Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
Nature (Science) 2026-06-17

A 98-qubit trapped-ion quantum computer with all-to-all connectivity

Quantum computers require both high-fidelity operations and large qubit numbers to surpass classical capabilities1. Trapped-ion platforms have demonstrated the highest gate fidelities of any modality2–6 but scaling to larger qubit numbers while preserving performance has remained a central challenge. We report on Quantinuum Helios, a 98-qubit trapped-ion quantum processor based on the quantum charge-coupled device (QCCD) architecture7. Helios features 137Ba+ hyperfine qubits8,9, all-to-all connectivity enabled by a rotatable ion storage ring connecting two quantum operation regions by a junction10,11, speed improvements from parallelized operations12 and a new software stack with real-time compilation of dynamic programs13. Averaged over all operational zones in the system, we achieve average infidelities of 2.5(1) × 10−5 for single-qubit (1Q) gates, 7.9(2) × 10−4 for two-qubit (2Q) gates and 3.3(5) × 10−4 for state preparation and measurement (SPAM), none of which are fundamentally limited and probably able to be improved. These component infidelities are predictive of system-level performance in both random Clifford circuits and random circuit sampling (RCS), the latter demonstrating that Helios operates well beyond the reach of classical simulation and establishes a new frontier of fidelity and complexity for quantum computers14. A new quantum computer, Quantinuum Helios, which is a 98-qubit trapped-ion quantum processor built on the QCCD architecture, demonstrates performance well beyond classical capabilities and provides a path for scaling up quantum computing.

02.
arXiv (CS.AI) 2026-06-18

An In-depth Study of LLM Contributions to the Bin Packing Problem

arXiv:2510.27353v2 Announce Type: replace Abstract: Recent studies have suggested that Large Language Models (LLMs) could provide interesting ideas contributing to mathematical discovery. This claim was motivated by reports that LLM-based genetic algorithms produced heuristics offering new insights into the online bin packing problem under uniform and Weibull distributions. In this work, we reassess this claim through a detailed analysis of the heuristics produced by LLMs, examining both their behavior and interpretability. Despite being human-readable, these heuristics remain largely opaque even to domain experts. Building on this analysis, we propose a new class of algorithms tailored to these specific bin packing instances. The derived algorithms are significantly simpler, more efficient, more interpretable, and more generalizable, suggesting that the considered instances are themselves relatively simple. We then discuss the limitations of the claim regarding LLMs' contribution to this problem, which appears to rest on the mistaken assumption that the instances had previously been studied. Our findings instead emphasize the need for rigorous validation and contextualization when assessing the scientific value of LLM-generated outputs.

03.
arXiv (CS.AI) 2026-06-19

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

arXiv:2510.21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However, the RLVR recipe introduces a significant risk of capability regression, in which models forget foundational skills after prolonged training without employing regularization strategies. We empirically confirm this concern, observing that open-source reasoning models suffer performance degradation on core capabilities such as perception and faithfulness. While imposing regularization terms like KL divergence can help prevent deviation from the base model, these terms are computed on the current task and therefore do not guarantee preservation of broader knowledge. Meanwhile, commonly used experience replay across heterogeneous domains makes it nontrivial to decide how much training emphasis each objective should receive. To address this, we propose RECAP-a replay strategy with dynamic objective reweighting for general knowledge preservation. Our reweighting mechanism adapts online using short-horizon signals of convergence and instability, shifting the post-training focus away from saturated objectives and toward underperforming or volatile ones. Our method is end-to-end and readily applicable to existing RLVR pipelines without training additional models or heavy tuning. Extensive experiments on benchmarks using Qwen2.5-VL-3B and Qwen2.5-VL-7B demonstrate the effectiveness of our method, which not only preserves general capabilities but also improves reasoning by enabling more flexible trade-offs among in-task rewards.

04.
arXiv (quant-ph) 2026-06-17

Optimal Calibration of Quantum Network Links

arXiv:2606.18167v1 Announce Type: new Abstract: The reliable distribution of entanglement is essential for the effective operation of quantum networks. Due to fundamental differences between quantum and classical communication systems, it is necessary to develop specialised algorithms and protocols that also account for quantum-specific constraints. In this work, we focus on the issue of recalibration. As suggested by recent experimental studies, the process of local entanglement generation in a quantum link degrades over time due to environmental changes that have to be estimated and compensated via a calibration operation, during which the link is not available. Therefore, in such a quantum network, every link alternates between an activation period, during which it operates normally, and a calibration period, during which it cannot participate in the end-to-end entanglement distribution, thereby creating a trade-off between link quality (the fidelity of generated pairs, which decays during activation) and availability (the fraction of time the link is usable, which calibration reduces). We develop analytically a protocol for optimally assigning activation periods to each link in linear quantum repeater chains, subject to any general end-to-end fidelity requirements and local initial fidelity thresholds. Building on this foundation, we extend to general quantum networks, where multiple paths may cross at common links, proposing a heuristic approach evaluated in simulations and compared with a benchmark, numerical approach, and theoretical bounds.

05.
arXiv (CS.LG) 2026-06-15

Ensembling Sparse Autoencoders

arXiv:2505.16077v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that a single SAE captures only a limited subset of features that can be extracted from the activation space. Motivated by this limitation, we introduce and formalize SAE ensembles. Furthermore, we propose to ensemble multiple SAEs through naive bagging and boosting. In naive bagging, SAEs trained with different weight initializations are ensembled, whereas in boosting SAEs sequentially trained to minimize the residual error are ensembled. Theoretically, naive bagging and boosting are justified as approaches to reduce reconstruction error. Empirically, we evaluate our ensemble approaches with three settings of language models and SAE architectures. Our empirical results demonstrate that, compared to an expanded SAE that matches the number of features in the ensemble, ensembling SAEs improves the reconstruction of language model activations along with SAE stability. Additionally, on downstream tasks such as concept detection and spurious correlation removal, SAE ensembles achieve better performance, showing improved practical utility.

06.
arXiv (CS.CV) 2026-06-24

Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image

Generating explicit 3D city assets from a single satellite image is important for digital twins, urban simulation, and geospatial intelligence. Unlike satellite-to-street-view synthesis, the task requires a reusable textured mesh with plausible geometry and controllable appearance rather than a 3D proxy optimized only for rendering a small set of images or videos. The ICCV Sat2City framework made a first step by conditioning cascaded sparse-voxel latent diffusion on satellite-derived height maps, but its appearance was random, its training data were synthetic, and its task-specific VAE did not scale well to noisy real-world reconstructions. We present Sat2City v2, a journal extension that adapts a pretrained native structured-latent 3D foundation model to weakly aligned satellite images and textured meshes. We build a real-world dataset with 16,241 satellite-mesh pairs across 24 regions in 9 cities. Instead of learning a 3D representation from noisy city meshes, Sat2City v2 encodes each mesh into a pretrained native 3D latent space, fine-tunes a satellite-conditioned geometry flow, and uses the decoded shape to anchor satellite-conditioned texturing. This retains Sat2City's geometry-to-appearance cascade while enabling appearance-controllable generation from the satellite input. Experiments on metric-scale DSM reconstruction and generative city-asset benchmarks for geometry and appearance show that Sat2City v2 achieves the best overall performance among evaluated baselines. Overall, Sat2City v2 advances satellite-to-city generation from rendering-oriented 3D proxies to explicit textured mesh assets, supported by, to the best of our knowledge, the first documented satellite-mesh paired dataset collected from matched geographic crops for this asset-level task. Project page: https://ai4city-hkust.github.io/Sat2City-v2/

07.
arXiv (CS.CV) 2026-06-17

High-Fidelity 3D Geometric Reconstruction of Pelvic Organs from MRI: A Hybrid Deep Learning and Iterative Optimization Approach

Patient-specific 3D reconstruction of pelvic organ geometry from MRI is important for pelvic floor modeling and downstream patient-specific analysis. However, while previous studies have focused primarily on either image segmentation or downstream use of 3D models, the reconstruction of high-fidelity, high-quality geometries remains labor-intensive and poorly standardized. The study introduced a hybrid deformable shape modeling framework that integrates deep learning prediction with iterative optimization for the reconstruction of the bladder, uterus, and rectum. The framework consists of three core components: a geometry-aware multi-level deep learning architecture that preserves topological consistency of pelvic organs; a two-stage amortized optimization training strategy that balances global shape capture and local surface refinement; and a holistic synergy mechanism–where iterative optimization provides supervision for deep learning during the training phase, and during inference, deep learning rapidly predicts the global organ morphology, followed by iterative optimization to refine local surfaces and mesh quality. This framework demonstrated marked superiority in geometric fidelity than current mainstream deep learning-based organ reconstruction models. For individual anatomical structures, the reconstructed 3D geometries for the bladder, rectum, and uterus achieved significantly lower Chamfer Distance values and higher Dice Similarity Coefficient scores. In addition, while maintaining high computational efficiency, the proposed architecture yielded superior overall volumetric mesh quality. At the patient level, the framework achieved higher mean values for the 10 worst elements for both minSICN and minSIGE compared to traditional geometric post-processing algorithms.

08.
medRxiv (Medicine) 2026-06-15

Diabetes and the Life-Course: Evidence from Panel Data and Electronic Health Records

Incidence of type 2 diabetes is increasing at ages when education, work, family, and financial transitions are taking place, yet we lack robust evidence of whether earlier treatment changes life-course outcomes and over which time span this takes place. This paper uses the medical cutoff for diabetes diagnosis (HbA1c of 6.5 percent) as a natural experiment to study the effects of diabetes treatment using electronic health records (EHR) and panel data. This paper has three main findings. First, using EHR data, we find that there is a sharp increase in the probability of both diagnosis of diabetes and prescription when the HbA1c equals 6.5 percent. Second, we find that treating diabetes reduces HbA1c levels, weight, BMI, and blood pressure and increases the amount of care received, proxied by the number of HbA1c tests. Both the diagnosis and a prescription are independently able to produce positive changes in metabolic health, although a prescription is more effective in this regard. Third, we conclude that treating diabetes does not have a significant effect on life-course outcomes for a cohort of young Americans aged 24-32, although it does result in a reduction in HbA1c levels that are seen even eight years after the intervention. Taken together, these findings suggest that receiving a diagnosis and prescription are both effective treatments for diabetes, but they do not translate to significant alterations in the lives of young adults in the medium-term.

09.
arXiv (CS.CV) 2026-06-19

Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection

Pose-flow video anomaly detectors are attractive for one-class surveillance because they provide likelihood-based rankings for tracked skeleton windows. However, a single likelihood score may hide multimodal normal behavior and be sensitive to pose-observation noise. We study a frozen-detector setting in which the pose-flow backbone, cached skeleton tracks, and evaluation pipeline are fixed. Reliability-Aware Prototype Calibration (RPC) is a post-hoc score calibration method for this setting. It adds a standardized nearest-prototype deviation in the frozen latent space to the standardized flow score, and uses keypoint confidence only to gate this added geometric evidence. Thus, RPC preserves the original density signal while correcting the ranking with empirical normal-mode structure under pose reliability. Across two frozen pose-flow backbones and four datasets, RPC improves frame-level AUROC in all eight backbone-dataset pairs, with gains ranging from 0.34 to 4.49 percentage points and averaging 2.03 points. Ablation and reliability analyses show that prototype deviation is the main corrective signal, while reliability gating is most useful when pose observations are less trustworthy. These results suggest that lightweight post-hoc calibration can strengthen cached pose-flow systems when retraining or reproducing the full pose pipeline is impractical.

10.
arXiv (CS.AI) 2026-06-17

Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation

arXiv:2606.17459v1 Announce Type: new Abstract: Evaluating the decision-making capabilities of large language models (LLMs) is a growing research priority, yet existing benchmarks focus on isolated cognitive tasks such as reasoning, knowledge retrieval, and economic rationality in stylized settings. These evaluations overlook the defining challenge of real executive decision-making: integrating conflicting recommendations from specialized stakeholders under information asymmetry, organizational constraints, and temporal dependencies. We introduce \textsc{CEO-Bench}, a multi-agent benchmark that evaluates LLMs on CEO-level strategic resource reallocation – the process of redirecting capital across business units in a multi-round, constraint-rich organizational environment. In \textsc{CEO-Bench}, LLM agents receive conflicting advice from four role-conditioned C-suite advisors (CFO, CTO, COO, CMO), each with private signals and distinct priorities, and must synthesize these into a concrete allocation plan evaluated along four dimensions: role integration, conditional boldness, history-sensitive judgment, and plan validity. Experiments across five frontier models on 13 scenarios reveal that all models achieve high structural validity but diverge sharply on strategic calibration – the hardest capability layer. We identify systematic failure modes including single-advisor capture, conservative default under ambiguity, and historical amnesia, and uncover a structural integration-boldness tradeoff: models that engage more deeply with conflicting perspectives tend to produce less decisive action. These findings delineate the current capability boundary of LLMs as organizational decision-makers and inform the design of future AI-assisted executive systems.

11.
medRxiv (Medicine) 2026-06-15

Routine use of oral iron for people with heart failure and iron deficiency in primary care; retrospective cohort study

Aims: Iron deficiency is common among people with heart failure and associated with morbidity and mortality. While intravenous iron improves clinical outcomes, oral iron continues to be prescribed in routine practice despite limited evidence of benefit. Methods: We completed a retrospective primary care cohort study (2016 to 2021) to investigate the proportion of people with an incident diagnosis of heart failure who had iron deficiency identified (defined as ferritin

12.
arXiv (CS.CV) 2026-06-24

Segmentation and Classification of Pap Smear Images for Cervical Cancer Detection Using Deep Learning

Cervical cancer remains a significant global health concern and a leading cause of cancer-related deaths among women. Early detection through Pap smear tests is essential to reduce mortality rates; however, the manual examination is time consuming and prone to human error. This study proposes a deep learning framework that integrates U-Net for segmentation and a classification model to enhance diagnostic performance. The Herlev Pap Smear Dataset, a publicly available cervical cell dataset, was utilized for training and evaluation. The impact of segmentation on classification performance was evaluated by comparing the model trained on segmented images and another trained on non-segmented images. Experimental results showed that the use of segmented images marginally improved the model performance on precision (about 0.41 percent higher) and F1-score (about 1.30 percent higher), which suggests a slightly more balanced classification performance. While segmentation helps in feature extraction, the results showed that its impact on classification performance appears to be limited. The proposed framework offers a supplemental tool for clinical applications, which may aid pathologists in early diagnosis.

13.
arXiv (CS.AI) 2026-06-16

SMEPilot: Characterizing and Optimizing LLM Inference with Scalable Matrix Extensions

arXiv:2606.16332v1 Announce Type: cross Abstract: Modern CPUs increasingly integrate matrix extensions, such as Arm Scalable Matrix Extension (SME), that provide high-throughput matrix execution within the CPU. For LLM inference, however, these units are not a universal replacement for conventional CPU cores: prefill, decode, attention, and KV-cache operations expose different arithmetic intensities, vector behavior, and layout requirements, while SME units and CPU cores still compete for shared memory bandwidth. This paper studies this mismatch through a roofline-based characterization of SME-enabled CPUs and uses the resulting model to guide operator-level execution choices. We present SMEPilot, an LLM inference engine that selects CPU-only, SME-only, or cooperative SME+CPU execution for each operator shape. SMEPilot partitions matrix work across SME and CPU cores at tile granularity, overlaps SME-suitable matrix stages with CPU-suitable vector stages in attention, and maintains layout state so packed tensor representations are reused rather than repeatedly rebuilt on critical paths. Across Llama-3.2-3B, Qwen3-4B, and Qwen3-30BA3B on phone, PC, and server platforms, SMEPilot improves end-to-end inference performance by up to 3.94$\times$.

14.
arXiv (CS.AI) 2026-06-17

Temporal Preference Optimization for Unsupervised Retrieval

arXiv:2606.17664v1 Announce Type: cross Abstract: Unsupervised dense retrievers offer scalability by learning semantic similarity from unlabeled documents via contrastive learning, but they struggle to capture the temporal relevance, retrieving semantically related but temporally misaligned documents-an important aspect when a document collection spans multiple time periods (e.g., retrieving documents from 2018-2025 for "Who is the president in 2019?" introduces temporal ambiguity). Existing methods rely on supervised training with explicit timestamps, which are not always feasible. We propose TPOUR (Temporal Preference Optimization for Unsupervised Retriever), which uses our novel training method Temporal Retrieval Preference Optimization (TRPO). TRPO reinterprets preference learning in the temporal dimension, guiding the retriever to favor temporally aligned documents. TPOUR further generalizes to unseen time periods via interpolation in a learned time embedding, enabling continuous temporal alignment. Experiments on temporal information retrieval (T-IR), TPOUR outperforms both unsupervised and supervised baselines. Compared to Qwen-Embedding-8B, despite being about 72.7x smaller, TPOUR Contriever improves average nDCG@5 by +4.04 (+12.15%) on explicit and +4.98 (+15.21%) on implicit queries. We provide our code at https://github.com/agwaBom/TPOUR.

15.
arXiv (CS.CV) 2026-06-19

ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentation

Imperfectly supervised video polyp segmentation (VPS) aims to learn dense, temporally consistent masks from inexpensive supervision, including weak annotations (points, scribbles) and semi-supervision with few densely labeled frames. This setting is clinically valuable but challenging due to weak contrast, ambiguous boundaries, motion blur, and specular highlights, compounded by sparse pixel-level guidance. While SAM2 can generate dense masks from sparse inputs, direct pseudo-labeling often yields geometry-degraded masks with boundary leakage, underutilizes temporal consistency, and ignores reliability. To address these issues, we propose ARTEMIS, a unified framework for imperfectly supervised VPS driven by agent-guided reliability-aware temporal mask evolution. ARTEMIS initializes coarse masks from available supervision: SAM2 converts points/scribbles, while dense labels serve as reliable anchors. A debate-and-judge vision-language agent selects reliable temporal anchors under weak supervision, which are propagated bidirectionally with SAM2 to refine unreliable or unlabeled frames. Finally, ARTEMIS trains the segmenter using temporal reliability-aware robust learning, incorporating reliability-guided reference selection, a Reference Prototype Transport Module, and reliability-aware robust loss. These components assess mask reliability, evolve anchors over time, transport target identity across frames, and down-weight noisy supervision instead of discarding difficult samples. Experiments on SUN-SEG and CVC-ClinicDB-612 under scribble, point, and limited-label settings demonstrate that ARTEMIS achieves state-of-the-art performance. Code will be released at https://github.com/wangtong627/ARTEMIS.

16.
arXiv (CS.AI) 2026-06-24

Context-Aware Prediction of Student Quiz Performance with Multimodal Textbook Features

Authors:

arXiv:2606.24770v1 Announce Type: cross Abstract: 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.

17.
arXiv (CS.AI) 2026-06-16

SorryDB: Can AI Provers Complete Real-World Lean Theorems?

arXiv:2603.02668v2 Announce Type: replace Abstract: We present SorryDB, a dynamically-updating benchmark of open Lean tasks drawn from 78 real world formalization projects on GitHub. Unlike existing static benchmarks, often composed of competition problems, hillclimbing the SorryDB benchmark will yield tools that are aligned to the community needs, more usable by mathematicians, and more capable of understanding complex dependencies. Moreover, by providing a continuously updated stream of tasks, SorryDB mitigates test-set contamination and offers a robust metric for an agent's ability to contribute to novel formal mathematics projects. We evaluate a collection of approaches, including generalist large language models, agentic approaches, and specialized symbolic provers, over a selected snapshot of 1000 tasks from SorryDB. We show that current approaches are complementary: even though an agentic approach based on Gemini Flash is the most performant, it is not strictly better than other off-the-shelf large-language models, specialized provers, or even a curated list of Lean tactics.

18.
arXiv (CS.CL) 2026-06-24

Reinforcement Learning Towards Broadly and Persistently Beneficial Models

As AI systems are deployed across increasingly diverse and high-stakes settings, model alignment must generalize beyond the tasks and domains seen during training. This is especially important for reinforcement learning (RL), which can introduce unexpected misalignment through reward hacking, deception, or other unintended strategies. We study whether RL on beneficial behavior, instantiated in realistic domains, can produce broad and persistent alignment generalization beyond the training distribution. We construct a dataset of realistic situations designed to measure and train beneficial traits, such as truthfulness, fairness, risk awareness, and corrigibility, spanning varied domains, including health, science, and education. We then train models with RL on this dataset and evaluate them on more than 50 independent benchmarks of alignment and beneficial behavior. Compared to a compute-matched baseline, beneficial trait RL improves performance on over 80% of these out-of-distribution benchmarks. We observe substantial out-of-distribution alignment transfer: a beneficial-behavior RL intervention entirely limited to one domain, health, produces broad improvements on non-health alignment evaluations, including reduced reward hacking, deception, and general misalignment. Finally, we study alignment persistence: whether behavior remains robustly aligned under attempts to steer models towards misalignment. Models trained with beneficial trait RL show improved persistence, including greater resistance to adversarial prompting and harmful finetuning; further work is required to isolate the sources of these effects. These results suggest that RL to reinforce beneficial behavior in realistic domains can produce models that are more robustly aligned with human flourishing.

19.
arXiv (CS.LG) 2026-06-15

Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining

arXiv:2605.26759v2 Announce Type: replace Abstract: Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies. Existing approaches typically rely on dataset-specific optimization, making it difficult to transfer their causal discovery capabilities to new time series governed by diverse causal mechanisms. In this paper, we propose PTCD, a novel Pretraining framework for Time-series Causal Discovery, which improves cross-task generalization through context-conditioned modeling and transferable causal augmentation. To model complex temporal causal dependencies, PTCD employs a dual-scale iterative attention mechanism to capture window-level causal relationships, and a Gaussian mixture with a context-level routing mechanism to handle heterogeneous exogenous distributions. To further address distribution shifts across causal graphs, PTCD adopts a pretraining paradigm on synthetic datasets that integrates intervention-based learning and a causal mixup strategy, promoting stable causal discovery and stronger generalization. Extensive experiments on multiple real-world out-of-distribution (OOD) datasets demonstrate that PTCD excels in both causal discovery and root cause identification.

20.
arXiv (CS.CL) 2026-06-16

Can Agents Read the Room? Benchmarking Visual Social Intelligence in Multimodal Simulation

Social interaction depends on both language and visible social signals, such as facial expressions, posture, gaze, and emotional shifts. Yet existing social-agent benchmarks are largely text-based and rarely test whether multimodal agents can use visual cues to guide interaction. We introduce \textsc{\benchmarkname{}}, a benchmark evaluating visual social intelligence in multimodal social simulation. It contains 240 scenarios, 585 role instances, and 2,340 role-task instances, combining aligned textual-visual evidence, structured role profiles, and four role-level tasks: expression task, characteristic task, interaction regulation task, and interaction outcome task. Evaluating seven recent MLLMs under verbalized-vision and direct-vision reveals a clear gap between local role enactment and interaction management: role-specific expression and conflict handling are near saturation, whereas interaction regulation and visually grounded outcome achievement remain substantially more difficult. The code is released at https://github.com/JunsWan/AgentViSS, and the dataset is available at https://huggingface.co/datasets/JunsWan/AgentViSS.

21.
arXiv (CS.AI) 2026-06-16

ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM Agents

arXiv:2606.15508v1 Announce Type: new Abstract: Tool-augmented large language model agents increasingly operate over large tool libraries, but existing evaluations often focus on whether a model can call a tool correctly rather than how the visible tool menu shapes reliability, efficiency, and safety-relevant risk exposure. We introduce ToolMenuBench, a benchmark for evaluating tool-menu construction in multi-step LLM agents. ToolMenuBench varies tool-menu size, distractor type, state-dependent task structure, and risk exposure, and reports both filter-level and downstream agent metrics, including visible-tool count, risky-tool exposure, task success, wrong-tool calls, premature actions, and token usage. In a controlled evaluation across seven model backends, three tool-menu sizes, six filtering methods, and seven evaluation settings, CMTF improves task success from 32.1% under all-tools exposure to 85.7%, while reducing average token usage by roughly 98%. Causal minimal tool filtering achieves the strongest overall tradeoff, reducing visible tools, wrong-tool calls, premature actions, and risky-tool exposure relative to unfiltered exposure, lexical filtering, state-aware filtering, and broader causal-path baselines. ToolMenuBench provides a reusable evaluation framework for studying the agent-interface problem: which tools should be visible, when they should be visible, and under what cost or risk constraints.

22.
medRxiv (Medicine) 2026-06-22

A Parent-Generated Framework of Early Connection: Findings from a CBPR Qualitative Study

Background: Early relational health (ERH) constructs are derived fromresearch observations rather than lived experiences. This study foregrounds diverse parent voices to examine how they describeconnectionwith their young children. Methods: Usingcommunity-based participatory research (CBPR),this study was co-designed withparent leadersfromReach Out and Read. A semi-structured interview guidewas co-designed,and parent leaderssubsequentlyconducted and transcribed 18 interviews with parents from their networks.Researchersanalyzed transcripts using Reflexive Thematic Analysis.Member checking sessions with parent leadersinformedthe analytic framework. Results:Sixorganizing principleswereidentified.(1) Parent-child connection begins with an instinctual sense of responsibility.(2)Connectionebbs and flows as parent and child adapt to one another through dailyactivities.(3) Family circumstances, including family structure, cultural expectations, and intergenerational values, directly shape this connection. (4) Parents' own upbringings and past relationships indirectly shape how they connect with their child. (5) Forconnectionto grow, parents must show up physically and emotionally for their children despite competing demands. (6) Parentsgrow through engaged parenting, and that growth feeds back into the connection, creating a self-sustaining cycle of relational health.Conclusions:Our analysis generated twoconstructs underspecified in ERH frameworks.Parents described their sense of responsibility as immediate and instinctual, preceding an emotional bond.Parentsdemonstratedtheir agency in deciding what to carry forward from their relational histories, a pattern this study termsrelational legacy. Integrating parent-generated language into ERH measurementresearchmay shape a more comprehensive picture of ERHreflectinghow families experience connection.

23.
arXiv (CS.AI) 2026-06-12

CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation

arXiv:2606.13513v1 Announce Type: new Abstract: Driven by conservative over-provisioning to guarantee service reliability, resource utilization in cloud data centers remains at low levels. To mitigate this, the forecast-then-optimize paradigm has emerged to optimize consolidation by anticipating future demands. While emerging time series foundation models promise to enhance this paradigm through zero-shot generalization, existing benchmarks focus solely on prediction error metrics. The actual decision utility of these advanced models remains unverified, rendering their practical value for downstream tasks uncertain. To bridge this gap, we propose CloudCons, a comprehensive end-to-end benchmark designed to evaluate forecasting models within the specific context of cloud resource consolidation. We build high-quality datasets that cover diverse workloads from Huawei Cloud, Microsoft Azure, and Google Borg, capturing distinct service characteristics ranging from synchronized diurnal rhythms to stochastic, pulse-like bursts and high-frequency noise. We conduct an extensive evaluation of statistical, deep learning, and foundation models. Our experiments reveal a pivotal finding: while foundation models demonstrate superior zero-shot forecasting accuracy, this advantage does not inherently translate into better decision utility. Of practical significance, we systematically analyze how the selection of predictive quantiles acts as a critical lever. We provide actionable guidelines for calibrating these selections to balance the trade-off between resource efficiency and service reliability, offering vital insights for real-world deployment decisions.

24.
arXiv (CS.CV) 2026-06-11

P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning

Multimodal large language models can write code to produce complex programs as well as use programs to do 3D modeling, which opens up a new avenue for 3D generation powered by their priors, world knowledge and reasoning. Yet existing benchmarks rarely evaluate 3D modeling through code. Such modeling demands more than runnable code: from a text or visual specification, a model must generate a parametric 3D program that is geometrically precise, semantically aligned and assembly-consistent. We introduce P3D-Bench, a benchmark for parametric 3D generation. Unlike a 3D mesh, a parametric 3D program exposes explicit dimensions, construction operations and part relations, revealing whether a model recovers a design's structure, not just its appearance. Under a unified protocol, P3D-Bench covers three task families (Text-to-3D, Image-to-3D and Assembly-3D) and scores each output for executability, geometric fidelity, topology, text-grounded constraints, multiview semantic alignment and part-level structure. We evaluate frontier MLLMs and text-only LLMs on 400 text cases, 400 image cases and 203 annotated assemblies, with domain-specific models as reference points. Our extensive evaluation yields three findings. First, assemblies are the hardest setting, where models still fail to compose multiple parts into a coherent structure. Second, models can often recover the global shape and semantic identity of the target object, yet fail to reproduce the precise parametric geometry specified by the input. Third, part-level modeling remains weak on assemblies, where models recover neither the geometry of each part nor the right number of parts. These results position P3D-Bench as a benchmark for evaluating precise parametric geometry and part-level structure in parametric 3D generation.

25.
arXiv (CS.CV) 2026-06-11

Slots, Transitions, Loops: Learning Composable World Models for ARC

ARC tests in-context rule induction: given a few input-output demonstrations, a model must infer the hidden rule and apply it to a new query. While many approaches express ARC rules through language, code, or symbolic programs, ARC itself is visual-symbolic: rules appear as grid transitions over objects, colors, shapes, and spatial relations. We introduce Loop-OWM, an object-centric world-modeling architecture that learns these rules as composable transitions over structured states. It combines color-prototype slots, demonstration-conditioned task summaries, and a looped transition model with dense propagation and slot-conditioned correction. On both ARC-1 and ARC-2, Loop-OWM outperforms non-looped and looped baselines with comparable or fewer parameters. These results suggest that ARC rules can be learned not only as language descriptions or searched programs, but also as transitions over visual-symbolic world states.