework that repurposes the denoising process for fast, end-to-end discriminative learning. Unlike prior work that uses diffusion only for generation or feature extraction, Noise2Map directly predicts semantic or change maps using task-specific noise schedules and timestep conditioning, avoiding the costly sampling procedures of traditional diffusion models. The model is pretrained via self-supervised denoising and fine-tuned with supervision, enabling both interpretability and robustness. Our architecture supports both tasks (SS and CD) through a shared backbone and task-specific noise schedulers. Extensive evaluations on the SpaceNet7, WHU, and xView2 buildings damaged by wildfires datasets demonstrate that Noise2Map ranks on average 1st among seven models on semantic segmentation and 1st on change detection by a cross-dataset rank metric (average F1 primary, IoU tie-break). Ablation studies highlight the robustness of our model against different training noise schedulers and timestep control in the diffusion process, as well as the ability of the model to perform multi-task learning. --- ### Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing Authors: Max Lovig Published: 2026-04-30 Categories: math.ST, cs.IT, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.27883v1 In modern parametric model training, full-batch gradient descent (and its variants) suffers due to progressively stronger biasing towards the exact realization of training data; this drives the systematic ``generalization gap'', where the train error becomes an unreliable proxy for test error. Existing approaches either argue this gap is benign through complex analysis or sacrifice data to a validation set. In contrast, we introduce decoupled descent (DD), a novel theory-based training algorithm that satisfies a train-test identity -- enforcing the train error to asymptotically track the test error for stylized Gaussian mixture models. Within this specific regime, leveraging approximate message passing theory, DD iteratively cancels the biases due to data reuse, rigorously demonstrating the feasibility of zero-cost validation and $100\%$ data utilization. Moreover, DD is governed by a low-dimensional state evolution recursion, rendering the dynamics of the algorithm transparent and tractable. We validate DD on XOR classification, yielding superior performance compared to GD; additionally, we implement noisy MNIST and non-linear probing of CIFAR-10, demonstrating that even when our stylized assumptions are relaxed, DD narrows the generalization gap compared to GD. --- ### Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needs Authors: Giuseppe Arbore, Andrea Sillano, Luigi De Russis Published: 2026-04-30 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.27882v1 Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilities behind unified interfaces. However, today's agent systems typically rely on hard-coded agent architectures with fixed roles, coordination patterns, and interaction flows that limit end-user personalization and make adaptation to individual needs and contexts difficult. Given this limitation, we argue that on-demand persona-based agent generation offers a promising path towards more efficient and contextually appropriate interaction within agentic workflows. By dynamically crafting agents and personas at run-time to match user characteristics, task demands, and workflow context, agentic platforms can move beyond one-size-fits-all configurations. We present a pipeline for on-demand persona generation in agentic platforms, detailing how real-time crafting of AI personas can be systematically integrated within agent systems, aiming to open new possibilities in agentic platform design paradigms. --- ### Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection Authors: Shuchang Zhou, Shangkun Wu, Jiwei Wei, Ke Liu, Ran Ran, Caiyan Qin, Yang Yang Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27875v1 AI-generated images are becoming increasingly realistic and diverse, posing significant challenges for generalizable detection. While Vision Foundation Models (VFMs) provide rich semantic representations and frequency-based methods capture complementary artifact cues, existing approaches that combine these modalities still suffer from limited generalization, with notable performance degradation on unseen generative models. We attribute this limitation to two key factors: frequency shortcut bias toward easily distinguishable cues associated with specific generators and cross-domain representation conflict between high-level semantics and low-level frequency patterns. To address these issues, we propose a Frequency-aware Gated Injection Network (FGINet) to improve generalization. Specifically, we design a Band-Masked Frequency Encoder (BMFE) that applies cross-band masking in the frequency domain to reduce reliance on generator-specific patterns and encourage more diverse and generalizable representations. We further introduce a Layer-wise Gated Frequency Injection (LGFI) mechanism to progressively inject frequency cues into the VFM backbone with adaptive gating, aligning with its hierarchical abstraction and alleviating representation conflict. Moreover, we propose a Hyperspherical Compactness Learning (HCL) framework with a cosine margin objective to learn compact and well-separated representations. Extensive experiments demonstrate that FGINet achieves state-of-the-art performance and strong generalization across multiple challenging datasets. --- ### Modeling Clinical Concern Trajectories in Language Model Agents Authors: Sukesh Subaharan, Venkatesan VS, Murugadasan P, Sivakumar D, Gautham N, Ganeshkumar M Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27872v1 Large language model (LLM) agents deployed in clinical settings often exhibit abrupt, threshold-driven behavior, offering little visibility into accumulating risk prior to escalation. In real-world care, however, clinicians act on gradually rising concern rather than instantaneous triggers. We study whether explicit state dynamics can expose such pre-escalation signals without delegating clinical authority to the agent. We introduce a lightweight agent architecture in which a memoryless clinical risk encoder is integrated over time using first- and second-order dynamics to produce a continuous escalation pressure signal. Across synthetic ward scenarios, stateless agents exhibit sharp escalation cliffs, while second-order dynamics produce smooth, anticipatory concern trajectories despite similar escalation timing. These trajectories surface sustained unease prior to escalation, enabling human-in-the-loop monitoring and more informed intervention. Our results suggest that explicit state dynamics can make LLM agents more clinically legible by revealing how long concern has been rising, not just when thresholds are crossed. --- ### Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs Authors: Nuria Alabau-Bosque, Jorge Vila-Tomas, Paula Dauden-Oliver, Valero Laparra, Jesus Malo Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27870v1 Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastically degrade performance due to their reliance on spatially dependent fully connected layers. In this work, we resolve this vulnerability by proposing a lightweight 'Online Architecture' strategy. By strategically inserting Global Average Pooling (GAP) layers at various network depths, we effectively decouple feature recognition from spatial location. Using VGG-16 as a primary case study, we demonstrate that this architectural modification achieves a massive 98% reduction in trainable parameters (from 5.2M to just 82K) and a 90% reduction in total network size (138M to 14M). Despite this drastic pruning, our variants maintain competitive Top-1 accuracy on ImageNet (66.4%) while doubling translational robustness, reducing average relative loss from 0.09 to 0.05. Furthermore, our analysis identifies a fundamental limit to invariance: while GAP resolves macroscopic sensitivity, discrete pooling operations introduce a residual periodic aliasing that prevents perfect pixel-level stability. Finally, we extend these findings to Perceptual Image Quality Assessment (IQA) by integrating our invariant backbones into the LPIPS framework. The resulting metric significantly outperforms the retrained baseline in generalization across the KADID-10k dataset (Spearman 0.89 vs. 0.75) and achieves a near-perfect alignment with human psychophysical response curves on the RAID dataset (Spearman 0.95). These results confirm that enforcing architectural invariance is a far more efficient and biologically plausible path to robustness than traditional data augmentation. Data and code are publicly available. The data and code are publicly available to facilitate validation and further research. --- ### KellyBench: A Benchmark for Long-Horizon Sequential Decision Making Authors: Thomas Grady, Kip Parker, Iliyan Zarov, Henry Course, Chengxi Taylor, Ross Taylor Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27865v1 Language models are saturating benchmarks for procedural tasks with narrow objectives. But they are increasingly being deployed in long-horizon, non-stationary environments with open-ended goals. In this paper we introduce KellyBench, an environment for evaluating sequential decision-making in sports betting markets. Agents are placed in a sequential simulation of the 2023-24 English Premier League season and tasked with maximising their long-term bankroll growth. They are given detailed historical data, including advanced statistics, lineups, and public odds. To succeed they must build machine learning models, identify edge in public markets, and adapt as the environment changes over time. We find that all frontier models evaluated lose money on average over the course of the season for five seeds. The best performing model achieves an average return of -8%, and many models experiencing ruin across seeds. To judge strategy sophistication, we use a human expert rubric to grade each model and find their approaches to be unsophisticated compared to human baselines; Claude Opus 4.6 achieves a rubric score of 26.5%, which means there is significant room for improvement. KellyBench is available as an open-access API endpoint at https://openreward.ai/GeneralReasoning/KellyBench. --- ### TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning Authors: Bowen Sun, Chaozhuo Li, Yaodong Yang, Yiwei Wang, Chaowei Xiao Published: 2026-04-30 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.27861v1 Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collectively reconstruct prohibited content. In real-world deployments, LLMs face a continuous, untraceable stream of fully anonymized and arbitrarily interleaved requests, infiltrated by covertly distributed adversarial queries. Under this rigorous threat model, state-of-the-art defensive strategies exhibit fundamental limitations. In the absence of trustworthy user metadata, they are incapable of tracking global historical contexts, while their deployment of generative models for real-time monitoring introduces computationally prohibitive overhead. To address this, we present TwinGate, a stateful dual-encoder defense framework. TwinGate employs Asymmetric Contrastive Learning (ACL) to cluster semantically disparate but intent-matched malicious fragments in a shared latent space, while a parallel frozen encoder suppresses false positives arising from benign topical overlap. Each request requires only a single lightweight forward pass, enabling the defense to execute in parallel with the target model's prefill phase at negligible latency overhead. To evaluate our approach and advance future research, we construct a comprehensive dataset of over 3.62 million instructions spanning 8,600 distinct malicious intents. Evaluated on this large-scale corpus under a strictly causal protocol, TwinGate achieves high malicious intent recall at a remarkably low false positive rate while remaining highly robust against adaptive attacks. Furthermore, our proposal substantially outperforms stateful and stateless baselines, delivering superior throughput and reduced latency. --- ### Rethinking Agentic Reinforcement Learning In Large Language Models Authors: Fangming Cui, Ruixiao Zhu, Cheng Fang, Sunan Li, Jiahong Li Published: 2026-04-30 Categories: cs.AI, cs.ET arXiv: https://arxiv.org/abs/2604.27859v3 Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly complex, open-ended tasks has catalyzed a paradigm shift towards agentic paradigms within RL. This emerging framework extends beyond traditional RL by emphasizing the development of autonomous agents capable of goal-setting, long-term planning, dynamic strategy adaptation, and interactive reasoning in uncertain, real-world environments. Unlike conventional approaches that rely heavily on static objectives and episodic interactions, LLM-based Agentic RL incorporates cognitive-like capabilities such as meta-reasoning, self-reflection, and multi-step decision-making directly into the learning loop. In this paper, we provide a deep insight for looking the conceptual foundations, methodological innovations, and effective designs underlying this trend. Furthermore, we identify critical challenges and outline promising future directions for building LLM-based Agentic RL. --- ### AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework Authors: Xubin Luo, Cheng Yang Published: 2026-04-30 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2604.27855v2 AI inference is becoming a persistent and geographically distributed source of electricity demand. Unlike many traditional electrical loads, inference workloads can sometimes be executed away from the user-facing service location, provided that latency, state locality, capacity, and regulatory constraints remain acceptable. This paper studies when such digital relocation of computation can be interpreted as latency-constrained relocation of electricity demand. We develop an energy-geography framework for geo-distributed AI inference. The framework models a three-layer architecture of clients, service nodes, and compute nodes, and formulates inference placement as a constrained optimization problem over electricity prices, marginal carbon intensity, power usage effectiveness, compute capacity, network latency, and migration frictions. The key object is the energy-latency frontier: the marginal cost and carbon benefit unlocked by relaxing inference latency budgets. The paper makes four contributions. First, it distinguishes physical electricity transmission from digital relocation of electricity-consuming computation. Second, it formulates a geo-distributed inference placement model with feasibility masks and migration frictions. Third, it introduces operational metrics, including relocatable inference demand, energy return on latency, carbon return on latency, and a relocation break-even condition. Fourth, it provides a transparent stylized simulation over representative global compute regions to show how heterogeneous latency tolerance separates workloads into local, regional, and energy-oriented execution layers. The results show that latency relaxation expands feasible geography, while migration frictions, egress costs, state locality, legal constraints, and capacity limits can sharply reduce realized benefits. --- ### NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains Authors: Shiyao Peng, Qianhe Zheng, Zhuodi Hao, Zichen Tang, Rongjin Li, Qing Huang, Jiayu Huang, Jiacheng Liu, Yifan Zhu, Haihong E Published: 2026-04-30 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.27852v1 Although precise recall is a core objective in Retrieval-Augmented Generation (RAG), a critical oversight persists in the field: improvements in retrieval performance do not consistently translate to commensurate gains in downstream reasoning. To diagnose this gap, we propose the Recall Conversion Rate (RCR), a novel evaluation metric to quantify the contribution of retrieval to reasoning accuracy. Our quantitative analysis of mainstream RAG methods reveals that as Recall@5 improves, the RCR exhibits a near-linear decay. We identify the neglect of retrieval quality in these methods as the underlying cause. In contrast, approaches that focus solely on quality optimization often suffer from inferior recall performance. Both categories lack a comprehensive understanding of retrieval quality optimization, resulting in a trade-off dilemma. To address these challenges, we propose comprehensive retrieval quality optimization criteria and introduce the NeocorRAG framework. This framework achieves holistic retrieval quality optimization by systematically mining and utilizing Evidence Chains. Specifically, NeocorRAG first employs an innovative activated search algorithm to obtain a refined candidate space. Then it ensures precise evidence chain generation through constrained decoding. Finally, the retrieved set of evidence chains guides the retrieval optimization process. Evaluated on benchmarks including HotpotQA, 2WikiMultiHopQA, MuSiQue, and NQ, NeocorRAG achieves SOTA performance on both 3B and 70B parameter models, while consuming less than 20% of tokens used by comparable methods. This study presents an efficient, training-free paradigm for RAG enhancement that effectively optimizes retrieval quality while maintaining high recall. Our code is released at https://github.com/BUPT-Reasoning-Lab/NeocorRAG. --- ### Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems Authors: Oier Ijurco, Oier Lopez de Lacalle Published: 2026-04-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27850v1 Task-based dialogue systems assist users in achieving specific goals, such as executing actions or retrieving information, through natural language interactions. Accurate coreference resolution is essential, as it involves identifying object references within the dialogue - a task that becomes increasingly challenging in visually grounded environments characterized by complex scenes and diverse object metadata. However, coreference resolution in task-based dialogue remains limited by poor generalization across domains and heavy reliance on supervised models that often overfit to dataset-specific artifacts. In this work, we propose a unimodal test-time reasoning approach that enables large language models (LLMs) to reason over detailed object metadata and dialogue history to improve coreference resolution. Empirical results on the SIMMC 2.1 dataset demonstrate that LLMs can generate step-by-step reasoning processes that effectively align dialogue context with objects present in the scene. Extensive experiments highlight the models' ability to link conversations and objects accurately. Moreover, we show that test-time reasoning under few-shot settings generalizes effectively to unseen scenarios and novel objects, outperforming encoder-based supervised methods in cross-domain evaluations. These findings underscore the critical role of structured metadata and careful prompt engineering in enhancing the robustness and generalization of task-oriented dialogue systems. --- ### A Grid-Aware Agent-Based Model for Analyzing Electric Vehicle Charging Systems Authors: Khalil Al-Rahman Youssefi, Marija Gojkovic, Walter Stefanutti, Mika Auer, Melanie Schranz Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27849v1 This paper presents a configurable, grid-aware Agent-Based Model (ABM) for the systematic analysis of electric vehicle (EV) charging systems under configurable infrastructure and operational conditions. The model integrates heterogeneous EV behavior, charging column constraints, and a shared Energy Sandbox that regulates aggregate power allocation, enabling the joint study of user-centric charging dynamics and facility-level power behavior. Implemented in Python using the SimPy discrete-event framework, the approach supports scalable, event-driven simulations across varying system sizes, charger compositions, and scheduling strategies. A representative workplace charging scenario is investigated to illustrate how infrastructure configuration and coordination mechanisms influence energy delivery performance, infrastructure utilization, and aggregate load characteristics. The results highlight the context-dependence of infrastructure suitability and demonstrate how charging strategies and charger types reshape both service-level outcomes and grid-facing behavior. The proposed ABM provides a flexible and extensible simulation environment for exploring technical, operational, and grid-aware aspects of EV charging ecosystems, and for serving as a methodological basis for subsequent studies on advanced coordination strategies beyond the specific scenario analyzed in this study. --- ### Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health Authors: Yuxi Ma, Jieming Cui, Muyang Li, Ye Zhao, Yu Li, Yixuan Wang, Chi Zhang, Yinyin Zang, Yixin Zhu Published: 2026-04-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27846v2 How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools miss discourse structure, while embeddings conflate local coherence with global organization. No existing framework maps these techniques onto the hierarchical processes through which narratives are constructed. Here we introduce a three-level framework - micro-level lexical features, meso-level semantic embeddings, and macro-level LLM narrative evaluation - and show, across 830 Chinese therapeutic texts spanning depression, anxiety, and trauma, that macro-level evaluation substantially outperforms lexical and embedding features for mental health prediction. This challenges the field's emphasis on word-counting: formal structural features (Labov's story grammar, RST coherence, propositional composition) demonstrate that narrative organization per se carries predictive signal, while clinically-grounded narrative dimensions capture how psychological states are expressed through discourse. Semantic embeddings add minimal independent value but yield incremental gains in multi-level classification. By grounding computational levels in discourse processing theory, this framework identifies macro-structural organization as the primary locus of clinical signal and generates testable hypotheses for intervention design and longitudinal research. --- ### Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health Authors: Yuxi Ma, Jieming Cui, Muyang Li, Ye Zhao, Yu Li, Yixuan Wang, Chi Zhang, Yinyin Zang, Yixin Zhu Published: 2026-04-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27846v1 How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools miss discourse structure, while embeddings conflate local coherence with global organization. No existing framework maps these techniques onto the hierarchical processes through which narratives are constructed. Here we introduce a three-level framework - micro-level lexical features, meso-level semantic embeddings, and macro-level LLM narrative evaluation - and show, across 830 Chinese therapeutic texts spanning depression, anxiety, and trauma, that macro-level evaluation substantially outperforms lexical and embedding features for mental health prediction. This challenges the field's emphasis on word-counting: formal structural features (Labov's story grammar, RST coherence, propositional composition) demonstrate that narrative organization per se carries predictive signal, while clinically-grounded narrative dimensions capture how psychological states are expressed through discourse. Semantic embeddings add minimal independent value but yield incremental gains in multi-level classification. By grounding computational levels in discourse processing theory, this framework identifies macro-structural organization as the primary locus of clinical signal and generates testable hypotheses for intervention design and longitudinal research. --- ### ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training Authors: Wenxiang Lin, Xinglin Pan, Ruibo Fan, Shaohuai Shi, Xiaowen Chu Published: 2026-04-30 Categories: cs.DC, cs.CL arXiv: https://arxiv.org/abs/2604.27844v1 Communication has emerged as a critical bottleneck in the distributed training of large language models (LLMs). While numerous approaches have been proposed to reduce communication overhead, the potential of lossless compression has remained largely underexplored since compression and decompression typically consume larger overheads than the benefits of reduced communication traffic. We observe that the communication data, including activations, gradients and parameters, during training often follows a near-Gaussian distribution, which is a key feature for data compression. Thus, we introduce ZipCCL, a lossless compressed communication library of collectives for LLM training. ZipCCL is equipped with our novel techniques: (1) theoretically grounded exponent coding that exploits the Gaussian distribution of LLM tensors to accelerate compression without expensive online statistics, (2) GPU-optimized compression and decompression kernels that carefully design memory access patterns and pipeline using communication-aware data layout, and (3) adaptive communication strategies that dynamically switch collective operations based on workload patterns and system characteristics. Evaluated on a 64-GPU cluster using both mixture-of-experts and dense transformer models, ZipCCL reduces communication time by up to 1.35$\times$ and achieves end-to-end training speedups of up to 1.18$\times$ without any impact on model quality. --- ### CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting Authors: Bokai Pan, Mingyue Cheng, Zhiding Liu, Shuo Yu, Xiaoyu Tao, Yuchong Wu, Qi Liu, Defu Lian, Enhong Chen Published: 2026-04-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.27840v2 Recently, large language models (LLMs) have shown great promise in time series forecasting. However, most existing LLM-based forecasting methods still follow a static generative paradigm that directly maps historical observations to future values in a single pass. Under this paradigm, forecasting is constrained by limited temporal pattern extraction, single-round acquisition of contextual features, one-shot forecast generation, and lack of support from ensemble forecasts. To address these limitations, in this work, we propose CastFlow, a dynamic agentic forecasting framework that enables multi-view temporal pattern extraction, multi-round contextual features acquisition, iterative forecast refinement, and forecasting with ensemble forecasts. First, CastFlow organizes the forecasting process into planning, action, forecasting, and reflection, establishing an agentic workflow. Second, this workflow is supported by a memory module that retrieves prior experience and a multi-view toolkit that constructs diagnostic evidence and provides a reliable ensemble forecast baseline. Third, CastFlow adopts a role-specialized design that combines general-purpose reasoning with specialized numerical forecasting. Under this design, a frozen LLM preserves general-purpose reasoning, while a fine-tuned domain-specific LLM performs evidence-guided numerical forecasting based on the ensemble forecast baseline, rather than from scratch. To optimize a fine-tuned domain-specific LLM, we further develop a two-stage workflow-oriented training that combines supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). To evaluate the effectiveness of CastFlow, we conduct extensive experiments on diverse datasets and show that it achieves superior overall results against strong baselines. We hope that this work can serve as a step toward more adaptive and accurate time series forecasting. --- ### Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning Authors: Yuhua Wang, Qinnan Zhang, Xiaodong Li, Huan Zhang, Yifan Sun, Wangjie Qiu, Hainan Zhang, Yongxin Tong, Zhiming Zheng Published: 2026-04-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.27833v1 Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes, but directly sharing them poses privacy risks. A common defense involves per-example $\ell_2$ clipping before prototype computation to bound sensitivity, followed by isotropic Gaussian noise to enforce Local Differential Privacy (LDP). However, Isotropic Gaussian Prototype Perturbation (IGPP) typically over-perturbs discriminative dimensions and struggles to balance the clipping threshold with representation fidelity. In this paper, we propose VPDR, a client-side privacy plug-in that seamlessly integrates into existing ProtoPFLs. Motivated by the observation that dimension-wise class variance reflects discriminability, we introduce Variance-adaptive Prototype Perturbation (VPP), which allocates less noise to discriminative subspaces, preserving semantic separability while ensuring privacy. We further develop Distillation-guided Clipping Regularization (DCR), which enables feature norms to adaptively concentrate near the predefined clipping threshold while maintaining prediction consistency. Theoretical analysis shows that our groupwise mechanism provides privacy guarantees no weaker than the isotropic baseline under the same privacy constraints. Extensive experiments on multi-domain benchmarks demonstrate that VPDR achieves a superior privacy-utility trade-off, outperforming IGPP in personalized federated fine-tuning without sacrificing robustness against realistic attacks. --- ### ObjectGraph: From Document Injection to Knowledge Traversal -- A Native File Format for the Agentic Era Authors: Mohit Dubey, Open Gigantic Published: 2026-04-30 Categories: cs.AI, cs.DB, cs.IR, cs.MA arXiv: https://arxiv.org/abs/2604.27820v1 Every document format in existence was designed for a human reader moving linearly through text. Autonomous LLM agents do not read - they retrieve. This fundamental mismatch forces agents to inject entire documents into their context window, wasting tokens on irrelevant content, compounding state across multi-turn loops, and broadcasting information indiscriminately across agent roles. We argue this is not a prompt engineering problem, not a retrieval problem, and not a compression problem: it is a format problem. We introduce OBJECTGRAPH (.og), a file format that reconceives the document as a typed, directed knowledge graph to be traversed rather than a string to be injected. OBJECTGRAPH is a strict superset of Markdown - every .md file is a valid .og file - requires no infrastructure beyond a two-primitive query protocol, and is readable by both humans and agents without tooling. We formalize the Document Consumption Problem, characterise six structural properties no existing format satisfies simultaneously, and prove OBJECTGRAPH satisfies all six. We further introduce the Progressive Disclosure Model, the Role-Scoped Access Protocol, and Executable Assertion Nodes as native format primitives. Empirical evaluation across five document classes and eight agent task types demonstrates up to 95.3 percent token reduction with no statistically significant degradation in task accuracy (p > 0.05). Transpiler fidelity reaches 98.7 percent content preservation on a held-out document benchmark. --- ### MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents Authors: Haonan Li, Tianjun Sun, Yongqing Wang, Qisheng Zhang Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27819v1 Multi-server MCP agents create an information-flow control problem: faithful tool composition can turn individually benign read/write permissions into cross-boundary credential propagation -- a structural side effect of workflow topology, not necessarily malicious model behavior. We present MCPHunt, to our knowledge the first controlled benchmark that isolates non-adversarial, verbatim credential propagation across multi-server MCP trust boundaries, with three methodological contributions: (1) canary-based taint tracking that reduces propagation detection to objective string matching; (2) an environment-controlled coverage design with risky, benign, and hard-negative conditions that validates pipeline soundness and controls for credential-format confounds; (3) CRS stratification that disentangles task-mandated propagation (faithful execution of verbatim-transfer instructions) from policy-violating propagation (credentials included despite the option to redact). Across 3,615 main-benchmark traces from 5 models spanning 147 tasks and 9 mechanism families, policy-violating propagation rates reach 11.5--41.3% across all models. This propagation is pathway-specific (25x cross-mechanism range) and concentrated in browser-mediated data flows; hard-negative controls provide evidence that production-format credentials are not necessary -- prompt-directed cross-boundary data flow is sufficient. A prompt-mitigation study across 3 models reduces policy-violating propagation by up to 97% while preserving 80.5% utility, but effectiveness varies with instruction-following capability -- suggesting that prompt-level defenses alone may not suffice. Code, traces, and labeling pipeline are released under MIT and CC BY 4.0. --- ### Probabilistic Circuits for Irregular Multivariate Time Series Forecasting Authors: Christian Klötergens, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme Published: 2026-04-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27814v2 Joint probabilistic modeling is essential for forecasting irregular multivariate time series (IMTS) to accurately quantify uncertainty. Existing approaches often struggle to balance model expressivity with consistent marginalization, frequently leading to unreliable or contradictory forecasts. To address this, we propose CircuITS, a novel architecture for probabilistic IMTS forecasting based on probabilistic circuits. Our model is flexible in capturing intricate dependencies between time series channels while structurally guaranteeing valid joint distributions. Experiments on four real world datasets demonstrate that CircuITS achieves superior joint and marginal density estimation compared to state of the art baselines. --- ### Hyper-Dimensional Fingerprints as Molecular Representations Authors: Jonas Teufel, Luca Torresi, André Eberhard, Pascal Friederich Published: 2026-04-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27810v2 Computational molecular representations underpin virtual screening, property prediction, and materials discovery. Conventional fingerprints are efficient and deterministic but lose structural information through hash-based compression, particularly at low dimensionalities. Learned representations from graph neural networks recover this expressiveness but require task-specific training and substantial computational resources. Here we introduce hyperdimensional fingerprints (HDF), which replace the learned transformations of message-passing neural networks with algebraic operations on high-dimensional vectors, producing deterministic molecular representations without any training. Across diverse property prediction benchmarks, HDF outperforms conventional fingerprints in the majority of tasks while exhibiting greater consistency across datasets and models. Crucially, HDF embeddings preserve molecular similarity faithfully: at 32 dimensions, distances in HDF space achieve a 0.9 Pearson correlation with graph edit distance, compared to 0.55 for Morgan fingerprints at equivalent size. This structural fidelity persists at low dimensions where hash-based methods degrade, allowing simple nearest-neighbor regression to remain predictive with as few as 64 components. We further demonstrate the practical impact in Bayesian molecular optimization, where HDF-based surrogate models achieve substantially improved sample efficiency in regimes where Morgan fingerprints perform comparably to random search. HDF thus provides a general-purpose, training-free alternative to conventional molecular fingerprints, suggesting that the information loss long accepted as inherent to fixed-length fingerprints is a limitation of the hash-based encoding scheme rather than the fingerprint paradigm itself. --- ### Autonomous Systems Dependability in the era of AI: Design Challenges in Safety, Security, Reliability and Certification Authors: Behnaz Ranjbar, Kirankumar Raveendiran, Sudeep Pasricha, Samarjit Chakraborty, Cecilia Carbonelli, Akash Kumar Published: 2026-04-30 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2604.27807v2 The design of embedded safety-critical systems such as those used in next-generation automotive and autonomous platforms, is increasingly challenged by escalating system complexity, hardware-software heterogeneity, and the integration of intelligent, data-driven components. Ensuring dependability in such systems requires a holistic approach that spans multiple abstraction layers and encompasses both design- and run-time assurance. Traditional methods for reliability, safety, and security management often fall short in addressing the dynamic and uncertain behaviors introduced by Artificial Intelligence (AI) and Machine Learning (ML) components, especially under stringent real-time, power, and safety constraints. While AI and ML offer powerful predictive, adaptive, and self-optimizing capabilities that can enhance system dependability, their inherent non-determinism, data-dependence, and lack of formal guarantees introduce new challenges for verification, validation, and certification. This paper explores emerging methodologies, architectures, and frameworks for designing dependable autonomous and embedded systems in the era of AI. It highlight advances in reliability modeling, secure system design, and certification approaches that account for imperfect, learning-enabled components, aiming to bridge the gap between AI innovation and certifiable system-level dependability. --- ### Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures Authors: Ishrak Hamim Mahi, Siam Ferdous, Md Sakib Sadman Badhon, Nabid Hasan Omi, Md Habibun Nabi Hemel, Farig Yousuf Sadeque, Md. Tanzim Reza Published: 2026-04-30 Categories: cs.CV, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.27804v1 The rapid proliferation of image generation models and other artificial intelligence (AI) systems has intensified concerns regarding data privacy and user consent. As the availability of public datasets declines, major technology companies increasingly rely on proprietary or private user data for model training, raising ethical and legal challenges when users request the deletion of their data after it has influenced a trained model. Machine unlearning seeks to address this issue by enabling the removal of specific data from models without complete retraining. This study investigates a modified SISA (Sharded, Isolated, Sliced, and Aggregated) framework designed to achieve class-level unlearning in Convolutional Neural Network (CNN) architectures. The proposed framework incorporates a reinforced replay mechanism and a gating network to enhance selective forgetting efficiency. Experimental evaluations across multiple image datasets and CNN configurations demonstrate that the modified SISA approach enables effective class unlearning while preserving model performance and reducing retraining overhead. The findings highlight the potential of SISA-based unlearning for deployment in privacy-sensitive AI applications. The implementation is publicly available at https://github.com/SiamFS/ sisa-class-unlearning. --- ### Post-Optimization Adaptive Rank Allocation for LoRA Authors: Vishnuprasadh Kumaravelu, Sunil Gupta, P. K. Srijith Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27796v1 Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregard the varying intrinsic dimensionality of model layers and enforce a uniform rank, leading to parameter redundancy. We propose Post-Optimization Adaptive Rank Allocation (PARA), a data-free compression method for LoRA that integrates seamlessly into existing fine-tuning pipelines. PARA leverages Singular Value Decomposition to prune LoRA ranks using a global threshold over singular values across all layers. This results in non-uniform rank allocation based on layer-wise spectral importance. As a post-hoc method, PARA circumvents the training modifications and resulting instabilities that dynamic architectures typically incur. We empirically demonstrate that PARA reduces parameter count by 75-90\% while preserving the predictive performance of the original, uncompressed LoRA across multiple vision and language benchmarks. Code will be published upon acceptance. --- ### How Generative AI Disrupts Search: An Empirical Study of Google Search, Gemini, and AI Overviews Authors: Riley Grossman, Songjiang Liu, Michael K. Chen, Mike Smith, Cristian Borcea, Yi Chen Published: 2026-04-30 Categories: cs.IR, cs.AI, cs.CL, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2604.27790v1 Generative AI is being increasingly integrated into web search for the convenience it provides users. In this work, we aim to understand how generative AI disrupts web search by retrieving and presenting the information and sources differently from traditional search engines. We introduce a public benchmark dataset of 11,500 user queries to support our study and future research of generative search. We compare the search results returned by Google's search engine, the accompanying AI Overview (AIO), and Gemini Flash 2.5 for each query. We have made several key findings. First, we find that for 51.5\% of representative, real-user queries, AIOs are generated, and are displayed above the organic search results. Controversial questions frequently result in an AIO. Second, we show that the retrieved sources are substantially different for each search engine (<0.2 average Jaccard similarity). Traditional Google search is significantly more likely to retrieve information from popular or institutional websites in government or education, while generative search engines are significantly more likely to retrieve Google-owned content. Third, we observe that websites that block Google's AI crawler are significantly less likely to be retrieved by AIOs, despite having access to the content. Finally, AIOs are less consistent when processing two runs of the same query, and are less robust to minor query edits. Our findings have important implications for understanding how generative search impacts website visibility, the effectiveness of generative engine optimization techniques, and the information users receive. We call for revenue frameworks to foster a sustainable and mutually beneficial ecosystem for publishers and generative search providers. --- ### Test Before You Deploy: Governing Updates in the LLM Supply Chain Authors: Mohd Sameen Chishti, Damilare Peter Oyinloye, Jingyue Li Published: 2026-04-30 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.27789v1 Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version changes. These silent updates can introduce behavioral drift, causing regressions in functionality, formatting, safety constraints, or other application-specific requirements. Existing approaches focus primarily on regression testing or versioning but do not provide deployer-side mechanisms for governing compatibility during opaque model evolution. This paper proposes a deployment-side governance framework based on three components: clearly defined rules for how the model is allowed to behave (production contracts), focused testing organized by deployment risk categories (risk-category-based testing suite), and release checkpoints that block updates unless they meet defined safety and performance standards (compatibility gates). Through exploratory validation across multiple LLM versions, we provide evidence that targeted testing in specific risk areas can uncover performance regressions that overall metrics miss. We also identify several open research challenges, including how to systematically build effective test suites, how to set reliable performance thresholds in non-deterministic systems, and how to detect and explain model drift when providers offer limited transparency. Overall, we frame LLM update management as a software supply chain governance problem and outline a research agenda for putting deployer-side compatibility controls into practice. --- ### On the Expressive Power of GNNs to Solve Linear SDPs Authors: Chendi Qian, Christopher Morris Published: 2026-04-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27786v2 Semidefinite programs (SDPs) are a powerful framework for convex optimization and for constructing strong relaxations of hard combinatorial problems. However, solving large SDPs can be computationally expensive, motivating the use of machine learning models as fast computational surrogates. Graph neural networks (GNNs) are a natural candidate in this setting due to their sparsity-awareness and ability to model variable-constraint interactions. In this work, we study what expressive power is sufficient to recover optimal SDP solutions. We first prove negative results showing that standard GNN architectures fail on recovering linear SDP solutions. We then identify a more expressive architecture that captures the key structure of SDPs and can, in particular, emulate the updates of a standard first-order solver. Empirically, on both synthetic and \textsc{SdpLib} benchmarks of various classes of SDPs, this more expressive architecture achieves consistently lower prediction error and objective gap than theoretically weaker baselines. Finally, using the learned high-quality predictions to warm-start the first-order solver yields practical speedups of up to 80%. --- ### RuC: HDL-Agnostic Rule Completion Benchmark Generation Authors: Arnau Ayguadé Domingo, Miquel Alberti-Binimelis, Cristian Gutierrez-Gomez, Emanuele Parisi, Razine Moundir Ghorab, Miquel Moreto, Gokcen Kestor, Dario Garcia-Gasulla Published: 2026-04-30 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2604.27780v1 Large Language Models (LLMs) have rapidly improved in performance across code-related tasks, making their integration into Register Transfer Level (RTL) development increasingly attractive. Mimicking the behavior of inline code assistants, many benchmarks evaluate LLMs' capabilities in code completion, either assessing the generation of entire hardware modules or the completion of a single line within a module. However both of these approaches lack the ability to control the granularity of the code-completion sample size and the syntactic range of completions. To overcome these limitations, we present a framework for language-agnostic rule completion (RuC), a grammar-driven, rule-selectable benchmark generator that automatically produces RTL code-completion tasks from a set of input hardware description sources. RuC uses the target Hardware Description Language (HDL) grammar to mask syntactically defined code regions and prompts a model to regenerate them using the surrounding unmasked code as context, enabling a controlled and scalable evaluation of the domain-specific model's code-understanding capabilities, ranging from assignments to the reconstruction of entire logic blocks. We use RuC to generate two SystemVerilog rule-completion benchmarks from the Tiny Tapeout shuttle TT07 and the CVE2 RISC-V core to demonstrate RuC's applicability to a broad range of designs, and conduct a comparative study of the code completion capabilities of modern open-source LLMs across diverse settings. Results indicate that completion performance strongly depends on the model type, the grammatical structure of the masked region, and the prompting strategy. Specifically, the highest scores are obtained with Fill-in-the-Middle (FIM) prompting. These findings highlight the value of grammar-driven, arbitrarily granular benchmarks for meaningful evaluation of LLM capabilities in RTL development workflows. --- ### WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments Authors: Jinchao Li, Yunxin Li, Chenrui Zhao, Zhenran Xu, Baotian Hu, Min Zhang Published: 2026-04-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.27776v1 While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating across multiple applications to accomplish complex profession-specific workflows. To bridge this gap, we present a computer-use benchmark in cross-application workflows, named WindowsWorld, designed to systematically assess GUI Agents on complex multi-step tasks that mirror real-world professional activities. Our methodology uses a multi-agent framework steered by 16 occupations to generate four difficulty-level tasks with intermediate inspection, which are then refined by human review and executed in a simulated environment. The resulting benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application. Experimental results of leading large models and agents show that: 1) All computer-use agents perform poorly on multi-application tasks (< 21% success rate), far below the performance of simple single-app tasks; 2) They largely fail at tasks requiring conditional judgment and reasoning across $\geq$ 3 applications, stalling at early sub-goals; 3) Low execution efficiency, where tasks often fail despite far exceeding human step limits. Code, benchmark data, and evaluation resources are available at github.com/HITsz-TMG/WindowsWorld. --- ### Data-Efficient Indentation Size Effect Correction in Steels Using Machine Learning and Physics-Constrained Neural Network Authors: Radmir Karamov, Tagir Karamov Published: 2026-04-30 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2604.27775v3 Shallow nanoindentation enables mechanical characterization of thin films, individual phases, and other volume-constrained materials, but the measured hardness is inflated by the indentation size effect (ISE). Classical corrections such as Nix-Gao require a deep linear regime and fail when only shallow measurements are accessible. We present a data-efficient workflow that recovers a high-load reference hardness directly from shallow, size-affected indentation data. Over 700 indentations on three certified steel reference blocks (2-6.5 GPa) were expanded by physics-guided augmentation and used to train conventional regressors (Ridge, Random Forest, XGBoost, neural networks) and a physics-constrained neural network (PCNN) that reconstructs hardness through the bounded form H_ref = H_app/sqrt(1+q), with the signed correction q learned from dimensionless contact-mechanics descriptors (E_r,ref*P_max/S^2, W_p/W_tot, H/E_r). On a quarantined fourth steel tested at loads offset from the training schedule, only the constrained formulation generalized: the dimensionless-input PCNN achieved RMSE = 0.28 GPa and MAPE = 3.6%, and remained stable beyond the training load range, where tree-based models failed structurally. Ablation attributed this robustness to the bounded reconstruction and a load-independence regularizer. Deliberate application to fused silica produced systematic failure, delimiting the method to dislocation-mediated crystalline plasticity. A few hundred laboratory indentations thus suffice to train a physically constrained ISE correction operating on single shallow indentations, offering a template for materials lacking analytical size-effect models. --- ### Instruction-Guided Poetry Generation in Arabic and Its Dialects Authors: Abdelrahman Sadallah, Kareem Elozeiri, Mervat Abassy, Rania Elbadry, Mohamed Anwar, Abed Alhakim Freihat, Preslav Nakov, Fajri Koto Published: 2026-04-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.27766v1 Poetry has long been a central art form for Arabic speakers, serving as a powerful medium of expression and cultural identity. While modern Arabic speakers continue to value poetry, existing research on Arabic poetry within Large Language Models (LLMs) has primarily focused on analysis tasks such as interpretation or metadata prediction, e.g., rhyme schemes and titles. In contrast, our work addresses the practical aspect of poetry creation in Arabic by introducing controllable generation capabilities to assist users in writing poetry. Specifically, we present a large-scale, carefully curated instruction-based dataset in Modern Standard Arabic (MSA) and various Arabic dialects. This dataset enables tasks such as writing, revising, and continuing poems based on predefined criteria, including style and rhyme, as well as performing poetry analysis. Our experiments show that fine-tuning LLMs on this dataset yields models that can effectively generate poetry that is aligned with user requirements, based on both automated metrics and human evaluation with native Arabic speakers. The data and the code are available at https://github.com/mbzuai-nlp/instructpoet-ar --- ### GourNet: A CNN-Based Model for Mango Leaf Disease Detection Authors: Ekram Alam, Jaydip Sanyal, Akhil Kumar Das, Arijit Bhattacharya, Farhana Sultana Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27764v1 Mango cultivation is crucial in the agricultural sector, significantly contributing to economic development and food security. However, diseases affecting mango leaves can significantly reduce both the production and overall fruit grade. Detecting leaf diseases at an early stage with precision is key to effective disease prevention and sustaining crop productivity. In this paper, we introduce a "deep learning" model named "GourNet", which leverages "Convolutional Neural Networks" to identify infections in mango leaves. We utilize the "MangoLeafBD" (MBD) dataset to train and assess the effectiveness of the presented model. The MBD dataset contains seven disease classes and a Healthy class, making a total of eight classes. To enhance model performance, the images are preprocessed through steps like resizing, rescaling, and data augmentation prior to training. To properly evaluate the model, the dataset is separated into 80% for training, with the remaining 20% equally split between validation and testing. Our model uses only 683,656 total parameters and achieves a classification accuracy of 97%. This research's source code can be found at: https://github.com/ekramalam/GourNet-Repo. --- ### Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions Authors: Zhuoran Pan, Yue Li, Zhi Guan, Jianbin Hu, Zhong Chen Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27763v1 The emergence of Large Language Models (LLMs) offers a transformative interface for Web3, yet existing benchmarks fail to capture the complexity of translating high-level user intents into functionally correct, state-dependent on-chain transactions. We present \textsc{Intent2Tx}, a high-fidelity benchmark featuring 29,921 single-step and 1,575 multi-step instances meticulously derived from 300 days of real-world Ethereum mainnet traces. Unlike prior works that rely on synthetic instructions, \textsc{Intent2Tx} grounds natural language intents in real-world protocol interactions across 11 categories, including diverse long-tail Decentralized Finance (DeFi) primitives. To enable rigorous evaluation, we propose an execution-aware framework that transcends surface-level text matching by employing differential state analysis on forked mainnet environments. Our extensive evaluation of 16 state-of-the-art LLMs reveals that while scaling and retrieval-augmentation enhance logical consistency and parameter precision, current models struggle with out-of-distribution generalization and multi-step planning. Crucially, our execution-based analysis demonstrates that syntactically valid outputs often fail to achieve intended state transitions, highlighting a significant gap in current "reasoning-to-execution" capabilities. \textsc{Intent2Tx} serves as a critical foundation for developing autonomous, reliable agents in intent-centric Web3 ecosystems. Code and data: https://anonymous.4open.science/r/Intent2Tx_Bench-97FF . --- ### Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition Authors: Gurucharan Srinivas, Joshua Niemeijer, Frank Köster Published: 2026-04-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.27759v1 Integrating domain knowledge into deep neural networks is a promising way to improve generalization. Existing methods either encode prior knowledge in the loss function or apply post-processing modules, but both depend on identifying useful symbolic knowledge to integrate. Since such rules are often unavailable in real-world vision tasks, we propose a method for targeted knowledge discovery. We propose a Differentiable Knowledge Unit (DKU) that enables modulating the classifier logits, yielding refined class probabilities. The DKU uses implication rules to represent relationships between task classes and implicit concepts learned entirely from the main task supervision, without requiring concept labels. Concepts are identified by dedicated classifiers, whose probabilities are passed to DKU alongside the primary class probabilities. DKU computes a logic-based adjustment vector via fuzzy inference, which modulates the primary class logits to yield refined class probabilities. When concept classifiers represent concepts that do not support the logical rule structure, the resulting adjustments to the class probabilities do not directly minimize the supervision loss. Consequently, optimizing the supervision loss on these adjusted class probabilities implicitly trains the concept classifiers. We construct the rule base so that bidirectional logical relations connect concepts and classes. We enforce the concepts to be distinct from each other and with respect to the classes. This design enforces a clean supervision signal for concept learning. We evaluate our methods on the PASCAL-VOC, COCO, and MedMNIST datasets. We demonstrate improvement through our knowledge integration across these datasets. We conduct domain generalization and hard-sample ablation studies and find that our implicit knowledge discovery and integration outperforms the baseline. --- ### Autonomous Traffic Signal Optimization Using Digital Twin and Agentic AI for Real-Time Decision-Making Authors: Salman Jan, Toqeer Ali Syed, Shahid Kamal, Qamar Wali, Ali Akarma Published: 2026-04-30 Categories: cs.AI, cs.ET, cs.MA arXiv: https://arxiv.org/abs/2604.27753v1 This article outlines a new framework of traffic light optimization through a digital twin of the transport infrastructure, managed by agentic AI to ensure real-time autonomous decisions. The framework relies on physical sensors and edge computing to measure real-time traffic information and simulate traffic flow in a constantly updated digital twin. The traffic light is automatically controlled through the digital twin according to traffic congestion, travel delay and traffic patterns. This approach is implemented as a three-layer system: perception, conceptualization and action. The perception layer receives data on physical systems; the conceptualization layer uses LangChain to process the data; and the action layer links to the Model Context Protocol (MCP) and traffic management APIs to implement optimised traffic signal control algorithms. The results show that the framework minimizes waiting time at traffic lights and positively affects the effectiveness of the entire traffic flow, which is better than the fixed-time and reinforcement learning-based baselines. --- ### Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Authors: Jiaju Chen, Chongming Gao, Chenxiao Fan, Haoyan Liu, Qingpeng Cai, Peng Jiang, Xiangnan He Published: 2026-04-30 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.27747v1 Large language model (LLM)-based generative list-wise recommendation has advanced rapidly, but decoding remains sequential and thus latency-prone. To accelerate inference without changing the target distribution, speculative decoding (SD) uses a small draft model to propose several next tokens at once and a target LLM to verify and accept the longest prefix, skipping multiple steps per round. In generative recommendation, however, each item is represented by multiple semantic-ID tokens, often with separators, and current drafts typically treat these tokens uniformly. This overlooks two practical facts: (i) a token's semantics depend on its within-item slot, and (ii) uncertainty tends to increase with speculation depth. Without modeling these effects, SD's speedups can be limited. We introduce PAD-Rec, Position-Aware Drafting for generative Recommendation, a lightweight module that augments the draft model with two complementary signals. Item position embeddings explicitly encode the within-item slot of each token, strengthening structural awareness. Step position embeddings encode the draft step, allowing the model to adapt to depth-dependent uncertainty and improve proposal quality. To harmonize these signals with base features, we add simple gates: a learnable coefficient for item slots and a context-driven gate for draft steps. The module is trainable, easy to integrate with standard draft models, and adds negligible inference overhead. Extensive experiments on four real-world datasets show up to 3.1x wall-clock speedup and about 5% average wall-clock speedup gain over strong SD baselines, while largely preserving recommendation quality. --- ### Consumer Attitudes Towards AI in Digital Health: A Mixed-Methods Survey in Australia Authors: Wei Zhou, Rashina Hoda, Joycelyn Ling Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27744v1 AI applications are increasingly being introduced into digital health. While technical performance has advanced rapidly, successful deployment mainly depends on consumer attitudes, especially to patient-facing applications. However, most existing research examines consumer attitudes towards healthcare AI at an abstract level rather than in response to concrete artefacts. We report a mixed-methods survey study in Australia (N=275) examining consumer readiness, acceptance, trust, and risk perceptions of healthcare AI, combined with a scenario-based evaluation of an AI-generated versus clinician-written consultation summary. Participants expressed moderate optimism and strong perceived usefulness and ease of use, but also substantial concerns about accuracy, safety, and data use. In the scenario task, the AI-generated summary was strongly preferred for quality, empathy, and overall usefulness, yet identification of the AI summary was near chance. Findings show that consumers judge AI through concrete communication quality and visible human governance, underscoring the need for clinically supervised deployment frameworks beyond technical performance alone. --- ### Why Self-Supervised Encoders Want to Be Normal Authors: Yuval Domb Published: 2026-04-30 Categories: cs.IT, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.27743v2 Self-supervised learning has achieved remarkable empirical success in learning robust representations without explicit labels, most recently demonstrated within the framework of Joint-Embedding Predictive Architectures (JEPA). However, a fundamental question remains: what analytical principles drive these encoders toward specific distributional states? In this paper, we demonstrate that the preference for normal distributions in self-supervised encoders is a direct consequence of the Information Bottleneck (IB) principle. By recasting the IB objective as a rate-distortion problem over the predictive manifold, we provide a theoretical basis for why optimal, target-neutral, latent representations should tend towards isotropic Gaussian states. Under this framework, we show that latent representations correspond to soft clustering of inputs sharing similar predictive distributions, organized within a natural simplex structure. This perspective unifies a wide range of existing supervised and less-supervised objectives and provides a principled explanation for commonly used regularization schemes. Furthermore, we derive practical loss objectives that approximate this structure and demonstrate their effectiveness on standard benchmarks. Ultimately, our framework offers a geometric lens to understanding representation collapse and it establishes a mathematical system for regularization strategies to be used to ensure high-entropy, informative embeddings in modern self-supervised models. --- ### Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction Authors: Mehryar Mohri, Yutao Zhong Published: 2026-04-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.27742v2 A fundamental dichotomy in the theory of classification sets smoothness against statistical efficiency: smooth surrogate losses such as the logistic loss enable fast $O(1/T)$ optimization but yield slow square-root $H$-consistency bounds, while piecewise-linear losses like the Hinge loss achieve optimal linear $H$-consistency rates but are non-differentiable. We introduce Linear-Core (LC) Surrogates, the first family of explicit convex loss functions that provably resolve this tension. By stitching a linear core to a smooth tail, we construct surrogates that are differentiable everywhere ($C^1$, and even $C^2$ under mild conditions) while retaining strict linear $H$-consistency bounds, the strongest known form of consistency guarantee. We establish these linear bounds across three increasingly complex settings: binary classification, multi-class classification, and structured prediction. To our knowledge, this is the first explicit construction to simultaneously achieve smoothness and linear $H$-consistency in any of these settings. Beyond their theoretical appeal, Linear-Core Surrogates offer practical advantages. In multi-class classification, their constant gradient profile near the decision boundary provides natural robustness to instance-dependent label noise, outperforming Cross-Entropy by 2.6% on corrupted CIFAR-10. In structured prediction, their smoothness enables an unbiased stochastic gradient estimator that bypasses the $O(|Y|^2)$ per-step complexity of exact inference, yielding a 23$\times$ speedup over Structured SVMs on large-vocabulary sequence tagging tasks. --- ### Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction Authors: Mehryar Mohri, Yutao Zhong Published: 2026-04-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.27742v1 The choice of loss function in classification involves a fundamental trade-off: smooth losses (like Cross-Entropy) enable fast optimization rates but yield slow square-root consistency bounds, while piecewise-linear losses (like Hinge) offer fast linear consistency rates but suffer from non-differentiability. We propose Linear-Core (LC) Surrogates, a new family of convex loss functions that resolve this tension by stitching a linear core to a smooth tail. We prove that these surrogates are differentiable everywhere while retaining strict linear $H$-consistency bounds, effectively combining the optimization benefits of smoothness with the statistical efficiency of margin-based losses. In the structured prediction setting, we show that this smoothness unlocks a massive computational and energy advantage: it allows for an unbiased stochastic gradient estimator that bypasses the quadratic complexity $O(|\mathscr{Y}|^2)$ of exact inference (e.g., Viterbi). Empirically, our method achieves a 23$\times$ speedup over Structured SVMs on large-vocabulary sequence tagging tasks and demonstrates superior robustness to instance-dependent label noise, outperforming Cross-Entropy by 2.6% on corrupted CIFAR-10. ---