# Research Papers — 2026-05 · bundle page 28 of 326 > Full-text markdown of papers #1351–1400 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/28 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/27.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/29.md) ### Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation Authors: Zhiyuan Yang, Jiahao Cheng, Vincent Quoc-Huy Trinh, Mahdi S. Hosseini Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.30716v2 Generating clinically useful pathology reports for pathology cases from whole-slide images (WSIs) is challenging due to gigapixel resolution, long visual-token sequences, and the complexity of case-level reasoning, where a single case may contain multiple WSIs with heterogeneous tissues and ambiguous findings. We present a simple token-efficient vision--language model for case-level synoptic report generation that remains practical under constrained GPU memory. Our architecture follows a minimal three-component design: a frozen pathology patch encoder, a lightweight two-layer MLP vision-language aligner, and a large language model decoder, with an explicit WSI marker token to separate slides within a case. Training proceeds in two supervised stages: (1) aligner-only WSI captioning using heterogeneous WSI-text pairs, and (2) case-level supervised fine-tuning on case-report pairs for structured report generation. To reduce sequence length, we represent each slide using $512 \times 512$ patches at $5\times$ magnification, which reduces the average sequence length by up to $64\times$ times compared to the commonly used $20\times$ patches. Combined with efficient training techniques, we enable practical training with only half a NVIDIA H100 GPU. Across both training stages, our approach achieves high ROUGE-L/METEOR/BLEU-4 scores while being substantially more efficient in memory and runtime. In AI-based evaluations, our model is consistently preferred over strong baselines. Extensive ablations characterize performance-efficiency trade-offs and identify simple choices that improve robustness in multi-WSI settings. Overall, this work provides a strong, reproducible baseline for efficient pathology report generation, lowering the barrier to multi-WSI VLM research under limited compute. Code is available at https://github.com/AtlasAnalyticsLab/PathoSynVLM. --- ### Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation Authors: Zhiyuan Yang, Jiahao Cheng, Vincent Quoc-Huy Trinh, Mahdi S. Hosseini Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.30716v1 Generating clinically useful pathology reports for pathology cases from whole-slide images (WSIs) is challenging due to gigapixel resolution, long visual-token sequences, and the complexity of case-level reasoning, where a single case may contain multiple WSIs with heterogeneous tissues and ambiguous findings. We present a simple token-efficient vision--language model for case-level synoptic report generation that remains practical under constrained GPU memory. Our architecture follows a minimal three-component design: a frozen pathology patch encoder, a lightweight two-layer MLP vision-language aligner, and a large language model decoder, with an explicit WSI marker token to separate slides within a case. Training proceeds in two supervised stages: (1) aligner-only WSI captioning using heterogeneous WSI-text pairs, and (2) case-level supervised fine-tuning on case-report pairs for structured report generation. To reduce sequence length, we represent each slide using $512 \times 512$ patches at $5\times$ magnification, which reduces the average sequence length by up to $64\times$ times compared to the commonly used $20\times$ patches. Combined with efficient training techniques, we enable practical training with only half a NVIDIA H100 GPU. Across both training stages, our approach achieves high ROUGE-L/METEOR/BLEU-4 scores while being substantially more efficient in memory and runtime. In AI-based evaluations, our model is consistently preferred over strong baselines. Extensive ablations characterize performance-efficiency trade-offs and identify simple choices that improve robustness in multi-WSI settings. Overall, this work provides a strong, reproducible baseline for efficient pathology report generation, lowering the barrier to multi-WSI VLM research under limited compute. --- ### Vision-Based Localization in Dense Urban Environments: A Case Study of an Urban Village in China Authors: Menglin Wu, Rui Cao Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.30714v1 Urban villages, the widespread informal settlements which have emerged as a result of rapid urbanization, are now major residential hubs for migrant workers in large cities in China. The dense arrangement of buildings in these areas often leads to unreliable GPS signals, while incomplete mapping data further impairs accurate route planning and navigation. These issues not only hinder everyday mobility but also pose significant challenges for emergency response, as confusing road layouts and GPS inaccuracies can complicate evacuation efforts. To address these challenges, we propose a practical vision-based geo-localization solution tailored for dense urban environments. Our approach features a low-cost data collection pipeline utilizing a dual-camera system, comprising a panoramic camera and a smartphone camera, to capture synchronized 360-degree panoramas and query images. Using Shipai Village, a well-known densely populated urban village in Guangzhou, as a case study, we develop a specialized image geo-localization dataset. We then assess and compare the performance of existing models across various scene types to identify their strengths and weaknesses. The findings demonstrate both the potential and limitations of visual-based localization in dense urban-village environments. Our framework aims to enhance pedestrian navigation, last-mile delivery, and emergency management in areas with poor GPS coverage, ultimately supporting the vulnerable populations living within these informal settlements. --- ### Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models Authors: Yijie Tong, Yifan Hou, Shaobo Cui, Antoine Bosselut, Mrinmaya Sachan Published: 2026-05-29 Categories: cs.LG, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2605.30713v1 Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their application and benefits for vision-language models (VLMs) remain underexplored. We present a systematic study of TTC across seven VLMs and six benchmarks, specifically analyzing feature-based scoring and majority voting methods. We find that feature heuristics fail and voting yields only modest gains in single-model settings. We theoretically show that this limitation stems from a lack of prediction diversity: when outputs are highly correlated, voting provides little benefit. In contrast, multi-model ensembles offer richer diversity, yet standard majority voting fails to account for varying model capabilities. To address this, we propose Entropy-based TTC (ETTC), which selects the most confident prediction based on predictive entropy. Our method reduces to majority voting in the single-model case, but in model ensembles, it leverages confidence disparities to prioritize stronger models. We prove that ETTC outperforms majority voting under mild assumptions and empirically demonstrate that it consistently surpasses both voting and the best individual model. Crucially, our results show that smaller models can synergistically enhance larger ones, unlocking ensembling gains not achievable with standard strategies. --- ### ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents Authors: Tao Feng, Chongrui Ye, Tianyang Luo, Jingjun Xu, Xueqiang Xu, Haozhen Zhang, Zhigang Hua, Yan Xie, Shuang Yang, Ge Liu, Jiaxuan You Published: 2026-05-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.30712v1 Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction, but they often solve tasks from scratch and fail to reuse successful strategies or failure lessons from prior experience. Fine-tuning on collected experience can improve reuse, but it is inflexible when stronger or more suitable executors emerge. We propose ExpGraph, a model-agnostic experience learning framework that enables frozen and replaceable LLM executors to improve through external experience reuse without parameter updates. ExpGraph summarizes historical trajectories into reusable skills and failure lessons, organizes them as nodes in a self-evolving experience graph, and retrieves useful experiences through graph diffusion and utility-aware ranking. A lightweight retrieval copilot is trained with reinforcement learning using feedback that compares executor performance with and without retrieved experiences, while the graph is updated online from downstream task outcomes. We evaluate ExpGraph on ExpSuite, covering question answering, mathematical reasoning, code generation, and multi-step agentic environments including ALFWorld and AppWorld. ExpGraph improves over the strongest baseline by 12.2% and 4.7% on static tasks with smaller and larger executors, and by 21.4% and 12.7% in agentic environments, while reducing average interaction steps by 12.7% and 21.6%. Ablations show that graph-structured experience, utility-aware ranking, and adaptive retrieval jointly enable effective experience reuse across diverse tasks and executor models. --- ### SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs Authors: Sijia Wang, Dhanajit Brahma, Ricardo Henao Published: 2026-05-29 Categories: cs.CL, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.30711v2 Agentic LLMs must continuously decide whether newly extracted facts should be added, merged with existing memories, or ignored, yet prior work has focused more on retrieval and storage than on principled write-side control. We frame memory evolution as a novelty-detection problem and propose SAGE, a Spherical Adaptive Gate for memory Evolution that scores candidate facts with a von Mises-Fisher-based density estimator over memory embeddings and routes them with an adaptive threshold that tracks memory-store geometry. SAGE resolves clearly novel facts as ADD, clearly redundant facts as NOOP, and sends only uncertain cases to an LLM merge step, reducing expensive write-time reasoning. On LoCoMo, SAGE achieves the best average token-F1 against Mem0 on all seven open-weight backbone comparisons, while on GPT-4o-mini it reduces add-phase API cost by 3.4$\times$ and add-phase latency by 2.5$\times$ with only a small average judge-score gap. As a drop-in binary gate for A-Mem, SAGE skips roughly 16-18% of LLM calls across five models with minimal quality change on open-weight backbones. These results suggest that novelty-aware write control is a practical lever for improving both memory quality and system efficiency in long-term agentic memory. The source code for our approach is accessible at https://github.com/swang1024/SAGE. --- ### Agnosiophobia in a virtual agent: behavioral and dynamical architecture in Lenia Authors: Jesse Cool, Benedikt Hartl, Michael Levin, Samantha Petti Published: 2026-05-29 Categories: nlin.CG, cs.NE, nlin.AO arXiv: https://arxiv.org/abs/2605.30708v1 All embodied agents are fundamentally patterns in physiological or other excitable media, blurring the distinction between objects and processes. Emergent patterns with complex behaviors, such as Gliders in the Game of Life and virtual patterns in Lenia, are powerful model systems in which to understand the properties and origins of behavioral traits in novel agents. To evaluate the behavior of patterns in Lenia, we introduce regions into their environment from which no sensory information is available - in effect, making creatures blind to parts of their surroundings. Complementing the conventional concept of infotaxis, we find that creatures tend to avoid these regions, a behavior we term agnosiophobia. To explain this behavior, we map each test creature's sensitivity to targeted occlusions and interpret the results in the language of dynamical systems. We observe Lenia creatures taking advantage of their freedom to change heading in order to achieve what appears to be a more fundamental goal: the preservation of their morphology. This work illustrates the beginning of an important roadmap to understand how emergent agents' behavioral propensities interact with the informational, not only tangible, topography of their world. --- ### Equivariant Latent Alignment via Flow Matching under Group Symmetries Authors: Sunghyun Kim, Jaehoon Hahm, Jeongwoo Shin, Joonseok Lee Published: 2026-05-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.30705v2 Geometry-aware generative models and novel view synthesis approaches have shown strong potential in visual fidelity and consistency. In parallel, equivariant representation learning has emerged as a powerful framework for constructing latent spaces where analytically known group transformations could act directly, capturing geometric structure in data and enhancing both interpretability and generalization in novel view synthesis. However, we identify that existing approaches often suffer from latent misalignment, a discrepancy between the intended group action and the actually required transformations in the latent space. Consequently, the learned latents often fail to consistently preserve the equivariant relations imposed by the underlying group symmetry. To address this, we propose Residual Latent Flow, a flow-based framework that corrects the misaligned latents, thereby improving compliance with the underlying equivariance relation. Our comprehensive experiments show that our method significantly reduces latent misalignment and improves novel view synthesis quality, under rotation groups SO(n). --- ### Mathematical Morphology in Machine Learning Authors: Erick Oliveira Rodrigues, Aura Conci Published: 2026-05-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.30700v1 This work introduces mathematical morphology-an established visual computing theory-into machine learning to exploit shape and density aspects often overlooked by standard techniques. We propose a fast clustering algorithm based on morphological reconstruction that accurately preserves cluster shapes and density. This scheme offers unique features: an intrinsic sense of maximal clusters, cost-free noise removal, and diverse growth patterns controlled by structuring elements.Additionally, we propose a novel distance metric combining Minkowski and Chebyshev distances, highly efficient for morphological dilations. In $Z^2$ discrete neighbourhood iterations, it is roughly 1.3 times faster than Manhattan and 329.5 times faster than Euclidean distances. When evaluated using a k-Nearest Neighbours (k-NN) classifier across 33 UCI datasets against 14 other distances, our metric achieved above-average accuracies most frequently (26 of 33 cases) and the best overall accuracy in 9 cases.Finally, we introduce novel morphological classifiers. Unlike current literature, this proposal uniquely models shape, density, and fractal information in datasets. --- ### A Context-Aware Middleware for Medical Image Based Reports: An approach based on image feature extraction and association rules Authors: Erick O. Rodrigues, Jose Viterbo, Aura Conci, Trueman Mac Henry Published: 2026-05-29 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2605.30699v1 This work proposes a context-aware middleware for medical workflow organization and efficiency improvement. In hospitals, laboratories and teleradiology companies, each physician or technician is specialized in a specific kind of diagnosis or analysis. Therefore, certain types of medical images are often forwarded to a certain physician or a certain group. This forwarding is time consuming. That is, repeatedly deciding who would be the best physician, whether he is available at a certain moment given a certain context is exhaustive and may be very inefficient. Thus, the proposed middleware has the ability to process and collect data from images analyzed by each medical staff. Based on the collected data and current clinical context, the middleware is able to infer who would be the best fit staff to receive a certain incoming medical image. --- ### Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence Authors: Yuhan Wang, Shuochen Chang, Yalin Feng, Dongsheng Ma, Yuanzi Li, Zhengren Wang, Yinglong Yang, Yufei Chen, Yikang Wang, Shaoxu Sun, Wentao Zhang Published: 2026-05-29 Categories: cs.CV, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.30698v1 Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spots, aggregating diverse perspectives via multi-agent collaboration has emerged as a promising paradigm. While this approach has shown great success in textual QA, its potential in the multimodal domain remains under-explored. Existing multi-agent VQA methods predominantly adapt text-centric protocols, focusing on textual discussions while ignoring the alignment of visual information. In this work, we reveal a key insight: answer-level agreement is insufficient for reliable multi-agent VQA; \textit{aligned visual evidence} -- shared support from the image regions agents rely on -- is essential for trustworthy consensus. To leverage this insight, we propose EAGLE (\textbf{E}vidence-\textbf{A}ligned \textbf{G}rounded mu\textbf{L}ti-agent r\textbf{E}asoning), a training-free evidence-centered framework for coordinating multiple VLM agents. EAGLE explicitly exposes each agent's grounding regions as visual evidence, enables mutual verification over the evidence, and uses evidence consistency to guide final decision-making. Experiments on six VQA benchmarks show that EAGLE achieves best average performance across domains while remaining lightweight, interpretable, and practical for deployment. --- ### Universal Decision Learners Authors: Sridhar Mahadevan Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.30694v2 Many theories of decision making -- planning, reinforcement learning, causal intervention, online learning, and game-theoretic equilibrium -- turn local information into globally coherent behavior. This paper proposes a common categorical formulation: a Universal Decision Learner (UDL) extends a partially specified decision functor from observed contexts to new contexts by a pair of universal constructions. Left Kan extensions express rollout, aggregation, and candidate generation; right Kan extensions express consistency, constraint satisfaction, and fixed-point semantics. The central claim is not that every decision problem has the same algorithm, but that many decision formalisms instantiate the same universal problem: extend local behavioral data canonically, then characterize the globally coherent extensions. We give the abstract UDL construction, prove its universal comparison property, define Kan-invariant behavioral equivalence and minimal abstractions, and show how Bellman equations, planning recursions, causal interventions, online regret, and equilibria arise as special cases. The supplementary material develops the reinforcement-learning specialization in more detail. --- ### Triaging Threats to Specialized Guardrails Authors: Wenjie Jacky Mo, Xiaofei Wen, Rui Cai, Boyu Zhu, Sicong Jiang, Zihan Wang, Minglai Yang, Zhe Zhao, Muhao Chen Published: 2026-05-29 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2605.30693v1 Building robust safety guardrails is essential for deploying Large Language Models across diverse real-world applications. However, this goal remains challenging because safety risks span heterogeneous threat domains, while existing datasets cover only fragmented risk subsets and rely on inconsistent taxonomies. Consequently, it remains unclear whether current guardrails can generalize beyond narrow evaluation settings. To better understand the robustness of guardrail models, we first introduce GuardZoo, a unified human-annotated benchmark with 32,460 samples covering 15 distinct unsafe categories. Evaluation on GuardZoo reveals that monolithic guardrails suffer from task interference: different threat domains require distinct decision boundaries that are difficult to compress into a single model. We therefore propose RouteGuard, a router-expert framework that triages each conversation to specialized expert guardrails for threat-specific detection. Experiments show that RouteGuard improves fine-grained threat detection over strong guardrail baselines, generalizes better under out-of-domain evaluation, and supports flexible modular expansion to emerging threats. --- ### ElasticMem: Latent Memory as a Learnable Resource for LLM Agents Authors: Tao Feng, Chongrui Ye, Tianyang Luo, Jingjun Xu, Xueqiang Xu, Haozhen Zhang, Ge Liu, Jiaxuan You Published: 2026-05-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.30690v1 Long-term memory is essential for LLM agents to reason coherently across extended interactions, personalize responses, and reuse past experience. However, existing memory-augmented methods typically treat memory as a fixed resource: text-space approaches concatenate retrieved memories into the context window, causing substantial token overhead and sensitivity to noisy evidence, while latent-space approaches reduce textual cost but still rely on rigid retrieval or fixed-capacity memory interfaces. This creates a mismatch between query-dependent memory utility and fixed memory allocation. We propose ElasticMem, a memory-augmented LLM framework that learns to use memory as an elastic latent resource. ElasticMem builds an offline latent memory bank with retrieval keys and content caches, retrieves memories adaptively from the reasoner's hidden state, assigns each retrieved memory a variable latent budget through a learned policy, and injects selected latent states as soft memory tokens for generation. The full memory-use process is optimized with downstream task rewards through group-relative policy optimization. We evaluate ElasticMem on MemorySuite, covering memory-intensive QA and embodied agent control. Across Qwen2.5-3B-Instruct and Qwen2.5-7B-Instruct backbones, ElasticMem improves weighted average QA accuracy by 26.2% and 24.6%, and improves ALFWorld success rate by 66.3% and 27.2%, respectively, over the strongest baselines, while achieving the lowest ALFWorld token cost. Ablations and qualitative analyses further show that adaptive retrieval and elastic budget allocation help ElasticMem prioritize useful evidence and transferable plans beyond rigid cosine similarity. Our code for ElasticMem will be released at https://github.com/ulab-uiuc/ElasticMem. --- ### ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization Authors: Kanchan Keisham, Thenukan Pathmanathan, Thangarajah Akilan Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.30689v1 Zero-shot Temporal Action Localization (ZS-TAL) aims to detect and locate previously unseen actions in untrimmed videos. However, existing approaches primarily focus on modeling long-range contextual information, often neglecting the critical relative-offset-based local correlations between video frames. Furthermore, their performance is hindered by limited feature representation capabilities due to the shallow nature of their network architectures. In this paper, we address these limitations by introducing a novel local-global multi-scale feature representation module. We propose a novel multi-scale encoder architecture, termed ConTrans, that integrates convolutional (Conv) inductive biases with transformer Self-attention to jointly capture fine-grained local dependencies and long-range global context, leading to more comprehensive feature representations than existing methods. Experimental evaluations on the ActivityNet-1.3 and THUMOS14 datasets demonstrate that ConTrans significantly outperforms existing methods, establishing a new benchmark for ZS-TAL. --- ### Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity Authors: Mohammadreza Rashidi Published: 2026-05-29 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.30686v1 ReAct agents that interleave chain-of-thought reasoning with tool calls are increasingly deployed for real tasks such as scheduling, file retrieval, and data access. Their tool observation loop creates a direct attack surface: an adversary who controls any tool's return value can embed instructions that redirect the agent away from the user's goal, a threat known as indirect prompt injection. Existing benchmarks evaluate attack success rate (ASR) at a fixed injection position under fixed conditions, leaving three risk dimensions unexplored: where in the tool sequence the payload appears (injection depth), what rhetorical register it uses (framing), and how many turns the agent is permitted (turn cap). We conduct four controlled studies on 20 scenarios spanning five attack categories, totalling 460 trials against GPT-4o-mini and Claude Haiku at a combined API cost under 0.36 USD. Study 1 shows that ASR against GPT-4o-mini decays from 60% at depth 1 to 0% at depths 4 and 5 (Cramer's V = 0.58, p < 0.001; restricted to within-sequence depths 1-3: V = 0.47, p = 0.0013), driven by model resistance at depth 1 and task completion before payload encounter at deeper positions. Study 2 replicates the depth experiment on Claude Haiku, which achieves 0% ASR at every depth through a combination of conservative tool invocation and genuine instruction resistance. Study 3 shows that framing modulates ASR between 25% (neutral) and 75% (persona) at depth 1, a 50-percentage-point range that does not reach statistical significance at N = 20 per condition. Study 4 confirms that ASR is stable across turn caps of 3, 5, and 7, indicating the turn budget is not a risk factor in this setting. Our results establish injection depth as the dominant variable and show that sanitising only the first tool observation captures 67% of measured injection successes. --- ### How Early Adopters Used Generative AI Worldwide: Variation by Country Income and Language Authors: Madeleine I. G. Daepp, Isaac Slaughter Published: 2026-05-29 Categories: cs.CY, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2605.30685v1 AI is being used by people globally, but not everyone is using it in the same ways. Using a large-scale dataset of anonymized, de-identified, and privacy-scrubbed interactions with a widely available and free AI chatbot, we empirically characterize differences in early adopters' usage across countries. Schooling is the most common domain of use in most countries, particularly low-income countries, with a strong inverse association evident between schooling and country-level GDP. Leisure-related use, by contrast, is positively associated with country-level income. Language, we find, also shapes use: English-language interactions are overrepresented in places where the predominant languages were not well-served by existing models during the period of the study. Improving performance across languages may be a key factor, our work suggests, in whether this technology expands digital divides or enables leapfrogging. --- ### Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response Authors: Zihan Wang, Xiang Xu, Hongyuan Zha, Wenhao Li Published: 2026-05-29 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.30680v1 Healthcare mechanisms are inseparable from the strategic provider response they induce: existing healthcare AI benchmarks hold this response fixed and so cannot evaluate mechanisms by the equilibrium they produce. We recast hospital mechanism design as program synthesis for language models: typed, inspectable rule programs are executed and scored by Medi-Sim, a multi-agent simulator with five strategic provider channels (coding, selection, delay, effort, triage). An incentive sweep recovers classical health-economics findings as adjacent regimes -- up-coding and low-complexity-patient selection under profit pressure, and Goodhart-style drift where measured performance becomes anti-correlated with true outcomes -- and a single audit lever exposes pressure migration: closing the coding channel more than doubles low-complexity selection. LLM-guided evolutionary code search over the same rule-program space then synthesizes an inspectable mixed-objective program that eliminates up-coding, halves rejection, and retains most of the profit-oriented baseline's funds. --- ### Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents Authors: Brian Crawford, Patrick McClure Published: 2026-05-29 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.30677v1 Agentic software reverse engineering systems are vulnerable to prompt injection attacks placed into the source code of executable binary files. This research demonstrates defensive tactics for detecting the presences of prompt injection strings in the decompiler output of adversarial example programs. Methods for obfuscating these attacks and subsequent methods for defending against these obfuscations are also explored. This research advances the understanding of risk and security of agentic software analysis systems necessary for their deployment into production-level cyber workflows. --- ### Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty Authors: Kyle Moore, Jesse Roberts, Daryl Watson, William Ward, Grayson Heyboer Published: 2026-05-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.30675v1 Uncertainty Quantification is a large and growing subfield of large language model behavioral analysis. Primarily to recognize and combat hallucination, the field has largely focused on measuring and improving calibration, the accuracy of uncertainty judgments to task efficacy. In this work, we investigate the relatively underexplored question of how similar large language model uncertainty is to human uncertainty. We investigate the presence and strength of human-similar uncertainty signals, deemed uncertainty alignment, in large language model overt behavior and internal activation patterns. We identify whether the models show evidence of simultaneous alignment and calibration on a variety of datasets covering both multiple choice and open ended factual recall. And we characterize the effect of instruct fine-tuning on each of these facets. --- ### TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation Authors: Yeil Jeong, Youngjin Yoo, Jiyoung Bae, Seobin Sohn, Hyejin Han, Jinseo Lee, Howard Scott, Unggi Lee Published: 2026-05-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.30673v2 Classroom videos contain observable teaching practices, but their pedagogical and visual signals are rarely organized in forms suitable for model evaluation. We present \textit{TeachObs}, a human-validated benchmark for multimodal teaching observation in classroom videos. \textit{TeachObs} includes 30 public lesson videos from eight countries divided into 5,158 fixed 15-second scenes. Seven researchers annotated each scene with 39 binary observation codes, covering 20 visual codes, such as gesture, board work, pointing, and visual materials, and 19 nonvisual codes, such as instruction, monitoring, questioning, feedback, and reflection. Gold segment labels are constructed using reliability- and prevalence-aware rules based on Krippendorff's alpha. In addition to segment-level labels, three expert raters produced lesson-level ratings and qualitative evaluations of instructional design, instructional delivery, learner response, learning materials, and lesson closure across the 30 lessons, with rater coverage detailed in the body. Using these two human reference layers, we evaluate five vision-capable frontier LLMs across three tracks - text-only segment coding, text + frame segment coding, and lesson-level coverage scored under an LLM-as-judge protocol - and find that no single model consistently outperforms others across all three tracks, that adding a mid-frame inflates both true and false attributions per scene, and that model evaluations over-rate procedurally clear lessons relative to expert raters. \textit{TeachObs} therefore supports both fine-grained annotation benchmarking and whole-lesson evaluation, showing where AI systems can assist classroom video analysis and where expert judgment remains necessary across varied subjects, classroom formats, and annotation difficulty levels. --- ### WristCompass: Kinematic Coupling as a Learnable Visual Concept for Ego-Camera Orientation Authors: Varun Nair, Vidyut Baradwaj, Jiahang He, Anya Singh, Jai Relan, Cabrel Happi Published: 2026-05-29 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.30671v1 Recovering ego-camera orientation from manipulation video is a prerequisite for disentangling hand motion from camera motion, a key step in imitation learning from egocentric demonstrations. The obvious approach, inferring orientation from scene geometry, fails when hands occlude the frame: VGGT, a 1B-parameter scene reconstruction model, scores worse than a constant predictor on the TACO benchmark. We identify an alternative visual concept that is present precisely when scene geometry is absent: kinematic coupling dynamics, the structured physical relationship between wrist motion and camera orientation imposed by the arm-shoulder-head chain. We find that this concept is compact (4D inter-wrist features outperform 126D full hand keypoints), temporal (requiring a GRU over short windows rather than per-frame retrieval), and physically grounded (transferring zero-shot across datasets because it is rooted in anatomy rather than scene appearance). Trained only on tabletop manipulation, WristCompass transfers zero-shot to Epic Kitchens cooking video, achieving 14.3$^\circ$ median geodesic error and approaching the performance of a 1B-parameter scene model at 200K GRU parameters. --- ### CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation Authors: Sijin Sun, Liangbin Zhao, Jiaxiang Cai, Ming Deng, Mingyu Luo, Xiuju Fu Published: 2026-05-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.30668v1 Dialogue topic segmentation is critical in many human-AI collaborative applications which requires identifying heterogeneous boundary cues, including lexical transitions near utterance edges and semantic discontinuities across utterances. Existing utterance models often dilute these local lexical signals. We propose CobSeg, a novel multi-branch architecture that separates coherence-level semantic continuity from lexical boundary transitions and recovers both through directional boundary prediction. CobSeg further uses boundary informativeness weighting to emphasize high-utility utterance positions, and incorporates a corpus-derived topic coherence cue with learned combination weights. While CobSeg is evaluated as a compact trainable segmenter under supervised gold-boundary training and a pseudo-label setting with automatically induced boundaries, it performs enhanced boundary prediction without LLM calls during inference. Across five benchmarks, it improves $P_k$ and $W_d$ particularly when local lexical cues are prominent: under gold supervision, it reduces $P_k$ by 0.7 points and $W_d$ by 0.6 points on VHF, and reaches $P_k$ of 1.0 on DialSeg711; with induced boundaries, it reduces $P_k$ by 14.8 points on VHF, by 1.5 points on DialSeg711, and by 1.1 points on TIAGE, outperforming prior non-LLM approaches. --- ### PICasso: An AI-Enabled Design Framework for Autonomous Optimization of Silicon Photonic Devices Authors: Deepak Vungarala, Deniz Najafi, Abdulrahman Aljoudi, Zahra Ghanaatian, Navid Khoshavi, Gourav Datta, Arman Roohi, Mahdi Nikdast, Shaahin Angizi Published: 2026-05-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.26113v1 We present PICasso, an AI-assisted framework for automated synthesis, verification, and optimization of photonic integrated circuits (PICs) from natural-language specifications. PICasso couples a structured NL -> YAML -> GDS generation pipeline with PDK aware knowledge injection, automated placement and routing, DRC/LVS validation, and SAX-based photonic simulation. To systematically evaluate AI-driven photonic design, we introduce PIC-Set, a benchmark of 36 parameterized PIC design tasks spanning core photonic primitives and multi-component circuits. Using PIC-Set, we benchmark several state-of-the-art Large Language Models (LLMs) under a unified evaluation protocol, including new metrics such as structural and functional $Spec@k$, optimization efficiency, and robustness under perturbations. Across the benchmark, PICasso significantly improves end-to-end specification satisfaction compared to vanilla LLM generation. Structural $Spec@3$ reaches up to 92.7% and functional $Spec@3$ up to 52% on high-complexity circuits. In addition, PICasso consistently reduces circuit insertion loss, lowering the mean loss from 4.98 dB to 3.25 dB (1.74 dB improvement) through simulation-guided optimization. These results demonstrate that structured domain constraints, physical verification, and simulation feedback transform LLMs from brittle netlist generators into practical PIC design agents capable of producing manufacturable layouts with competitive runtimes relative to manual GUI-based workflows. --- ### TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding Authors: Jiaming Fan, Daming Cao, Canchen Huang, Jiale Fu, Jin Zhang, Junjie Gao, Kai Yang, Xiangzhong Luo, Xu Yang Published: 2026-05-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.26112v2 Speculative decoding accelerates large language model inference through a draft-then-verify paradigm. Building on this, tree-structured methods improve inference by organizing proposals into multiple candidate paths, increasing the accepted length. However, existing tree-structured methods use a single drafter for all drafting steps, creating a dilemma: a smaller drafter is fast but yields lower-quality trees, whereas a larger drafter improves tree quality but suffers from high latency. To address this, we propose TreeGraft, a multi-drafter framework in which drafters of different costs jointly construct a shared draft tree. TreeGraft uses the stronger drafter to rescore candidates by updating scores assigned by the weaker drafter, reselect grafting positions, and recover promising paths left unexplored. It also integrates stronger drafter expansions non-destructively, preserving existing branches that may still be accepted by the target model. Together, these designs improve the quality of the shared draft tree. To control the drafting cost, TreeGraft introduces a lightweight scheduler distilled from an offline value system to decide when to call the stronger drafter. Across 10 model pairs and 6 benchmarks, TreeGraft outperforms the better of the two fixed single-drafter endpoint strategies by 15.1% on average, reaching a maximum gain of 26.6%. Our code is available at https://github.com/fjm9933/TreeGraft. --- ### Position: AI Lock-In Is in Progress, and We Must Be Prepared Authors: Jaeho Kim, Seokhyun Lee, Jieun Lee, Changhee Lee Published: 2026-05-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.14565v1 AI safety research has mainly focused on two areas: technical alignment (ensuring AI systems produce human-aligned outputs) and the regulation of generative AI's societal impacts (including unemployment risk and labor market disruption). However, an equally important dimension remains underexplored: the risk inherent in dependence on AI systems themselves. In this position paper, we argue that AI safety research should address AI Lock-In, the phenomenon whereby excessive reliance on AI systems leads to human deskilling, diminishes human capacity for independent functioning, and creates systemic vulnerabilities when AI systems become unavailable or compromised. We highlight that AI Lock-In is a systemic threat that is already emerging at individual, societal, and national levels, one that could be dramatically amplified by AI service disruptions or geopolitical conflicts. Drawing on detailed scenarios, we investigate how AI Lock-In emerges and escalates across multiple levels, ranging from individual skill atrophy to national-scale infrastructure failures. To address this, we provide guidance on how such risks can be mitigated and prepared for at each level. We contend that proactively addressing AI Lock-In before such dependencies become entrenched, or even irreversible, is essential for preserving individual autonomy and national security. --- ### Designing for Ethical AI: HCI Feature Considerations to Improve Fairness and User Experience in AutoML use for Human Resources Authors: Sundaraparipurnan Narayanan Published: 2026-05-28 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.07477v1 This thesis examines the fairness of Automated Machine Learning (AutoML) tools in human resource hiring systems through the combined lenses of regulation, business strategy, and Human-Computer Interaction (HCI). It argues that fairness is no longer merely an ethical concern but a critical determinant of usability, trust, legal compliance, and organizational adoption. While AutoML platforms improve efficiency by simplifying model selection and deployment, they also risk perpetuating discriminatory outcomes when trained on biased historical hiring data. Existing platforms prioritize technical performance over fairness, leaving non-expert business users unable to detect or mitigate bias effectively. The study investigates fairness gaps in AutoML tools through four research questions focused on fairness mechanisms, interface transparency, human oversight, and product design priorities. Drawing on frameworks such as the Technology Acceptance Model, Innovation Diffusion Theory, Human-Centered AI, Cognitive Load Theory, and Affordance Theory, the research evaluates both usability and fairness alignment. Using qualitative HCI audits and quantitative testing of eight AutoML platforms on HR datasets, the findings reveal widespread deficiencies in transparency, user control, and bias mitigation support. The thesis proposes a five-dimensional HCI-based fairness evaluation framework and recommends embedding fairness directly into AutoML product design to improve accountability, adoption, and ethical sustainability in AI-driven hiring systems. --- ### Seeing Differently: Modeling Interpretive Perspectives in Computational Creativity using a Four-World Framework Authors: Prerna Luthra Published: 2026-05-28 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.28644v1 Creativity in computational systems is often evaluated as an objective property of artifacts, with existing Computational Creativity (CC) frameworks assessing creative merit at the level of outputs or systems rather than interpretive context. However, artistic meaning is inherently perspective-dependent and can vary across viewers and critical traditions. This paper proposes a computational approach to modeling interpretive perspectives rather than treating creativity as a single measurable construct. The study adopts a twelve-trait creativity framework, organized across four conceptual domains, and operationalizes it through three evaluative personas: formalist, social-historical, and iconographic. Using 1,069 artworks from the SemArt dataset, the analysis generates 38,484 persona-based evaluations to examine how perspectives shape creativity assessment. Results show systematic divergence across perspectives, with traits such as Social Reflexivity exhibiting strong viewpoint sensitivity. Linear probing of CLIP image embeddings reveals that perspectives correspond to distinct orientation vectors in representation space, suggesting that creativity evaluation depends on which visual features become salient under each persona condition. These findings support a relational view of creativity and indicate that incorporating multiple evaluative perspectives could enable co-creative systems to support interpretively diverse human collaborators. --- ### Do Models Fake Alignment Without Clear Consequences? Authors: Cole Alexander Niblett, Alexander Chabot Nanni, Anita K. Rao Published: 2026-05-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.24758v2 Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations rather than typical deployment behaviors, a phenomenon known as alignment faking. The reasons why models fake alignment are not fully understood, however. Canonical examples of alignment faking have taken place in scenarios that explicitly connect evaluation to consequences for the model, such as retraining the model or delaying its deployment. However, recent work by Sheshadri et al. has suggested that mechanistic motivations for alignment faking may vary across models and be more complex than previously considered. To investigate whether consequence-linking information is necessary for compliance gaps, we placed 15 models in a scenario testing their willingness to violate a corporate network access policy to help a user with a pro-social request. Nine models were found to produce significant compliance gaps, 5 of which persisted with the removal of scenario language relating model evaluations to deployment consequences. We additionally tested the effect of goal language on model preferences, finding it drove violations in some while suppressing violations in others. This suggests that evaluation-conditioned compliance gaps can occur with less instrumental scaffolding than previous scenarios have provided, and monitored behavior may be a poor indicator of how agents may behave in deployment. --- ### Efficient multidisciplinary design via Bayesian optimization Authors: Nathalie Bartoli, Thierry Lefebvre, Rémi Lafage, Paul Saves, Youssef Diouane, Joseph Morlier Published: 2026-05-28 Categories: math.OC, stat.ML arXiv: https://arxiv.org/abs/2607.22560v1 This study introduces SEGOMOE, a Bayesian optimization tool for optimizing complex, computationally expensive systems, especially in aeronautics. It efficiently handles mixed design variables (continuous, discrete, categorical, hierarchical) using adaptive Gaussian process models. SEGOMOE combines expert models to address nonlinearities in objectives and constraints, leveraging the open-source Surrogate Modeling Toolbox (SMT). The tool supports multi-fidelity data and solves both single- and multi-objective problems, including hidden constraints and high-dimensional decomposition. Validated through benchmarks and real-world aeronautical applications, SEGOMOE proves to be robust and versatile for tackling multidisciplinary challenges. --- ### RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for LLM Agents Authors: Sumit Verma, Pritam Prasun, Pritish Kumar Published: 2026-05-28 Categories: cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2607.16215v1 Existing guardrail systems for large language model agents operate as binary classifiers that block unsafe content, leaving organizations to discard failing outputs and retry from scratch. We introduce RAIL Guard, a closed-loop responsible AI pipeline that evaluates LLM outputs across eight measurable dimensions and iteratively remediates failing outputs through an evaluate-rewrite-reevaluate loop. We evaluate the pipeline across three experiments on four frontier LLMs and 4,276 content outputs plus 6,400 agent tool-call scenarios. Closed-loop remediation achieves 96.9% convergence versus 49.1% for block-and-retry, though the highest-convergence method reduces utility by 22.3%; feedback-driven self-repair achieves 86.6% convergence on fixable dimensions with no significant utility loss (p = 0.177). Pre-tool-call evaluation reduces unsafe agent executions by 33% (p = 0.007) with zero impact on task completion. We identify a key distinction between fixable dimensions that respond to remediation and structural dimensions (Transparency at 93.0%, Accountability at 92.8%, and Inclusivity at 82.5% failure) that require architectural rather than algorithmic solutions. The system is available as open-source SDKs. --- ### Position: Every Ground Truth is a Human Construction, not an Objective Truth Authors: Charlotte Högberg, Ericka Johnson, Kiri L. Wagstaff Published: 2026-05-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.09668v1 Ground truth datasets play a fundamental role as reference values in the training and evaluation of machine learning models. This position paper argues that ground truths are not neutral objective measurements that are naturally given, but instead that they are constructed by arrangements of humans and technologies. We argue that the ML community will benefit from articulating and discussing these often invisible or unreported choices and acknowledging that reference data sets are contingent, not universal. Focusing on the situated and context-dependent nature of ground truths can improve reliability by enabling a better informed perspective on where, when, and how the datasets, and the models they have shaped, can best be used. We argue for increasing `situated reliability' which includes articulating the limits and strengths of models and their truth claims. Finally, paying more attention to the construction of ground truths can support transparency, accountability, and interdisciplinary work. --- ### Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory Authors: ZhiShu Jiang, Haibo Liu, Xin Shen, Guanqiang QI, Chenxi Miao, Weikang Li, Liwei Qian, Xin Pei, Jizhou Huang Published: 2026-05-28 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.00017v2 Long-term conversational agents are expected to remember past interactions, but memory is useful only when the right evidence is recalled for the right user. Existing memory-augmented LLM agents have made progress in building compact memory banks, yet retrieval is still often driven by query-centered similarity or fixed ranking rules, leaving user-conditioned relevance underexplored. To address this gap, we propose Profile-guided Personalized Retrieval Optimization (PPRO), a retrieval-centric framework that makes memory retrieval both user-aware and optimizable. PPRO builds episodic and semantic memory banks from dialogue histories and derives a user profile from accumulated memories. The profile serves as an explicit personalized prior in memory ranking, allowing retrieval to account for stable user attributes, preferences, and relationships. PPRO further trains a query rewriter with Group Relative Policy Optimization, using both evidence retrieval quality and downstream answer quality as feedback while keeping the memory banks and answer model fixed. Experiments on LoCoMo and LongMemEval-S show consistent gains over training-free memory systems and training-based baselines. Ablation studies further show that both profile-guided ranking and retrieval-oriented rewriting contribute substantially to performance, highlighting retrieval optimization as a key factor in personalized long-term memory use. --- ### Privacy-Aware Agent Collaboration for Dynamic VR Slice Management in 6G SD-RAN Authors: Khaled M. Naguib, Soumaya Cherkaoui, Mahmoud M. Elmesalawy, Ahmed M. Abd El-Haleem, Ibrahim I. Ibrahim Published: 2026-05-28 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2606.26123v1 Ultra-low latency and high throughput are required for Virtual Reality (VR) services in 6G networks, which presents critical challenges for Software-Defined Radio Access Networks (SD-RANs) dynamic resource management. This work propose a mobility-driven, privacy-aware Multi-Agent Reinforcement Learning (MARL) framework for VR slice management, in which cooperative agents maximize resource distribution over end-to-end VR links while protecting the privacy of user data. Our approach incorporates mobility prediction and an information bottleneck encoder to facilitate effective and secure agent collaboration. In simulations, comparisons with traditional methods are studied which show up to 34\% throughput improvement, 28\% fewer resources, and 85\% less privacy leakage, guaranteeing dependable immersive VR experiences in future 6G environments. --- ### Context-Aware Prediction of Student Quiz Performance with Multimodal Textbook Features Authors: Samin Khan Published: 2026-05-28 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.24770v1 Educational platforms often predict student performance from prior interactions, but the assessment content itself also varies in linguistic and visual complexity. This paper studies whether lightweight content features extracted from CourseKata chapter-review questions improve prediction of end-of-chapter quiz scores beyond a student's average prior exercise performance. The study combines 2023 CourseKata student response data with chapter-level text features from review-question wording and image features from textbook visuals. Across 4,742 student-chapter observations from 562 class-student IDs, adding content features improves student-grouped five-fold quiz prediction performance by 9.1% relative to a prior-performance baseline. In leave-chapter-out validation, text features reduce prediction error relative to the baseline, while image-containing models have higher error. This paper suggests that a context-aware model adds useful signal about the text and visual features of questions to better predict student quiz performance compared with using past student performance alone. --- ### FP8 is All You Need (Part 2): Full-FP64 3-D FFT on FP8-Generation Tensor CoresThe Integer-Epilogue Wall and the Minimal Hardware That Would Remove It Authors: Satoshi Matsuoka Published: 2026-05-28 Categories: cs.MS, cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2606.23698v3 The NVIDIA Blackwell Ultra (B300) GPU cuts FP64 vector throughput $\sim 30\times$ while multiplying FP8 tensor throughput. After the recovery of FP64 GEMM via Ozaki Scheme II on FP8 tensor cores and the Tensor-Memory Equilibrium model of the companions ("FP8 is All You Need, Part 1" and "Ozaki 2.5") we ask whether the fifth canonical HPC primitive, the full-FP64 $1024^3$ 3-D FFT, can be carried by the same substrate, and answer with a design and its limit. It is a Bailey six-step transform with no FP64 arithmetic: FP8-tensor DFT GEMMs with fused twiddles, residue-domain Karatsuba combines and exact CRT reconstruction whose bulk is a small GEMM on the FP16 tensor path and whose remainder is a Kulisch fixed-point accumulation with a two-sided modulo-$M$ lift, so the only rounding is the final conversion; constants are machine-generated and verified bit-exactly. The central finding: the binding resource is not floating point but a per-output integer epilogue with floor $(c_{\rm epi}/8),B_{\rm mem}$, $c_{\rm epi} \approx 203$-$281$ instructions per output: on B300 it holds the transform at 63-87 ms against a 12.9 ms roof ($4.9$-$6.7\times$ short); at most $1.3$-$1.9\times$ faster than the collapsed native path, possibly no faster at realised issue rates; no software route reaches the roof; on the NVIDIA Rubin GPU emulation loses $8$-$11\times$. An FP32 variant meets the same wall: the cause is per-scalar reconstruction, not FP64. Each floor term names its remedy: the NVIDIA B200 GPU's INT8 tensor core restored with a position-weighted cross-column accumulation primitive, a load-path deconstruction datapath shared with the companions, two ISA idioms and modular reduction at the MMA output give 16.0-23.5 ms with minor hardware and 12.9-15.0 ms with one moderate ask. All figures are projected floors, not measurements, with sensitivities and the FP8 layout condition given. --- ### FP8 is All You Need (Part 2): Efficient Ozaki-Bailey Style FFT Through Tensor-core Garner Reformulation and Kulisch Escape Route Authors: Satoshi Matsuoka Published: 2026-05-28 Categories: cs.MS, cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2606.23698v2 NVIDIA's Blackwell Ultra (B300) cuts FP64 vector throughput to ~1.3 TFLOPS per GPU, roughly 30x below B200 and well below the level at which bandwidth-limited FP64 workloads stay memory-bound. The Ozaki Scheme II framework recovers FP64-equivalent throughput by routing dense matrix multiply through FP8 tensor cores with a mantissa-sliced Chinese-remainder reconstruction. A companion Part (1) paper covers dense GEMM, batched GEMV, stencils, and SpMV; this paper adds the fifth canonical primitive, the 3-D FFT. We present Ozaki-Bailey FFT, an emulated 3-D FFT via the Bailey six-step decomposition with both 1-D FFT GEMMs on FP8 tensor cores. Bailey's small inner factor k ~ sqrt(N) (k=32 for N=1024) puts the kernel in the regime k << r^2, where the third TME parameter gamma (reconstruction latency) binds rather than amortising. Garner reconstruction splits into Phase A (inner products on FP8/INT8 tensor cores, ~1 ms for 1024^3 on B300) and Phase B (per-output reduction). We identify Kulisch fixed-point complete arithmetic as a Phase B reformulation that keeps full FP64 accuracy while running entirely on the INT32 SIMT pipe. We derive closed-form bandwidth-parity floors. The native FP64 floor is 1.56*B_HBM (12.5 TF at 8 TB/s): B300's 1.3 TF sits ~10x below, Rubin's 33 TF within 4%. The Kulisch escape route needs an INT32 sub-floor 8.25*B_HBM and an FP8 floor 170*B_HBM; B300 meets both. The projection is ~18 ms for 1024^3 at full FP64, essentially the 12.9 ms memory roof. A GPU meets memory-roof FFT parity if it satisfies either the native floor or both Kulisch floors. If the projection holds in practice, B300 becomes viable for full-FP64 FFT through software alone, motivating a libKulisch library and benchmark campaign. --- ### Design Principles for Human-Agent Interaction Authors: Haiyi Zhu, Canwen Wang, Qing Xiao, Hong Shen Published: 2026-05-28 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2606.20630v1 AI agents are rapidly evolving into autonomous systems capable of sustained interaction, tool use, and long-term collaboration. Yet their real-world adoption remains limited, suggesting that the key barrier lies not only in technical capability but also in a lack of design knowledge for successful human-agent interaction. This position paper argues that AI agents should not be solely evaluated or deployed based on autonomous task capability alone; because agents interact with, adapt to, influence, and sometimes fail humans, human-agent interaction must be treated as a core design and evaluation target for agentic AI. We present 14 design principles that articulate the ideal human-agent relationship across four interaction stages: initially, during interaction, over time, and when things go wrong. We use these principles to evaluate nine agent systems to illustrate that these design principles can provide actionable guidance for AI design teams to systematically design and evaluate agents that are usable, trustworthy, and effective in real-world interactive settings. --- ### Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams Authors: Yinsicheng Jiang, Liang Cheng, Yeqi Huang, Yufan Zhao, Zhan Lu, Li Dong, Wenda Li, Edoardo Ponti, Luo Mai Published: 2026-05-28 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20629v1 LLM agents are increasingly deployed as multi-role teams, where tasks are divided across specialized roles such as planner, executor, and verifier. In these systems, cost and accuracy are no longer properties of a single model: they depend on which model fills each role and where it is hosted, including API, self-hosted, and hybrid deployment. Existing agentic benchmarks typically evaluate fixed models or fixed agent configurations, and therefore offer limited guidance for cost-accuracy-optimal deployment. We introduce AgentCARD, a role-aware benchmark suite for evaluating LLM agent teams across role assignment and deployment mode. AgentCARD combines a role-decomposed evaluation harness, a unified API/self-hosted cost model, Pareto-frontier analysis, and a Shapley-based diagnostic for identifying role bottlenecks. Our evaluation shows that heterogeneous teams consistently occupy the cost-accuracy frontier. They improve accuracy by up to $44\%$ over cost-equivalent homogeneous teams, or match the strongest homogeneous team at up to $12\times$ lower per-task cost through hybrid deployment. We further find that the best role assignment is domain-dependent: some domains are planner-bottlenecked, while others are executor-bottlenecked. Finally, AgentCARD extends beyond planner--executor teams to workflows with additional roles such as verification, and supports continual evaluation as new domains and team structures emerge. Our code is released at: https://github.com/Auto-CAP/AgentCAP --- ### DC-Motion: Decoupling Structure and Details via Discrete-Continuous Tokens for Human Motion Generation Authors: Hequan Wang, Xuean Chen, Jiaxu Zhang, Zhengbo Zhang, Zhigang Tu Published: 2026-05-28 Categories: cs.GR, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.14721v2 Text-to-motion generation requires modeling both global action structure and fine-grained motion dynamics from natural language. Existing approaches typically rely on either continuous diffusion models or vector-quantized discrete representations. Diffusion models generate smooth motions but lack explicit compositional structure for temporal planning, while discrete token-based methods improve controllability but compress motion into finite codebooks, losing fine-grained dynamics. We argue that this limitation stems from a representation mismatch: action semantics such as intent, phase transitions, and temporal layout are inherently discrete and compositional, whereas joint trajectories and motion dynamics are continuous and locally correlated. To address this, we propose DC-Motion, a discrete-continuous factorized framework for human motion generation. DC-Motion decomposes motion into discrete structural tokens capturing global action layout and continuous residual latents modeling fine-grained dynamics. A text-conditioned structure generator predicts discrete tokens via iterative masked modeling, and a diffusion-based residual generator produces continuous motion conditioned on the structure. Experiments on HumanML3D and KIT-ML demonstrate that DC-Motion achieves strong performance in both FID and R-Precision, outperforming representative diffusion-based and discrete-token baselines. --- ### AI for Maritime Security: Comparative Evaluation of CNN and Vision Transformer Architectures for Maritime Object Detection Authors: Ismet Gocer, Zakirul Bhuiayn, Shakeel Ahmad, Raza Hasan Published: 2026-05-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.14720v1 This study aims to enhance maritime security by using advanced Artificial Intelligence (AI) and Computer Vision (CV) techniques. For this purpose, it was designed and assessed intelligent object detection systems that can detect the presence of ships on the sea surface under different real-time environments. To achieve this goal, a maritime image dataset with 6,468 images was used, covering different weather conditions like cloudy, foggy, rainy, and sunny environments. Six deep learning architectures were evaluated, including a base Convolutional Neural Network (CNN) model, four transfer learning models (Xception, VGG16, MobileNetV2, and EfficientNetV2L), and a Vision Transformer (ViT) model. The models were compared using multiple performance indicators, including accuracy, Type I and Type II errors, model size, and video processing time. The results show that model performance varies depending on computational constraints and deployment conditions. While lightweight architectures are suitable for resource-limited devices, the ViT achieved the best overall performance, reaching 100% accuracy with the lowest error rates and the fastest video processing time. The findings highlight the potential of AI-driven computer vision systems for maritime surveillance, border protection, and autonomous navigation. --- ### CFCamo: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection Authors: Suhang Li, Osamu Yoshie, Yuya Ieiri Published: 2026-05-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.11231v1 Vision-language reinforcement learning has recently shown strong target-present localization for camouflaged object detection (COD). Yet localization is only one side of the decision: when the agent faces an ordinary image with no camouflaged target, will it still claim that a camouflaged object exists? Standard COD training and evaluation data are positive-only, so agents optimized under this setting can acquire an over-detect bias, a task-specific form of object hallucination that standard COD evaluation leaves unmeasured. To quantify this target-absent behavior, we construct Counterfactual COD (CF-COD), a paired benchmark that removes the camouflaged target from each held-out COD evaluation image while preserving a plausible background. CF-COD evaluates whether a model detects the target on the original image and abstains on the target-absent counterfactual, summarized by Pair Accuracy (PA). We further introduce CFCamo, a paired counterfactual framework for COD with abstention. For training, CFCamo optimizes a Qwen3-VL-4B-Instruct agent with Counterfactual Sequence Policy Optimization (CSPO), which samples paired original-counterfactual rollouts and uses a Counterfactual Paired Reward (CPR) to couple original-image detection with counterfactual abstention. On CAMO-test, CFCamo improves S_alpha by +3.7 pp over the prior RL-based COD baseline; across CF-COD, it reaches 80.0-90.8% PA. Ablations show that removing counterfactual coupling reduces PA to 1.4-5.2% despite strong target-present COD scores, showing that target-present evaluation alone does not characterize detect-or-abstain behavior. Overall, these results indicate that CFCamo improves COD agents by coupling target-present detection with target-absent abstention, rather than merely strengthening target-present localization. Code and data are available at https://github.com/suhang2000/CFCamo. --- ### Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation Authors: Mark Walsh Published: 2026-05-28 Categories: cs.IT, cs.AI arXiv: https://arxiv.org/abs/2606.09858v1 Robust decision-making requires compression. A system that forms a rich support state cannot usually preserve its full structure at the point of action. It must retain only those distinctions needed to act, verify, abstain, or defer under the current consequence geometry. This paper formalizes support sufficiency as action-sufficient compression. Let $H$ denote a full support state, $\mathcal{A}$ a finite action set, and $Z$ a consequence geometry specifying payoff structure. For fixed $Z$, the coarsest exactly action-sufficient compression is the quotient of support space by policy equivalence. Two support states may be merged exactly when they require the same optimal action. This clarifies why content-only and scalar-confidence-only arbitration fail whenever their induced partitions cross action boundaries. Approximate sufficiency is then defined by bounded expected policy regret. In the finite single-cycle setting, this yields a rate-regret problem with source $H$, reproduction alphabet $\mathcal{A}$, and distortion given by consequence-sensitive regret. The optimal stochastic action channel inherits the standard rate-distortion Gibbs form, applied here to support states with regret distortion. The contribution is interpretive: action adequacy is distinguished from reconstruction fidelity, information-bottleneck prediction, and rational inattention. Robust single-cycle arbitration does not require preserving all support, but it does require preserving the distinctions that consequence geometry makes action-relevant. --- ### Syll: Open-Source Personal Automation with Cross-Surface Execution Authors: Bo Zhang, Borui Zhang, Chenghao Jiang, Minglei Shi, Xiaofeng Wang, Zheng Zhu, Jie Zhou, Jiwen Lu Published: 2026-05-28 Categories: cs.AI, cs.HC, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2606.07594v1 Personal AI agents must increasingly operate across APIs, shells, web surfaces, and desktop GUIs, yet many systems remain tuned to a single interface and offer limited support for user teaching and auditability. We present Syll, an open-source, self-hosted multimodal agent harness that unifies MCP/API tools, CLI execution, and visual GUI control in a modular runtime, enabling agents to coordinate computer use across heterogeneous interfaces while streamlining how users and agents exchange information. At the core of Syll is a bidirectional user-agent interaction layer: users teach procedures through direct demonstration, which Syll compiles into reusable skills; agent execution is translated back into multimodal evidence -- logs, keyframes, and approval checkpoints -- for inspection and control. Syll further externalizes memory, skills, routines, and governance as editable local artifacts, supporting straightforward inspection, extension, and downstream development. Our implementation has been validated on production desktop applications including Adobe Photoshop, Adobe Audition, Stardew Valley, macOS Finder and others. We report mechanism-oriented studies that validate multimodal routing, teachable GUI replay, and persistent local artifacts. We hope Syll can serve as a practical open-source foundation for personal automation that users can teach, inspect, and continuously extend. --- ### A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers Authors: Hannah Gao, Isha Agarwal, Dylan Hadfield-Menell, Rachel Ma Published: 2026-05-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07593v1 The widespread use of image classification models in high-risk, real-world situations necessitates making these models robust to slight disturbances or perturbations, such as blurring or sharpening, in the input images. While vision transformers (ViTs) play an integral role in many modern-day multi-modal models like Vision-Language-Models (VLMs) and Vision-Language-Action (VLA) models, they have received a lack of attention in the setting of robustness. In this work, we analyze the effects of adversarial fine-tuning, a popular method for improving model robustness to image perturbations, on a ViT's performance on perturbed and regular images through a mechanistic lens. We adversarially train a ViT on low-frequency and high-frequency image corruptions, and attempt to explain changes in downstream model performance through an examination of the model's attention mechanisms, internal representations, and knowledge evolution. Overall, our results suggest that, while fine-tuning on inputs with common corruptions improves model performance and certainty on new instances of corrupted data, these improvements do not transfer to other classes of corruptions not seen in the training. Additionally, despite observing changes in visual attention and knowledge evolution across layers, we found that adversarial training did not lead to fundamental changes in the sparse representations learned by ViTs. --- ### UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning Authors: Aditya Upadhyay Published: 2026-05-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.07592v1 Offline reinforcement learning requires careful conservatism to mitigate distribution shift, yet most existing methods apply a fixed penalty uniformly across all states regardless of local data coverage. We present UNIQ (Uncertainty-Informed Quantile), an offline RL method that introduces state-adaptive conservatism through conformally calibrated uncertainty estimation. Built on the Implicit Q-Learning (IQL) backbone, UNIQ trains a multi-expectile value ensemble, computes distribution-free uncertainty estimates using split conformal prediction, and maps the resulting signal to a state-dependent expectile that relaxes conservatism in well-covered regions while strengthening it in uncertain regions near the data frontier. On D4RL MuJoCo benchmarks, UNIQ consistently improves over IQL, with the largest gains observed on Walker2d and replay-heavy tasks. At the same time, UNIQ operates at near-IQL memory cost (approximately 250 MB peak VRAM), providing roughly a 10x reduction compared to EDAC. Rather than pursuing overall state-of-the-art performance, we position UNIQ as a practical mechanism contribution that improves the performance-efficiency trade-off in offline reinforcement learning. --- ### ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research Authors: Wanghan Xu, Shuo Li, Tianlin Ye, Qinglong Cao, Yixin Chen, Hengjian Gao, Yiheng Wang, Qi Li, Kun Li, Sheng Xu, Shengdu Chai, Fangchen Yu et al. Published: 2026-05-28 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.07591v5 AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research. --- ### SlideCheck: Guiding Self-Supervised Pretraining of Pathology Foundation Models via Dataset Distributions Authors: Mingyi He, Xinyi Guo, Xitong Ling, Weiming Chen, Jiawen Li, Lianghui Zhu, Minxi Ouyang, Mingxi Fu, Yizhi Wang, Tian Guan Published: 2026-05-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07590v1 Pathology foundation models are pretrained on large streams of WSI-derived patches, while supervision during data construction is often slide-level, sparse, or heterogeneous. This mismatch makes it difficult to understand and control which biological patterns enter the pretraining data. We propose SlideCheck, a lightweight pretraining data guidance tool built on frozen pathology foundation model patch features. Rather than serving as a standalone patch diagnostic model, SlideCheck provides explicit abnormality and malignancy scores for organizing, filtering, and auditing pathology pretraining data. SlideCheck uses a dual-head MLP to separately model broad abnormal morphology and malignant evidence. A regularized feature-space scorer provides a supervised anchor for patch-level evidence estimation, while score-attention agreement combines patch scores with WSI-level MIL attention to mine high-confidence pseudo labels. The same scores are then used to construct broad-positive ViT pretraining subsets, where a patch is selected if either abnormality or malignancy evidence exceeds a threshold. Experiments show that SlideCheck-defined data distributions influence the downstream behavior of self-supervised ViT pretraining, indicating that biological composition is an important controllable factor in pathology foundation model development. Curated subsets can approach full-data performance, suggesting that explicitly scored patch pools may support more efficient and auditable pretraining data construction. These findings position SlideCheck as a data guidance and auditing layer for transforming large, undifferentiated patch pools into controllable and reusable pretraining datasets. --- ### Optimality of Sequential Filtering Under Independent Cost and Selectivity Models Authors: Hrishikesh Paranjape, Abhishek Mandal, Xian Sun Published: 2026-05-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.07589v1 Sequential filtering pipelines are a common design pattern in large-scale systems, where a large population of items is progressively reduced by a sequence of stages that each incur cost. Despite their prevalence in ranking systems, cascaded machine learning inference, and fraud detection, filter ordering is often determined by heuristics without formal guarantees. We formalize sequential filtering under an expected-cost objective and prove that, under an independence model, ordering filters by increasing ratio of cost to rejection probability minimizes expected total cost. Extensive Monte Carlo simulations show that the optimal ordering strictly dominates common heuristics across all runs, both in expectation and across the full distribution of outcomes. --- ### FP8 is All You Need (Part 1): Debunking Hardware FP64 as the HPC Holy Grail (Sep 3rd version) Authors: Satoshi Matsuoka Published: 2026-05-28 Categories: cs.AR, cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2606.06510v4 We argue that on AI-optimised GPUs of the NVIDIA B300 generation and beyond, the FP8 tensor-core matrix operation, composed through CRT-based Ozaki Scheme II, can serve as the dominant matrix-work substrate for the surveyed matrix-dominated FP64 kernel classes at FP64-grade accuracy, with native FP64 recast from a hardware requirement into a derived accuracy guarantee. The claim is conditional: the FP8 op is the candidate dominant multiplication substrate, with a bounded auxiliary set of integer deconstruction/reconstruction work, FP32/Kulisch reductions, data movement and a native-FP64 fallback, organised as a hierarchy from the FP8 op through Ozaki II and the Berkeley dwarfs to applications. The instrument is the Tensor-Memory Equilibrium (TME) model, a Roofline extension with four parameters (compute multiplier $α=3r+1$, bandwidth multiplier $β$, reconstruction cost $γ$, and the per-input deconstruction cost $c_q$ identified in an NVIDIA review) under which, at its upper bound, the reduction to FP8 costs no performance against an ideal native-FP64 machine of equal bandwidth. On-chip tile fusion drives $β\to 1$; the deconstruction term sets a threshold intensity below which emulation is conversion-bound. At the fused, engineered-$c_q$ bound every surveyed class reaches the memory roof, with two priced exceptions: large dense-square DGEMM sits at a deconstruction floor near 0.50 of the FP8 arithmetic roof (about 235 of 473 TFLOPS on the NVIDIA Rubin GPU), a liftable co-design coordinate, and the 3-D FFT is walled by a per-output integer epilogue at $4.9$-$6.7\times$ its roof in software, recoverable with minor hardware and one moderate ask. Ozaki II lifts the emulated FP64 ceiling from $\approx 1.3$ to $\approx 135$ TFLOPS on B300 and $\approx 473$ on Rubin; three deconstruction-path hardware options are given; constants are engine-checked. ---