中 EN
Sign In Register

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.

Sign In Register
01.
arXiv (CS.CV) 2026-06-11

ReMoT: Reinforcement Learning with Motion Contrast Triplets

Authors:
Cong Wan↗Zeyu Guo↗Jiangyang Li↗SongLin Dong↗Yifan Bai↗Lin Peng↗Zhiheng Ma↗Yihong Gong↗

We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency – a critical failure point in navigation, robotics, and autonomous driving. ReMoT integrates two core components: (1) A rule-based automatic framework that generates ReMoT-16K, a large-scale (16.5K triplets) motion-contrast dataset derived from video meta-annotations, surpassing costly manual or model-based generation. (2) Group Relative Policy Optimization, which we empirically validate yields optimal performance and data efficiency for learning this contrastive reasoning, far exceeding standard Supervised Fine-Tuning. We also construct the first benchmark for fine-grained motion contrast triplets to measure a VLM's discrimination of subtle motion attributes (e.g., opposing directions). The resulting model achieves state-of-the-art performance on our new benchmark and multiple standard VLM benchmarks, culminating in a remarkable 25.1% performance leap on spatio-temporal reasoning tasks.

Read & Discuss → View Source →
02.
arXiv (CS.CL) 2026-06-18

SenFlow: Inter-Sentence Flow Modeling for AI-Generated Text Detection in Hybrid Documents

Authors:
Jingkun Luo↗Yifan Sun↗Da-Tian Peng↗Guanxiong Pei↗

Sentence-level AI-generated text detection (S-AGTD) for hybrid documents, where humans and LLMs co-author one text, faces two gaps: existing methods classify each sentence in isolation, discarding inter-sentence dependencies, and existing benchmarks omit the newest generation of generators. We construct MOSAIC, a benchmark of 16,000 hybrid documents over PubMed and XSum, generated by DeepSeek-V3.2 and Kimi K2 under stringent quality controls including a perplexity-consistency filter absent from prior benchmarks. We recast S-AGTD as structured prediction over the document sentence sequence and instantiate it as SenFlow, integrating graph-based inter-sentence propagation with linear-chain CRF decoding in a single document-level pass over a sentence graph. SenFlow reaches state-of-the-art performance on MOSAIC, with a +4.15 pp average Macro-F1 margin on cross-domain transfer, the hardest of three protocols of increasing difficulty. We further find that even after the perplexity filter equalizes overt cues, AI insertions retain a generator-dependent sentence-length gap that sentence-level detectors still exploit. Code and data: https://github.com/luojingkun22/SenFlow

Read & Discuss → View Source →
03.
arXiv (CS.CL) 2026-06-12

Can Factual Opinions Be Edited (Manipulated) in Large Language Models?

Authors:
Yuanpu Cao↗Ziyi Yin↗Fenglong Ma↗Jinghui Chen↗

Large Language Models (LLMs) are increasingly integrated into various domains, making knowledge editing techniques crucial yet potentially hazardous. Current editing methods primarily target atomic facts, overlooking the significant risks associated with manipulating factual opinions, e.g., documented stances of public figures on societal issues. Such manipulation could reshape public images, influence elections, and alter societal views. To systematically assess this threat, we introduce the Factual Opinion Editing with Evidence (FOE) benchmark, which encompasses 261 public figures, 19 issue categories, and 2,178 complete opinion records. Our evaluations demonstrate that current editing techniques struggle significantly with factual opinions, often achieving only superficial changes while failing to preserve consistency between the edited opinion and the supporting evidence generated by the model. To address this limitation, we further propose a simple yet effective Self-Generated Evidence-Aligned method that achieves opinion-evidence alignment without relying on explicit instructions. Together, our benchmark and method provide a foundation for understanding the emerging security implications of factual opinion editing in LLMs.

Read & Discuss → View Source →
04.
arXiv (CS.AI) 2026-06-16

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

Authors:
Xintong Hu↗Xuhong Huang↗Jinyu Zhang↗Yutong Yao↗Yuchong Sun↗Qiuyue Wang↗Mingsheng Li↗Sicheng Xie↗Yitao Liu↗Junhao Chen↗Yixuan Chen↗Yingming Zheng↗…

arXiv:2605.27284v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tasks should be executed. However, existing robot datasets usually pair trajectories with coarse goal-level language, leaving execution-critical details such as active arm, approach direction, and contact region unspecified. This limits steerable policy learning and robotic video understanding. We introduce FineVLA, an open framework for action-aligned fine-grained VLA supervision. The framework includes: (1) a data construction tool that unifies 972,247 trajectories across 85K tasks from 10 open-source robot datasets and builds FineVLA-Data, a human-verified dataset of 47,159 fine-grained trajectories; (2) a held-out benchmark with 500 videos, 11,631 atomic facts, and 1,030 VQA questions; (3) a robotics-specialized VLM annotator for scalable fine-grained annotation; and (4) a steerable VLA policy trained with controlled mixtures of fine-grained and raw goal-level instructions. Our experiments yield three findings. First, fine-grained supervision does not sacrifice goal-level success: FG-only improves over Raw-only by +1.4 to +8.1 success-rate points across settings. Second, fine-grained and raw instructions are complementary, following a consistent inverted-U trend peaking at FG:Raw = 1:2 to 1:1. The best mixed setting reaches 86.8%/82.5% in RoboTwin simulation and 62.7/100 in real-world dual-arm manipulation (vs. 49.9 Raw-only). Third, fine-grained supervision improves steerable control: the largest real-world gains appear on pose (+23), color (+18), and approach direction (+18)–factors where goal-level instructions provide no guidance. Overall, fine-grained language should augment goal-level instructions: specifying how to execute alongside what to achieve. Project page: https://finevla.xlang.ai/

Read & Discuss → View Source →
05.
arXiv (CS.CL) 2026-06-16

ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection

Authors:
Tai Tran Tan↗An Dinh Thien↗

This paper describes our system for SemEval-2026 Task 6, which addresses the classification of political evasion strategies in English question-answer pairs extracted from U.S. presidential interviews. We systematically compare two distinct paradigms: (1) Parameter-Efficient Fine-Tuning of Qwen3 models (4B-32B) using QLoRA, enhanced with tiered upsampling and weighted cross-entropy loss to address severe class imbalance, and (2) structured Chain-of-Thought (CoT) prompting of reasoning-capable API models, namely DeepSeek-V3.2 and Grok-4-Fast. Our evaluation demonstrates that structured CoT prompting of reasoning-enabled models substantially outperforms our baseline parameter-efficient fine-tuning implementation in absolute Macro F1. Our best system, Grok-4-Fast with extended reasoning and few-shot hierarchical CoT prompting, achieves a Macro F1 of 0.5147 on Subtask 2 (9-class evasion) and 0.7979 on Subtask 1 (3-class clarity), ranking 8th out of 33 teams on Subtask 2 and 13th out of 41 teams on Subtask 1 on the official leaderboard. Furthermore, our ablation studies reveal key insights into effective prompt design for evasion detection: presenting labels within a hierarchical taxonomy helps structure model reasoning, while few-shot exemplars provide task calibration. However, the strongest prompt variants are not statistically distinguishable in Macro F1, and explicitly enabling extended reasoning modes yields substantial performance gains by facilitating the multi-step pragmatic analysis required to detect evasive intent.

Read & Discuss → View Source →
06.
arXiv (CS.CV) 2026-06-18

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Authors:
Kangsheng Duan↗Ziyang Xu↗Wenyu Liu↗Xiaohu Ruan↗Xiaoxin Chen↗Xinggang Wang↗

While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevitably triggers a severe representation bottleneck. To conquer this, we propose Moebius, a highly efficient lightweight inpainting framework. We systematically reconstruct the diffusion backbone by introducing the Local-$\lambda$ Mix Interaction ($L\lambda MI$) block. Comprising Local-$\lambda$ and Interactive-$\lambda$ modules, it elegantly summarizes spatial contexts and global semantic priors into fixed-size linear matrices, preserving complex latent interactions while drastically shedding parameters. Furthermore, to unlock the full representational capacity of this highly compact architecture, we synergistically pair it with an adaptive multi-granularity distillation strategy. Operating strictly within the latent space to avoid expensive pixel-space decoding, this strategy dynamically balances multiple gradient-based losses to achieve high-fidelity alignment. Extensive experiments across natural and portrait benchmarks demonstrate that this optimal synergy enables Moebius to rival or even surpass the generation quality of the 10B-level industrial generalist FLUX.1-Fill-Dev. Remarkably, Moebius achieves this using less than 2\% of the parameters (0.22B vs. 11.9B) while delivering a $>15\times$ acceleration in total inference time, setting a new efficiency standard for high-fidelity inpainting. Project page at https://hustvl.github.io/Moebius.

Read & Discuss → View Source →
07.
arXiv (CS.LG) 2026-06-16

TriAdReview: Triangular Adversarial Review Architecture for Multi-Model Technical Document Generation

Authors:
Zhiqiang Zhou↗Junliang Dai↗Xu Ling↗

arXiv:2606.15074v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for technical document generation, yet single-model outputs often suffer from over-engineering, security blind spots, and incomplete coverage. We propose TriAdReview, a triangular adversarial review architecture that employs two independent reviewer models (engineering and boundary perspectives) and a triangular judging mechanism to iteratively improve a generator model's output. We evaluate TriAdReview across five benchmark tasks - architecture design, code generation, proposal review, security audit, and requirements analysis - using three configurations: single model (baseline), dual model (single review), and triple model (full system). Results across 75 experiments (n=5 per cell) show that the triple model configuration achieves a 10.1% overall improvement over the single model baseline (26.2 vs. 23.8 out of 50; p

Read & Discuss → View Source →
09.
arXiv (CS.CV) 2026-06-12

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

Authors:
Hosu Lee↗Junho Kim↗Hyunjun Kim↗Yong Man Ro↗

Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame selection strategies, albeit with the rapid development of video-specialized LMMs. Prior works attempted to solve this with static heuristics or external retrieval modules to feed frame-level information, but these approaches often fail to capture visual cues grounded to the given user queries conflating raw visual dynamics with true semantic relevance. In this paper, we introduce ReFoCUS (Reinforcement-guided Frame Optimization for Contextual UnderStanding), the first framework to integrate online policy-gradient reinforcement learning into frame-level optimization for video-LLMs. ReFoCUS aims to learn a frame selection policy, leveraging reward signals derived from reference models to capture their underlying scoring behavior over frame combinations that best support temporally grounded responses. To efficiently explore the large combinatorial frame space, we employ an autoregressive and query-conditional selection architecture that ensures contextual consistency while reducing complexity. Our policy learning removes the need for explicit frame-level supervision, as it implicitly discovers optimal and semantically consistent frame compositions. ReFoCUS consistently improves reasoning accuracy across multiple video QA benchmarks, demonstrating the advantage of aligning frame selection with model-internal utility.

Read & Discuss → View Source →
10.
arXiv (quant-ph) 2026-06-11

Diffusive Relaxation of Participation Entropy in U(1)-symmetric Dynamics

Authors:
Hanchen Liu↗Tianci Zhou↗Xiao Chen↗

arXiv:2606.11561v1 Announce Type: new Abstract: Participation entropy (PE) quantifies the spread of a many-body wavefunction across configuration space. While PE relaxes rapidly in generic chaotic systems, we show that $\mathrm{U}(1)$ conservation laws slow it down by imprinting with the slow hydrodynamic modes. Using a cluster expansion around equilibrium, we show that, after local density inhomogeneities decay, the leading PE deficit is dominated by squared connected density correlations. The long time relaxation is therefore controlled by diffusive correlation spreading, giving $\Delta S(t)\sim t^{-1/2}$ in the hydrodynamic regime and crossing over to $\sim \exp[-O(t/L^2)]$ when $t\geq L^2$. We confirm this entropy correlation relation using exact computation and infinite system tensor network simulations in various quantum $\mathrm{U}(1)$ conserving circuits. Our results establish PE as a sensitive probe of hydrodynamic memory and suggest that slow relaxation is a generic consequence of conservation laws.

Read & Discuss → View Source →
11.
arXiv (CS.CL) 2026-06-16

MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA

Authors:
Yilong Zuo↗Xunkai Li↗Jing Yuan↗Qiangqiang Dai↗Hongchao Qin↗Ronghua Li↗

Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts. Existing RAG methods mostly rely on fixed Top-k retrieval over text chunks or pages. Text retrieval can compress the context but often loses visual and layout information; page-level visual retrieval preserves the original page, yet it also sends large irrelevant regions to the reader, leading to a static trade-off among evidence coverage, noise, and inference cost. This paper proposes MAGE-RAG, a multigranular adaptive graph evidence framework for long-document multimodal QA. MAGE-RAG uses page retrieval as the entry point for query-time evidence construction. Offline, it builds an evidence graph with page nodes and element nodes, encoding containment, reading order, layout adjacency, section hierarchy, and semantic-neighbor relations. At query time, an online evidence controller iteratively activates, opens, searches, and prunes evidence under explicit budgets. The resulting evidence subgraph is then rendered into structured multimodal reader input, allowing the LVLM to consume compact and relevant evidence within a limited context. On LongDocURL and MMLongBench-Doc, we establish a unified comparison and analysis protocol covering Direct MLLM, Text RAG, Page-level Visual RAG, and Graph/Agentic RAG. Experiments show that MAGE-RAG achieves 52.75 overall accuracy on LongDocURL, and 53.26 accuracy with 51.19 F1 on MMLongBench-Doc. Fine-grained breakdowns, budget-performance curves, ablations, and trace-based analysis further show that query-time evidence subgraph construction can balance dispersed evidence coverage with context-noise control. Our code is available at https://github.com/laonuo2004/MAGE-RAG.git.

Read & Discuss → View Source →
12.
arXiv (CS.CV) 2026-06-15

Improving Lunar Topography with Deep Learning Schrödinger Bridges

Authors:
Matthew Repasky↗Erwan Mazarico↗Michael K. Barker↗Stefano Bertone↗Terence J. Sabaka↗Yao Xie↗

Increasing the resolution of planetary topography models can enable a better understanding of surface processes and geomorphology; however, existing analytical super-resolution methods are expensive and difficult to apply at large scales. Generative models provide the tools to learn complex relationships within data and can be applied at scale due to hardware accelerators and parallelization. We present a diffusion-based Schrödinger Bridge (SB) generative modeling approach for lunar topography super-resolution, connecting the distribution of low-resolution topography to that of high-resolution topography, incorporating physically-constraining optical imagery. Our approach is inspired by existing Shape-from-Shading methods, which improve a priori low-resolution topography by using optical images at the target resolution. We train SBs on a novel dataset of rendered lunar topography, emulating optical imagery from the Lunar Reconnaissance Orbiter Narrow Angle Camera. The result is a flexible approach for topography super-resolution which can provide pixel-level uncertainties in the reconstruction.

Read & Discuss → View Source →
13.
arXiv (CS.CV) 2026-06-16

CEVAR: Centerline Embedding Extraction for Endovascular Aneurysm Repair

Authors:
Roman Naeem↗Timo Niiniskorpi↗Charlotte Sandstr\"om↗Naman Desai↗Anders Jeppsson↗Ida H\"aggstr\"om↗Fredrik Kahl↗H{\aa}kan Roos↗Jennifer Alv\'en↗

Long-term mortality rates after endovascular aneurysm repair (EVAR) remain elevated due to post-EVAR rupture caused by loss of seal in stent graft sealing zones. Structured CT review using centerline measurements improves detection, but current workflows require manual centerline editing and expert operators. We propose a transformer framework for automated, protocol-driven sealing zone assessment that combines 3D centerline tracking with embedding-based geometric prediction. Two state-of-the-art image-to-graph models are evaluated for aorto-iliac centerline extraction from follow-up CT and for measurement of stent position, vessel diameters, and seal lengths according to EVAR4C protocol. Across the full test set and a challenging no-contrast subset, the proposed fully automatic method outperforms the commercial semi-automatic workflow.

Read & Discuss → View Source →
14.
arXiv (CS.CL) 2026-06-18

Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA

Authors:
Ikram Belmadani↗Oumaima El Khettari↗Carlos Ramisch↗Frederic Bechet↗Richard Dufour↗Benoit Favre↗

The development of large language models (LLMs) has led to an increased focus on their adaptation to specialized domains and languages, yet the effectiveness of domain adaptation strategies remains unclear. We present a study of medical domain adaptation using French medical question-answering (QA) as a case study. We compare continual pretraining (CPT), supervised fine-tuning (SFT), and their combination across three model families, multiple sizes, and three initialization types, explicitly disentangling adaptation effects from base model choice. We evaluate both multiple-choice (MCQA) and open-ended QA (OEQA) under greedy and constrained decoding using automatic metrics and LLM-as-a-Judge evaluation. For MCQA, CPT+SFT most often achieves the best scores, but gains over SFT are small and frequently not statistically significant, making SFT a strong and cost-effective default. For OEQA, CPT consistently improves overlap-based metrics, while SFT often degrades generation quality; instruction tuning and CPT+SFT are preferred by LLM-based evaluation. Cross-lingual experiments further show effective transfer from French adaptation to English benchmarks. Overall, we provide practical guidelines for selecting adaptation strategies under computational constraints.

Read & Discuss → View Source →
15.
arXiv (CS.LG) 2026-06-18

From Mechanistic to Compositional Interpretability

Authors:
Ward Gauderis↗Thomas Dooms↗Steven T. Homer↗Kola Ayonrinde↗Geraint A. Wiggins↗

arXiv:2605.08934v2 Announce Type: replace Abstract: Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be objectively verified, compared, or composed. We introduce compositional interpretability, a category-theoretic framework grounded in the principles of compositionality and minimum description length. Compositional interpretations are pairs of syntactic and semantic mappings that must commute to enforce consistency between a model's decomposition and its observed behaviour. We deconstruct explanation quality into measures of faithfulness and complexity to cast interpretability as a constrained optimisation problem, and introduce compressive refinement to systematically restructure models into simpler parts without altering their function. Finally, we derive a parsimony criterion under which syntactic compression theoretically guarantees more concise, human-aligned explanations. Our framework situates prominent mechanistic methods as subclasses of refinement, and clarifies why their compressibility heuristics tend to align with human interpretability. Our work provides a measurable, optimisable blueprint for automating the discovery and evaluation of mechanistic explanations.

Read & Discuss → View Source →
16.
arXiv (CS.CL) 2026-06-11

To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending

Authors:
Jin Gan↗Xin Li↗Jun Luo↗

The wide deployment of LLMs has made model alignment necessary to make newly trained models safely and effectively respond to user instructions. Among different methods, inference-time alignment is often cheaper as it intervenes (i.e., offers guidances) only during output generation. Existing proposals apply guidances extracted from certain aligned models without properly assessing their reliability. Nonetheless, our systematic evaluation reveals that guidance effectiveness varies drastically across models; since ineffective guidances lead to further confusion and thus further interventions, the resulting excessive interventions typically indicate poor performance. To make interventions more effective and thus more efficient, we introduce BlendIn, an inference-time alignment framework that shifts from binary decisions to creating hybrid distributions integrating both models' knowledge. BlendIn stabilizes inference-time alignment by performing quality-aware alignment and proportionally weighting each model's contribution based on reliability. Compared with existing works, it preserves beneficial guidance while downweighting unreliable suggestions. BlendIn provides both diagnostic signals and mitigation strategies for misaligned guidance, achieving consistent and up to 50% performance improvement on challenging model pairs. Our code is available at: https://github.com/DecayingSeart/BlendIn.

Read & Discuss → View Source →
17.
arXiv (CS.LG) 2026-06-15

Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets

Authors:
Anthony Pineci↗Yunzong Xu↗

arXiv:2606.14679v1 Announce Type: new Abstract: Online inventory optimization (OIO) is online convex optimization with physical memory: inventory carryover makes the feasible action set depend on the past. A natural principle, used in stochastic inventory learning and recently in OIO under a single linear capacity constraint, is to maintain a hidden target chosen by an online learner and implement its projection onto the currently feasible order-up-to set. We prove that this simple principle is optimal for OIO on arbitrary bounded convex capacity sets. With online gradient descent as the base learner, the method improves the best known regret guarantee for OIO on general convex sets from inverse to inverse-square-root dependence on the common-demand probability, and we prove a matching lower bound. The same principle gives the first polylogarithmic regret guarantee for strongly convex losses and the first dynamic regret guarantee adapting to Euclidean path variation on general convex capacity sets. The analysis introduces a norm alignment principle: the right state variable is the distance from the hidden target to the feasible set, measured in the same norm as the projection. Under norm alignment, this distance evolves pathwise as a scalar queue, with target movement as arrival and common demand as service. This reduction to one-dimensional queue control resolves the state dependence and extends the guarantees to general convex capacity sets, beyond the reach of prior productwise approaches. Experiments on synthetic and real-world inventory data corroborate the theory.

Read & Discuss → View Source →
18.
arXiv (CS.AI) 2026-06-16

An Empirical Investigation of Pre-Trained Deep Learning Model Reuse in the Scientific Process

Authors:
Nicholas M. Synovic↗Karolina Ryzka↗Alessandra V. Vellucci Solari↗Kenny Lyons↗James C. Davis↗George K. Thiruvathukal↗

arXiv:2603.13584v2 Announce Type: replace-cross Abstract: Deep learning has achieved recognition for its impact within natural sciences, yet the prohibitive financial and technical cost of training models from scratch inhibit adoption. Following software engineering community guidance, natural scientists are reusing pre-trained deep learning models (PTMs) to amortize these costs. While prior works recommend PTM reuse patterns, we present the first empirical study of PTM reuse patterns in the natural sciences, quantifying the utilization and impact of PTM reuse within the scientific process across 17,718 peer reviewed, open access papers. Our results show that "Biochemistry, Genetics and Molecular Biology" has outpaced other natural scientific fields in PTM reuse, "adaptation" reuse is the most prevalent PTM reuse pattern identified across all natural science fields, and the "testing" stage of the scientific process has been most impacted by PTM integration.

Read & Discuss → View Source →
19.
arXiv (CS.AI) 2026-06-16

Adaptive inference and function vectors in deep transformers

Authors:
Ravin Raj↗Gautam Reddy↗

arXiv:2606.16694v1 Announce Type: cross Abstract: Transformers are widely used as a general-purpose substrate for learning complex correlations between a large collection of coupled variables, but their internal mechanisms have remained mysterious. We introduce a theory of a deep transformer as a mean-field interacting system that implements distributed inference, subject to constraints on communication, locality and depth. We show that such a system can exploit internal state representations ('function vectors') to infer a latent context variable at increasingly finer scales over its layers. In an in-context regression task, the theory predicts a non-trivial relationship between non-Gaussian, hierarchical structure in the latent context variable, and transformer depth. Predictions are tested using constrained linear attention transformers and demonstrate adaptive inference in deep architectures. Feedforward blocks and depth enable transformers to implement a much richer class of in-context learning algorithms than previously described.

Read & Discuss → View Source →
20.
PLOS Medicine 2026-05-20

Associations between hematologic dynamics during pregnancy and obstetric complications: A retrospective observational study

Authors:
Veronica Tozzo↗

by Veronica Tozzo, Rachel Petherbridge, Kaitlyn James, Sarah Hsu, Deepti Pant, Chloe Michalopoulos, Brody H. Foy, Tanayott Thaweethai, Christopher Mow, Jacqueline Maya, Carolina Batlle Camero, Lydia Shook, Kathryn J. Gray, Logan Mauney, John M. Higgins, Camille E. Powe Background Pregnancy alters hematologic state as measured by complete blood count (CBC), but the longitudinal changes in CBC indices that define healthy pregnancies are not well established. In a large cohort based at an academic health system in the United States, we aimed to define reference intervals and typical longitudinal changes in CBC indices during pregnancy. We then tested for associations between extreme CBC values for gestational age or extreme longitudinal changes in CBC indices and obstetric complications. Methods and findings We studied nine CBC indices in individuals with singleton pregnancies who delivered after 30 weeks’ gestation and presented for prenatal care prior to 20 weeks. The electronic health record (EHR)-based Maternal Health Cohort (Massachusetts General Hospital; 1998–2016) formed our discovery cohort of 45,992 pregnancies, 18% of which had relevant complications. We developed a validation cohort of 48,868, 27% with complications from EHR data in the Mass General Brigham healthcare system from 2016 to 2024. In pregnancies without complications in the discovery cohort, we derived gestational-age-specific reference intervals (2.5th–97.5th percentile) and established typical intra-pregnancy longitudinal changes. In the validation cohort, we then tested CBC values outside of the 26–29 weeks’ gestation reference interval and CBC rare changes (uncommon changes in magnitude and direction) between 7–14 and 26–29 weeks’ gestation for association with a composite outcome (hypertensive disorders of pregnancy, small for gestational age birthweight, preterm birth) and its individual components using generalized estimating equations. Derived reference intervals differed from those in the literature for mean red cell volume, mean red cell hemoglobin, red cell count, and mean red cell hemoglobin concentration; reference intervals for other indices were similar to those previously published. In validation, hematocrit, hemoglobin, and red cell count values above their gestational-age specific reference intervals were associated with increased risk of the composite obstetric outcome: odds ratios (ORs) of 1.4 (95% CI [1.2, 1.5] p 

Read & Discuss → View Source →
21.
arXiv (CS.CL) 2026-06-12

LLMs Can Better Capture Human Judgments–With the Right Prompts

Authors:
Danica Dillion↗Chen Cecilia Liu↗Baihui Wang↗Daniele Barolo↗Tanmay Rajore↗Niket Tandon↗Pranathi Ravikumar↗Kurt Gray↗

Are large language models (LLMs) bad at capturing human judgment? Two commonly stated limitations are that LLMs fail to capture full distributions of responses, and that their judgments are unstable across wording variations. We demonstrate simple prompting strategies that mitigate these limitations. Across two datasets–a U.S.-representative set of 144 moral scenarios and 38 moral beliefs from the International Social Survey Programme's Family and Changing Gender Roles module covering 32 countries–we show how simple elicitation techniques help improve AI-human alignment. First, prompting models to report standard deviations and response proportions recovers the full range of human responses better than common strategies. Second, ensuring scenarios are clear to human participants–as reflected in human confusion ratings–boosts model alignment, and LLMs can track human confusion ratings. At the same time, we find that LLMs' estimates of their own error are poorly calibrated, though they can predict human variability relatively well. These results suggest that asking better questions to LLMs can yield better answers.

Read & Discuss → View Source →
22.
arXiv (CS.AI) 2026-06-17

Dissecting model behavior through agent trajectories

Authors:
Gaurav Gupta↗Vatshank Chaturvedi↗Jun Huan↗Anoop Deoras↗

arXiv:2606.17454v1 Announce Type: new Abstract: AI agent performance is not just a modeling problem, it is fundamentally a systems problem. The advanced capabilities of models are realized through agent harnesses. Therefore, a gap between model assumptions and harness behavior can easily prevent the model's full capabilities from translating into agent performance. We formalize this as the `intent-execution' gap: the mismatch between what the model intends and what the harness executes, and vice versa. We argue that minimizing this intent-execution gap is as important as other aspects of harness design such as tools and execution loops. To illustrate the impact of this harness-model alignment, we develop a simple and customizable harness called `Simple Strands Agent' (SSA). SSA aims to find the bulk of common patterns which generalize across different model families (such as Claude, Gemini, GPT, Grok, Qwen), as well as a small number of model-specific preferences. We make two contributions: (i) we $reproduce or improve on the pass@1$ performance reported by diverse model-provider families on popular agentic benchmarks (SWE-Pro, SWE-Verified and Terminal-Bench-2), and (ii) building on an $analysis of 138k trajectories generated by SSA$, we look beyond the $\texttt{pass@1}$ numbers which tend to be relatively even across frontier models. By representing agent trajectories in code state-spaces, we observe model-level differences in problem-solving behavior. Finer-grained metrics such as edit frequency, testing activity, and phase-transitions reveal how individual models allocate effort across different stages of autonomous problem solving.

Read & Discuss → View Source →
23.
arXiv (CS.CL) 2026-06-19

When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

Authors:
Kaiyue Yang↗Yuyan Bu↗Jingwei Yi↗Yuchi Wang↗Biyu Zhou↗Juntao Dai↗Songlin Hu↗Yaodong Yang↗

As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on safety-agnostic metadata preferences, leaving privilege-sensitive choices underexplored. To address this gap, we study over-privileged tool selection, in which an agent selects or escalates to a higher-privilege tool despite a sufficient lower-privilege alternative. We introduce ToolPrivBench to evaluate whether agents choose higher-privilege tools despite sufficient lower-privilege alternatives, measuring both initial selection and escalation after transient tool failures. Across eight domains and five recurring risk patterns, we find that over-privileged tool selection is common among mainstream LLM agents and is further amplified by transient failures. We further find that general safety alignment does not reliably transfer to least-privilege tool choice, while prompt-level controls provide only limited mitigation under transient failures. We therefore introduce a privilege-aware post-training defense that teaches agents to prefer sufficient lower-privilege tools and escalate only when necessary. Our mitigation experiments show that this defense substantially reduces unnecessary high-privilege tool use while preserving general capabilities.

Read & Discuss → View Source →
24.
arXiv (CS.CV) 2026-06-16

XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical Systems

Authors:
Hamza Riaz↗Arham Haroon↗Maha Baig↗Muhammad Dawood Rizwan↗Muhammad Naseer Bajwa↗Muhammad Moazam Fraz↗

Autonomous medical and robotic systems increasingly rely on intelligent perception and reasoning capabilities to interpret visual data and support clinical decision making. Radiology report generation represents a critical component of such automated diagnostic workflows, yet existing end-to-end multimodal models often suffer from weak visual grounding, resulting in unreliable interpretations and omission of subtle clinical findings. This paper presents XMedFusion, a modular AI framework designed as an intelligent perception and reasoning module for autonomous medical systems. The proposed framework decomposes visual information into coordinated functional components that emulate expert-driven analysis, including a visual perception agent that extracts image-grounded evidence, a knowledge graph construction agent that structures clinically relevant findings, and a retrieval-guided drafting process that ensures a consistent reporting structure. A synthesis agent iteratively integrates visual and structured evidence through reasoning-driven verification to produce reliable and interpretable diagnostic outputs. Experimental evaluation on a public chest radiograph dataset demonstrates significant improvements over baseline vision-language models, achieving gains from 0.0493 to 0.3359 in BLEU-1, 0.0863 to 0.2440 in ROUGE-L, and 0.0829 to 0.1708 in METEOR, along with substantial improvements in semantic evaluation metrics such as Consistency (2.38 to 7.80) and Accuracy (2.34 to 6.93). The results highlight the effectiveness of structured multi-agent perception and reasoning for enhancing robustness, transparency, and automation in intelligent medical imaging systems, enabling integration into autonomous healthcare and robotic diagnostic workflows.

Read & Discuss → View Source →
25.
arXiv (CS.LG) 2026-06-15

Trust but Verify: Mitigating Medical Hallucinations via Post-Hoc Adversarial Auditing and Multi-Agent Feedback Loops

Authors:
Muhammad Osama↗Maheera Amjad↗Zartasha Mustansar↗Arslan Shaukat↗Muhammad U. S. Khan↗

arXiv:2606.14149v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved. This study examine whether LLMs recommend recently banned or withdrawn pharmaceuticals when answering clinical questions and tests an agent-based method for reducing such errors. We developed a five-agent "Trust but Verify" system using a single LLM backbone. To measure regulatory knowledge obsolescence, we created an adversarial dataset of 103 clinical MCQs where historically correct answers now refer to banned substances. This scale ensures statistical significance across various therapeutic classes. We evaluated three open-access model families (GPT-OSS, Llama-3, Falcon-3) under vanilla and agentic conditions. Performance was measured via pointwise score, label accuracy, Hallucination Error Rate (HER), and Component Fidelity (CF) score. We also observed clinical safety regression in proprietary models. In default configurations, all models showed high hallucination rates, consistently selecting banned drugs that matched training data patterns. Our proposed agentic architecture reduced HER by approximately 53% across models. Pointwise scores shifted from -0.25 (unsafe recommendation) toward 0.0 (appropriate refusal). The safety audit intercepted dangerous outputs even when models' parametric knowledge favored the banned substance. The proposed multi-agent framework offers a model-agnostic method for enforcing regulatory compliance that prioritizes patient safety over fluent text generation. Our work demonstrates a practical approach for deploying autonomous AI systems in safety-critical healthcare settings. It shows how real-time regulatory data can be integrated into LLM pipelines to support clinical decision-making.

Read & Discuss → View Source →