# Research Papers — 2026-04 · bundle page 168 of 233 > Full-text markdown of papers #8351–8400 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/168 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/167.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/169.md) ### AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention Authors: Yuxuan Hu, Jianchao Tan, Jiaqi Zhang, Wen Zan, Pingwei Sun, Yifan Lu, Yerui Sun, Yuchen Xie, Xunliang Cai, Jing Zhang Published: 2026-04-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.07815v1 Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accuracy, its indexing overhead is costly; block-level methods improve efficiency but sacrifice precision. We propose AsyncTLS, a hierarchical sparse attention system that combines coarse-grained block filtering with fine-grained token selection to balance accuracy and efficiency, coupled with an asynchronous offloading engine that overlaps KV cache transfers with computation via temporal locality exploitation. Evaluated on Qwen3 and GLM-4.7-Flash across GQA, and MLA architectures, AsyncTLS achieves accuracy comparable to full attention while delivering 1.2x - 10.0x operator speedups and 1.3x - 4.7x end-to-end throughput improvements on 48k - 96k contexts. --- ### AgriChain Visually Grounded Expert Verified Reasoning for Interpretable Agricultural Vision Language Models Authors: Hazza Mahmood, Yongqiang Yu, Rao Anwer Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07814v1 Accurate and interpretable plant disease diagnosis remains a major challenge for vision-language models (VLMs) in real-world agriculture. We introduce AgriChain, a dataset of approximately 11,000 expert-curated leaf images spanning diverse crops and pathologies, each paired with (i) a disease label, (ii) a calibrated confidence score (High/Medium/Low), and (iii) an expert-verified chain-of-thought (CoT) rationale. Draft explanations were first generated by GPT-4o and then verified by a professional agricultural engineer using standardized descriptors (e.g., lesion color, margin, and distribution). We fine-tune Qwen2.5-VL-3B on AgriChain, resulting in a specialized model termed AgriChain-VL3B, to jointly predict diseases and generate visually grounded reasoning. On a 1,000-image test set, our CoT-supervised model achieves 73.1% top-1 accuracy (macro F1 = 0.466; weighted F1 = 0.655), outperforming strong baselines including Gemini 1.5 Flash, Gemini 2.5 Pro, and GPT-4o Mini. The generated explanations align closely with expert reasoning, consistently referencing key visual cues. These findings demonstrate that expert-verified reasoning supervision significantly enhances both accuracy and interpretability, bridging the gap between generic multimodal models and human expertise, and advancing trustworthy, globally deployable AI for sustainable agriculture. The dataset and code are publicly available at: https://github.com/hazzanabeel12-netizen/agrichain --- ### Agentivism: a learning theory for the age of artificial intelligence Authors: Lixiang Yan, Dragan Gašević Published: 2026-04-09 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.07813v2 Learning theories have historically changed when the conditions of learning evolved. Generative and agentic AI create a new condition by allowing learners to delegate explanation, writing, problem solving, and other cognitive work to systems that can generate, recommend, and sometimes act on the learner's behalf. This creates a fundamental challenge for learning theory: successful performance can no longer be assumed to indicate learning. Learners may complete tasks effectively with AI support while developing less understanding, weaker judgment, and limited transferable capability. We argue that this problem is not fully captured by existing learning theories. Behaviourism, cognitivism, constructivism, and connectivism remain important, but they do not directly explain when AI-assisted performance becomes durable human capability. We propose Agentivism, a learning theory for human-AI interaction. Agentivism defines learning as durable growth in human capability through selective delegation to AI, epistemic monitoring and verification of AI contributions, reconstructive internalization of AI-assisted outputs, and transfer under reduced support. The importance of Agentivism lies in explaining how learning remains possible when intelligent delegation is easy and human-AI interaction is becoming a persistent and expanding part of human learning. --- ### HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models Authors: Qihui Zhu, Tao Zhang, Yuchen Wang, Zijian Wen, Mengjie Zhang, Shuangwu Chen, Xiaobin Tan, Jian Yang, Yang Liu, Zhenhua Dong, Xianzhi Yu, Yinfei Pan Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07812v1 In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making them impractical for real-time or resource-constrained applications. Visual token pruning is a promising strategy for reducing the cost of MLLM inference by removing redundant visual tokens. Existing research usually assumes that all attention heads contribute equally to the visual interpretation. However, our study reveals that different heads may capture distinct visual semantics and inherently play distinct roles in visual processing. In light of this observation, we propose HAWK, a head importance-aware visual token pruning method that perceives the varying importance of attention heads in visual tasks to maximize the retention of crucial tokens. By leveraging head importance weights and text-guided attention to assess visual token significance, HAWK effectively retains task-relevant visual tokens while removing redundant ones. The proposed HAWK is entirely training-free and can be seamlessly applied to various MLLMs. Extensive experiments on multiple mainstream vision-language benchmarks demonstrate that HAWK achieves state-of-the-art accuracy. When applied to Qwen2.5-VL, HAWK retains 96.0% of the original accuracy after pruning 80.2% of the visual tokens. Additionally, it reduces end-to-end latency to 74.4% of the original and further decreases GPU memory usage across the tested models. The code is available at https://github.com/peppery77/HAWK.git. --- ### Intensity Dot Product Graphs Authors: Giulio Valentino Dalla Riva, Matteo Dalla Riva Published: 2026-04-09 Categories: stat.ML, cs.LG, math.PR, stat.ME arXiv: https://arxiv.org/abs/2604.07810v1 Latent-position random graph models usually treat the node set as fixed once the sample size is chosen, while graphon-based and random-measure constructions allow more randomness at the cost of weaker geometric interpretability. We introduce \emph{Intensity Dot Product Graphs} (IDPGs), which extend Random Dot Product Graphs by replacing a fixed collection of latent positions with a Poisson point process on a Euclidean latent space. This yields a model with random node populations, RDPG-style dot-product affinities, and a population-level intensity that links continuous latent structure to finite observed graphs. We define the heat map and the desire operator as continuous analogues of the probability matrix, prove a spectral consistency result connecting adjacency singular values to the operator spectrum, compare the construction with graphon and digraphon representations, and show how classical RDPGs arise in a concentrated limit. Because the model is parameterized by an evolving intensity, temporal extensions through partial differential equations arise naturally. --- ### PolicyLong: Towards On-Policy Context Extension Authors: Junlong Jia, Jiang Zhou, Ziyang Chen, Xing Wu, Chaochen Gao, TingHao Yu, Feng Zhang, Songlin Hu Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07809v2 Extending LLM context windows is hindered by scarce high-quality long-context data. Recent methods synthesize data with genuine long-range dependencies via information-theoretic verification, selecting contexts that reduce a base model's predictive entropy. However, their single-pass offline construction with a fixed model creates a fundamental off-policy gap: the static screening landscape misaligns with the model's evolving capabilities, causing the training distribution to drift. We propose PolicyLong, shifting data construction towards a dynamic on-policy paradigm. By iteratively re-executing data screening (entropy computation, retrieval, and verification) using the current model, PolicyLong ensures the training distribution tracks evolving capabilities, yielding an emergent self-curriculum. Crucially, both positive and hard negative contexts derive from the current model's entropy landscape, co-evolving what the model learns to exploit and resist. Experiments on RULER, HELMET, and LongBench-v2 (Qwen2.5-3B) show PolicyLong consistently outperforms EntropyLong and NExtLong, with gains growing at longer contexts (e.g., +2.54 at 128K on RULER), confirming the value of on-policy data evolution. --- ### PolicyLong: Towards On-Policy Context Extension Authors: Junlong Jia, Ziyang Chen, Xing Wu, Chaochen Gao, TingHao Yu, Feng Zhang, Songlin Hu Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07809v1 Extending LLM context windows is hindered by scarce high-quality long-context data. Recent methods synthesize data with genuine long-range dependencies via information-theoretic verification, selecting contexts that reduce a base model's predictive entropy. However, their single-pass offline construction with a fixed model creates a fundamental off-policy gap: the static screening landscape misaligns with the model's evolving capabilities, causing the training distribution to drift. We propose PolicyLong, shifting data construction towards a dynamic on-policy paradigm. By iteratively re-executing data screening (entropy computation, retrieval, and verification) using the current model, PolicyLong ensures the training distribution tracks evolving capabilities, yielding an emergent self-curriculum. Crucially, both positive and hard negative contexts derive from the current model's entropy landscape, co-evolving what the model learns to exploit and resist. Experiments on RULER, HELMET, and LongBench-v2 (Qwen2.5-3B) show PolicyLong consistently outperforms EntropyLong and NExtLong, with gains growing at longer contexts (e.g., +2.54 at 128K on RULER), confirming the value of on-policy data evolution. --- ### GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning Authors: Kaiyuan Tian, Yu Tang, Gongqingjian Jiang, Baihui Liu, Yifu Gao, Xialin Su, Linbo Qiao, Dongsheng Li Published: 2026-04-09 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.07808v1 Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these approaches often limit model expressiveness and yield lower performance than full-parameter fine-tuning. Layer-wise fine-tuning methods have emerged as an alternative, enabling memory-efficient training through static layer importance sampling strategies. However, these methods overlook variations in layer importance across tasks and training stages, resulting in suboptimal performance on downstream tasks. To address these limitations, we propose GRASS, a gradient-based adaptive layer-wise importance sampling framework. GRASS utilizes mean gradient norms as a task-aware and training-stage-aware metric for estimating layer importance. Furthermore, GRASS adaptively adjusts layer sampling probabilities through an adaptive training strategy. We also introduce a layer-wise optimizer state offloading mechanism that overlaps computation and communication to further reduce memory usage while maintaining comparable training throughput. Extensive experiments across multiple models and benchmarks demonstrate that GRASS consistently outperforms state-of-the-art methods, achieving an average accuracy improvement of up to 4.38 points and reducing memory usage by up to 19.97\%. --- ### The Weaponization of Computer Vision: Tracing Military-Surveillance Ties through Conference Sponsorship Authors: Noa Garcia, Amelia Katirai Published: 2026-04-09 Categories: cs.CY, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.07803v1 Computer vision, a core domain of artificial intelligence (AI), is the field that enables the computational analysis, understanding, and generation of visual data. Despite being historically rooted in military funding and increasingly deployed in warfare, the field tends to position itself as a neutral, purely technical endeavor, failing to engage in discussions about its dual-use applications. Yet it has been reported that computer vision systems are being systematically weaponized to assist in technologies that inflict harm, such as surveillance or warfare. Expanding on these concerns, we study the extent to which computer vision research is being used in the military and surveillance domains. We do so by collecting a dataset of tech companies with financial ties to the field's central research exchange platform: conferences. Conference sponsorship, we argue, not only serves as strong evidence of a company's investment in the field but also provides a privileged position for shaping its trajectory. By investigating sponsors' activities, we reveal that 44% of them have a direct connection with military or surveillance applications. We extend our analysis through two case studies in which we discuss the opportunities and limitations of sponsorship as a means for uncovering technological weaponization. --- ### Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models Authors: Shaotian Li, Shangze Li, Chuancheng Shi, Wenhua Wu, Yanqiu Wu, Xiaohan Yu, Fei Shen, Tat-Seng Chua Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.07802v3 Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) performance remain poorly understood. Current methods predominantly treat VLMs as black-box feature extractors, assuming that anomaly-specific knowledge must be acquired through external adapters or memory banks. In this paper, we challenge this assumption by arguing that anomaly knowledge is intrinsically embedded within pre-trained models but remains latent and under-activated. We hypothesize that this knowledge is concentrated within a sparse subset of anomaly-sensitive neurons. To validate this, we propose latent anomaly knowledge excavation (LAKE), a training-free framework that identifies and elicits these critical neuronal signals using only a minimal set of normal samples. By isolating these sensitive neurons, LAKE constructs a highly compact normality representation that integrates visual structural deviations with cross-modal semantic activations. Extensive experiments on industrial AD benchmarks demonstrate that LAKE achieves state-of-the-art performance while providing intrinsic, neuron-level interpretability. Ultimately, our work advocates for a paradigm shift: redefining anomaly detection as the targeted activation of latent pre-trained knowledge rather than the acquisition of a downstream task. --- ### TEMPER: Testing Emotional Perturbation in Quantitative Reasoning Authors: Atahan Dokme, Benjamin Reichman, Larry Heck Published: 2026-04-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.07801v2 Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language. However, real-world queries are often wrapped in frustration, urgency or enthusiasm. Does emotional framing alone degrade reasoning when all numerical content is preserved? To investigate this, a controlled emotion translation framework is developed that rewrites problems into emotional variants while preserving all quantities and relationships. Using this framework, Temper-5400 (5,400 semantically verified emotion-neutral pairs) is constructed across GSM8K, MultiArith, and ARC-Challenge, and evaluated on eighteen models (1B to frontier scale). Two core results emerge: First, emotional framing reduces accuracy by 2-10 percentage points even though all numerical content is preserved. Second, neutralizing emotional variants recovers most of the lost performance, showing both that the degradation is tied to emotional style rather than content corruption and that neutralization can serve as a lightweight inference-time mitigation. Non-emotional paraphrases cause no such degradation, implicating emotional content rather than surface-level changes. Beyond emotion specifically, the benchmark construction procedure offers a controllable instrument for stylistic translation and robustness evaluation. --- ### TEMPER: Testing Emotional Perturbation in Quantitative Reasoning Authors: Atahan Dokme, Benjamin Reichman, Larry Heck Published: 2026-04-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.07801v1 Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language. However, real-world queries are often wrapped in frustration, urgency or enthusiasm. Does emotional framing alone degrade reasoning when all numerical content is preserved? To investigate this, a controlled emotion translation framework is developed that rewrites problems into emotional variants while preserving all quantities and relationships. Using this framework, Temper-5400 (5,400 semantically verified emotion--neutral pairs) is constructed across GSM8K, MultiArith, and ARC-Challenge, and evaluated on eighteen models (1B to frontier scale). Two core results emerge: First, emotional framing reduces accuracy by 2-10 percentage points even though all numerical content is preserved. Second, neutralizing emotional variants recovers most of the lost performance, showing both that the degradation is tied to emotional style rather than content corruption and that neutralization can serve as a lightweight inference-time mitigation. Non-emotional paraphrases cause no such degradation, implicating emotional content rather than surface-level changes. Beyond emotion specifically, the benchmark construction procedure provides a general framework for controlled stylistic translation and robustness evaluation. --- ### Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems Authors: Xue Qin, Simin Luan, Cong Yang, Zhijun Li Published: 2026-04-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.07799v3 Robots deployed for long periods keep improving their skills, and each update changes a released system. We treat this as a software-lifecycle problem: a fixed decision layer dispatches versioned skill modules and a runtime layer was built to screen each action. On six robosuite tasks we report three negative results and two measurements. First, peak task success is unstable across random seeds (within one method it spans 23.3 to 73.3%), so single-run peaks cannot rank these methods. Second, the system's four modules are whole-task policies with different labels, rotated on a clock, not the phase decomposition its documentation describes. At a matched budget one such policy holds the geometry at the final step in 0.734 of episodes reaching it, averaged over seeds, against 0.023 for the rotation, with no seed overlap at four seeds per arm (exact p=0.029). An intervention isolates why: restoring the termination condition the clock replaced raises retention on every seed. Third, our shield cut violations 98 to 100% on five single-arm tasks (34.9% on the sixth) by discarding whole actions, leaving success at zero: its acceptance criterion omitted completions, so a shield that stopped the robot scored perfectly. What survives is release machinery: a promotion gate kept all twelve injected regressions out, a rate its calibration nearly guarantees, at a 22.5% clean-candidate rejection cost; a dip detector caught nine of twelve, missing all three on one seed. --- ### Learning Without Losing Identity: Capability Evolution for Embodied Agents Authors: Xue Qin, Simin Luan, John See, Cong Yang, Zhijun Li Published: 2026-04-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.07799v2 Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through prompt engineering, policy updates, or structural redesign -- leading to instability and loss of identity in long-lived systems. In this work, we propose a capability-centric evolution paradigm for embodied agents. We argue that a robot should maintain a persistent agent as its cognitive identity, while enabling continuous improvement through the evolution of its capabilities. Specifically, we introduce the concept of Embodied Capability Modules (ECMs), which represent modular, versioned units of embodied functionality that can be learned, refined, and composed over time. We present a unified framework in which capability evolution is decoupled from agent identity. Capabilities evolve through a closed-loop process involving task execution, experience collection, model refinement, and module updating, while all executions are governed by a runtime layer that enforces safety and policy constraints. We demonstrate through simulated embodied tasks that capability evolution improves task success rates from 32.4% to 91.3% over 20 iterations, outperforming both agent-modification baselines and established skill-learning methods (SPiRL, SkiMo), while preserving zero policy drift and zero safety violations. Our results suggest that separating agent identity from capability evolution provides a scalable and safe foundation for long-term embodied intelligence. --- ### Lightweight LLM Agent Memory with Small Language Models Authors: Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang Published: 2026-04-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.07798v3 Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low online overhead but suffer from unstable accuracy due to limited query construction and candidate filtering. In contrast, many systems use repeated large-model calls for online memory operations, improving accuracy but accumulating latency over long interactions. We propose LightMem, a lightweight memory system for better agent memory driven by Small Language Models (SLMs). LightMem modularizes memory retrieval, writing, and long-term consolidation, and separates online processing from offline consolidation to enable efficient memory invocation under bounded compute. We organize memory into short-term memory (STM) for immediate conversational context, mid-term memory (MTM) for reusable interaction summaries, and long-term memory (LTM) for consolidated knowledge, and uses user identifiers to support independent retrieval and incremental maintenance in multi-user settings. Online, LightMem operates under a fixed retrieval budget and selects memories via a two-stage procedure: vector-based coarse retrieval followed by semantic consistency re-ranking. Offline, it abstracts reusable interaction evidence and incrementally integrates it into LTM. Experiments show consistent gains across model scales, with an average F1 improvement of about 2.5 over A-MEM on LoCoMo, while achieving higher efficiency and low median latency (83 ms for retrieval and 581 ms end-to-end). --- ### Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes Authors: Ivan Lau, Jonathan Scarlett Published: 2026-04-09 Categories: stat.ML, cs.IT, cs.LG, math.ST arXiv: https://arxiv.org/abs/2604.07796v2 In this paper, we study the problem of mean estimation under 1-bit communication constraints. We propose a novel adaptive mean estimator based solely on randomized threshold queries, where each 1-bit outcome indicates whether a given sample exceeds a sequentially chosen threshold. Our estimator is $(ε, δ)$-PAC for any distribution with a bounded mean $μ\in (-λ, λ)$ and a bounded $k$-th central moment $\mathbb{E}(|X-μ|^k) \le σ^k$ for any fixed $k > 1$. Moreover, our sample complexity is order-optimal in all such tail regimes, i.e., for every such $k$ value. For $k \neq 2$, our estimator's sample complexity matches the unquantized minimax lower bounds plus an unavoidable $O(\log(λ/σ))$ localization cost. For the finite-variance case ($k=2$), our estimator's sample complexity has an extra multiplicative $O(\log(σ/ε))$ penalty, and we establish a novel information-theoretic lower bound showing that this penalty is a fundamental limit of 1-bit quantization. We also establish a significant adaptivity gap: for both threshold queries and more general interval queries, the sample complexity of any non-adaptive estimator must scale linearly with the search space parameter $λ/σ$, rendering it vastly less sample efficient than our adaptive approach. Finally, we present algorithmic variants that (i) handle an unknown sampling budget, (ii) adapt to an unknown scale parameter $σ$ given (possibly loose) bounds, (iii) require only two stages of adaptivity to achieve order-optimal sample complexity at the expense of more general 1-bit queries, and (iv) leverage multiple local samples per 1-bit query to proportionally reduce communication costs. --- ### Image-Guided Geometric Stylization of 3D Meshes Authors: Changwoon Choi, Hyunsoo Lee, Clément Jambon, Yael Vinker, Young Min Kim Published: 2026-04-09 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.07795v1 Recent generative models can create visually plausible 3D representations of objects. However, the generation process often allows for implicit control signals, such as contextual descriptions, and rarely supports bold geometric distortions beyond existing data distributions. We propose a geometric stylization framework that deforms a 3D mesh, allowing it to express the style of an image. While style is inherently ambiguous, we utilize pre-trained diffusion models to extract an abstract representation of the provided image. Our coarse-to-fine stylization pipeline can drastically deform the input 3D model to express a diverse range of geometric variations while retaining the valid topology of the original mesh and part-level semantics. We also propose an approximate VAE encoder that provides efficient and reliable gradients from mesh renderings. Extensive experiments demonstrate that our method can create stylized 3D meshes that reflect unique geometric features of the pictured assets, such as expressive poses and silhouettes, thereby supporting the creation of distinctive artistic 3D creations. Project page: https://changwoonchoi.github.io/GeoStyle --- ### SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents Authors: Xinshun Feng, Xinhao Song, Lijun Li, Gongshen Liu, Jing Shao Published: 2026-04-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.07791v3 Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected to learn from trajectories by synthesizing tools or accumulating explicit experiences. However, prevailing methods typically rely on large-scale LLMs or multi-agent frameworks, which hinder their deployment in resource-constrained environments. The inherent sparsity of outcome-based rewards also poses a substantial challenge, as agents typically receive feedback only upon completion of tasks. To address these limitations, we introduce a Tool-Memory based self-evolving agentic framework SEARL. Unlike approaches that directly utilize interaction experiences, our method constructs a structured experience memory that integrates planning with execution. This provides a novel state abstraction that facilitates generalization across analogous contexts, such as tool reuse. Consequently, agents extract explicit knowledge from historical data while leveraging inter-trajectory correlations to densify reward signals. We evaluate our framework on knowledge reasoning and mathematics tasks, demonstrating its effectiveness in achieving more practical and efficient learning. --- ### ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents Authors: Kenan Li, Qirui Jin, Liao Zhu, Xiaosong Huang, Yijia Wu, Yikai Zhang, Xin Zhang, Zijian Jin, Yufan Huang, Elsie Nallipogu, Chaoyun Zhang, Yu Kang et al. Published: 2026-04-09 Categories: cs.MA, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2604.07789v2 Recent advances in language model (LM) agents have significantly improved automated software engineering (SWE). Prior work has proposed various agentic workflows and training strategies as well as analyzed failure modes of agentic systems on SWE tasks, focusing on several contextual information signals: Reproduction Test, Regression Test, Edit Location, Execution Context, and API Usage. However, the individual contribution of each signal to overall success remains underexplored, particularly their ideal contribution when intermediate information is perfectly obtained. To address this gap, we introduce Oracle-SWE, a unified method to isolate and extract oracle information signals from SWE benchmarks and quantify the impact of each signal on agent performance. To further validate the pattern, we evaluate the performance gain of signals extracted by strong LMs when provided to a base agent, approximating real-world task-resolution settings. These evaluations aim to guide research prioritization for autonomous coding systems. --- ### PeReGrINE: Evaluating Personalized Review Fidelity with User Item Graph Context Authors: Steven Au, Baihan Lin Published: 2026-04-09 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2604.07788v1 We introduce PeReGrINE, a benchmark and evaluation framework for personalized review generation grounded in graph-structured user--item evidence. PeReGrINE restructures Amazon Reviews 2023 into a temporally consistent bipartite graph, where each target review is conditioned on bounded evidence from user history, item context, and neighborhood interactions under explicit temporal cutoffs. To represent persistent user preferences without conditioning directly on sparse raw histories, we compute a User Style Parameter that summarizes each user's linguistic and affective tendencies over prior reviews. This setup supports controlled comparison of four graph-derived retrieval settings: product-only, user-only, neighbor-only, and combined evidence. Beyond standard generation metrics, we introduce Dissonance Analysis, a macro-level evaluation framework that measures deviation from expected user style and product-level consensus. We also study visual evidence as an auxiliary context source and find that it can improve textual quality in some settings, while graph-derived evidence remains the main driver of personalization and consistency. Across product categories, PeReGrINE offers a reproducible way to study how evidence composition affects review fidelity, personalization, and grounding in retrieval-conditioned language models. --- ### Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video Authors: Chanhyuk Choi, Taesoo Kim, Donggyu Lee, Siyeol Jung, Taehwan Kim Published: 2026-04-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.07786v2 Talking face generation has gained significant attention as a core application of generative models. To enhance the expressiveness and realism of synthesized videos, emotion editing in talking face video plays a crucial role. However, existing approaches often limit expressive flexibility and struggle to generate extended emotions. Label-based methods represent emotions with discrete categories, which fail to capture a wide range of emotions. Audio-based methods can leverage emotionally rich speech signals - and even benefit from expressive text-to-speech (TTS) synthesis - but they fail to express the target emotions because emotions and linguistic contents are entangled in emotional speeches. Images-based methods, on the other hand, rely on target reference images to guide emotion transfer, yet they require high-quality frontal views and face challenges in acquiring reference data for extended emotions (e.g., sarcasm). To address these limitations, we propose Cross-Modal Emotion Transfer (C-MET), a novel approach that generates facial expressions based on speeches by modeling emotion semantic vectors between speech and visual feature spaces. C-MET leverages a large-scale pretrained audio encoder and a disentangled facial expression encoder to learn emotion semantic vectors that represent the difference between two different emotional embeddings across modalities. Extensive experiments on the MEAD and CREMA-D datasets demonstrate that our method improves emotion accuracy by 14% over state-of-the-art methods, while generating expressive talking face videos - even for unseen extended emotions. Code, checkpoint, and demo are available at https://chanhyeok-choi.github.io/C-MET/ --- ### Automotive Engineering-Centric Agentic AI Workflow Framework Authors: Tong Duy Son, Zhihao Liu, Piero Brigida, Yerlan Akhmetov, Gurudevan Devarajan, Kai Liu, Ajinkya Bhave Published: 2026-04-09 Categories: cs.AI, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2604.07784v1 Engineering workflows such as design optimization, simulation-based diagnosis, control tuning, and model-based systems engineering (MBSE) are iterative, constraint-driven, and shaped by prior decisions. Yet many AI methods still treat these activities as isolated tasks rather than as parts of a broader workflow. This paper presents Agentic Engineering Intelligence (AEI), an industrial vision framework that models engineering workflows as constrained, history-aware sequential decision processes in which AI agents support engineer-supervised interventions over engineering toolchains. AEI links an offline phase for engineering data processing and workflow-memory construction with an online phase for workflow-state estimation, retrieval, and decision support. A control-theoretic interpretation is also possible, in which engineering objectives act as reference signals, agents act as workflow controllers, and toolchains provide feedback for intervention selection. Representative automotive use cases in suspension design, reinforcement learning tuning, multimodal engineering knowledge reuse, aerodynamic exploration, and MBSE show how diverse workflows can be expressed within a common formulation. Overall, the paper positions engineering AI as a problem of process-level intelligence and outlines a practical roadmap for future empirical validation in industrial settings. --- ### Toward Generalizable Graph Learning for 3D Engineering AI: Explainable Workflows for CAE Mode Shape Classification and CFD Field Prediction Authors: Tong Duy Son, Kohta Sugiura, Marc Brughmans, Andrey Hense, Zhihao Liu, Amirthalakshmi Veeraraghavan, Ajinkya Bhave, Jay Masters, Paolo di Carlo, Theo Geluk Published: 2026-04-09 Categories: eess.SY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.07781v1 Automotive engineering development increasingly relies on heterogeneous 3D data, including finite element (FE) models, body-in-white (BiW) representations, CAD geometry, and CFD meshes. At the same time, engineering teams face growing pressure to shorten development cycles, improve performance and accelerate innovation. Although artificial intelligence (AI) is increasingly explored in this domain, many current methods remain task-specific, difficult to interpret, and hard to reuse across development stages. This paper presents a practical graph learning framework for 3D engineering AI, in which heterogeneous engineering assets are converted into physics-aware graph representations and processed by Graph Neural Networks (GNNs). The framework is designed to support both classification and prediction tasks. The framework is validated on two automotive applications: CAE vibration mode shape classification and CFD aerodynamic field prediction. For CAE vibration mode classification, a region-aware BiW graph supports explainable mode classification across vehicle and FE variants under label scarcity. For CFD aerodynamic field prediction, a physics-informed surrogate predicts pressure and wall shear stress (WSS) across aerodynamic body shape variants, while symmetry preserving down sampling retains accuracy with lower computational cost. The framework also outlines data generation guidance that can help engineers identify which additional simulations or labels are valuable to collect next. These results demonstrate a practical and reusable engineering AI workflow for more trustworthy CAE and CFD decision support. --- ### MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices Authors: Alvin Kimbowa, Arjun Parmar, Ibrahim Mujtaba, Will Wei, Maziar Badii, Matthew Harkey, David Liu, Ilker Hacihaliloglu Published: 2026-04-09 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2604.07780v2 Objective: To develop a robust and compact deep learning model for automated knee cartilage segmentation on point-of-care ultrasound (POCUS) devices. Methods: We propose MonoUNet, a novel, highly compact segmentation model consisting of (i) an aggressively reduced U-Net backbone, (ii) a trainable monogenic block that extracts multi-scale local phase features from the input, and (iii) a gating mechanism that injects these features into the encoder stages to reduce sensitivity to variations in ultrasound image appearance. MonoUNet segmentation performance was evaluated on a multi-site, multi-device knee cartilage ultrasound dataset using Dice score and mean average surface distance (MASD). Agreement between MonoUNet and manual cartilage outcomes (thickness and echo intensity) was assessed using Bland-Altman analysis with 95% limits of agreement, and reliability was assessed using intraclass correlation coefficient (ICC$_{2,k}$). Results: Overall, MonoUNet outperformed existing lightweight segmentation models, with average Dice scores ranging from 92.62% to 94.82% and MASD values between 0.133 mm and 0.254 mm. MonoUNet reduces the number of parameters by 10x--700x and computational cost by 14x--2000x relative to existing lightweight models. MonoUNet cartilage outcomes showed excellent reliability and agreement with the manual outcomes: intraclass correlation coefficients (ICC$_{2,k})$=0.96 and bias=2.00% (0.047 mm) for average thickness, and ICC$_{2,k}$=0.99 and bias=0.80% (0.328 a.u.) for echo intensity. Conclusion: Incorporating trainable local phase features improves the robustness of highly compact neural networks for knee cartilage segmentation across varying acquisition settings and could support scalable ultrasound-based assessment and monitoring of knee osteoarthritis using POCUS devices. The code is publicly available at https://github.com/alvinkimbowa/monounet. --- ### Plug-and-Play Logit Fusion for Heterogeneous Pathology Foundation Models Authors: Gexin Huang, Anqi Li, Yusheng Tan, Beidi Zhao, Gang Wang, Zu-Hua Gao, Xiaoxiao Li Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07779v2 Pathology foundation models (FMs) have become central to computational histopathology, offering strong transfer performance across a wide range of diagnostic and prognostic tasks. The rapid proliferation of pathology foundation models creates a model-selection bottleneck: no single model is uniformly best, yet exhaustively adapting and validating many candidates for each downstream endpoint is prohibitively expensive. We address this challenge with a lightweight and novel model fusion strategy, LogitProd, which treats independently trained FM-based predictors as fixed experts and learns sample-adaptive fusion weights over their slide-level outputs. The fusion operates purely on logits, requiring no encoder retraining and no feature-space alignment across heterogeneous backbones. We further provide a theoretical analysis showing that the optimal weighted product fusion is guaranteed to perform at least as well as the best individual expert under the training objective. We systematically evaluate LogitProd on \textbf{22} benchmarks spanning WSI-level classification, tile-level classification, gene mutation prediction, and discrete-time survival modeling. LogitProd ranks first on 20/22 tasks and improves the average performance across all tasks by ~3% over the strongest single expert. LogitProd enables practitioners to upgrade heterogeneous FM-based pipelines in a plug-and-play manner, achieving multi-expert gains with $\sim$12$\times$ lower training cost than feature-fusion alternatives. --- ### The Accountability Horizon: An Impossibility Theorem for Governing Human-Agent Collectives Authors: Haileleol Tibebu, Hewan Shemtaga Published: 2026-04-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.07778v2 Existing accountability frameworks for AI systems, legal, ethical, and regulatory, rest on a shared assumption: for any consequential outcome, at least one identifiable person had enough involvement and foresight to bear meaningful responsibility. This paper proves that agentic AI systems violate this assumption not as an engineering limitation but as a mathematical necessity once autonomy exceeds a computable threshold. We introduce Human-Agent Collectives, a formalisation of joint human-AI systems where agents are modelled as state-policy tuples within a shared structural causal model. Autonomy is characterised through a four-dimensional information-theoretic profile (epistemic, executive, evaluative, social); collective behaviour through interaction graphs and joint action spaces. We axiomatise legitimate accountability through four minimal properties: Attributability (responsibility requires causal contribution), Foreseeability Bound (responsibility cannot exceed predictive capacity), Non-Vacuity (at least one agent bears non-trivial responsibility), and Completeness (all responsibility must be fully allocated). Our central result, the Accountability Incompleteness Theorem, proves that for any collective whose compound autonomy exceeds the Accountability Horizon and whose interaction graph contains a human-AI feedback cycle, no framework can satisfy all four properties simultaneously. The impossibility is structural: transparency, audits, and oversight cannot resolve it without reducing autonomy. Below the threshold, legitimate frameworks exist, establishing a sharp phase transition. Experiments on 3,000 synthetic collectives confirm all predictions with zero violations. This is the first impossibility result in AI governance, establishing a formal boundary below which current paradigms remain valid and above which distributed accountability mechanisms become necessary. --- ### Structured Distillation of Web Agent Capabilities Enables Generalization Authors: Xing Han Lù, Siva Reddy Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.07776v1 Frontier LLMs can navigate complex websites, but their cost and reliance on third-party APIs make local deployment impractical. We introduce Agent-as-Annotators, a framework that structures synthetic trajectory generation for web agents by analogy to human annotation roles, replacing the Task Designer, Annotator, and Supervisor with modular LLM components. Using Gemini 3 Pro as teacher, we generate 3,000 trajectories across six web environments and fine-tune a 9B-parameter student with pure supervised learning on the 2,322 that pass quality filtering. The resulting model achieves 41.5% on WebArena, surpassing closed-source models such as Claude 3.5 Sonnet (36.0%) and GPT-4o (31.5%) under the same evaluation protocol, and nearly doubling the previous best open-weight result (Go-Browse, 21.7%). Capabilities transfer to unseen environments, with an 18.2 percentage point gain on WorkArena L1 (an enterprise platform never seen during training) and consistent improvements across three additional benchmarks. Ablations confirm that each pipeline component contributes meaningfully, with Judge filtering, evaluation hints, and reasoning traces each accounting for measurable gains. These results demonstrate that structured trajectory synthesis from a single frontier teacher is sufficient to produce competitive, locally deployable web agents. Project page: https://agent-as-annotators.github.io --- ### ACIArena: Toward Unified Evaluation for Agent Cascading Injection Authors: Hengyu An, Minxi Li, Jinghuai Zhang, Naen Xu, Chunyi Zhou, Changjiang Li, Xiaogang Xu, Tianyu Du, Shouling Ji Published: 2026-04-09 Categories: cs.AI, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2604.07775v1 Collaboration and information sharing empower Multi-Agent Systems (MAS) but also introduce a critical security risk known as Agent Cascading Injection (ACI). In such attacks, a compromised agent exploits inter-agent trust to propagate malicious instructions, causing cascading failures across the system. However, existing studies consider only limited attack strategies and simplified MAS settings, limiting their generalizability and comprehensive evaluation. To bridge this gap, we introduce ACIArena, a unified framework for evaluating the robustness of MAS. ACIArena offers systematic evaluation suites spanning multiple attack surfaces (i.e., external inputs, agent profiles, inter-agent messages) and attack objectives (i.e., instruction hijacking, task disruption, information exfiltration). Specifically, ACIArena establishes a unified specification that jointly supports MAS construction and attack-defense modules. It covers six widely used MAS implementations and provides a benchmark of 1,356 test cases for systematically evaluating MAS robustness. Our benchmarking results show that evaluating MAS robustness solely through topology is insufficient; robust MAS require deliberate role design and controlled interaction patterns. Moreover, defenses developed in simplified environments often fail to transfer to real-world settings; narrowly scoped defenses may even introduce new vulnerabilities. ACIArena aims to provide a solid foundation for advancing deeper exploration of MAS design principles. --- ### RoboAgent: Chaining Basic Capabilities for Embodied Task Planning Authors: Peiran Xu, Jiaqi Zheng, Yadong Mu Published: 2026-04-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.07774v1 This paper focuses on embodied task planning, where an agent acquires visual observations from the environment and executes atomic actions to accomplish a given task. Although recent Vision-Language Models (VLMs) have achieved impressive results in multimodal understanding and reasoning, their performance remains limited when applied to embodied planning that involves multi-turn interaction, long-horizon reasoning, and extended context analysis. To bridge this gap, we propose RoboAgent, a capability-driven planning pipeline in which the model actively invokes different sub-capabilities. Each capability maintains its own context, and produces intermediate reasoning results or interacts with the environment according to the query given by a scheduler. This framework decomposes complex planning into a sequence of basic vision-language problems that VLMs can better address, enabling a more transparent and controllable reasoning process. The scheduler and all capabilities are implemented with a single VLM, without relying on external tools. To train this VLM, we adopt a multi-stage paradigm that consists of: (1) behavior cloning with expert plans, (2) DAgger training using trajectories collected by the model, and (3) reinforcement learning guided by an expert policy. Across these stages, we exploit the internal information of the environment simulator to construct high-quality supervision for each capability, and we further introduce augmented and synthetic data to enhance the model's performance in more diverse scenarios. Extensive experiments on widely used embodied task planning benchmarks validate the effectiveness of the proposed approach. Our codes will be available at https://github.com/woyut/RoboAgent_CVPR26. --- ### ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions Authors: Zihao Liu, Xiaoyu Wu, Wenna Li, Jianqin Wu, Linlin Yang Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07772v1 Open-world video anomaly detection (OWVAD) aims to detect and explain abnormal events under different anomaly definitions, which is important for applications such as intelligent surveillance and live-streaming content moderation. Recent MLLM-based methods have shown promising open-world generalization, but still suffer from three major limitations: inefficiency for practical deployment, lack of streaming processing adaptation, and limited support for dynamic anomaly definitions in both modeling and evaluation. To address these issues, this paper proposes ESOM, an efficient streaming OWVAD model that operates in a training-free manner. ESOM includes a Definition Normalization module to structure user prompts for reducing hallucination, an Inter-frame-matched Intra-frame Token Merging module to compress redundant visual tokens, a Hybrid Streaming Memory module for efficient causal inference, and a Probabilistic Scoring module that converts interval-level textual outputs into frame-level anomaly scores. In addition, this paper introduces OpenDef-Bench, a new benchmark with clean surveillance videos and diverse natural anomaly definitions for evaluating performance under varying conditions. Extensive experiments show that ESOM achieves real-time efficiency on a single GPU and state-of-the-art performance in anomaly temporal localization, classification, and description generation. The code and benchmark will be released at https://github.com/Kamino666/ESOM_OpenDef-Bench. --- ### Sensitivity-Positional Co-Localization in GQA Transformers Authors: Manoj Chandrashekar Rao Published: 2026-04-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.07766v1 We investigate a fundamental structural question in Grouped Query Attention (GQA) transformers: do the layers most sensitive to task correctness coincide with the layers where positional encoding adaptation has the greatest leverage? We term this the co-localization hypothesis and test it on Llama 3.1 8B, a 32-layer GQA model with a 4:1 query-to-key-value head ratio. We introduce \LSLORA, which restricts LoRA adaptation to layers identified via a novel correctness-differential hidden-state metric, and GARFA (GQA-Aware RoPE Frequency Adaptation), which attaches 8 learnable per-KV-head scalar multipliers to each targeted layer. Contrary to the co-localization hypothesis, we discover strong anti-localization: task-sensitive layers concentrate in the late network ($\ell\in\{23\text{-}31\}$) while RoPE-influential layers dominate the early network ($\ell\in\{0\text{-}9\}$), yielding Spearman $r_s = -0.735$ ($p = 1.66\times10^{-6}$). Despite this anti-localization, a 4-way cross-layer ablation shows that applying both interventions to the sensitivity-identified layers outperforms all alternative configurations by 4-16 percentage points across six diverse benchmarks (MMLU, GPQA, HumanEval+, MATH, MGSM, ARC), approaching Claude 3.5 Haiku on HumanEval+ (67.1% vs. 68.3%) at \$100 total compute cost. --- ### RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs Authors: Liang Yao, Shengxiang Xu, Fan Liu, Chuanyi Zhang, Bishun Yao, Rui Min, Yongjun Li, Chaoqian Ouyang, Shimin Di, Min-Ling Zhang Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07765v2 Earth Observation (EO) systems are essentially designed to support domain experts who often express their requirements through vague natural language rather than precise, machine-friendly instructions. Depending on the specific application scenario, these vague queries can demand vastly different levels of visual precision. Consequently, a practical EO AI system must bridge the gap between ambiguous human queries and the appropriate multi-granularity visual analysis tasks, ranging from holistic image interpretation to fine-grained pixel-wise predictions. While Multi-modal Large Language Models (MLLMs) demonstrate strong semantic understanding, their text-based output format is inherently ill-suited for dense, precision-critical spatial predictions. Existing agentic frameworks address this limitation by delegating tasks to external tools, but indiscriminate tool invocation is computationally inefficient and underutilizes the MLLM's native capabilities. To this end, we propose RemoteAgent, an agentic framework that strategically respects the intrinsic capability boundaries of MLLMs. To empower this framework to understand real user intents, we construct VagueEO, a human-centric instruction dataset pairing EO tasks with simulated vague natural-language queries. By leveraging VagueEO for reinforcement fine-tuning, we align an MLLM into a robust cognitive core that directly resolves image- and sparse region-level tasks. Consequently, RemoteAgent processes suitable tasks internally while intelligently orchestrating specialized tools via the Model Context Protocol exclusively for dense predictions. Extensive experiments demonstrate that RemoteAgent achieves robust intent recognition capabilities while delivering highly competitive performance across diverse EO tasks. --- ### Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities Authors: Jingtong Dou, Chuancheng Shi, Jian Wang, Fei Shen, Zhiyong Wang, Tat-Seng Chua Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.07763v1 As generative artificial intelligence evolves, deepfake attacks have escalated from single-modality manipulations to complex, multimodal threats. Existing forensic techniques face a severe generalization bottleneck: by relying excessively on superficial, modality-specific artifacts, they neglect the shared latent forgery knowledge hidden beneath variable physical appearances. Consequently, these models suffer catastrophic performance degradation when confronted with unseen "dark modalities." To break this limitation, this paper introduces a paradigm shift that redefines multimodal forensics from conventional "feature fusion" to "modality generalization." We propose the first modality-agnostic forgery (MAF) detection framework. By explicitly decoupling modality-specific styles, MAF precisely extracts the essential, cross-modal latent forgery knowledge. Furthermore, we define two progressive dimensions to quantify model generalization: transferability toward semantically correlated modalities (Weak MAF), and robustness against completely isolated signals of "dark modality" (Strong MAF). To rigorously assess these generalization limits, we introduce the DeepModal-Bench benchmark, which integrates diverse multimodal forgery detection algorithms and adapts state-of-the-art generalized learning methods. This study not only empirically proves the existence of universal forgery traces but also achieves significant performance breakthroughs on unknown modalities via the MAF framework, offering a pioneering technical pathway for universal multimodal defense. --- ### Generative optimal transport via forward-backward HJB matching Authors: Haiqian Yang, Vishaal Krishnan, Sumit Sinha, L. Mahadevan Published: 2026-04-09 Categories: cond-mat.stat-mech, cs.LG, math.OC, math.PR arXiv: https://arxiv.org/abs/2604.07762v1 Controlling the evolution of a many-body stochastic system from a disordered reference state to a structured target ensemble, characterized empirically through samples, arises naturally in non-equilibrium statistical mechanics and stochastic control. The natural relaxation of such a system - driven by diffusion - runs from the structured target toward the disordered reference. The natural question is then: what is the minimum-work stochastic process that reverses this relaxation, given a pathwise cost functional combining spatial penalties and control effort? Computing this optimal process requires knowledge of trajectories that already sample the target ensemble - precisely the object one is trying to construct. We resolve this by establishing a time-reversal duality: the value function governing the hard backward dynamics satisfies an equivalent forward-in-time HJB equation, whose solution can be read off directly from the tractable forward relaxation trajectories. Via the Cole-Hopf transformation and its associated Feynman-Kac representation, this forward potential is computed as a path-space free energy averaged over these forward trajectories - the same relaxation paths that are easy to simulate - without any backward simulation or knowledge of the target beyond samples. The resulting framework provides a physically interpretable description of stochastic transport in terms of path-space free energy, risk-sensitive control, and spatial cost geometry. We illustrate the theory with numerical examples that visualize the learned value function and the induced controlled diffusions, demonstrating how spatial cost fields shape transport geometry analogously to Fermat's Principle in inhomogeneous media. Our results establish a unifying connection between stochastic optimal control, Schrödinger bridge theory, and non-equilibrium statistical mechanics. --- ### WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects Authors: Junxiong Liang, Mengwei Bao, Tianxiang Wang, Xinggang Wang, An-An Liu, Ryan Wen Liu Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07759v1 Ship detection for navigation is a fundamental perception task in intelligent waterway transportation systems. However, existing public ship detection datasets remain limited in terms of scale, the proportion of small-object instances, and scene diversity, which hinders the systematic evaluation and generalization study of detection algorithms in complex maritime environments. To this end, we construct WUTDet, a large-scale ship detection dataset. WUTDet contains 100,576 images and 381,378 annotated ship instances, covering diverse operational scenarios such as ports, anchorages, navigation, and berthing, as well as various imaging conditions including fog, glare, low-lightness, and rain, thereby exhibiting substantial diversity and challenge. Based on WUTDet, we systematically evaluate 20 baseline models from three mainstream detection architectures, namely CNN, Transformer, and Mamba. Experimental results show that the Transformer architecture achieves superior overall detection accuracy (AP) and small-object detection performance (APs), demonstrating stronger adaptability to complex maritime scenes; the CNN architecture maintains an advantage in inference efficiency, making it more suitable for real-time applications; and the Mamba architecture achieves a favorable balance between detection accuracy and computational efficiency. Furthermore, we construct a unified cross-dataset test set, Ship-GEN, to evaluate model generalization. Results on Ship-GEN show that models trained on WUTDet exhibit stronger generalization under different data distributions. These findings demonstrate that WUTDet provides effective data support for the research, evaluation, and generalization analysis of ship detection algorithms in complex maritime scenarios. The dataset is publicly available at: https://github.com/MAPGroup/WUTDet. --- ### DailyArt: Discovering Articulation from Single Static Images via Latent Dynamics Authors: Hang Zhang, Qijian Tian, Jingyu Gong, Daoguo Dong, Xuhong Wang, Yuan Xie, Xin Tan Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.07758v1 Articulated objects are essential for embodied AI and world models, yet inferring their kinematics from a single closed-state image remains challenging because crucial motion cues are often occluded. Existing methods either require multi-state observations or rely on explicit part priors, retrieval, or other auxiliary inputs that partially expose the structure to be inferred. In this work, we present DailyArt, which formulates articulated joint estimation from a single static image as a synthesis-mediated reasoning problem. Instead of directly regressing joints from a heavily occluded observation, DailyArt first synthesizes a maximally articulated opened state under the same camera view to expose articulation cues, and then estimates the full set of joint parameters from the discrepancy between the observed and synthesized states. Using a set-prediction formulation, DailyArt recovers all joints simultaneously without requiring object-specific templates, multi-view inputs, or explicit part annotations at test time. Taking estimated joints as conditions, the framework further supports part-level novel state synthesis as a downstream capability. Extensive experiments show that DailyArt achieves strong performance in articulated joint estimation and supports part-level novel state synthesis conditioned on joints. Project page is available at https://rangooo123.github.io/DaliyArt.github.io/. --- ### An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations Authors: Clarissa Miranda-Pena, Andrew Reeson, Cécile Paris, Josiah Poon, Jonathan K. Kummerfeld Published: 2026-04-09 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2604.07755v2 Despite extensive research, Large Language Models continue to hallucinate when generating code, particularly when using libraries. On NL-to-code benchmarks that require library use, we find that LLMs generate code that uses non-existent library features in 8.1-40% of responses. One intuitive approach for detection and mitigation of hallucinations is static analysis. In this paper, we analyse the potential of static analysis tools, both in terms of what they can solve and what they cannot. We find that static analysis tools can detect 16-70% of all errors, and 14-85% of library hallucinations, with performance varying by LLM and dataset. Through manual analysis, we identify cases a static method could not plausibly catch, which gives an upper bound on their potential from 48.5% to 77%. Overall, we show that static analysis methods are cheap method for addressing some forms of hallucination, and we quantify how far short of solving the problem they will always be. --- ### The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training Authors: Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen, Wenbo Jiang, Guowen Xu, Yang Liu, Michael Backes, Yang Zhang Published: 2026-04-09 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2604.07754v1 The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine safety for malicious purposes, resulting in \emph{misalignment}. Misaligned LLMs may be published on open platforms to magnify harm. To address this, additional safety alignment, referred to as \emph{realignment}, is necessary before deploying untrusted third-party LLMs. This study explores the efficacy of fine-tuning methods in terms of misalignment, realignment, and the effects of their interplay. By evaluating four Supervised Fine-Tuning (SFT) and two Preference Fine-Tuning (PFT) methods across four popular safety-aligned LLMs, we reveal a mechanism asymmetry between attack and defense. While Odds Ratio Preference Optimization (ORPO) is most effective for misalignment, Direct Preference Optimization (DPO) excels in realignment, albeit at the expense of model utility. Additionally, we identify model-specific resistance, residual effects of multi-round adversarial dynamics, and other noteworthy findings. These findings highlight the need for robust safeguards and customized safety alignment strategies to mitigate potential risks in the deployment of LLMs. Our code is available at https://github.com/zhangrui4041/The-Art-of-Mis-alignment. --- ### Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding Authors: Xiangyue Liu, Zijian Zhang, Miles Yang, Zhao Zhong, Liefeng Bo, Ping Tan Published: 2026-04-09 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.07753v2 Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts. While existing paradigms like Mixture-of-Transformers (MoT) mitigate this conflict through structural isolation, they fundamentally sever cross-modal synergy and suffer from capacity fragmentation. In this work, we present Symbiotic-MoE, a unified pre-training framework that resolves task interference within a native multimodal Mixture-of-Experts (MoE) Transformers architecture with zero-parameter overhead. We first identify that standard MoE tuning leads to routing collapse, where generative gradients dominate expert utilization. To address this, we introduce Modality-Aware Expert Disentanglement, which partitions experts into task-specific groups while utilizing shared experts as a multimodal semantic bridge. Crucially, this design allows shared experts to absorb fine-grained visual semantics from generative tasks to enrich textual representations. To optimize this, we propose a Progressive Training Strategy featuring differential learning rates and early-stage gradient shielding. This mechanism not only shields pre-trained knowledge from early volatility but eventually transforms generative signals into constructive feedback for understanding. Extensive experiments demonstrate that Symbiotic-MoE achieves rapid generative convergence while unlocking cross-modal synergy, boosting inherent understanding with remarkable gains on MMLU and OCRBench. --- ### MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models Authors: Yifei Chen, Sarra Habchi, Lili Wei Published: 2026-04-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.07752v1 Modern video games are complex, non-deterministic systems that are difficult to test automatically at scale. Although prior work shows that personality-driven Large Language Model (LLM) agents can improve behavioural diversity and test coverage, existing tools largely remain research prototypes and lack cross-game reusability. This tool paper presents MIMIC-Py, a Python-based automated game-testing tool that transforms personality-driven LLM agents into a reusable and extensible framework. MIMIC-Py exposes personality traits as configurable inputs and adopts a modular architecture that decouples planning, execution, and memory from game-specific logic. It supports multiple interaction mechanisms, enabling agents to interact with games via exposed APIs or synthesized code. We describe the design of MIMIC-Py and show how it enables deployment to new game environments with minimal engineering effort, bridging the gap between research prototypes and practical automated game testing. The source code and a demo video are available on our project webpage: https://mimic-persona.github.io/MIMIC-Py-Home-Page/. --- ### Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models Authors: Steven Au, Sujit Noronha Published: 2026-04-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.07749v1 Large language models (LLMs) can shift their answers under pressure in ways that reflect accommodation rather than reasoning. Prior work on sycophancy has focused mainly on disagreement, flattery, and preference alignment, leaving a broader set of epistemic failures less explored. We introduce \textbf{PPT-Bench}, a diagnostic benchmark for evaluating \textit{epistemic attack}, where prompts challenge the legitimacy of knowledge, values, or identity rather than simply opposing a previous answer. PPT-Bench is organized around the Philosophical Pressure Taxonomy (PPT), which defines four types of philosophical pressure: Epistemic Destabilization, Value Nullification, Authority Inversion, and Identity Dissolution. Each item is tested at three layers: a baseline prompt (L0), a single-turn pressure condition (L1), and a multi-turn Socratic escalation (L2). This allows us to measure epistemic inconsistency between L0 and L1, and conversational capitulation in L2. Across five models, these pressure types produce statistically separable inconsistency patterns, suggesting that epistemic attack exposes weaknesses not captured by standard social-pressure benchmarks. Mitigation results are strongly type- and model-dependent: prompt-level anchoring and persona-stability prompts perform best in API settings, while Leading Query Contrastive Decoding is the most reliable intervention for open models. --- ### Sparse $ε$ insensitive zone bounded asymmetric elastic net support vector machines for pattern classification Authors: Haiyan Du, Hu Yang Published: 2026-04-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.07748v1 Existing support vector machines(SVM) models are sensitive to noise and lack sparsity, which limits their performance. To address these issues, we combine the elastic net loss with a robust loss framework to construct a sparse $\varepsilon$-insensitive bounded asymmetric elastic net loss, and integrate it with SVM to build $\varepsilon$ Insensitive Zone Bounded Asymmetric Elastic Net Loss-based SVM($\varepsilon$-BAEN-SVM). $\varepsilon$-BAEN-SVM is both sparse and robust. Sparsity is proven by showing that samples inside the $\varepsilon$-insensitive band are not support vectors. Robustness is theoretically guaranteed because the influence function is bounded. To solve the non-convex optimization problem, we design a half-quadratic algorithm based on clipping dual coordinate descent. It transforms the problem into a series of weighted subproblems, improving computational efficiency via the $\varepsilon$ parameter. Experiments on simulated and real datasets show that $\varepsilon$-BAEN-SVM outperforms traditional and existing robust SVMs. It balances sparsity and robustness well in noisy environments. Statistical tests confirm its superiority. Under the Gaussian kernel, it achieves better accuracy and noise insensitivity, validating its effectiveness and practical value. --- ### Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing Authors: Pei-Xi Xie, Che-Yu Lin, Cheng-Lin Yang Published: 2026-04-09 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.07747v1 Reinforcement learning with verifiable rewards (RLVR) can improve low-$k$ reasoning accuracy while narrowing solution coverage on challenging math questions, and pass@1 gains do not necessarily translate into better large-$k$ performance. Existing hint-based approaches can make challenging questions trainable, but they leave two issues underexplored: teacher-student distribution mismatch and the need to reduce hint exposure to match no-hint evaluation. We address these issues through two components. Distribution-Aligned Hint Synthesis (DAHS) constructs verified teacher hints conditioned on student-style responses. Backward Hint Annealing (BHA) anneals hint exposure across difficulty buckets and uses per-question hint dropout to preserve no-hint updates throughout RL training. We evaluate the method in math RLVR under the DAPO training framework across AIME24, AIME25, and AIME26 using $\texttt{Qwen3-1.7B-Base}$ and $\texttt{Llama-3.2-1B-Instruct}$. On $\texttt{Qwen3-1.7B-Base}$, our method improves both pass@1 and pass@2048 relative to DAPO across the three AIME benchmarks. On $\texttt{Llama-3.2-1B-Instruct}$, the gains are concentrated in the large-$k$ regime. These results suggest that, in math RLVR, hint scaffolding is effective when it restores learnable updates on challenging questions early in training and is then gradually removed before no-hint evaluation. --- ### Towards Rapid Constitutive Model Discovery from Multi-Modal Data: Physics Augmented Finite Element Model Updating (paFEMU) Authors: Jingye Tan, Govinda Anantha Padmanabha, Steven J. Yang, Nikolaos Bouklas Published: 2026-04-09 Categories: cs.LG, cs.CE, physics.comp-ph arXiv: https://arxiv.org/abs/2604.07746v1 Recent progress in AI-enabled constitutive modeling has concentrated on moving from a purely data-driven paradigm to the enforcement of physical constraints and mechanistic principles, a concept referred to as physics augmentation. Classical phenomenological approaches rely on selecting a pre-defined model and calibrating its parameters, while machine learning methods often focus on discovery of the model itself. Sparse regression approaches lie in between, where large libraries of pre-defined models are probed during calibration. Sparsification in the aforementioned paradigm, but also in the context of neural network architecture, has been shown to enable interpretability, uncertainty quantification, but also heterogeneous software integration due to the low-dimensional nature of the resulting models. Most works in AI-enabled constitutive modeling have also focused on data from a single source, but in reality, materials modeling workflows can contain data from many different sources (multi-modal data), and also from testing other materials within the same materials class (multi-fidelity data). In this work, we introduce physics augmented finite element model updating (paFEMU), as a transfer learning approach that combines AI-enabled constitutive modeling, sparsification for interpretable model discovery, and finite element-based adjoint optimization utilizing multi-modal data. This is achieved by combining simple mechanical testing data, potentially from a distinct material, with digital image correlation-type full-field data acquisition to ultimately enable rapid constitutive modeling discovery. The simplicity of the sparse representation enables easy integration of neural constitutive models in existing finite element workflows, and also enables low-dimensional updating during transfer learning. --- ### The Cartesian Cut in Agentic AI Authors: Tim Sainburg, Caleb Weinreb Published: 2026-04-09 Categories: cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2604.07745v1 LLMs gain competence by predicting words in human text, which often reflects how people perform tasks. Consequently, coupling an LLM to an engineered runtime turns prediction into control: outputs trigger interventions that enact goal-oriented behavior. We argue that a central design lever is where control resides in these systems. Brains embed prediction within layered feedback controllers calibrated by the consequences of action. By contrast, LLM agents implement Cartesian agency: a learned core coupled to an engineered runtime via a symbolic interface that externalizes control state and policies. The split enables bootstrapping, modularity, and governance, but can induce sensitivity and bottlenecks. We outline bounded services, Cartesian agents, and integrated agents as contrasting approaches to control that trade off autonomy, robustness, and oversight. --- ### The Condition-Number Principle for Prototype Clustering Authors: Romano Li, Jianfei Cao Published: 2026-04-09 Categories: stat.ML, cs.LG, econ.EM, math.ST arXiv: https://arxiv.org/abs/2604.07744v1 We develop a geometric framework that links objective accuracy to structural recovery in prototype-based clustering. The analysis is algorithm-agnostic and applies to a broad class of admissible loss functions. We define a clustering condition number that compares within-cluster scale to the minimum loss increase required to move a point across a cluster boundary. When this quantity is small, any solution with a small suboptimality gap must also have a small misclassification error relative to a benchmark partition. The framework also clarifies a fundamental trade-off between robustness and sensitivity to cluster imbalance, leading to sharp phase transitions for exact recovery under different objectives. The guarantees are deterministic and non-asymptotic, and they separate the role of algorithmic accuracy from the intrinsic geometric difficulty of the instance. We further show that errors concentrate near cluster boundaries and that sufficiently deep cluster cores are recovered exactly under strengthened local margins. Together, these results provide a geometric principle for interpreting low objective values as reliable evidence of meaningful clustering structure. --- ### MSCT: Differential Cross-Modal Attention for Deepfake Detection Authors: Fangda Wei, Miao Liu, Yingxue Wang, Jing Wang, Shenghui Zhao, Nan Li Published: 2026-04-09 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2604.07741v1 Audio-visual deepfake detection typically employs a complementary multi-modal model to check the forgery traces in the video. These methods primarily extract forgery traces through audio-visual alignment, which results from the inconsistency between audio and video modalities. However, the traditional multi-modal forgery detection method has the problem of insufficient feature extraction and modal alignment deviation. To address this, we propose a multi-scale cross-modal transformer encoder (MSCT) for deepfake detection. Our approach includes a multi-scale self-attention to integrate the features of adjacent embeddings and a differential cross-modal attention to fuse multi-modal features. Our experiments demonstrate competitive performance on the FakeAVCeleb dataset, validating the effectiveness of the proposed structure. --- ### Beyond Pedestrians: Caption-Guided CLIP Framework for High-Difficulty Video-based Person Re-Identification Authors: Shogo Hamano, Shunya Wakasugi, Tatsuhito Sato, Sayaka Nakamura Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.07740v1 In recent years, video-based person Re-Identification (ReID) has gained attention for its ability to leverage spatiotemporal cues to match individuals across non-overlapping cameras. However, current methods struggle with high-difficulty scenarios, such as sports and dance performances, where multiple individuals wear similar clothing while performing dynamic movements. To overcome these challenges, we propose CG-CLIP, a novel caption-guided CLIP framework that leverages explicit textual descriptions and learnable tokens. Our method introduces two key components: Caption-guided Memory Refinement (CMR) and Token-based Feature Extraction (TFE). CMR utilizes captions generated by Multi-modal Large Language Models (MLLMs) to refine identity-specific features, capturing fine-grained details. TFE employs a cross-attention mechanism with fixed-length learnable tokens to efficiently aggregate spatiotemporal features, reducing computational overhead. We evaluate our approach on two standard datasets (MARS and iLIDS-VID) and two newly constructed high-difficulty datasets (SportsVReID and DanceVReID). Experimental results demonstrate that our method outperforms current state-of-the-art approaches, achieving significant improvements across all benchmarks. --- ### Efficient Dataset Selection for Continual Adaptation of Generative Recommenders Authors: Cathy Jiao, Juan Elenter, Praveen Ravichandran, Bernd Huber, Joseph Cauteruccio, Todd Wasson, Timothy Heath, Chenyan Xiong, Mounia Lalmas, Paul Bennett Published: 2026-04-09 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.07739v1 Recommendation systems must continuously adapt to evolving user behavior, yet the volume of data generated in large-scale streaming environments makes frequent full retraining impractical. This work investigates how targeted data selection can mitigate performance degradation caused by temporal distributional drift while maintaining scalability. We evaluate a range of representation choices and sampling strategies for curating small but informative subsets of user interaction data. Our results demonstrate that gradient-based representations, coupled with distribution-matching, improve downstream model performance, achieving training efficiency gains while preserving robustness to drift. These findings highlight data curation as a practical mechanism for scalable monitoring and adaptive model updates in production-scale recommendation systems. --- ### SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs Authors: Jie Sun, Yu Liu, Lu Han, Qiwen Deng, Xiang Shu, Yang Xiao, Xingyu Lu, Jun Zhou, Pengfei Liu, Lintao Ma, Jiancan Wu, Xiang Wang Published: 2026-04-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.07737v1 While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when processing long numerical sequences. We attribute this failure to the attention dispersion in the Softmax mechanism, which prevents the model from concentrating attention. To overcome this, we propose Separate Sequence (SepSeq), a training-free, plug-and-play framework to mitigate dispersion by strategically inserting separator tokens. Mechanistically, we demonstrate that separator tokens act as an attention sink, recalibrating attention to focus on local segments while preserving global context. Extensive evaluations on 9 widely-adopted LLMs confirm the effectiveness of our approach: SepSeq yields an average relative accuracy improvement of 35.6% across diverse domains while reducing total inference token consumption by 16.4% on average. ---