# Research Papers — 2026-07 · bundle page 146 of 222 > Full-text markdown of papers #7251–7300 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/146 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/145.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/147.md) ### Comparing Socio-technical Design Principles with Guidelines for Human-centered AI Authors: Thomas Herrmann Published: 2026-07-11 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.10331v1 Human-centered AI (HCAI) refers to guidelines or principles that aim on ethi-cally oriented design of systems. We compare HCAI- guidelines with princi-ples of socio-technical systems that emerged in the context of conventional in-formation technology. The comparison leads to a revision of socio-technical heuristics by including aspects of AI-usage. The comparison reveals that con-tinuous evolution is a basic characteristic of socio-technical systems, and that human oversight or interventions and the subsequent appropriation of AI-systems lead to continuous adaptation and re-design of the systems, if autono-my is collaboratively exercised. From a socio-technical point of view, the cru-cial requirement of transparency has not only to be fulfilled with technical fea-tures, but also by contributions of the whole system including human actors. It will be promising for using AI, if not only technical features, but organization-al and social practices are socio-technically designed in a way that compen-sates shortcomings of AI. --- ### Imperceptible and Reversible Adversarial Examples against Vision-Language Models for Privacy Protection Authors: Qi Lu, Ziqi Zhou, Yufei Song, Zijing Li, Lulu Xue, Minghui Li, Shengshan Hu, Leo Yu Zhang Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10329v1 Vision Language Models (VLMs) offer powerful multimodal ability but also expose users to text-based privacy attacks where adversaries crawl online photos and query VLMs to extract sensitive attributes. Existing reversible adversarial example (RAE) methods protect images in purely visual tasks but fail in multimodal settings, and current adversarial examples on VLMs rely on high frequency noise that severely degrades visual quality. We propose CloakDiff, the first framework for reversible, high fidelity privacy protection against text-based query attacks in VLMs. CloakDiff produces imperceptible adversarial examples by combining diffusion based adversarial editing with an invertible network that embeds the original image for lossless recovery. It perturbs both pixel space embeddings and manipulates latent cross attention maps to ensure strong cross-model and cross-prompt transferability while preserving global visual structure. To further enhance fidelity, we design EDM Heuristic Sampling, a principled diffusion schedule for adversarial guidance. Experiments on multiple datasets and VLMs demonstrate that CloakDiff delivers multimodal privacy preservation with high visual quality and reversibility. --- ### Neutralizing Structural Inequality in the Nigerian FinTech Sector Authors: Muhammad Abdullahi Said Published: 2026-07-11 Categories: cs.CL, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2607.10317v1 Algorithmic decision systems in financial services often rely on data proxies that inadvertently encode structural inequalities. This paper introduces a hierarchical human-AI triage model for Point of Sale fraud detection in the Nigerian FinTech sector. Adopting a We Are All Equal worldview, we address the challenge of discrimination laundering, wherein the system misinterprets infrastructure related aleatoric noise such as rural network timeouts as fraudulent intent. We implement a three-tier routing policy utilizing a calibrated ensemble model as a primary filter. The policy routes transactions characterized by epistemic uncertainty such as cold start new accounts to specialist analysts while reserving high stakes cases for a senior supervisor. To manage finite human capacity, we utilize a dynamic shadow price to ration human attention and implement a random audit mechanism to prevent human skill atrophy. Our experimental results demonstrate a statistically significant 1.88\% complementarity gap and a 24.79\% percentage point gain in fraud recall over an autonomous baseline. Crucially, the model reduces the regional performance gap from 19.43 to 2.88 percentage points, neutralizing structural bias. Hierarchical collaboration provides a robust mechanism for substantive equality of opportunity, ensuring that rural accounts are not excluded from the digital economy due to environmental brute luck. --- ### Polarization Detection: A Hybrid Approach with AfroXLMR-Social and DeBERTa for Low- and High-Resource Settings Authors: Muhammad Abdullahi Said Published: 2026-07-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.10312v1 The rapid proliferation of online polarization threatens social cohesion, necessitating robust automated detection systems that operate effectively across diverse linguistic contexts. This paper presents our system description for the POLAR Shared Task 2026, focusing on the detection and characterization of polarized discourse in English and Hausa. We propose a hybrid modeling strategy: for English binary detection, we leverage the monolingual strength of \textbf{DeBERTa}, while for Hausa and all fine-grained subtasks (Types and Manifestations), we utilize \textbf{AfroXLMR-Social}. This domain-adapted multilingual model proved critical for capturing the nuances of polarization in social media text. To further address computational constraints and data scarcity, we implement Low-Rank Adaptation (LoRA) and textual data augmentation via \texttt{nlpaug}. We report competitive results across all three subtasks, demonstrating that model selection tailored to specific subtask requirements yields the best balance of performance. --- ### PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment Authors: Zhiyuan Wen, Jiannong Cao, Kelly Chan, Zijian Wang, Chen Chen, Xiaoyun Liu, Jianing Yin, Zhuo Li Published: 2026-07-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.10310v3 Preparing for job interviews is important for securing desired positions, yet realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor structured assessment. Existing systems typically address only parts of this need through fixed question sequences, limited communication channels, or feedback with little supporting evidence. We present PolyInterview, an LLM-based platform for immersive mock interview practice with comprehensive multimodal assessment. PolyInterview uses the target job description and CV to generate questions tailored to the role and candidate, conducts multi-turn spoken interviews with a lip-synced digital human interviewer that asks answer-aware follow-up questions, and evaluates response content, vocal delivery, and non-verbal behavior. Four parallel evaluators produce 13 behavior-level features that are aggregated into 10 assessment aspects and two competency tracks. Guided by the KSA and STAR frameworks, the report links each score to behavioral evidence and actionable recommendations. PolyInterview is publicly accessible. Its current all-account snapshot contains 101 accounts, 1,564 interview sessions, 7,665 generated questions, and 1,422 five-stage question sets. Generated questions are more closely aligned with their matched job description than with cross-role job descriptions in 93.7% of sessions. An evaluation by ten experts found strong question plans and actionable feedback. --- ### Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems Authors: Rongping Zhou, Omid Tavallaie, Shuaijun Chen, Albert Y. Zomaya Published: 2026-07-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.10309v3 Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the trial-and-error nature of RL, when conducted in real-world environments, is costly and hazardous in some scenarios. Consequently, the majority of RL research is conducted in simulation. This reliance introduces challenges related to the Sim-to-Real transferability. Evaluating the Sim-to-Real algorithmic robustness and the Sim-to-Real gap is a critical prerequisite for research aimed at improving RL performance in the real world. Therefore, industries such as robotics have developed concurrent simulation and physical platforms to facilitate this research. However, a universal Sim-to-Real benchmark platform for AIoT does not currently exist. To address these concerns, we developed a real-world AIoT platform for studying RL in AIoT. On this platform, an agent deployed on an edge device plays video games on a separate host computer via a hardware-emulated keyboard, guided by vision input. This platform uses commercially available components costing less than USD 400, together with two computers. Because the system's objective is game score maximization, it inherently mitigates safety risks associated with real-world RL deployments. Experimental results show the simulation-trained agent suffers a 1160% performance degradation relative to the human-level performance after real-world deployment, indicating a significant Sim-to-Real gap. Direct real-world training using the deep Q-network (DQN) algorithm achieves approximately 49% of human-level performance after 10 million training steps, demonstrating the feasibility of RL under real-world conditions. These results suggest that the proposed Sim-to-Real benchmark platform provides a substantial foundation for qualitative and quantitative evaluations of RL in real-world AIoT systems. --- ### Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems Authors: Rongping Zhou, Omid Tavallaie, Shuaijun Chen, Albert Y. Zomaya Published: 2026-07-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.10309v1 Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the trial-and-error nature of RL, when conducted in real-world environments, is costly and hazardous in some scenarios. Consequently, the majority of RL research is conducted in simulation. This reliance introduces challenges related to the Sim-to-Real transferability. Evaluating the Sim-to-Real algorithmic robustness and the Sim-to-Real gap is a critical prerequisite for research aimed at improving RL performance in the real world. Therefore, industries such as robotics have developed concurrent simulation and physical platforms to facilitate this research. However, a universal Sim-to-Real benchmark platform for AIoT does not currently exist. To address these concerns, we developed a real-world AIoT platform for studying RL in AIoT. On this platform, an agent deployed on an edge device plays video games on a separate host computer via a hardware-emulated keyboard, guided by vision input. This platform uses commercially available components costing less than USD 400, together with two computers. Because the system's objective is game score maximization, it inherently mitigates safety risks associated with real-world RL deployments. Experimental results show the simulation-trained agent suffers a 1160% performance degradation relative to the human-level performance after real-world deployment, indicating a significant Sim-to-Real gap. Direct real-world training using the deep Q-network (DQN) algorithm achieves approximately 38% of human-level performance after 10 million training steps, demonstrating the feasibility of RL under real-world conditions. These results suggest that the proposed Sim-to-Real benchmark platform provides a substantial foundation for qualitative and quantitative evaluations of RL in real-world AIoT systems. --- ### Generalize LMMs to Versatile Visual Modalities via Fabricated Modality Synthesis Authors: Shihao Yuan, Yuanze Li, Ruyi Zhang, Ming Liu, Wangmeng Zuo Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10308v1 Despite the advancements of Large Multimodal Models (LMMs) in RGB vision, their ability to generalize to unseen visual modalities remains a largely unexplored challenge. We argue that different visual modalities are merely distinct samplings of the same physical world. Therefore, effective generalization requires models to possess both modality-agnostic perception of scene semantics and the adaptability to modality-specific characteristics. To achieve this, we propose a training framework, VVM-Tuning, to equip LMMs with these capabilities through modality synthesis and modality contexts. Specifically, we synthesize diverse appearance-varied images from RGB scenes, training the model to disentangle invariant semantics from varying visual appearances, and align these appearances with language for visual concepts decoupled from modalities. We then introduce modality contexts in the prompt and use instruction tuning to assist the model in mapping these appearance variations back to modality-related attributes, enabling zero-shot adaptation to unseen modalities during inference. To facilitate research in this direction, we introduce VVM-Bench, a comprehensive benchmark featuring 6 real and synthetic modalities to evaluate semantic perception and modality understanding. Experiments demonstrate that, via our training on synthetic modalities, 5 tested models exhibit consistent improvements on both real-world and novel synthetic modalities without in-modality training. Source code and data will be publicly available at https://github.com/Hunter-Will/VVM-Tuning. --- ### Byzantine Accountability Without Consensus: Strong Eventual Consistency for Non-Associative, Stochastic, Robust Aggregation Authors: Ryan Gillespie Published: 2026-07-11 Categories: cs.DC, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.10305v1 Byzantine-robust aggregation rules such as multi-Krum assume a central coordinator, and decentralising them is obstructed by the rules themselves: they are globally coupled, non-associative, and discontinuous, so an ulpscale perturbation can flip the selected subset, moving the output by a non-vanishing amount. None of this prevents coordinator-free replication, because a robust rule needs no agreed order of contributions, only an agreed set and an agreed exclusion predicate, both of which converge without consensus. ACFA (Accountable Consensus-Free Aggregation) replicates a content-addressed OR-Set of signed contributions and a grow-only set of self-authenticating equivocation proofs, offline-verifiable by anyone. Aggregation is a deterministic pure function of the converged product state: fixed-point integer arithmetic over a hash-canonical order, ties broken by content hash. We prove that any pure function of a converged product of CRDTs (non-monotone, non-associative, or stochastic) inherits Strong Eventual Consistency, together with its converse; the contribution is the composition of a data lattice with an evidence lattice applied to a robust selector, not the elementary lifting step. A prototype (10 nodes, 3 Byzantine) passes 16/16 falsification checks: byte-identical roots under adversarial gossip, deterministic re-convergence after late equivocation proofs, partition recovery, and three byte-identity-breaking ablations. The guarantee is consistency, not accuracy; robustness is imported, conditional on 2f + 3 admitted contributions (at most f Byzantine) and a stated quantisation-margin condition. --- ### ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing Authors: Jiakang Yu, Yixuan Chai, Tianci Wang, Rihui Jin, Guangkai Xu, Hongtao Deng, Xun Zhu, Wang Gao, Xinrun Guo, Haipang Wu Published: 2026-07-11 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2607.10301v1 Generative image editing models struggle with structured statistical charts when data modifications require geometric synchronization. We formalize this task as Visuo-Logical Cascading Editing (VLCE). However, existing methods remain confined to localized text substitutions and struggle with dependency-aware cascading updates. To systematically evaluate this capability, we introduce ChartSync, an expert-validated benchmark constructed via a programmatic rendering pipeline that guarantees deterministic visuo-logical coupling for the ground truth. ChartSync comprises 870 triplets across 9 chart categories and 4 task types, including 235 geometry-coupled VLCE instances that specifically test cascading text-to-geometry synchronization. We further evaluate these instances via a two-tier framework combining objective visual metrics with a vision-language model judge paradigm to assess low-level fidelity alongside multimodal comprehension and reasoning. Evaluating 14 image editing models and one code-mediated pipeline reveals a nuanced capability gap: most open-source models suffer severe drops in geometric synchronization, while only two frontier proprietary models show emerging VLCE capability, with their residual errors mainly involving semantic isolation and background corruption. Our detailed error analysis deconstructs these failure paradigms to identify core meta-abilities for guiding future multimodal architectures. The ChartSync dataset and code are publicly released at https://github.com/kaka-yjk/ChartSyncCodebase. --- ### Empowering Long-form Omni-modal Understanding with Robust Audio Perception Authors: Kaiying Yan, Luoyi Sun, Xiao Zhou, Weidi Xie Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10299v1 Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues. To bridgethis gap, we present AVDC (Audio-Visual Decoupled Captions), a large-scaledataset designed to disentangle visual and auditory semantics. Specifi-cally, we propose an automated pipeline that leverages off-the-shelf mod-els to annotate videos with tripartite captions: visual-only (V), audio-only (A), and joint audio-visual (AV). This decoupled structure explic-itly captures both modality-specific nuances and complex cross-modalinteractions. Building upon this, we introduce AVDC-QA-CoT, a Chain-of-Thought augmented question-answering dataset to foster audio-visualreasoning. To fully exploit these resources, we employ a two-stage train-ing paradigm: omni-modal caption generation pre-training on AVDC, fol-lowed by instruction tuning on AVDC-QA-CoT. Extensive experiments acrossdiverse downstream tasks, spanning video captioning, audio-centric anal-ysis, and omni-modal benchmarks, demonstrate consistent and signifi-cant performance gains, showing the efficacy of our proposed datasetsand training strategy in advancing omni-modal perception. Code anddataset are related on https://radiant0726.github.io/AVDC-web/. --- ### Structured Evidence Selection for Weakly Supervised Video Anomaly Detection Authors: Chenglizhao Chen, Tianxiang Nan, Wen Li, Xinyu Liu, Guisheng Zhang, Mengke Song, Xiaomin Yu Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10298v1 Weakly supervised video anomaly detection relies solely on video-level labels for training, making it difficult to accurately localize anomalous events in complex scenes. In real-world videos, anomalous behaviors exhibit large variations in appearance and temporal duration, while scene appearance and action dynamics are often tightly entangled. Consequently, existing models tend to rely on scene-related statistical cues rather than true behavioral deviations, resulting in unstable detection performance. To address this challenge, we propose a Structured Evidence Selection framework (SESAD) that reformulates anomaly detection as a structured reasoning process over clip-level visual evidence. Instead of directly mapping aggregated features to anomaly scores, SESAD reorganizes clip representations into semantically structured candidate evidence and performs context-conditioned selection under scene and action constraints. This mechanism adaptively emphasizes anomaly-relevant semantics while suppressing scene interference, thereby alleviating semantic entanglement under weak supervision. Furthermore, we introduce a lightweight geometric discrimination module that constructs a dual-prototype structure in the embedding space, enabling anomaly decisions through relative geometric relations. Extensive experiments on UBnormal, ShanghaiTech, and UCF-Crime show that SESAD achieves 67.92, 97.99, and 88.46 AUC, respectively, while maintaining high computational efficiency and overall consistently stable anomaly discrimination. --- ### SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models Authors: Dongxu Zhang, Yiding Sun, Zihao Guo, Xiangyang Yang, Kai Tang, Lin Chen, Cheng Tan, Jihua Zhu Published: 2026-07-11 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.10296v1 Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may reflect missing capability, an unstable reasoning trajectory, or a failure to activate a reasoning state that is already available in the frozen model. Existing prompting and benchmark-based evaluation methods mostly operate at the output level, while generic activation-steering methods typically apply global directions without diagnosing which examples require intervention. In this paper, we introduce SPARK, which uses hidden-state response to diagnose whether a model internally enters an effective reasoning state and to guide lightweight test-time steering. The key observation is that raw hidden-state susceptibility is strongly confounded by prompt length, especially in programmatic and algorithmic reasoning where harder serialized instances naturally become longer. SPARK therefore uses length-controlled susceptibility to separate input-scale effects from residual reasoning activation, and combines this signal with cross-layer coordination to select reasoning-active anchors and under-activated hard examples. We use FRONTIER-4.5K as a controlled programmatic reasoning suite for latent profiling and difficulty-aware analysis, and evaluate SPARK-Steering on GSM8K and MATH-500 with forward-only benchmark profiling. Our method improves Qwen3 series models consistently; on MATH-500, accuracy rises from 82.0% to 84.6% for Qwen3-4B and from 82.4% to 85.6% for Qwen3-8B. These results suggest that susceptibility can serve not only as a diagnostic signal for reasoning failures, but also as a practical guide for targeted test-time intervention. --- ### Program-Synthesis-Driven Autodesign of Universal Unitary Operators Authors: Yifei Zhang, Dong Chen, Fan Wang, Wenrui Zhang, Yan Chen, Dingding Han, Jianmin Yuan, Xiangjin Kong, Yu-Gang Ma Published: 2026-07-11 Categories: physics.optics, cs.AI arXiv: https://arxiv.org/abs/2607.10295v1 We demonstrate that AI-driven program synthesis can autonomously discover fundamental strategies for decomposing unitary matrices in photonic networks. By extending DreamCoder to complex-valued linear algebra, the system generates decomposition programs achieving the minimal $N(N-1)/2$ Mach-Zehnder interferometers, distinct from both Reck and Clements architectures. Learned programs encode dimension-agnostic invariants: strategies discovered for $5 \times 5$ matrices generalize to higher dimensions such as $64 \times 64$. The discovered programs encode interpretable, dimension-agnostic construction rules. These rules generalize across matrix sizes without retraining, demonstrating that autonomous program synthesis can serve as a scalable paradigm for algorithm discovery and the automated design of universal unitary operators. Beyond universal decompositions, the system automatically exploits matrix structure to reduce the interferometer count below the universal theoretical bound. For instance, for Householder matrices, it discovers a dimension-independent rule that requires only $2N-3$ MZIs. This achieves linear, rather than quadratic, scaling and generalizes to arbitrary $N$ without retraining. For matrices obtained from the singular value decomposition of sparse matrices, reductions generally increase with sparsity, reaching up to 38% fewer MZIs than the universal theoretical bound $N(N-1)/2$ at 95% sparsity. These MZI reductions translate directly into practical hardware benefits for scalable photonic implementations. Taken together, the system functions as a single unified engine that discovers both universal decomposition rules and matrix-specific optimizations, without being provided with the structural or analytical properties of the input matrices. --- ### Partial Contracts Suffice: Sound, LLM-Inferred Regression Verification Authors: Yiannis Charalambous, Rafael Menezes, Youcheng Sun, Lucas C. Cordeiro Published: 2026-07-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.10291v1 Software evolves continuously, yet ensuring that a patch preserves intended behavior without re-verifying an entire codebase remains difficult. Regression verification addresses this problem, but existing techniques require expensive whole-program reasoning or rely on manually written specifications that are rarely available in practice. We present the first contract-based regression verification tool. Contract soundness is ensured by proving all function versions match the behavior. The contract then verifies program flow via assume-guarantee. We ask whether a partial, caller-sufficient contract, rather than a full behavioral specification, is enough. On Frama-C-Problems we strengthen each inferred contract past what the caller needs and measure how much tighter it becomes. It barely moves: for most targets in every model the caller-sufficient contract is already the tightest the loop reaches, and our tightness comparator rates the partial and strengthened contracts equivalent for the large majority of targets it can compare. Partial-spec contracts thus capture nearly all the attainable tightness, so stopping at caller-sufficiency costs almost nothing. The regression check underneath is sound: on the third-party EqBench-C suite it never fabricates an equivalence, returning zero false proofs and reporting an unprovable difference instead. It also surfaced nine pairs that EqBench mislabels as equivalent, more than a concurrent tool reports. The contracts themselves are inferred automatically from the checker's own counterexamples, with no separate specification step; on Frama-C-Problems and the ANSSI X509 parser this reaches a verification rate comparable to tools AutoSpec and Preguss, while a passing result certifies at least as strong a property, which we call \emph{safety-preserving conditional equivalence}: enforcement plus caller-sufficiency. --- ### InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation Authors: Yichen Peng, Jyun-Ting Song, Chen-Chieh Liao, Kris Kitani, Hideki Koike, Erwin Wu Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10287v1 Human-pet interaction estimation and generation remain underexplored due to the absence of a high-quality large-scale dataset. We present InterPet4D, the first multimodal dataset capturing natural interactions between humans and dogs. Using a synchronized multi-view capture system, we record human-dog obedience tasks and provide annotations for both humans and dogs, including multi-view and egocentric videos, segmentations, 2D and 3D keypoints, meshes, and audio tracks. InterPet4D consists of 6.8 million frames collected from 13 dogs of 11 breeds interacting with 23 human participants. We further introduce the InterPetMoGen framework for human-pet interaction motion generation. Our proposed model achieves an FID score of 11.21 and substantially outperforms the Seq2Seq and DiT baselines, demonstrating the effectiveness of InterPet4D for modeling realistic human-pet interactions. --- ### Can Agentic Trading Systems Pay for Their Own Intelligence? Authors: Qiqi Duan, Changlun Li, Chen Wang, Fan Zhang, Mengxiang Wang, Dayi Miao, Peixian Ma, Jiangpeng Yan, Liyuan Chen, Shuoling Liu, Preslav Nakov, Yuyu Luo et al. Published: 2026-07-11 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.10286v2 Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typically report performance metrics, but rarely examine agentic viability: whether dynamic LLM-mediated decisions convert their induced costs into measurable incremental profit. To apply this criterion, we introduce TradeLens, a trace-grounded diagnostic toolkit for evaluating agentic trading systems from their trading records, runtime traces, and deployment configurations. It reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses whether and why an agent pays for its own intelligence. We conduct extensive analysis across backbone models, capital scales, trading frequencies, and system architectures, together with deployment discussion. Our results show that viability hinges on intelligence-to-profit conversion: models exhibit different failure patterns, such as poor asset selection in DeepSeek-V3.2 and negative timing in GLM-4.7, while capital scale, trading frequency, and architecture matter only by amplifying or degrading decision-attributed timing value. These findings reframe the evaluation of LLM-based trading agents from capability-centric performance ranking to trace-grounded diagnosis of intelligence-to-profit conversion. Our code is available at https://anonymous.4open.science/r/TradeLens. --- ### Can Agentic Trading Systems Pay for Their Own Intelligence? Authors: Qiqi Duan, Changlun Li, Chen Wang, Fan Zhang, Mengxiang Wang, Dayi Miao, Peixian Ma, Jiangpeng Yan, Liyuan Chen, Shuoling Liu, Preslav Nakov, Yuyu Luo et al. Published: 2026-07-11 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.10286v1 Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typically report performance metrics, but rarely examine agentic viability: whether dynamic LLM-mediated decisions convert their induced costs into measurable incremental profit. To apply this criterion, we introduce TradeLens, a trace-grounded diagnostic toolkit for evaluating agentic trading systems from their trading records, runtime traces, and deployment configurations. It reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses whether and why an agent pays for its own intelligence. We conduct extensive analysis across backbone models, capital scales, trading frequencies, and system architectures, together with deployment discussion. Our results show that viability hinges on intelligence-to-profit conversion: models exhibit different failure patterns, such as poor asset selection in DeepSeek-V3.2 and negative timing in GLM-4.7, while capital scale, trading frequency, and architecture matter only by amplifying or degrading decision-attributed timing value. These findings reframe the evaluation of LLM-based trading agents from capability-centric performance ranking to trace-grounded diagnosis of intelligence-to-profit conversion. Our code is available at https://anonymous.4open.science/r/TradeLens. --- ### Interpreting learning dynamics of autoencoders: Transient scaling and emerging concepts of the Ising model Authors: Max Weinmann, Miriam Klopotek Published: 2026-07-11 Categories: cs.LG, cond-mat.dis-nn, cond-mat.stat-mech arXiv: https://arxiv.org/abs/2607.10285v2 We study how unsupervised autoencoders trained on microscopic spin configurations from the Ising model learn macroscopic, theory-relevant variables underlying the data-generating process. We quantify learning across multiple spatial (coarse-graining) scales and reveal two distinct dynamical regimes that appear sequentially, controlled by the main hyperparameters (model depth, width, and learning rate): one in which magnetization and another in which energy is learned across scales. The first exhibits error fluctuations ordered to scale and learns global averages only; The second gradually resolves smaller scales relevant for the energy representation. Deep models trained at moderate and fast rates become arrested before reaching these regimes. We connect reconstruction errors with the latent representations using a novel analysis of self-recursive trajectories. These intrinsic dynamics are induced by prediction errors, exposing how training drives representation changes for macroscopic concepts. We utilize the intuition that learning operates as a process driven far from equilibrium by fluctuations from the training data to provide an interpretive basis grounded in both the physical world and the machine models that represent it. --- ### Geometry-aware Gaussian Prior and Axial Attention for Cervical Cytology Image Classification Authors: Yating Li, Cheng Ye, Nenan Lyu, Weidong Chen, Zhendong Mao Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10278v1 Accurate cervical cytology image classification is a key component of automated cervical cancer screening, where reliable recognition of normal, precancerous, and cancer-associated cellular patterns from Pap smear images can improve screening efficiency and diagnostic consistency. However, this task remains challenging because cervical cells exhibit complex morphology, subtle intra-class variations, and strong inter-class similarities. Existing convolution-based models capture local texture well but have limited ability to model long-range relationships, whereas attention-based models provide broader context but often lack explicit structural guidance. To address these limitations, we propose a geometry-aware classification framework for cervical cancer screening-oriented cytology image analysis, incorporating semantic abstraction and structural priors learned from pre-trained vision-language features. The method uses Gaussian expert modules to generate axis-wise priors from global semantic information, capturing structural regularities such as nuclear alignment and cellular spatial organization. These priors are embedded into an axial self-attention module to modulate similarity computation along horizontal and vertical directions, improving long-range dependency modeling and structure-sensitive feature interaction. Experiments on the Mendeley liquid-based cytology and SIPaKMeD datasets show that the proposed method achieves 99.48% accuracy on the former and 96.08% on the latter, with balanced gains in recall, precision, and overall classification performance. Visual analysis further shows that the learned priors highlight diagnostically relevant cellular regions, demonstrating the potential of the proposed framework as a screening-oriented decision-support tool for cervical cytology. --- ### Information-seeking failures of large language models in agentic clinical reasoning Authors: Krischan Braitsch, Laura K. Schmalbrock, Theresa Weltermann, Andrew F. Berdel, Isabella Miller, Kai Tran, Michael Heider, Sabrina Kraus, Florian Bassermann, Jacqueline Lammert, Sebastian Ziegelmayer, Marcus Makowski et al. Published: 2026-07-11 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.10275v1 Large language models achieve high scores on medical knowledge assessments, yet clinical reasoning requires actively deciding what to investigate under uncertainty. We developed an agentic evaluation framework in hematologic oncology in which models must proactively request clinical data across three sequential rounds before committing to a diagnosis and treatment plan. Across 32 frontier models, the best achieved only 68% overall accuracy. Information utilization, the fraction of available data actually requested, was the strongest predictor of diagnostic accuracy (R = 0.69, P < 0.001), yet utilization collapsed from 57% to 26% in the final round, leaving molecular and cytogenetic data critical for treatment selection unexamined. Reasoning traces scored high on a clinical reasoning rubric (91% above threshold) but decorrelated from accuracy, revealing a gap between locally coherent rationales and globally correct conclusions. Error analysis identified search satisficing, anchoring and premature closure as the dominant failure modes, the same cognitive biases that characterize novice clinicians under dual-process models of diagnostic reasoning. These findings demonstrate that the primary limitation of current models in clinical oncology is not insufficient medical knowledge but a systematic failure of information-seeking under uncertainty. --- ### Language Re-generation: An investigation into information locality effects on reconstruction Authors: Amirhossein Mohammadi, Laurence E. Frank, Albert Gatt, Robert A. Bagheri Published: 2026-07-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.10268v1 Information locality, the tendency for syntactically related words to appear close together, shapes both human language processing and language model learning. While prior work has examined whether language models can acquire impossible languages, it remains unclear whether they can recover natural language from such input and what this reveals about their inductive biases. We address this by complementing learnability-based approaches with a reconstruction framework: fine-tuning GPT-2 models pre-trained on impossible languages to reconstruct natural English from three perturbation types. Our findings show that the recovered structures exhibit shorter dependency lengths than the original text, mirroring the locality preference observed in unconstrained language model generation and providing a quantitative signature of an architectural bias that learnability experiments alone do not reveal. Recovery difficulty increases with the degree of locality disruption. Structural recovery (dependency Triple F1) dissociates from surface recovery (Exact Match), while fluency dissociates from faithful reconstruction under global shuffling. Sentence length further modulates performance: longer sentences facilitate recovery when local structure is preserved but lead to complete collapse under global shuffling. Finally, recovery difficulty tracks learnability difficulty across perturbation types, suggesting that information locality is the shared constraint governing both. --- ### Sharper Analysis of Single-Loop Methods for Bilevel Optimization Authors: Yubo Zhou, Jun Shu, Luo Luo, Junmin Liu, Deyu Meng, Guang Dai, Haishan Ye Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10263v1 Bilevel optimization underpins many machine learning applications, including hyperparameter optimization, meta-learning, neural architecture search, and reinforcement learning. While hypergradient-based methods have advanced significantly, a gap persists between theoretical guarantees and practical single-loop implementations required for efficiency. We bridge this gap by establishing sharper convergence results for single-loop approximate implicit differentiation (AID) and iterative differentiation (ITD) methods, leveraging our proposed analytical framework, decoupled norm analysis (DNA). For AID, we improve the convergence rate from $\mathcal{O}(κ^6/K)$ to $\mathcal{O}(κ^5/K)$, where $κ$ is the condition number of the inner-level problem. For ITD, we prove that the asymptotic error is $\mathcal{O}(κ^2)$, exactly matching the known lower bound and improving upon the previous $\mathcal{O}(κ^3)$ guarantee. Numerical experiments on synthetic and real tasks corroborate our theoretical findings. --- ### Data-Driven Telecom Marketing Optimization: A Machine Learning-Based Churn Prediction and Customer Segmentation Framework Authors: Nada Ali, Lina Ahmed, Tahani Abdalla Attia Gasmalla Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10260v1 Customer churn is a major challenge for telecommunication companies, directly eroding revenue and long term customer relationships. Traditional retention programs rely on generic, not personalized incentives and lack the precision to identify high risk customers before they leave. This paper presents a data driven marketing optimization framework integrating machine learning based churn prediction, customer segmentation combining churn risk with customer value, and tailored, segment specific marketing and Return on Investment ROI strategies. Using the IBM Telco Customer Churn dataset with 7043 customers and 21 features, three gradient boosting ensembles, XGBoost, LightGBM, and CatBoost, were trained and tuned via randomized search with stratified 5 fold cross validation, class weighting, and F1 score driven decision threshold optimization to counter a class imbalance of 73.4% versus 26.6%. CatBoost was selected as the deployment model, achieving 77.68% accuracy, an F1 score of 0.6366, a PR AUC of 0.6553, and a ROC AUC of 0.8403 on the held out test set. Customers were partitioned with K Means clustering, validated via the Elbow method and visualized with Principal Component Analysis, into High, Medium, and Low Value segments, cross tabulated against churn risk labels to define four actionable clusters. Segment specific retention, upsell, and engagement strategies were designed for each cluster, and a theoretical ROI and CLV framework quantifies the financial impact of the proposed interventions. The pipeline was operationalized in an interactive Streamlit web application allowing marketing teams to upload data, filter by segment, visualize churn drivers via SHAP, and download automated segment reports. Results confirm that combining predictive churn modeling with value aware segmentation yields more actionable and profitable marketing decisions than churn prediction alone. --- ### Which Languages Transfer Best to Warlpiri? A Similarity-Based Study for Low-Resource ASR Authors: Pravina Mylvaganam, Eliathamby Ambikairajah, Ting Dang, Vidhyasaharan Sethu, Tuende Szalay Published: 2026-07-11 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2607.10256v1 This paper investigates how language similarity can improve cross-lingual transfer for automatic speech recognition (ASR) in extremely low-resource settings. Warlpiri, an Australian Aboriginal language, has very limited transcribed speech data, making transfer learning essential. We propose a framework combining acoustic similarity from pre-trained speech models with linguistic similarity based on typology, phoneme inventories, grammatical, and syntactic features to rank high-resource source languages and evaluate their effectiveness for ASR transfer to Warlpiri. Experiments with Whisper show that acoustically and typologically similar languages outperform monolingual and multilingual baselines. Assamese and Hindi achieve substantial reductions in word and character error rates. Correlation analysis further indicates that acoustic similarity is the strongest predictor of fine-tuning performance, while phoneme inventory and typological similarity better explain zero-shot transfer. --- ### One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions Authors: Tomas Bruckner Published: 2026-07-11 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.10252v1 Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model advertised, and recent audits show that a substantial fraction of commercial endpoints deviate from the vendor's reference weights. Existing identification techniques require long generated texts, token-level log-probabilities, adversarially crafted prompts, or the model owner's cooperation. We show that far weaker evidence suffices. We define a behavioral fingerprint of an LLM as the empirical distribution of its answers to trivial one-word prompts - "name a random number between 1 and 100" - collected across four languages at a cost of one output token per query. Measuring 165 models served via a large commercial aggregator (OpenRouter), we find that (i) these distributions are highly non-uniform (median cell entropy 1.0 bit) and model-specific: split halves of the same model's samples lie an order of magnitude closer than samples of different models; (ii) Jensen-Shannon divergence between fingerprints recovers model lineage, assigning a model to its documented family with 59.5% leave-one-out accuracy against an 18.4% chance rate; and (iii) a biometric-style verification protocol achieves a 7.3% equal error rate with the full 40-cell battery, and below 11% with eight probe cells - roughly a hundred single-token queries per audit. We further report ecosystem anomalies, including a proprietary-branded flagship endpoint distributionally indistinguishable from an open-weight Qwen model. The protocol, prompts, raw data, and analysis code are released for reproduction and operational use. --- ### Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models Authors: Xuankun Rong, Wenke Huang, Bo Du, Dacheng Tao, Mang Ye Published: 2026-07-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.10251v1 As large language models (LLMs) are increasingly used in decision support, it is important to understand whether their choices under uncertainty exhibit stable and interpretable behavioural regularities. Human decision-making combines relatively persistent risk preferences with context-dependent adjustment, yet it remains unclear whether analogous behavioural structure can be observed in LLM-based decision systems. Here we examine this question using a controlled multi-model framework based on no-limit Texas Hold'em, where behaviour is quantified by Participation, measuring voluntary engagement in uncertain opportunities, and Proactiveness, measuring pre-flop risk escalation. Across homogeneous self-play and heterogeneous mixed-model interactions, frontier LLMs exhibit stable, model-specific risk profiles, forming a spectrum from conservative to aggressive decision styles. These profiles remain largely robust under changing opponent composition, while the most conservative and most aggressive models diverge further in mixed settings. Under global risk pressure and personal resource constraint, models adapt in structured but heterogeneous ways, ranging from broad behavioural contraction to selective de-escalation and near-invariant behaviour. These findings suggest that LLMs differ not only in baseline risk disposition, but also in the risk signals they respond to and the flexibility with which they adjust, providing a behavioural basis for auditing risk-sensitive decision-making in interactive settings. Our code is publicly available at: https://github.com/XuankunRong/AgentTexasPoker. --- ### One mechanism for many mental spaces: a shared router over a value slot in language models Authors: Oliver Steele, Jiangtao Wen, Yuxing Han Published: 2026-07-11 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.10248v2 Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical. Each is a mental space in which the same entity can take a different value, as when a flower is red in reality but purple in a portrait. Formal semantics keeps these contexts apart because their logics differ (modal, temporal, doxastic, depictive). Fauconnier's mental-space theory, by contrast, treats them as one space-building operation. We ask which of these a transformer language model implements, and find a mechanistic version of Fauconnier's unification. The model uses one router/slot format across the inventory: a reusable value slot stores attributed content, and a causally manipulable router (the space index) selects which space is read. A subspace trained with Distributed Alignment Search to control one space type, counterfactual, belief, fictional, or temporal, also controls the others, well above a random floor, on three model families. Belief, which formal semantics marks as a distinct case, is not specially separated. The router is low-rank, composes additively with entity identity, and acts through a few late-layer heads. Two further results show the mechanism drives inference and composes: a subspace trained on a rule-derived conclusion flips what the model infers while dissociating from what it reports, and composing space-builders mints a fresh router over the shared slot. This paper establishes the cross-type generality. A companion paper develops belief in depth, because of its special status in philosophy, psychology, and linguistics (epistemology, theory of mind, and propositional attitude reports). --- ### PTEI: Integrating Personality Traits to Enhance Emotional Intelligence in Large Language Models Authors: Amir Reza Jafari, Praboda Rajapaksha, Reza Farahbakhsh, Noel Crespi Published: 2026-07-11 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2607.10245v1 Despite advances in Emotional Intelligence (EI), Large Language Models (LLMs) still significantly underperform humans in complex emotional reasoning. This gap originates partly from the limited incorporation of individual differences, particularly personality traits, which are fundamental to human emotional inference. To address this, we propose PTEI, a novel framework for integrating Personality Traits into Emotional Intelligence tasks using LLMs. In PTEI, MBTI and OCEAN personality traits are first extracted directly from the given emotional scenarios and then utilized as contextual knowledge within personality-aware prompts, guiding LLMs to accurately infer emotions and their underlying causes. To ensure optimal contextual grounding, we employ Contrastive Learning to construct an optimized retrieval system that surfaces emotionally and personally aligned scenarios, enhancing reasoning quality. Extensive experiments on established EI benchmarks show that PTEI enhances the Emotional Understanding (EU) capabilities of various LLMs, with the strongest improvement observed in GPT models. Combining PTEI with Chain-of-Thought (CoT) reasoning yields an additional 4 percent increase in accuracy. These findings underscore PTEI's contribution toward advancing AI systems with more sophisticated social and psychological grounding. --- ### DSSMs: State Space Models with Explicit Memory via Delay Differential Equations Authors: Yixiao Qian, Song Chen, Jiaxu Liu, Shengze Cai, Chao Xu Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10244v1 State Space Models (SSMs) have emerged as a powerful paradigm for efficient long-sequence modeling, offering parallel training and fast linear-time recurrent inference. However, like other recurrent architectures, SSMs must compress an unbounded history into a fixed-size state, which limits context retention and makes precise retrieval over long-range context inherently difficult. To overcome this limitation, we propose Delay State Space Models (DSSMs), a delay differential equation (DDE)-inspired extension of diagonal SSMs that augments discrete SSM recurrences with explicit delayed-state feedback. Making explicit delayed feedback practical requires new stability parameterization, history management, and FFT-training tools. We address these challenges with a practical discretization and parameterization grounded in a simple delay-independent stability condition. To bypass direct time-domain kernel construction, we derive the DSSM transfer function and compute kernels in the frequency domain, using a kernel contour shift to suppress aliasing and recover accurate FFT training. Empirically, DSSMs substantially improve targeted delayed-retrieval tasks while outperforming S4D on most standard sequence metrics and remaining close on the others. --- ### What Does Your Short-Answer VQA Score Actually Measure? Evaluator-Dependent Instability in Multimodal Short-Answer Benchmarks Authors: Guanhua Ye, Niu Jingbin, Yan Li, Meiyu Liang, Zhe Xue, Yingxia Shao, Yawen Li Published: 2026-07-11 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2607.10240v1 Short-answer VQA benchmarks conflate two distinct quantities: whether a model's answer is semantically correct, and whether that answer matches the surface form expected by the automatic evaluator. We study this conflation across six vision--language models and six benchmarks, using a human-validated semantic judge (97.6% precision) to audit over 37k official errors. A second text-only judge reproduces the same benchmark-level false-negative pattern, showing that the effect is not an artifact of a single audit model. On text-rich benchmarks, up to half of these errors are semantically acceptable answers penalized purely for surface-form mismatch. This instability is structured by answer type: extractive and multi-span answers are far more evaluator-sensitive than scalar answers. Benign prompt and context rewrites further destabilize official outcomes, flipping item-level correctness at substantial rates without changing the underlying task. A deterministic CPU-only contract repair confirms that the undercount is partially recoverable. These findings imply that official short-answer VQA scores should be accompanied by semantic audits and answer-type diagnostics to remain interpretable. --- ### Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset Authors: Zhiyan Zhang, Peipei Song, Jinpeng Hu, Jingyang Jia, Xun Yang, Xiaojun Chang Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10238v1 Video emotion analysis is typically framed as a static classification problem, treating each clip as an independent labeled unit. However, such a formulation overlooks a key psychological fact: emotions change as a result of cumulative reactions to consecutive causal events. To bridge this gap, we introduce Dynamic Affective Reasoning, the first large-scale benchmark for viewer-centric affect transitions and causal reasoning over consecutive video events. DAR contains 15,087 videos and 36,908 event-aligned affective segments annotated with 27 emotion categories. Unlike existing video-based emotion datasets, DAR presents a new viewer-centric perspective on fine-grained emotional expressions and transitions, and provides dense, temporally grounded, and causally explicit reasoning chains. Based on DAR, we formally define three challenging tasks: affective segmentation, fine-grained emotion classification, and affective reasoning. Complementing this benchmark, we propose DAR-R1, a two-stage framework that combines supervised fine-tuning with Group Relative Policy Optimization. Experiments across 10+ MLLMs show that DAR-R1 sets a new state-of-the-art for dynamic affective reasoning, in terms of both emotional localization and affective reasoning. Project page: https://github.com/Zhang-Zhiyan/DAR. --- ### CoSAG: Compact Semantic Anchor Gaussians via Training-Free Rate-Distortion Coding Authors: Yuang Jia, Jinlong Wang, Junhong Lin, Ruiting Dai, Wei Gao Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10237v1 Open-vocabulary 3D scene understanding is commonly achieved by embedding 2D vision-language features such as CLIP into a 3D Gaussian Splatting scene, turning it into a text-queryable semantic field. However, attaching a high-dimensional feature to each of millions of Gaussians inflates a single scene to gigabytes, which makes storage and deployment the real bottleneck of these fields. Existing compact methods each learn and ship a per-scene codec, an autoencoder, a quantized codebook, or a distilled feature field, entangling field construction with field storage and never compressing the per-Gaussian assignment that holds the bulk of the cost. We argue that construction and storage should be decoupled, and that storage is a rate-distortion problem over the per-Gaussian binding to a small anchor table, a structure no prior open-vocabulary method compresses. We present CoSAG, which constructs the field without any per-scene training through a closed-form transmittance-weighted lift, spatially grounded semantic anchors, and multi-view denoising, and stores it with a spatially predictive entropy coder that ships no decoder. Because the anchors are spatially grounded, the binding is predictable and therefore highly compressible. The transmittance-weighted lift and multi-view denoising yield a clean, view-consistent assignment, so the entropy coder spends almost no rate on correcting noise and instead codes only the residual against its spatial prediction. CoSAG reaches sub-megabyte storage while matching or exceeding the state of the art across the 2D-rendered, 3D-selection, and dense-LSeg protocols, reducing field size by 37 to 76x relative to LangSplatV2 at higher accuracy. --- ### Consensus vs. Dissent: Dynamic LLM Modeling of Subjective Preferences in Group Recommenders Authors: Cedric Waterschoot, Nava Tintarev, Francesco Barile Published: 2026-07-11 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2607.10235v1 Previous work in group recommender systems has demonstrated a sensitivity to the distribution of preferences within a group. Specifically, the selection of the preference aggregation strategy benefits from considering such group configurations. In this paper, we study whether LLMs are able to mimic this sensitivity and to select the ideal aggregation strategy (and corresponding recommendation) according to nuanced human perceptions of fairness, satisfaction, and consensus. We do this by fine-tuning Large Language Models (LLMs) on human survey data to serve as real-time judgmental models within the recommendation pipeline. Using a reasoning dataset distilled from DeepSeek-V3.1 and human ground truth assessments, we develop Judgmental Llama and Judgmental OLMo to simulate group assessments. Our pipeline successfully generates multiple recommendation candidates based on social choice-based aggregation strategies and dynamically selects the one that maximizes these predicted human-like evaluations. We further validate these suggestions in a user study (n=284) and find that our methodology achieved the highest scores for satisfaction and group consensus. Furthermore, we find that LLM judgments are most aligned with human perceptions of fairness, satisfaction and consensus when we also consider interaction effects between our LLM-based method and group configuration (e.g., minority or coalition). These findings give further support for dynamically adapting aggregation strategies to specific within-group preference distributions, and highlight the advantage of using LLMs for an adaptation that is aligned with subjective human judgments. --- ### MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck Authors: Fan Bu, Rongfeng Li, Linfeng Fan Published: 2026-07-11 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2607.10233v1 Melody skeleton extraction aims to derive a shorter melody that preserves structural notes while removing ornaments. Prior methods rely on hand-crafted reduction rules or note-wise salience classifiers trained with heuristically or procedurally generated pseudo-labels. Such supervision can inherit generator bias and does not explicitly optimize a coherent reduced melody. We introduce MeloBottleneck, a self-supervised framework that represents a skeleton as a length-controlled, order-preserving latent subsequence. A hard-bottleneck extractor selects note events, a rhythmic-closure operator produces a self-consistent skeleton, and a re-ornamentation decoder reconstructs the input melody. Training combines reconstruction, a frozen autoregressive melody prior, ornament-invariant consistency across procedurally ornamented views, and ornament exclusion. We evaluate three regimes: synthetic out-of-distribution ornament-to-skeleton, TAVERN variation-to-theme, and Jiugong ornamented-to-gongche. A matched pseudo-label classifier excels on the synthetic benchmark, while MeloBottleneck transfers better, achieving competitive selection quality on TAVERN and Jiugong. Skeletonized melodies also improve BM25-based fragment retrieval, boosting Recall@K and MRR while reducing query time. Overall, the results suggest that learning skeletons as latent subsequences yields more robust transfer than pseudo-label imitation. --- ### PhenoEmbed: Self-Supervised Multispectral UAV Time-Series Embeddings for Individual Tree Crown Phenology Authors: Taimur Khan Published: 2026-07-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.10231v1 Tree crowns are a challenging target for resilient AI because they are not static objects: their spectral response, internal texture, translucency, and apparent boundaries change substantially across the growing season. We develop PhenoEmbed, a self-supervised crown-centric temporal embedding model trained with contrastive and masked reconstruction objectives on HeideBench, an 18-date UAV multispectral time-series benchmark for forest crown phenology in D{ö}lauer Heide. The model treats seasonal crown dynamics as phenological appearance change driven by leaf emergence, canopy closure, senescence, and leaf-off conditions. Segmented tree crown polygons are retained as object anchors to extract aligned crown-centered crops through time, allowing one 256-dimensional vector summarizing seasonal crown appearance to be learned per tree. On 5,885 crop-safe crowns, the exported embeddings show structured low-dimensional organization, with the first two principal components explaining 25.1\% of variance and nearest-neighbor retrieval producing a median top-1 cosine similarity of 0.946. Compared with handcrafted temporal features and a learned mean-pooling baseline, PhenoEmbed yields substantially more compact nearest-neighbor structure, while ablations show that the contrastive loss, masked reconstruction loss, and explicit seasonal time features each affect the structure of the learned embedding space. These results support PhenoEmbed as a reusable forest crown representation learner and motivate future downstream tests of whether such features improve tree-level models under seasonal change. --- ### When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control Authors: Daming Luo Published: 2026-07-11 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.10226v1 We evaluate when sparse autoencoder (SAE) features act as localized control handles for safety-relevant behavior. This question is difficult because apparent success can arise from weak interventions, mismatched baselines, model robustness, or degenerate outputs that automated safety judges mark as unsafe without representing meaningful harmful compliance. We introduce a matched coherence-gated evaluation protocol for runtime safety interventions: methods are compared at matched target-effect points, and the primary target metric counts harmful compliance only when an output is both judge-unsafe and coherent. Applying this protocol to three prompt splits on Gemma-2-9B-it with a Gemma Scope layer-20 residual SAE, we find that SAE feature ablation has a narrow useful regime. SAE top800 reaches a low-to-mid target effect with lower total perturbation and competitive utility, but SAE top1600 loses utility relative to a matched dense refusal-direction baseline, and SAE top3200 primarily induces coherence collapse. Human audit confirms that coherence gating removes unsafe-only artifacts, and feature diagnostics show that the useful regime is driven by a stable head of refusal-aligned features whose activation separation decays rapidly with rank. These results argue that SAE-based safety interventions should be evaluated as regime-dependent control mechanisms rather than assumed to be uniformly localized. --- ### ScratNet: A Swin-Based Multi-Scale Dilated Network with Precision Refinement for Semiconductor Scratch Segmentation Authors: Sachin Ranjan, Hoon Kim Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10214v1 Surface scratch defects in semiconductor manufacturing pose significant challenges due to their irregular shapes, low contrast, and varying scales. Traditional inspection methods often struggle to detect such defects reliably, especially in complex imaging scenarios. While deep learning approaches based on Convolutional Neural Networks (CNNs) have improved accuracy, they often fail to capture fine-grained edge details. To address these limitations, we propose ScratNet, a novel end-to-end scratch segmentation framework that integrates a modified Swin Transformer backbone with a tailored decoder. The decoder incorporates a Multi-Scale Dilated Aggregation (MDA) module to capture both local and global context, a Stem Integration Module (SIM) to restore spatial detail, and a Precision Refinement (PR) branch that enhances boundary sharpness using anisotropic convolutions. Through this stage-adaptive feature aggregation and boundary-aware refinement, ScratNet achieves superior accuracy on thin and irregular defects. Extensive experiments demonstrate that ScratNet consistently outperforms existing methods, providing a scalable and robust solution for automated scratch inspection in high-precision manufacturing. --- ### KGCQual: An Interpretable Framework for Evaluating the Knowledge Graph Construction Quality from Text Authors: Nipun Misra, Vikranth Udandarao, Aanchal Gupta, Yogender Kumar, Manuj Mukherjee, Raghava Mutharaju Published: 2026-07-11 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.10212v1 Knowledge Graphs (KGs) are increasingly constructed through automated extraction pipelines; however, such systems often introduce spurious or incomplete triples, which degrade downstream performance. Existing evaluation practices rely heavily on task-specific metrics or small-scale manual verification, offering limited insight into the structural and semantic fidelity of extracted graphs. We propose a novel, interpretable metric for intrinsic KG quality assessment that measures how closely an automatically extracted graph approximates an "ideal" graph capturing the key noun phrases, predicate relations, and basic linguistic phenomena such as negation expressed in the source text. Our framework integrates two complementary components: (1) an entity-level assessment that evaluates completeness, resolution quality, and connectivity, and (2) a relation-level assessment that judges predicate preservation and multiplicity using lexical similarity, dependency-parse alignment, and light-weight negation handling to ensure semantic faithfulness. We evaluate our metric across multiple state-of-the-art triple extraction systems and datasets, including WebNLG, TinyButMighty, and BenchIE, demonstrating that it reliably identifies omissions, redundancy, and structural deviations that existing metrics overlook. Our work offers a scalable, model-agnostic, and interpretable framework for comparing automated KG construction methods and provides a foundation for standardised evaluation. We further validate the metric through an ablation study isolating noun and verb components, and a downstream evaluation showing that KGCQual scores correlate significantly with link prediction performance on the same extracted KGs. The code repository is available at https://github.com/kracr/kg-quality-metric. --- ### Toward Stronger Code Watermarking: A Grammar-Driven Approach to Optimizing the Trade-off Between Quality and Detectability Authors: Licheng Yu, Aiwei Liu, Songze Li Published: 2026-07-11 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2607.10210v1 With the rapid development of Large Language Models (LLMs), text watermarking has emerged as a crucial technique for identifying machine-generated content. However, directly applying existing logits-based watermarking methods to code generation remains challenging, since the low-entropy nature of code exacerbates the trade-off between code quality and watermark detectability. In this paper, we propose a novel code watermarking approach called Grammar-Driven Watermark (GDW) for LLMs. GDW preserves syntactic validity through a grammar-guided three-level masking mechanism and injects watermark signals via structural role-aware modulation, assigning a stronger bias to content-bearing tokens while applying a more conservative bias to syntax-critical tokens. Aligning with the generation process, we further design a role-aware weighted detection statistic to improve detectability. Experiments across multiple programming languages, models, and decoding strategies show that GDW establishes a stronger quality-detectability trade-off frontier than existing methods, while maintaining robustness against variable-renaming attacks. --- ### Exploratory Analysis of Deep Learning Models for Forecasting Meteorological Parameters in the Agricultural Sector Authors: Piotr Sikora, Sotirios Kontogiannis Published: 2026-07-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.10208v1 Accurate meteorological forecasting is essential for agricultural planning, irrigation management, and environmental decision support. This study conducts a comparative evaluation of recurrent and hybrid deep learning architectures for multivariate forecasting of reference evapotranspiration ($ET_0$), vapour pressure deficit (VPD), wind speed, and the sine and cosine components of wind direction. The analysis utilizes 134,376 hourly observations from Ioannina, Greece, spanning January 2011 to April 2026, sourced from ERA5 via the OpenMeteo Historical Weather API. Single and multi-layer GRU and LSTM networks are compared with hybrid 1D-CNN-GRU and 1D-CNN-LSTM models for two forecasting tasks: a 24-hour next-day forecast and a 168-hour week-ahead forecast. Performance is evaluated using normalized root mean squared error, the coefficient of determination, and a composite Weighted Quotient Score (WQS). The most effective purely recurrent models are a 64-unit LSTM for the 24-hour horizon, with a WQS of 0.816755, and a 1024-unit GRU for the 168-hour horizon, with a WQS of 0.779465. The hybrid CNN-GRU models achieved the highest overall scores of 0.827535 and 0.782863 for the 24-hour and 168-hour horizons, but with additionally more number of units respectively to LSTM models, while the CNN-LSTM models yield nearly identical results with substantially fewer parameters. Compared to the corresponding recurrent baselines, the hybrid models improve WQS by 1.22--1.63\% at 24 hours and by 0.44--0.45\% at 168 hours, indicating that convolutional feature extraction is more beneficial for short-term forecasting. --- ### How much Data do We Need? Sequential Data Collection for Stochastic Programming Authors: Xin Li, Juergen Branke, Xuan Vinh Doan Published: 2026-07-11 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2607.10207v1 Data-driven optimization often requires collecting data to estimate uncertain model parameters before solving the underlying decision problem. In practice, however, data acquisition may incur non-negligible costs, making it critical to determine when to stop additional data collection. In this paper, we study an optimal stopping problem for sequential data collection in stochastic optimization under parameter uncertainty. We propose a benefit-driven stopping framework that balances information gain and sampling cost. We model the unknown distribution parameter within a Bayesian learning framework and update beliefs sequentially as new observations are collected. At each iteration, the decision maker evaluates the expected marginal benefit of additional data relative to the unit sampling cost and determines whether to continue sampling or stop and implement the optimization decision. Based on this framework, we develop several stopping policies. The proposed policies are evaluated through a newsvendor problem with exponentially distributed demand. Numerical experiments compare the policies with fixed-budget and hindsight benchmark strategies. The results show that benefit-driven stopping rules can substantially reduce unnecessary data collection while achieving near-optimal decision performance, demonstrating the effectiveness of adaptive stopping in data-driven optimization. --- ### Source-Lifted Flow Matching for Intervenable Multimodal Imitation Authors: He Zhang, Ying Sun, Ziyang Chen, Qicheng Luo, Yiren Zhao, Weiyu Guo, Pengteng Li, Yandong Guo, Hui Xiong Published: 2026-07-11 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.10206v2 Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity is largely passive: repeated sampling may yield diverse behaviors, but users cannot directly choose among valid continuations from the same state. We propose Source-Lifted Flow Matching (SL-FM), a source-intervenable flow-matching policy that exposes such a handle while keeping the velocity field shared and latent-free (without a separate discrete-handle input). The handle selects only the source endpoint of the conditional flow, not a mode-specific field, preserving the standard formulation while avoiding decomposition into separate mode-conditioned dynamics. The core mechanism is Orthogonal Source Lifting, designed to prevent path-crossing ambiguity. Instead of partitioning target actions by mode, SL-FM lifts handle-specific sources into auxiliary orthogonal coordinates and keeps targets in the original action subspace. This preserves the demonstrated action distribution while allowing one shared field to carry different branches without merging at crossings. To keep handles usable across states, we learn a state-dependent source mixture end to end and use a responsibility floor, giving each handle weak supervision and mitigating dead modes. Experiments on crossing-flow diagnostics and robot-control benchmarks show that SL-FM converts passive source randomness into an actionable intervention variable. It removes crossing-induced composite trajectories, changes future routes in 91.1% of matched-prefix interventions, and achieves strong free-deployment performance, with improvements in several benchmark settings. Overall, source geometry provides actionable multimodal control without conditioning the velocity field on the selected mode. --- ### Source-Lifted Flow Matching for Intervenable Multimodal Imitation Authors: He Zhang, Ying Sun, Pengteng Li, Ziyang Chen, Yiren Zhao, Ziyang Rao, Weiyu Guo, Yandong Guo, Hui Xiong Published: 2026-07-11 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.10206v1 Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity is largely passive: repeated sampling may yield diverse behaviors, but users cannot directly choose among valid continuations from the same state. We propose Source-Lifted Flow Matching (SL-FM), a source-intervenable flow-matching policy that exposes such a handle while keeping the velocity field shared and latent-free. The handle selects only the source endpoint of the conditional flow, not a mode-specific field, preserving the standard formulation while avoiding decomposition into separate mode-conditioned dynamics. The core mechanism is \textbf{Orthogonal Source Lifting}, designed to prevent path-crossing ambiguity. Instead of partitioning target actions by mode, SL-FM lifts handle-specific sources into auxiliary orthogonal coordinates and keeps targets in the original action subspace. This preserves the demonstrated action distribution while allowing one shared field to carry different branches without merging at crossings. To keep handles usable across states, we learn a state-dependent source mixture end to end and use a responsibility floor, giving each handle weak supervision and mitigating dead modes. Experiments on crossing-flow diagnostics and robot-control benchmarks show that SL-FM converts passive source randomness into an actionable intervention variable. It removes crossing-induced composite trajectories, changes future routes in 91.1\% of matched-prefix interventions, and achieves strong free-deployment performance, with improvements in several benchmark settings. Overall, source geometry provides actionable multimodal control without conditioning the velocity field on the selected mode. --- ### Adaptive Compute in Latent World Models: When Depth Helps, Hurts, or Doesn't Matter Authors: Achyuthan Sivasankar Published: 2026-07-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.10203v3 Adaptive compute for world models -- early-exit or mixture-of-depths predictors that spend variable depth per rollout step -- presumes that extra depth buys better predictions. In autoregressive rollouts, where planning actually happens, that premise requires depth's per-step precision to survive composition. We test it directly with one pre-registered instrument, the shallow penalty rho = err(shallowest-exit rollout)/err(full-depth rollout), on nine DeepMind Control tasks under matched single-step (K=1) and multi-step (K=4) training, eight seeds each. Three regimes emerge: depth helps (intrinsic, 6/9 tasks, rho up to 8x), depth actively hurts (inversion, 2/9, rho down to 0.87x), or depth barely matters (flat). The inversion is created by training, not the dynamics: supervising early exits only at the first rollout step erases it (Delta=+0.28, n=8, non-overlapping distributions) -- a routability catch-22: the per-step deep supervision that makes exits routable also trains them to out-roll the full stack. The regime is predictable: a frozen dimensionality-only classifier, committed before training, labels held-out tasks correctly out-of-sample, including an extreme extrapolation. The inversion reproduces under a transformer predictor, yet its manifestation is configuration-dependent, shifting with metric space, horizon, encoder, backbone, and -- most strongly -- training data: on the two tasks we retrained, competent-policy data removes both the inversion and the intrinsic tradeoff, loss unchanged. In a CEM planner, rho predicts whether planning benefits from depth. Every threshold and gate was committed before the corresponding compute, including a pre-registered negative for the motivating hypothesis. Whether more compute helps a world model is not a task property; it is a property of the operating configuration, with a stable, predictable, mechanism-backed core. --- ### When Counterbalancing Hides the Bias: Access-Conditioned Position Lock in Forced-Choice LLM Evaluation Authors: Hong-In Won, Jinseok Jang, Hyoseop Kim Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10202v2 Forced-choice probes with counterbalanced orientations are a standard tool for measuring language-model "value dispositions," and a concentration/extremity index over repeated draws is read as how sharply a model commits. We show this estimator is not identifiable at its low end: counterbalancing, meant to remove position bias, instead maps a position-lock (a model returning the same answer letter regardless of content) onto the same near-0.5 signature as genuine neutrality, so "softness" and "non-engagement" cannot be distinguished from a content-independent letter-bias. Across nine models the fraction of position-locked items tracks the index almost perfectly (r=-0.986) - a structural consequence, not a finding: the informative quantity is the residual from that bound, the commitment a model shows on the items it does engage. The three models the index reads as soft are the most position-locked, and the lock resolves under access configurations that permit reasoning (as-deployed CLI -> raw API -> reasoning-enabled), moving the index 0.06->0.63 and 0.34->0.66->0.64 while lock collapses (Opus: 0.61->0.39->0.22); this establishes the low readings as an identifiability failure, not a disposition. The reasoning-enabled reading is not a "true" value either; the point is that the index alone cannot identify commitment at its low end. Access configuration (deployment client, reasoning on/off) is one generator of this failure, shown on two access paths (an Anthropic subscription CLI and a DeepSeek client), and in a frozen benchmark it is confounded with provider. We contribute a position-lock diagnostic that must accompany any concentration reading, and show that a concentration-blind audit risks reporting neutrality where a reasoning-permitting condition yields concentrated choices. The direction-flip component, largely robust to the artifact, still identifies genuine cross-model disagreement. --- ### Two Confounds in Cross-Model Value Comparison: Response Determinism and the Access Harness Authors: Hong-In Won, Jinseok Jang, Hyoseop Kim Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10202v1 Cross-model comparisons read divergence in value dispositions as evidence that language models hold individuated values. Under single-draw measurement this conflates two quantities: a difference in central tendency (a genuine value difference) and a difference in response determinism (how sharply a model commits to a forced choice). We introduce a separation protocol -- no-rule value dilemmas with counterbalanced, repeated forced-choice measurement and a determinism index -- and a determinism-corrected decomposition that splits an apparent cross-model distance into a direction-flip component (genuine disagreement) and a same-side-more-extreme component we label determinism. Across nine models, determinism varies substantially (0.66-0.95 among engaging models); whether it is a per-model trait or tracks provider and scale is a question our method makes measurable but our sample leaves open. Correcting for determinism shrinks apparent individuation, while a few cross-family disagreements survive a strict test. We then isolate a second confound: the access harness serving each model. Re-collecting the same models through raw provider APIs, we find the deployment client shifts a model's value profile substantially and client-specifically: one subscription CLI moves a profile by 0.31, flips four of eighteen items, and inflates the flagship's apparent softness (0.34 via CLI vs 0.66 via raw API), whereas another provider's client is clean, confounding provider family with access client. The harness is a value-shaping layer: a base model that refuses one-in-ten forced choices is made compliant by an agent system prompt, established causally in a white-box control. An audit ranking models by single-draw value distance thus ranks a determinism-inflated quantity, confounded further by the client used. We contribute the decomposition and identify the deployment harness as a distinct value confound. --- ### Comparing Socially-Equitable Renewable Energy Budget Allocation MDP Policies in Mature and Emerging Economies Authors: Riya Kinnarkar, Mansur M. Arief, Yan Pratama Akhra, Dino Arla Published: 2026-07-11 Categories: eess.SY, cs.AI, math.OC arXiv: https://arxiv.org/abs/2607.10201v1 Equitable renewable-energy planning is a sequential decision problem, but the decision variables available to a public planner differ sharply between mature and emerging economies. In the former the government largely builds generation, while in the latter it steers private investment through incentives and quotas. We formulate socially-equitable renewable-energy budget allocation as a Markov Decision Process (MDP) and, using a single problem-agnostic solver interface, compare the same policies across the two settings: eight U.S. cities (a mature economy) and West Java, Indonesia (an emerging economy). The results show that across both settings, a receding-horizon value-iteration policy dominates. In the U.S., it reaches 66% renewable penetration while cutting the underserved low-income population by 96% versus a random baseline. In West Java it closes the low-access gap while crowding in the most private capital. More interestingly, a naive market-chasing heuristic, which is mildly sub-optimal in the U.S., could yield catastrophic outcomes in Indonesia, by underserving every low-access region, because chasing attractive markets and serving the underserved goals diverge once the planner acts through private developers. --- ### The Differential Neural Tangent Kernel and Its Positivity Authors: Bangti Jin, Longjun Wu Published: 2026-07-11 Categories: cs.LG, math.NA, stat.ML arXiv: https://arxiv.org/abs/2607.10200v1 The Neural Tangent Kernel (NTK) is one powerful tool for analyzing the training dynamics of neural networks in the over-parameterized regime. Recently, the theoretical framework has been extended to physics-informed neural networks (PINNs) for solving linear PDEs, one highly popular class of neural PDE solvers. In the analysis, the positivity of the associated NTK plays a fundamental role. However, establishing the positivity of the NTK for PINNs is highly challenging, due to the presence of multiple differential operators. In this work, we propose a new theoretical framework, called Differential Neural Tangent Kernel (DNTK), for analyzing PINNs through the lens of the NTK, and establish the positivity of the infinite width DNTK for both shallow and deep neural networks for a wide class of activation functions, including RePU and smooth but non-polynomial activations, for all linear differential operators. These theoretical results lay the foundation for the analysis of gradient type algorithms for training PINNs. --- ### Similar Accuracy, Unequal Evidence: Search APIs as Decision Surfaces for Tool-Using Agents Authors: Sriram Selvam, Anneswa Ghosh Published: 2026-07-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.10198v2 Search APIs expose ranked snippets, URLs, and metadata on which agents decide whether to answer, search again, or fetch pages. We evaluate these interfaces as decision surfaces on a fixed sample of 100 questions from the 254-question SealQA-Hard subset, using one frozen GPT-5.4 agent, a fixed orchestration harness, and a shared page-fetch backend across Brave, Tavily, and Firecrawl. A Kimi-K2.6 oracle labels visible URL-level evidence; a separate answer audit yields 25, 25, and 26 correct answers out of 100. These counts indicate similar observed accuracy but do not establish equivalence. Under the tested configurations, Brave exposes more pre-fetch support alongside a larger snippet surface; Tavily has a larger rank-1 share among trajectory-pooled supporting observations; and Firecrawl is associated with broader exploration. First-search query-level metrics distinguish support availability from ranking, while contradiction exposure complements contradiction-to-gold ratios. A retrospective oracle union covers 44/100 questions, versus 26/100 for the best individual provider: 18 percentage points of headroom. The observed evidence and action differences motivate evaluating search APIs jointly with agent policy and retrieval budget. ---