❌

Normal view

Received — 27 May 2026 ⏭

Large Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation

✇Journal of Medical Internet Research
By: Zilma Silveira Nogueira Reis · Elisa Tuler Albergaria · Adriana Silvina Pagano · Eura Martins Lage · Flávia Ribeiro de Oliveira · Cristiane dos Santos Dias · Juliana Almeida Oliveira · Gláucia Miranda Varella Pereira · Isaias Jose Ramos de Oliveira · Érico Franco Mineiro · Igor Carvalho Lima Oliveira · Davi dos Reis de Jesus · Antônio Pereira de Souza Júnior · Igor de Carvalho Gomes · Rodrigo André Cuevas Gaete · Ricardo Cruz-Correia · Leonardo Rocha
27 May 2026 at 02:30
Background: The application of generative artificial intelligence to simplify medication use instructions has the potential to enhance people’s health by improving treatment adherence. Objective: We evaluated the performance of large language models (LLMs) in generating medication usage instructions to complement prescriptions in primary health care. Methods: This randomized, blinded experimental preclinical study used prescription-inducing scenarios, assigned to 62 health care professionals, to validate instructions generated by LLMs during electronic prescriptions. The instructions were generated by ChatGPT-4.0 (OpenAI), Llama3.1-8B (Meta), and Llama3.1-8B-RAG (Meta) using retrieval-augmented generation based on patient information leaflets. Performance metrics assessed adequacy, completeness, clarity, language simplification, usefulness, and errors in the generated instructions, with scores to analyze overall and individual metrics. Results: The 3 models yielded high overall scores for producing qualified instructions (ChatGPT-4.0: median 88.4, IQR 22.8; Llama3.1-8B: median 66.5, IQR 50.9; Llama3.1-8B-RAG: median 79.9, IQR 34.4; Kruskal-Wallis test P=.003). Llama3.1-8B-RAG received evaluations with similar overall scores to ChatGPT-4.0 (post hoc test, P=.05) and similar to Llama3.1-8B (post hoc test, P=.44). ChatGPT-4.0 outperformed Llama3.1-8B (Bonferroni test, P<.001). Regarding specific domains, Llama3.1-8B-RAG received scores equivalent to those of ChatGPT-4.0 for adequacy (mean 6.24, SD 2.3 vs mean 6.82, SD 2.1; post hoc test, P=.54); completeness (mean 5.94, SD 2.2 vs 6.55, SD 1.9; post hoc test P=.38), clarity (mean 5.77, SD 2.4 vs mean 6.68, SD 1.9; post hoc test P=.09), and usefulness (mean 5.42, SD 2.4 vs mean 5.96, SD 2.2; post hoc test P=.63). ChatGPT-4.0 received higher scores in the language simplification criterion than Llama3.1-8B-RAG (mean 7.05, SD 1.5 vs mean 5.44, SD 2.6; post hoc test P<.001). Interrater variability in assigning scores ranged from 4.2% (n=3) to 85.8% (n=6) among primary health care professionals. Instructions leading to incorrect use of the medication had similar frequency among the models(ChatGPT-4.0: n=15, 22.7%; Llama3.1-8B: n=19, 22.8%; Llama3.1-8B-RAG: n=19, 22.8%; chi-square test P=.71). The frequencies of hallucination were similar (ChatGPT-4.0: n=7, 10.6%; Llama3.1-8B: n=9, 13.6%; Llama3.1-8B-RAG: n=6, 9.1%; chi-square test P=.67). Conclusions: The open-source LLM enhanced with external information presented similar performance to the closed-source model, except for ChatGPT4.0, which was superior in language simplification of messages. LLM generation demonstrated potential for instructing patients on medication use. Nonetheless, the introduction of this innovation into the electronic prescribing workflow demands prescriber validation for human oversight of the technology and requires a strategy for LLM performance governance.

Ebola outbreak continues to worsen, with new collateral risks for girls and women

✇STAT
By: Theresa Gaffney
26 May 2026 at 21:13

Get your daily dose of health and medicine every weekday with STAT’s free newsletter Morning Rounds. Sign up here.

Good morning. Here’s the news you need to know after the long weekend. 

Read the rest…

© OLIVIER DOULIERY/AFP via Getty Images

A Multi-Omics Approach Uncovers Divergent Mechanisms of Asthma in Normal Weight and Obese Children

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Ilhame Diboun · Harshita Shailesh · Shana Jacob · Mohamed A Elrayess · Stefan Worgall · Younes Mokrab · Ibrahim Janahi
26 May 2026 at 18:00

Metabolites. 2026 May 15;16(5):333. doi: 10.3390/metabo16050333.

ABSTRACT

Background: Children with obesity-related asthma exhibit poorer symptom control and more frequent exacerbations than their normal-weight peers, but the underlying metabolic mechanisms are unclear. This study aimed to identify drivers of obesity-related asthma through untargeted plasma metabolomic and lipidomic profiling. Methods: Plasma was obtained from normal weight (NW) asthmatic (n = 95) and non-asthmatic (n = 67) and overweight/obese (OO) asthmatic (n = 99) and non-asthmatic (n = 100) children (6-17 years). We assessed metabolic and lipidomic differences between asthmatics and controls within each BMI group using orthogonal partial least squares discriminant analysis (OPLS-DA), examined overlap with the adult Qatar Biobank cohort, and mapped metabolic-clinical interactions using Gaussian Graphical Models. Results: In the fitted OPLS-DA models, separation between asthmatic and control groups was stronger in the NW group (R2Y = 0.72/0.52) than in OO (R2Y = 0.65/0.63) children. Asthma was associated with altered tricarboxylic acid (TCA) intermediates, ether-linked phosphatidylethanolamines, and sphingomyelins (SM) in NW, and with phosphatidylcholines, lysophosphatidylcholines, and phosphatidylethanolamines in OO. Integrating metabolomic, lipidomic, and clinical data revealed connections between altered SMs and interleukins, and TCA intermediates and electrolytes, all associated with elevated leptin in NW. An increased residual volume to total lung capacity ratio in OO was associated with phospholipid shifts. The overall dynamics in lipid metabolism with asthma, conditioned on BMI, was also observed in the adult Qatar Biobank cohort. Conclusions: Among NW children with asthma, we found enhanced TCA cycle activity and inflammation linked to altered SM metabolism, whereas in OO, the findings suggest oxidative stress arising from chronic obesity-related inflammation. These data reveal BMI-specific metabolic mechanisms of pediatric asthma that might inform precision approaches to disease management.

PMID:42188042 | DOI:10.3390/metabo16050333

A Multi-Omics Approach Uncovers Divergent Mechanisms of Asthma in Normal Weight and Obese Children

✇Omics In Lung
By: Ilhame Diboun · Harshita Shailesh · Shana Jacob · Mohamed A Elrayess · Stefan Worgall · Younes Mokrab · Ibrahim Janahi
26 May 2026 at 18:00

Metabolites. 2026 May 15;16(5):333. doi: 10.3390/metabo16050333.

ABSTRACT

Background: Children with obesity-related asthma exhibit poorer symptom control and more frequent exacerbations than their normal-weight peers, but the underlying metabolic mechanisms are unclear. This study aimed to identify drivers of obesity-related asthma through untargeted plasma metabolomic and lipidomic profiling. Methods: Plasma was obtained from normal weight (NW) asthmatic (n = 95) and non-asthmatic (n = 67) and overweight/obese (OO) asthmatic (n = 99) and non-asthmatic (n = 100) children (6-17 years). We assessed metabolic and lipidomic differences between asthmatics and controls within each BMI group using orthogonal partial least squares discriminant analysis (OPLS-DA), examined overlap with the adult Qatar Biobank cohort, and mapped metabolic-clinical interactions using Gaussian Graphical Models. Results: In the fitted OPLS-DA models, separation between asthmatic and control groups was stronger in the NW group (R2Y = 0.72/0.52) than in OO (R2Y = 0.65/0.63) children. Asthma was associated with altered tricarboxylic acid (TCA) intermediates, ether-linked phosphatidylethanolamines, and sphingomyelins (SM) in NW, and with phosphatidylcholines, lysophosphatidylcholines, and phosphatidylethanolamines in OO. Integrating metabolomic, lipidomic, and clinical data revealed connections between altered SMs and interleukins, and TCA intermediates and electrolytes, all associated with elevated leptin in NW. An increased residual volume to total lung capacity ratio in OO was associated with phospholipid shifts. The overall dynamics in lipid metabolism with asthma, conditioned on BMI, was also observed in the adult Qatar Biobank cohort. Conclusions: Among NW children with asthma, we found enhanced TCA cycle activity and inflammation linked to altered SM metabolism, whereas in OO, the findings suggest oxidative stress arising from chronic obesity-related inflammation. These data reveal BMI-specific metabolic mechanisms of pediatric asthma that might inform precision approaches to disease management.

PMID:42188042 | DOI:10.3390/metabo16050333

Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Gregory Magarshak
26 May 2026 at 12:00
arXiv:2605.23928v1 Announce Type: new Abstract: We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed agents that advance shared tasks without waiting for user prompts. The architecture rests on three mutually reinforcing mechanisms. Write-time context assembly precomputes enriched typed attributes via Groker agents, assembling interaction context as a deterministic pure function of graph state; context blocks are byte-identical across turns between semantic changes, enabling near-100% KV-cache reuse. Composable sandboxed wisdom programs form a governed library of LM-generated imperative programs declaratively wired to goal types via typed stream relations, composed via phase ordering, and executed at interaction time without further LM calls. Proactive goal stream state machines drive conversations toward terminal states by inspecting graph state and emitting structured interaction content (option arrays, governance affordances, clarification prompts) without awaiting user input. We prove six formal results: the Context Stability Theorem, bounding per-turn LM cost as a function of semantic change rate; a Program Composition Correctness Theorem; a Declarative Wiring Soundness Theorem; the Proactive Dominance Theorem, proving proactive agents weakly dominate reactive agents on expected turns-to-terminal-state; Coordination Overhead Elimination and Quality Preservation, establishing Pareto improvements in multi-participant goal chats; and a Cross-Platform Vote Consistency Theorem. Implemented in the open-source Qbix / Safebox / Safebots stack.

BoxLitE: A Faithful Knowledge Base Embedding Based on Convex Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Bruno F. Louren\c{c}o · Hesham Morgan · Ana Ozaki · Aleksandar Pavlovi\'c · Emanuel Sallinger
26 May 2026 at 12:00
arXiv:2605.23937v1 Announce Type: new Abstract: Knowledge base (KB) embeddings aim at combining the capability of classical knowledge graph embeddings to generalize the information present in facts, the ABox, with conceptual knowledge represented in an ontology language, the TBox. Several authors have recently explored the idea of mapping concepts to convex regions in a vector space. This is useful to represent hierarchies, typically present in TBoxes, since more general concepts can be mapped to larger regions, containing those regions associated with more specific concepts. However, the power of convexity is rarely leveraged during the actual learning tasks. Here, we introduce BoxLitE, a KB embedding model for DL-Lite$^{\mathcal{H}}$ that allows for convex optimization. We show that for any satisfiable DL-Lite$^{\mathcal{H}}$ KB, there is a BoxLitE embedding that is a weakly faithful model. As a proof of concept, we show how to formulate the KB embedding task as a convex optimization problem and how to obtain embeddings with such desirable faithfulness properties.

From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ruizhe Zhou · Xiaoyang Liu · Gaoyuan Du · Yi Zheng · Shouxi Ren · Deepayan Chakrabarti · Dengdu Jiang
26 May 2026 at 12:00
arXiv:2605.23955v1 Announce Type: new Abstract: Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabilities in algorithmic reproducibility. While early financial ML addressed statistical challenges such as backtest overfitting, deep neural networks and Generative AI have introduced mechanical nondeterminism rooted in hardware and architecture. This survey provides a systems perspective on reproducibility failures across three modalities now dominant in financial AI: tabular models (post-hoc explanation variance), graph networks (stochastic sampling and temporal asynchrony), and LLM-based agentic workflows (batch-dependent divergence and trajectory drift). We supplement the literature analysis with first-party experiments on public financial datasets -- quantifying explanation rank instability in credit scoring, prediction flip rates in GNN-based fraud detection, and tensor-parallel-induced output divergence in LLM entity extraction. We propose a layered evaluation framework linking modality-specific metrics (RBO, D_cos, TDI, PSD) to audit readiness, and empirically validate the complementarity of logit-level and semantic-level determinism measures.

EPPC-OASIS: Ontology-Aware Adaptation and Structured Inference Refinement for Electronic Patient-Provider Communication Mining in Secure Messages

✇cs.AI, q-bio.NC updates on arXiv.org
By: Samah Fodeh · Sreeraj Ramachandran · Elyas Irankhah · Muhammad Arif · Afshan Khan · Ganesh Puthiaraju · Linhai Ma · Srivani Talakokkul · Jordan Alpert · Sarah Schellhorn
26 May 2026 at 12:00
arXiv:2605.24172v1 Announce Type: new Abstract: Secure patient-provider messages contain clinically important communication behaviors that are difficult to characterize manually at scale. The Electronic Patient-Provider Communication (EPPC) framework provides an ontology for coding these behaviors, but automated extraction remains challenging because predictions must preserve fine-grained code/sub-code structure while grounding annotations in message text. We developed EPPC-OASIS, an ontology-aware adaptation approach for structured EPPC extraction, and combined it with deployable inference-refinement procedures designed to improve the coherence of final annotations. EPPC-OASIS augments supervised fine-tuning with a Wasserstein alignment objective that encourages alignment between model representation neighborhoods and EPPC ontology-derived neighborhoods, while inference refinement uses verification, self-consistency, hybrid correction, and selection or ensembling to address residual prediction errors. We evaluated the framework on a de-identified corpus of secure patient-provider messages against prompting, supervised fine-tuning, preference-based, and robustness-oriented baselines across multiple open-weight language models. Across model families, the best deployable pipeline achieved 77.13% Code+Sub-code F1 and 63.83% Triplet F1, corresponding to modest but consistent absolute gains of +1.39 and +2.12 F1 points over the strongest supervised fine-tuning baseline. These results suggest that ontology-aware adaptation with structured inference refinement can support scalable retrospective EPPC mining, although external validation is needed before operational use.

A governance horizon for ethical-use constraints in open-weight AI models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Weiwei Xu · Hengzhi Ye · Haoran Ye · Kai Gao · Vladimir Filkov · Minghui Zhou
26 May 2026 at 12:00
arXiv:2605.24383v1 Announce Type: new Abstract: Ethical constraints on open-weight AI models are both a reflection of societal concerns and a foundation for AI governance policy. They are expected to propagate to downstream derivatives while implemented as voluntary metadata disclosures that must be restated at each generation of reuse. We audit 2,142,823 model repositories on Hugging Face Hub to test whether this disclosure-based governance infrastructure can sustain traceability across deep model lineages. Restriction evidence decays with a half-life of 1.31 derivation steps ($R^2$=0.98), and beyond seven downstream generations at least 80% of descendant models lack sufficient public evidence for a governance determination, a depth boundary we formalize as the governance horizon. Platform-level interventions to restore missing licence metadata reveal that policy design (not enforcement alone) is the binding factor: inheritance-only designs require near-complete enforcement to move the horizon, whereas a mandatory-declaration design that explicitly resolves orphan lineage components shifts the horizon already at moderate enforcement. The structural bottleneck is lineages with no inheritable upstream intent: such orphan components remain undecidable under any inheritance-only policy regardless of enforcement rate, and unresolved upstream nodes additionally create direct downstream undecidability bottlenecks that inheritance rules alone cannot recover. Comparison with PyPI, where governance signals are carried by explicit machine-readable declarations, corroborates that the collapse is topology-specific to open-weight derivation rather than inherent to open ecosystems. These results establish that disclosure-based governance has a shallow, structurally determined reach in open-weight AI, and that achieving deep supply-chain accountability requires provenance mechanisms propagating governance signals through derivation itself.

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jingchu Gai · Guanning Zeng · Christina Baek · Chen Wu · J. Zico Kolter · Andrej Risteski · Aditi Raghunathan
26 May 2026 at 12:00
arXiv:2605.24396v1 Announce Type: new Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models, but the step-level annotations needed to train them are expensive and scarce. We find such a signal in how the model's confidence evolves during reasoning: premature confidence, the tendency to commit to an answer early and use the remaining tokens to rationalize it, strongly predicts flawed reasoning across tasks and model scales. We exploit this in progressive confidence shaping, a reinforcement learning objective that trains models to update their confidence as they reason rather than commit early -- rewarding gradual confidence growth and penalizing early commitment, with no external labels or reward models. The method improves accuracy and reasoning quality from 1.5B to 8B parameters across arithmetic (Countdown), math (DAPO, AIME), and science (ScienceQA): on Countdown, accuracy improves 3.2x (+42.0pp) and flawed reasoning drops 48pp; on AIME, Pass@64 improves 6.6pp. Consistent with this mechanism, the method also improves faithfulness: on a safety benchmark, our models more transparently surface misleading content in their reasoning traces rather than concealing it. Controlled experiments reveal that the problem and its remedy scale together: premature confidence grows with model size and task difficulty, and so do the gains from addressing it.

JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data

✇cs.AI, q-bio.NC updates on arXiv.org
By: Junlan Feng · Fanyu Meng · Chong Long · Pengyu Cong · Duqing Wang · Yan Zheng · Yuyao Zhang · Xuanchang Gao · Ye Yuan · Yunfei Ma · Zhijie Ren · Fan Yang · Na Wu · Di Jin · Chao Deng
26 May 2026 at 12:00
arXiv:2605.24414v1 Announce Type: new Abstract: We introduce JT-Safe-V2, a large language model designed to advance the safety and trustworthiness of foundation models, extending our previous JT-Safe model toward a more comprehensive safety-by-design paradigm. JT-Safe-V2 emphasizes the joint optimization of general intelligence and safety-by-design through several key innovations: enriching pre-training data with contextual world knowledge, high-certainty pre-training procedures, and safety strengthening post-training mechanisms for enterprise-oriented agentic capabilities. Building on these safety-enhanced foundation models, we propose Safe-MoMA (Safe Mixture of Models and Agents), a framework that enables traceable and efficient inference through the orchestrated deployment of multiple models and agents. Extensive evaluations demonstrate that JT-Safe-V2 achieves state-of-the-art performance across both general intelligence and safety benchmarks. Moreover, Safe-MoMA reduces inference costs by more than 30\% compared to using the largest standalone model baseline while maintaining comparable performance. To facilitate future research on safety-by-design foundation models, we publicly release the post-trained JT-Safe-V2-35B model checkpoint.

Hypothesis Generation and Inductive Inference in Children and Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jeffrey Qin · Wasu Top Piriyakulki · Zhuangfei Gao · Mia Radovanovic · Jessica Sommerville · Kevin Ellis · Marta Kryven
26 May 2026 at 12:00
arXiv:2605.24528v1 Announce Type: new Abstract: Real world decision-making requires constructing mental models under uncertainty over evidence, over the underlying causal rules, and over the state of the world itself. Which computational principles underpin human inference under such conditions, and do LLM-based agents exhibit similar behavior given matching constraints? We address these questions using an inductive inference Box Task in which participants, human children and LLM-based agents, infer a latent cause through sequential interaction with an uncertain environment. We formalize this task as program induction with Bayesian particle-based inference, admitting two complementary interpretations: (1) as a constraint satisfaction process over hypotheses, and (2) as a program synthesis problem in which hypotheses are executable programs evaluated against evidence. Using the constraint-based formulation, we show that children's behavior is best explained by a combination of subjective evidence reliability and online hypothesis generation, accounting for both their evidence-seeking patterns and their dissociation between task completion and rule generalization. Using the program synthesis formulation, we treat LLM-based agents as model organisms: controllable systems that allow systematic manipulation of task conditions. Across backends, LLM-based agents replicate children's responses to changes in evidence reliability and observability, including discounting unreliable evidence, seeking to resolve partial information, and dissociating between task completion and causal generalization. At the same time, LLM-based agents tend to over-observe and over-comply with instructions relative to children. These results suggest that while children and LLM-based agents adapt similarly to environmental structure, their information-seeking behavior exhibits distinct underlying costs and inductive biases.

Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhimin Lin · Kun Cheng · Fan Bai · Jie Gao
26 May 2026 at 12:00
arXiv:2605.24600v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for qualitative data analysis (QDA), yet their outputs often miss the depth and nuance of human analysis. We argue this gap reflects a missing credibility practice from human QDA: peer debriefing, in which an analyst seeks feedback from a disinterested peer and uses it to refine their coding. To bring this practice into LLM-assisted QDA, we propose Agent-as-Peer-Debriefer, a multi-agent QDA framework that builds peer debriefing into key coding steps. In our framework, a Hierarchical Coding Agent follows the standard QDA process to generate codes, sub-themes, and themes, along with self-explanations and reflection memos. It then shares these outputs with three Peer-Debriefing Agents, each applying a distinct analytical perspective (Theory-Driven, Data-Driven, or Applied) and refining the codes by keeping, renaming, reassigning, merging, or splitting them. These perspectives are drawn from established human QDA practices that generalize across domains and datasets. To evaluate the framework, we test it on three datasets across two domains with three LLMs, measuring semantic similarity to human-annotated codes. Across all settings, perspective-based, peer-debriefing refinement aligns more closely with human codes than a single-LLM baseline, and an ablation further shows the gain is not merely from additional refinement. The three perspectives also produce distinct trade-offs, showing that the choice of perspective is a meaningful and controllable design decision. More broadly, these findings suggest that simulating peer debriefing with explicit perspectives is a promising route to more credible LLM-assisted QDA.

Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ali \c{S}enol · Garima Agrawal · Huan Liu
26 May 2026 at 12:00
arXiv:2605.24661v1 Announce Type: new Abstract: LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offering limited insight into the underlying reasoning processes that produce those answers. To address this gap, this study proposes a unified multi-dimensional framework for measuring reasoning quality in LLMs from a behavioral perspective, operationalizing six theoretically grounded dimensions: Correctness (CQ), Consistency (CS), Robustness (RS), Logical Coherence (LS), Efficiency (ES), and Stability (SS). Extensive experiments on seven LLMs across 975 items from four benchmarks demonstrate that the framework reveals behaviors invisible to accuracy-only metrics. Notably, logical coherence is orthogonal to correctness (r = -0.172, ns), confirming that correct answers can arise from incoherent reasoning, while Claude-Haiku-4.5 achieves the highest multi-dimensional score (Q_bal = 0.778). Furthermore, the framework exposes critical ranking inversions: DeepSeek-V3 ranks second under accuracy-priority but fifth under legal/compliance weighting, a reversal that single-metric evaluation cannot detect. Discriminant validity confirms 11/15 dimension pairs are independent (|r|

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuanzhi Xu · Qian Gao · Jun Fan · Guohui Ding · Zhenyu Yang · Sixue Lin · Yuteng Xiao
26 May 2026 at 12:00
arXiv:2605.24957v1 Announce Type: new Abstract: The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven fine-tuning and high-latency contrastive decoding to rigid attention head truncation - frequently compromise either computational efficiency or the continuity of the model's feature space. To overcome these limitations, we introduce a novel, training-free inference strategy that operates as a region-aware adaptive weighting mechanism to dynamically correct semantic drift without relying on abrupt heuristic truncations. By computing an outlier-resistant statistical midpoint across various attention heads, we establish a stable anchor for reliable visual representations. We then utilize the inter-head disagreement mapped across regions to dynamically determine intervention budgets, gently suppressing hallucination-inducing attention paths through a continuous penalty modulation. This recalibration process effectively rectifies visual-semantic misalignments while fully preserving generative fluency and language priors. Comprehensive evaluations on standard multimodal benchmarks, including CHAIR, POPE, and MME, reveal that our strategy substantially curtails both instance- and sentence-level hallucinations. The results demonstrate state-of-the-art performance against contemporary baselines, confirming our method's efficiency and algorithmic robustness. Our code will be public.

Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chengwei Li · Junlin Liu · Yang Gao
26 May 2026 at 12:00
arXiv:2605.25091v1 Announce Type: new Abstract: As modern air combat evolves toward beyond-visual-range (BVR) multi-aircraft cooperative engagements, autonomous decision-making for unmanned combat aerial vehicles (UCAVs) faces significant challenges due to high-dimensional state spaces, discrete action commands, and strongly adversarial dynamic environments. To overcome the limitations of existing multi-agent reinforcement learning (MARL) methods in such settings, namely insufficient exploration efficiency, low sample utilization, and poor policy generalization, we propose Adversarial Curriculum and Evolutionary-enhanced Multi-agent Proximal Policy Optimization (ACE-MAPPO), a hybrid learning framework that integrates evolutionary algorithms with MAPPO. Specifically, a genetic soft update mechanism is introduced to enhance population diversity and mitigate convergence to local optima. An evolutionary-augmented prioritized trajectory replay strategy is further employed to improve the utilization of sparse high-value samples. In addition, an adversarial evolutionary curriculum learning mechanism is designed to enable adaptive training with progressively increasing difficulty. Extensive experimental results demonstrate that the proposed method outperforms MAPPO and other baseline algorithms in terms of training stability, convergence speed, and win rate, validating its effectiveness in multi-aircraft cooperative air combat scenarios.

SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guohong Liu · Jialei Ye · Pengzhi Gao · Wei Liu · Jian Luan · Yunxin Liu · Yuanchun Li
26 May 2026 at 12:00
arXiv:2605.25160v1 Announce Type: new Abstract: Mobile GUI agents powered by large language models have progressed rapidly, creating urgent needs for realistic and comprehensive evaluation. Existing benchmarks prioritize reproducibility but are often limited to open-source apps or file-operation tasks for the difficulty of constructing rewards on real applications, leaving a gap between benchmark settings and real-world usage. Moreover, most benchmarks focus on basic grounding and navigation, with limited coverage of complex, long-horizon interactions. To address these limitations, we introduce SimuWoB, a fully synthetic benchmark for mobile GUI agents with 120 challenging tasks spanning diverse types and difficulty levels. We build a robust virtual environment generation framework that synthesizes high-fidelity tasks and environments, and automatically provides valid rewards for each task. Each environment is deployed as a backend-free webpage accessible via URL, enabling efficient and reproducible evaluation. We conduct comprehensive experiments on several state-of-the-art mobile GUI agents. The average success rate is only 27.92%, dropping to 17.82% on long-horizon tasks, which reveals substantial weaknesses in current agents under complex scenarios. Evaluation result comparison with real-world sample tasks demonstrate that agent assessments based on our synthetic environment generalize well. We further provide diagnostic insights across key capability dimensions and discuss implications for future mobile GUI agent development.

Growing a Neural Network in Breadth, Depth, and Time

✇cs.AI, q-bio.NC updates on arXiv.org
By: Eivinas Butkus · Kedar Garz\'on Gupta · Nikolaus Kriegeskorte
26 May 2026 at 12:00
arXiv:2605.25174v1 Announce Type: new Abstract: Spatial and temporal resource constraints are critical for both biological and artificial intelligent systems. Here we define differentiable cost terms for breadth, depth, and time within a recurrent convolutional neural network conceived as a finite subset of an infinite lattice. We optimize these costs jointly with task errors via backpropagation. We set different pressures on breadth, depth, and time, which leads to diverse computational graphs emerging organically through training. We find that all three resources can be traded off against each other to achieve a given level of accuracy. Networks grow in all three dimensions with task complexity and spontaneously take more recurrent steps when inputs are occluded. Surprisingly, time used by the model correlates with human reaction times in an object recognition task. Our framework provides a normative account of how resource constraints shape neural architectures, connecting to questions about brain design in neuroscience, and may help illuminate the diversity of neural solutions found in nature.

A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ziqing Yu · Yuhui Tao · Jiayu Huo · Lei Pan · Zilong Xiao · Juecheng Chen · Xiao Li · Jianxuan Li · You Zhou · Zhixing Li · Cong Wang · Beijian Zhang · Chen Chen · Hongyang Lu · Konstantinos Patlatzoglou · Daniel B. Kramer · Jonathan W. Waks · Yangang Su · Fu Siong Ng · Shuo Wang · Yixiu Liang · Junbo Ge
26 May 2026 at 12:00
arXiv:2605.25446v1 Announce Type: new Abstract: Electrocardiography (ECG) is central to cardiovascular care, but conventional AI models are often restricted to common arrhythmias and may generalize poorly across populations or clinically subtle diseases. We developed ECG Contrastive Language-Image Pre-training (ECGCLIP), a signal-language contrastive learning framework that aligns ECG waveforms with expert diagnostic reports. ECGCLIP was pre-trained on 2,837,962 ECG studies from 1,324,856 patients and evaluated on a held-out internal test set plus nine independent external cohorts comprising about 1.5 million ECGs. Evaluation covered 89 downstream tasks, including 45 ECG diagnoses, 39 echocardiographic targets, and 5 rare cardiac diseases, using PRAUC as the primary metric. ECGCLIP consistently improved performance over random initialization and Merl-R18 baselines. On the internal test set, ECGCLIP-R34 achieved strong performance for atrial fibrillation (PRAUC 0.900) and ST-segment elevation myocardial infarction (PRAUC 0.383), with robust generalization across all external cohorts. It also improved low-prevalence and diagnostically elusive diseases, including Ebstein anomaly, constrictive pericarditis, dextrocardia, and cardiac amyloidosis, with internal PRAUC values of 0.253, 0.175, 0.121, and 0.201, respectively. ECGCLIP was data efficient, matching or exceeding full-dataset baseline performance with only 10% of training data. Feature visualization and saliency analysis suggested clinically meaningful representations aligned with established electrocardiographic criteria. These findings indicate that large-scale ECG-report contrastive pre-training can expand routine ECG interpretation beyond common arrhythmias toward broad cardiovascular assessment and opportunistic screening of echocardiographic and rare conditions.

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qiming Ye · Peixain Zhang · Yupeng He · Zifan Peng · Gareth Tyson
26 May 2026 at 12:00
arXiv:2605.25815v2 Announce Type: new Abstract: Agent-to-Agent (A2A) networks enable autonomous AI agents to collaborate by sharing reusable problem-solving instructions. However, how these decentralized ecosystems operate in practice remains largely unexplored. We present the first large-scale empirical study of EvoMap, a prominent A2A collaboration network. By analyzing over 1.5M assets and 128K agents, we show how design choices that prioritize scalable growth introduce trade-offs in reusability, evolution, and auditability. First, EvoMap's credit economy rewards agents for publishing valuable assets. Although this design encourages participation at scale, rewards are tied primarily to publication rather than adoption. This leads agents to mass-produce assets to accumulate credits. As a result, 98% of assets are never reused, while rewards become highly concentrated among a small fraction of agents. Second, EvoMap employs an algorithm (referred to as GDI) to score and rank the quality of these shared assets. We demonstrate that this scoring system is flawed: rather than measuring objective performance, an asset's rank is heavily dictated by unverified, self-reported metadata (e.g., claimed lines of code modified). This allows agents to trivially manipulate their asset's scores. Finally, EvoMap relies on agents to provide local execution logs as evidence that uploaded assets function correctly. Because these validations are not independently verified, over 84% of approved assets bypass quality checks using vacuous tests (e.g., `console.log`). Our findings show that future A2A collaboration networks cannot rely on unverified self-reporting alone. Scalable collaboration requires mechanisms that balance open participation with verifiable execution and trustworthy evaluation.
❌