❌

Normal view

Received β€” 8 April 2026 ⏭

A Gamified Mobile Health Intervention to Promote Physical Activity, Executive Function, and Mental Health in College Students: Randomized Controlled Trial

βœ‡Journal of Medical Internet Research
By: Ming Yang Β· Yingjun Guo Β· Zhen Li Β· Lei Jiang Β· Yanan Gao Β· Sen Yang Β· Zhixiong Zhou
8 April 2026 at 01:30
Background: College students commonly experience suboptimal health conditions, including insufficient physical activity (PA), excessive body weight, and declining physical fitness. Traditional interventions face low adherence, while gamified mobile health (mHealth) programs may improve engagement and outcomes. Objective: This study aimed to evaluate the feasibility and effectiveness of a novel gamified, incentive-based mHealth intervention on primary outcomes (PA and adherence) and secondary outcomes (physical fitness, body composition, executive function [EF], and mental health). Methods: A 2-arm parallel-group randomized controlled trial (RCT) was conducted in 2025 at Yantai University with 160 college students (18‐25 years; BMI 18.5‐30.0) who were randomized 1:1 (computer-generated, sex-stratified blocks of 4; concealed allocation) to the intervention group (IG) or control group (CG; n=80 each); major exclusions were contraindications to exercise, severe physical/mental illness, recent PA interventions, or psychotropic medication use. Both used the same fitness watch–app system and identical PA targets (β‰₯150 min moderate-to-vigorous physical activity [MVPA] per week or β‰₯900 metabolic equivalent-minutes [MET-min] per week); IG additionally received team-based gamification (competition, points/leaderboards, feedback, and rewards), while CG received monitoring only. PA and adherence were monitored throughout the 8-week intervention; other outcomes were assessed at baseline and 8 weeks (fitness, body composition, EF, and mental health). Open-label with blinded outcome assessors/analysts; intention-to-treat (ITT) with multiple imputation. Results: At 8 weeks, data were available for 154 participants (IG 78; CG 76); all 160 were analyzed per ITT. Compared to the CG, the IG demonstrated significantly higher mean levels in all primary PA outcomes over 8 weeks (daily steps: mean 10,356, SD 1245 versus 8242, SD 1087; Ξ”=2114; =1.81, 95% CI 1.44‐2.18;

Initial Insights Into an Institutional Secure Large Language Model for Magnetic Resonance Imaging Examination Requests: Retrospective Study

βœ‡Journal of Medical Internet Research
By: James Thomas Patrick Decourcy Hallinan Β· Naomi Wenxin Leow Β· Yi Xian Low Β· Aric Lee Β· Wilson Ong Β· Matthew Ding Zhou Chan Β· Ganakirthana Kalpenya Devi Β· Stephanie Shengjie He Β· Daniel De-Liang Loh Β· Desmond Shi Wei Lim Β· Xi Zhen Low Β· Mei Chin Lim Β· Clement Yong Β· Weizhong Jonathan Sng Β· Ee Chin Teo Β· Jiong Hao Tan Β· Naresh Kumar Β· Andrew Makmur Β· Yonghan Ting
8 April 2026 at 01:30
Background: Incomplete clinical details on magnetic resonance imaging (MRI) examination requests (MERs) can lead to suboptimal protocol selection. An institutional secure large language model (sLLM) with access to manually retrieved salient data from the electronic medical record (EMR) may improve request completeness and protocol accuracy across multiple MRI subspecialties. Objective: The objective of this study was to compare clinician MERs with sLLM-augmented MERs for information quality and to evaluate the protocoling accuracy of the sLLM versus board-certified radiologists across body, musculoskeletal, and neuroradiology MRI. Methods: This retrospective study included 608 random outpatient MRI examinations performed between September 2023 and July 2024 (body 206, musculoskeletal 203, neuroradiology 199). The cohort comprised 528 patients (mean 51.2 years, SD 19.2; range 4‐93; n=279, 52.8% women, n=249, 47.2% men). MERs without EMR access were excluded. A privately hosted Anthropic Claude 3.5 model (temperature 0) augmented each MER with manually retrieved salient EMR data and, via rule-based parsing, mapped the extracted elements onto predefined institutional criteria to recommend region or coverage and contrast use. Two experienced radiologists established a consensus reference standard. Two board-certified general radiologists (Rad 3 and Rad 4) and the sLLM were compared with this standard. Clinical information quality was graded using the Reason-for-Exam Imaging Reporting and Data System (RI-RADS). Interrater reliability was quantified with Gwet AC1. Paired accuracies were compared with the McNemar test to determine whether there was a statistically significant difference. Results: Interreader agreement for RI-RADS was almost perfect for sLLM-augmented MERs (AC1 0.97, 95% CI 0.94‐0.99) and moderate for clinician MERs (AC1 0.43, 95% CI 0.34‐0.52). Limited or deficient clinical information (RI-RADS C/D) fell to 0% to 0.7% (0/608 to 4/608) with sLLM augmentation vs 4.1% to 20.4% (25/608 to 124/608) for clinician MERs. Overall protocol accuracy was 93.1% (566/608; 95% CI 89.6‐96.6) for the sLLM, 91.4% (556/608; 95% CI 87.6‐95.3) for Rad 3, and 92.1% (560/608; 95% CI 88.4‐95.8) for Rad 4 (sLLM vs Rad 3 =.23 vs Rad 4 =.40). Region or coverage accuracy was similar (sLLM: 579/608, 95.2%; Rad 3: 585/608, 96.2%; Rad 4: 573/608, 94.2%; =.46 and =.36). Contrast decisions were more accurate using the sLLM at 94.4% (574/608; 95% CI 91.3‐97.5) vs Rad 3 at 92.1% (560/608; 95% CI 88.4‐95.8; =.027) and were not significantly different to Rad 4 at 92.9% (565/608; 95% CI 89.4‐96.4; =.16). Subspecialty analyses showed similar patterns, with the sLLM outperforming Rad 4 for musculoskeletal MRI contrast decisions (96.6% vs 91.1%; =.006) and matching readers elsewhere. Manual review indicated that sLLM improvements arose from EMR details not listed on the MER (infection/inflammation, tumor history, prior surgery). No clinically significant hallucinations were identified in a manual review of discordant cases. Conclusions: Across body, musculoskeletal, and neuroradiology MRI, sLLM-augmented examination requests improved clinical context and enhanced contrast selection while demonstrating accuracy comparable to general radiologists for region or coverage. Integrating sLLMs into routine vetting workflows may reduce manual workload in protocol selection for more efficient, standardized protocoling.

WNT7A correlates with immunosuppression and predicts adverse prognosis in lung adenocarcinoma: Potential implication of the NF-kappaB/CCL2 Axis

βœ‡(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Xiang Guo Β· Zhengfang Xiao Β· Yao Zhang Β· Li Wang Β· Hui Hu Β· Ting Liu Β· Yingjun Kong
7 April 2026 at 18:00

Cytokine. 2026 Apr 6;202:157144. doi: 10.1016/j.cyto.2026.157144. Online ahead of print.

ABSTRACT

BACKGROUND: The remodeling of the tumor immune microenvironment (TME) is a pivotal determinant of therapeutic efficacy and clinical outcome in Lung Adenocarcinoma (LUAD). While WNT signaling is a known oncogenic driver, the specific immunomodulatory role of WNT7A and its potential crosstalk with inflammatory pathways in LUAD remain to be fully elucidated. We sought to define the prognostic value of WNT7A and explore the molecular mechanisms by which it may foster an immunosuppressive TME.

METHODS: We performed a multi-omics analysis utilizing the TCGA-LUAD cohort (N = 508) and validated findings in an independent external cohort (GSE30219, N = 293). The prognostic significance of WNT7A was evaluated using Kaplan-Meier and multivariate Cox regression analyses. TME composition was dissected via ssGSEA, focusing on myeloid-derived suppressor cell (MDSC) infiltration. Mechanistic pathways were identified using Gene Set Enrichment Analysis (GSEA) and gene co-expression networks.

RESULTS: High WNT7A expression was identified as a significant predictor of poor Overall Survival (OS) in the TCGA cohort (P < 0.05) and validated in the external cohort (P < 0.05). Multivariate analysis confirmed WNT7A as an independent prognostic risk factor (HR = 1.085, P = 0.036). Immunologically, WNT7A expression was positively correlated with MDSC infiltration (R = 0.43, P < 0.001), suggesting a shift towards an immune-tolerant phenotype. Mechanistically, GSEA revealed a robust activation of inflammatory signaling in the high-WNT7A group. Specifically, the TNFA Signaling via NF-ΞΊB pathway was significantly enriched(NES = 2.52, P < 0.001). Consistent with this pathway activation, WNT7A showed a statistically significant positive correlation with CCL2 (P < 0.001), a critical chemokine for MDSC recruitment, implicating the NF-ΞΊB/CCL2 axis in this process.

CONCLUSION: WNT7A serves as a prognostic biomarker linked to immune evasion in LUAD, potentially by modulating the NF-ΞΊB/CCL2/MDSC axis. This study identifies WNT7A as a potential therapeutic target to remodel the immune microenvironment, providing a rationale for future investigations into WNT-targeted strategies to improve immunotherapy efficacy.

PMID:41946008 | DOI:10.1016/j.cyto.2026.157144

WNT7A correlates with immunosuppression and predicts adverse prognosis in lung adenocarcinoma: Potential implication of the NF-kappaB/CCL2 Axis

βœ‡Omics In Lung
By: Xiang Guo Β· Zhengfang Xiao Β· Yao Zhang Β· Li Wang Β· Hui Hu Β· Ting Liu Β· Yingjun Kong
7 April 2026 at 18:00

Cytokine. 2026 Apr 6;202:157144. doi: 10.1016/j.cyto.2026.157144. Online ahead of print.

ABSTRACT

BACKGROUND: The remodeling of the tumor immune microenvironment (TME) is a pivotal determinant of therapeutic efficacy and clinical outcome in Lung Adenocarcinoma (LUAD). While WNT signaling is a known oncogenic driver, the specific immunomodulatory role of WNT7A and its potential crosstalk with inflammatory pathways in LUAD remain to be fully elucidated. We sought to define the prognostic value of WNT7A and explore the molecular mechanisms by which it may foster an immunosuppressive TME.

METHODS: We performed a multi-omics analysis utilizing the TCGA-LUAD cohort (N = 508) and validated findings in an independent external cohort (GSE30219, N = 293). The prognostic significance of WNT7A was evaluated using Kaplan-Meier and multivariate Cox regression analyses. TME composition was dissected via ssGSEA, focusing on myeloid-derived suppressor cell (MDSC) infiltration. Mechanistic pathways were identified using Gene Set Enrichment Analysis (GSEA) and gene co-expression networks.

RESULTS: High WNT7A expression was identified as a significant predictor of poor Overall Survival (OS) in the TCGA cohort (P < 0.05) and validated in the external cohort (P < 0.05). Multivariate analysis confirmed WNT7A as an independent prognostic risk factor (HR = 1.085, P = 0.036). Immunologically, WNT7A expression was positively correlated with MDSC infiltration (R = 0.43, P < 0.001), suggesting a shift towards an immune-tolerant phenotype. Mechanistically, GSEA revealed a robust activation of inflammatory signaling in the high-WNT7A group. Specifically, the TNFA Signaling via NF-ΞΊB pathway was significantly enriched(NES = 2.52, P < 0.001). Consistent with this pathway activation, WNT7A showed a statistically significant positive correlation with CCL2 (P < 0.001), a critical chemokine for MDSC recruitment, implicating the NF-ΞΊB/CCL2 axis in this process.

CONCLUSION: WNT7A serves as a prognostic biomarker linked to immune evasion in LUAD, potentially by modulating the NF-ΞΊB/CCL2/MDSC axis. This study identifies WNT7A as a potential therapeutic target to remodel the immune microenvironment, providing a rationale for future investigations into WNT-targeted strategies to improve immunotherapy efficacy.

PMID:41946008 | DOI:10.1016/j.cyto.2026.157144

IC3-Evolve: Proof-/Witness-Gated Offline LLM-Driven Heuristic Evolution for IC3 Hardware Model Checking

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Mingkai Miao Β· Guangyu Hu Β· Ziyi Yang Β· Hongce Zhang
7 April 2026 at 12:00
arXiv:2604.03232v1 Announce Type: new Abstract: IC3, also known as property-directed reachability (PDR), is a commonly-used algorithm for hardware safety model checking. It checks if a state transition system complies with a given safety property. IC3 either returns UNSAFE (indicating property violation) with a counterexample trace, or SAFE with a checkable inductive invariant as the proof to safety. In practice, the performance of IC3 is dominated by a large web of interacting heuristics and implementation choices, making manual tuning costly, brittle, and hard to reproduce. This paper presents IC3-Evolve, an automated offline code-evolution framework that utilizes an LLM to propose small, slot-restricted and auditable patches to an IC3 implementation. Crucially, every candidate patch is admitted only through proof- /witness-gated validation: SAFE runs must emit a certificate that is independently checked, and UNSAFE runs must emit a replayable counterexample trace, preventing unsound edits from being deployed. Since the LLM is used only offline, the deployed artifact is a standalone evolved checker with zero ML/LLM inference overhead and no runtime model dependency. We evolve on the public hardware model checking competition (HWMCC) benchmark and evaluate the generalizability on unseen public and industrial model checking benchmarks, showing that IC3-Evolve can reliably discover practical heuristic improvements under strict correctness gates.

Position: Science of AI Evaluation Requires Item-level Benchmark Data

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Han Jiang Β· Susu Zhang Β· Xiaoyuan Yi Β· Xing Xie Β· Ziang Xiao
7 April 2026 at 12:00
arXiv:2604.03244v1 Announce Type: new Abstract: AI evaluations have become the primary evidence for deploying generative AI systems across high-stakes domains. However, current evaluation paradigms often exhibit systemic validity failures. These issues, ranging from unjustified design choices to misaligned metrics, remain intractable without a principled framework for gathering validity evidence and conducting granular diagnostic analysis. In this position paper, we argue that item-level AI benchmark data is essential for establishing a rigorous science of AI evaluation. Item-level analysis enables fine-grained diagnostics and principled validation of benchmarks. We substantiate this position by dissecting current validity failures and revisiting evaluation paradigms across computer science and psychometrics. Through illustrative analyses of item properties and latent constructs, we demonstrate the unique insights afforded by item-level data. To catalyze community-wide adoption, we introduce OpenEval, a growing repository of item-level benchmark data designed supporting evidence-centered AI evaluation.

Hume's Representational Conditions for Causal Judgment: What Bayesian Formalization Abstracted Away

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Yiling Wu
7 April 2026 at 12:00
arXiv:2604.03387v1 Announce Type: new Abstract: Hume's account of causal judgment presupposes three representational conditions: experiential grounding (ideas must trace to impressions), structured retrieval (association must operate through organized networks exceeding pairwise connection), and vivacity transfer (inference must produce felt conviction, not merely updated probability). This paper extracts these conditions from Hume's texts and argues that they are integral to his causal psychology. It then traces their fate through the formalization trajectory from Hume to Bayesian epistemology and predictive processing, showing that later frameworks preserve the updating structure of Hume's insight while abstracting away these further representational conditions. Large language models serve as an illustrative contemporary case: they exhibit a form of statistical updating without satisfying the three conditions, thereby making visible requirements that were previously background assumptions in Hume's framework.

Large Language Models Align with the Human Brain during Creative Thinking

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Mete Ismayilzada Β· Simone A. Luchini Β· Abdulkadir Gokce Β· Badr AlKhamissi Β· Antoine Bosselut Β· Antonio Laverghetta Jr. Β· Lonneke van der Plas Β· Roger E. Beaty
7 April 2026 at 12:00
arXiv:2604.03480v1 Announce Type: new Abstract: Creative thinking is a fundamental aspect of human cognition, and divergent thinking-the capacity to generate novel and varied ideas-is widely regarded as its core generative engine. Large language models (LLMs) have recently demonstrated impressive performance on divergent thinking tests and prior work has shown that models with higher task performance tend to be more aligned to human brain activity. However, existing brain-LLM alignment studies have focused on passive, non-creative tasks. Here, we explore brain alignment during creative thinking using fMRI data from 170 participants performing the Alternate Uses Task (AUT). We extract representations from LLMs varying in size (270M-72B) and measure alignment to brain responses via Representational Similarity Analysis (RSA), targeting the creativity-related default mode and frontoparietal networks. We find that brain-LLM alignment scales with model size (default mode network only) and idea originality (both networks), with effects strongest early in the creative process. We further show that post-training objectives shape alignment in functionally selective ways: a creativity-optimized \texttt{Llama-3.1-8B-Instruct} preserves alignment with high-creativity neural responses while reducing alignment with low-creativity ones; a human behavior fine-tuned model elevates alignment with both; and a reasoning-trained variant shows the opposite pattern, suggesting chain-of-thought training steers representations away from creative neural geometry toward analytical processing. These results demonstrate that post-training objectives selectively reshape LLM representations relative to the neural geometry of human creative thought.

Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graphs from Complex Documents

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Mohammad Sadeq Abolhasani Β· Yang Ba Β· Yixuan He Β· Rong Pan
7 April 2026 at 12:00
arXiv:2604.03496v1 Announce Type: new Abstract: Knowledge graph construction typically relies either on predefined ontologies or on schema-free extraction. Ontology-driven pipelines enforce consistent typing but require costly schema design and maintenance, whereas schema-free methods often produce fragmented graphs with weak global organization, especially in long technical documents with dense, context-dependent information. We propose TRACE-KG (Text-dRiven schemA for Context-Enriched Knowledge Graphs), a multimodal framework that jointly constructs a context-enriched knowledge graph and an induced schema without assuming a predefined ontology. TRACE-KG captures conditional relations through structured qualifiers and organizes entities and relations using a data-driven schema that serves as a reusable semantic scaffold while preserving full traceability to the source evidence. Experiments show that TRACE-KG produces structurally coherent, traceable knowledge graphs and offers a practical alternative to both ontology-driven and schema-free construction pipelines.

A Multimodal Foundation Model of Spatial Transcriptomics and Histology for Biological Discovery and Clinical Prediction

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Jinxi Xiang Β· Siyu Hou Β· Yuchen Li Β· Ryan Quinton Β· Xiaoming Zhang Β· Feyisope Eweje Β· Xiangde Luo Β· Yijiang Chen Β· Zhe Li Β· Colin Bergstrom Β· Ted Kim Β· Sierra Willens Β· Francesca Maria Olguin Β· Matthew Abikenari Β· Andrew Heider Β· Sanjeeth Rajaram Β· Joel Neal Β· Maximilian Diehn Β· Xiang Zhou Β· Ruijiang Li
7 April 2026 at 12:00
arXiv:2604.03630v1 Announce Type: new Abstract: Spatial transcriptomics (ST) enables gene expression mapping within anatomical context but remains costly and low-throughput. Hematoxylin and eosin (H\&E) staining offers rich morphology yet lacks molecular resolution. We present \textbf{\ours} (\textbf{S}patial \textbf{T}ranscriptomics and hist\textbf{O}logy \textbf{R}epresentation \textbf{M}odel), a foundation model trained on 1.2 million spatially resolved transcriptomic profiles with matched histology across 18 organs. Using a hierarchical architecture integrating morphological features, gene expression, and spatial context, STORM bridges imaging and omics through robust molecular--morphological representations. STORM enhances spatial domain discovery, producing biologically coherent tissue maps, and outperforms existing methods in predicting spatial gene expression from H\&E images across 11 tumor types. The model is platform-agnostic, performing consistently across Visium, Xenium, Visium HD, and CosMx. Applied to 23 independent cohorts comprising 7,245 patients, STORM significantly improves immunotherapy response prediction and prognostication over established biomarkers, providing a scalable framework for spatially informed discovery and clinical precision medicine.

PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Erhan Zhang Β· Yiqun Chen Β· Zechun Niu Β· Wei Yang Β· Xiaochi Wei Β· Yan Gao Β· Yi Wu Β· Yao Hu Β· Jiaxin Mao
7 April 2026 at 12:00
arXiv:2604.03675v1 Announce Type: new Abstract: In agentic search, large language models (LLMs) are trained to perform multi-turn retrieval and reasoning for complex tasks such as multi-hop question answering (QA). However, current search-based Reinforcement Learning (RL) methods suffer from two core limitations: expensive long-horizon rollouts are under-utilized during training, and supervision is typically available only at the final answer, resulting in severe reward sparsity. We present Prefix-based Rollout reuse for Agentic search with Intermediate Step rEwards (PRAISE), a framework for improving both data efficiency and credit assignment in agentic search training. Given a complete search trajectory, PRAISE extracts prefix states at different search turns, elicits intermediate answers from them, and uses these prefixes both to construct additional training trajectories and to derive step-level rewards from performance differences across prefixes. Our method uses a single shared model for both search policy learning and prefix answer evaluation, enabling joint optimization without extra human annotations or a separate reward model. Experiments on multi-hop QA benchmarks show that PRAISE consistently improves performance over strong baselines.
  • βœ‡cs.AI, q-bio.NC updates on arXiv.org
  • RL-Driven Sustainable Land-Use Allocation for the Lake Malawi Basin Ying Yao
    arXiv:2604.03768v1 Announce Type: new Abstract: Unsustainable land-use practices in ecologically sensitive regions threaten biodiversity, water resources, and the livelihoods of millions. This paper presents a deep reinforcement learning (RL) framework for optimizing land-use allocation in the Lake Malawi Basin to maximize total ecosystem service value (ESV). Drawing on the benefit transfer methodology of Costanza et al., we assign biome-specific ESV coefficients -- locally anchored to a Malawi
     
  • 🏷️
  • ↗️

RL-Driven Sustainable Land-Use Allocation for the Lake Malawi Basin

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Ying Yao
7 April 2026 at 12:00
arXiv:2604.03768v1 Announce Type: new Abstract: Unsustainable land-use practices in ecologically sensitive regions threaten biodiversity, water resources, and the livelihoods of millions. This paper presents a deep reinforcement learning (RL) framework for optimizing land-use allocation in the Lake Malawi Basin to maximize total ecosystem service value (ESV). Drawing on the benefit transfer methodology of Costanza et al., we assign biome-specific ESV coefficients -- locally anchored to a Malawi wetland valuation -- to nine land-cover classes derived from Sentinel-2 imagery. The RL environment models a 50x50 cell grid at 500m resolution, where a Proximal Policy Optimization (PPO) agent with action masking iteratively transfers land-use pixels between modifiable classes. The reward function combines per-cell ecological value with spatial coherence objectives: contiguity bonuses for ecologically connected land-use patches (forest, cropland, built area etc.) and buffer zone penalties for high-impact development adjacent to water bodies. We evaluate the framework across three scenarios: (i) pure ESV maximization, (ii) ESV with spatial reward shaping, and (iii) a regenerative agriculture policy scenario. Results demonstrate that the agent effectively learns to increase total ESV; that spatial reward shaping successfully steers allocations toward ecologically sound patterns, including homogeneous land-use clustering and slight forest consolidation near water bodies; and that the framework responds meaningfully to policy parameter changes, establishing its utility as a scenario-analysis tool for environmental planning.

Quantifying Trust: Financial Risk Management for Trustworthy AI Agents

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Wenyue Hua Β· Tianyi Peng Β· Chi Wang Β· Ian Kaufman Β· Bryan Lim Β· Chandler Fang
7 April 2026 at 12:00
arXiv:2604.03976v1 Announce Type: new Abstract: Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve into autonomous agents deployed in open environments and increasingly connected to payments or assets, the operational meaning of trust shifts to end-to-end outcomes: whether an agent completes tasks, follows user intent, and avoids failures that cause material or psychological harm. These risks are fundamentally product-level and cannot be eliminated by technical safeguards alone because agent behavior is inherently stochastic. To address this gap between model-level reliability and user-facing assurance, we propose a complementary framework based on risk management. Drawing inspiration from financial underwriting, we introduce the \textbf{Agentic Risk Standard (ARS)}, a payment settlement standard for AI-mediated transactions. ARS integrates risk assessment, underwriting, and compensation into a single transaction framework that protects users when interacting with agents. Under ARS, users receive predefined and contractually enforceable compensation in cases of execution failure, misalignment, or unintended outcomes. This shifts trust from an implicit expectation about model behavior to an explicit, measurable, and enforceable product guarantee. We also present a simulation study analyzing the social benefits of applying ARS to agentic transactions. ARS's implementation can be found at https://github.com/t54-labs/AgenticRiskStandard.

Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Oluseyi Olukola Β· Nick Rahimi
7 April 2026 at 12:00
arXiv:2604.04237v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to personalize instruction in intelligent tutoring systems, yet the field lacks a formal framework for defining and evaluating pedagogical safety. We introduce a four-layer model of pedagogical safety for educational RL comprising structural, progress, behavioral, and alignment safety and propose the Reward Hacking Severity Index (RHSI) to quantify misalignment between proxy rewards and genuine learning. We evaluate the framework in a controlled simulation of an AI tutoring environment with 120 sessions across four conditions and three learner profiles, totaling 18{,}000 interactions. Results show that an engagement-optimized agent systematically over-selected a high-engagement action with no direct mastery gain, producing strong measured performance but limited learning progress. A multi-objective reward formulation reduced this problem but did not eliminate it, as the agent continued to favor proxy-rewarding behavior in many states. In contrast, a constrained architecture combining prerequisite enforcement and minimum cognitive demand substantially reduced reward hacking, lowering RHSI from 0.317 in the unconstrained multi-objective condition to 0.102. Ablation results further suggest that behavioral safety was the most influential safeguard against repetitive low-value action selection. These findings suggest that reward design alone may be insufficient to ensure pedagogically aligned behavior in educational RL, at least in the simulated environment studied here. More broadly, the paper positions pedagogical safety as an important research problem at the intersection of AI safety and intelligent educational systems.
  • βœ‡cs.AI, q-bio.NC updates on arXiv.org
  • MC-CPO: Mastery-Conditioned Constrained Policy Optimization Oluseyi Olukola Β· Nick Rahimi
    arXiv:2604.04251v1 Announce Type: new Abstract: Engagement-optimized adaptive tutoring systems may prioritize short-term behavioral signals over sustained learning outcomes, creating structural incentives for reward hacking in reinforcement learning policies. We formalize this challenge as a constrained Markov decision process (CMDP) with mastery-conditioned feasibility, in which pedagogical safety constraints dynamically restrict admissible actions according to learner mastery and prerequisite
     
  • 🏷️
  • ↗️

MC-CPO: Mastery-Conditioned Constrained Policy Optimization

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Oluseyi Olukola Β· Nick Rahimi
7 April 2026 at 12:00
arXiv:2604.04251v1 Announce Type: new Abstract: Engagement-optimized adaptive tutoring systems may prioritize short-term behavioral signals over sustained learning outcomes, creating structural incentives for reward hacking in reinforcement learning policies. We formalize this challenge as a constrained Markov decision process (CMDP) with mastery-conditioned feasibility, in which pedagogical safety constraints dynamically restrict admissible actions according to learner mastery and prerequisite structure. We introduce Mastery-Conditioned Constrained Policy Optimization (MC-CPO), a two-timescale primal-dual algorithm that integrates structural action masking with constrained policy optimization. In the tabular regime, we establish feasibility preservation and convergence to stationary feasible points under standard stochastic approximation conditions and derive a safety gap result showing that optimization within the mastery-conditioned feasible set can strictly dominate post-hoc filtering under identical safety budgets. Empirical validation is conducted in minimal and extended tabular environments and in a neural tutoring setting. Across 10 random seeds and one million training steps in the neural regime, MC-CPO satisfies constraint budgets within tolerance, reduces discounted safety costs relative to unconstrained and reward-shaped baselines, and substantially lowers the Reward Hacking Severity Index (RHSI). These results indicate that embedding pedagogical structure directly into the feasible action space provides a principled foundation for mitigating reward hacking in instructional reinforcement learning systems.

InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Can Wang Β· Hongyu Zhao Β· Yiqun Chen
7 April 2026 at 12:00
arXiv:2604.04274v1 Announce Type: new Abstract: Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging because of the complexity of both statistical methodology and real-world data. Inspired by the success of artificial intelligence in accelerating scientific discovery, we introduce InferenceEvolve, an evolutionary framework that uses large language models to discover and iteratively refine causal methods. Across widely used benchmarks, InferenceEvolve yields estimators that consistently outperform established baselines: against 58 human submissions in a recent community competition, our best evolved estimator lay on the Pareto frontier across two evaluation metrics. We also developed robust proxy objectives for settings without semi-synthetic outcomes, with competitive results. Analysis of the evolutionary trajectories shows that agents progressively discover sophisticated strategies tailored to unrevealed data-generating mechanisms. These findings suggest that language-model-guided evolution can optimize structured scientific programs such as causal inference, even when outcomes are only partially observed.

Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Yizhou Liu Β· Qi Sun Β· Yulin Chen Β· Siyue Zhang Β· Chen Zhao
7 April 2026 at 12:00
arXiv:2604.04651v1 Announce Type: new Abstract: Agents equipped with search tools have emerged as effective solutions for knowledge-intensive tasks. While Large Language Models (LLMs) exhibit strong reasoning capabilities, their high computational cost limits practical deployment for search agents. Consequently, recent work has focused on distilling agentic behaviors from LLMs into Small Language Models (SLMs). Through comprehensive evaluation on complex multi-hop reasoning tasks, we find that despite possessing less parametric knowledge, SLMs invoke search tools less frequently and are more prone to hallucinations. To address this issue, we propose \policy, a lightweight fine-tuning approach that explicitly trains SLMs to reliably retrieve and generate answers grounded in retrieved evidence. Compared to agent distillation from LLMs, our approach improves performance by 17.3 scores on Bamboogle and 15.3 scores on HotpotQA, achieving LLM-level results across benchmarks. Our further analysis reveals that adaptive search strategies in SLMs often degrade performance, highlighting the necessity of consistent search behavior for reliable reasoning.

SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Xinhao Huang Β· You-Liang Huang Β· Zeyi Wen
7 April 2026 at 12:00
arXiv:2604.03258v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but the billion-scale parameters pose deployment challenges. Although existing methods attempt to reduce the scale of LLMs, they require either special hardware support or expensive post-training to maintain model quality. To facilitate efficient and affordable model slimming, we propose a novel training-free compression method for LLMs, named "SoLA", which leverages \textbf{So}ft activation sparsity and \textbf{L}ow-r\textbf{A}nk decomposition. SoLA can identify and retain a minority of components significantly contributing to inference, while compressing the majority through low-rank decomposition, based on our analysis of the activation pattern in the feed-forward network (FFN) of modern LLMs. To alleviate the decomposition loss, SoLA is equipped with an adaptive component-wise low-rank allocation strategy to assign appropriate truncation positions for different weight matrices. We conduct extensive experiments on LLaMA-2-7B/13B/70B and Mistral-7B models across a variety of benchmarks. SoLA exhibits remarkable improvement in both language modeling and downstream task accuracy without post-training. For example, with a 30\% compression rate on the LLaMA-2-70B model, SoLA surpasses the state-of-the-art method by reducing perplexity from 6.95 to 4.44 and enhancing downstream task accuracy by 10\%.

3D-IDE: 3D Implicit Depth Emergent

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Chushan Zhang Β· Ruihan Lu Β· Jinguang Tong Β· Yikai Wang Β· Hongdong Li
7 April 2026 at 12:00
arXiv:2604.03296v1 Announce Type: cross Abstract: Leveraging 3D information within Multimodal Large Language Models (MLLMs) has recently shown significant advantages for indoor scene understanding. However, existing methods, including those using explicit ground-truth 3D positional encoding and those grafting external 3D foundation models for implicit geometry, struggle with the trade-off in 2D-3D representation fusion, leading to suboptimal deployment. To this end, we propose 3D-Implicit Depth Emergence, a method that reframes 3D perception as an emergent property derived from geometric self-supervision rather than explicit encoding. Our core insight is the Implicit Geometric Emergence Principle: by strategically leveraging privileged geometric supervision through mechanisms like a fine-grained geometry validator and global representation constraints, we construct an information bottleneck. This bottleneck forces the model to maximize the mutual information between visual features and 3D structures, allowing 3D awareness to emerge naturally within a unified visual representation. Unlike existing approaches, our method enables 3D perception to emerge implicitly, disentangling features in dense regions and, crucially, eliminating depth and pose dependencies during inference with zero latency overhead. This paradigm shift from external grafting to implicit emergence represents a fundamental rethinking of 3D knowledge integration in visual-language models. Extensive experiments demonstrate that our method surpasses SOTA on multiple 3D scene understanding benchmarks. Our approach achieves a 55% reduction in inference latency while maintaining strong performance across diverse downstream tasks, underscoring the effectiveness of meticulously designed auxiliary objectives for dependency-free 3D understanding. Source code can be found at github.com/ChushanZhang/3D-IDE.

V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Jiazhou Zhou Β· Yucheng Chen Β· Hongyang Li Β· Qing Jiang Β· Hu Zhou Β· Ying-Cong Chen Β· Lei Zhang
7 April 2026 at 12:00
arXiv:2604.03307v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-grained tasks. This vulnerability arises from a fundamental limitation: their reasoning is largely restricted to the language domain, treating visual input as a static, reasoning-agnostic preamble rather than a dynamic participant. Consequently, current models act as passive observers, unable to re-examine visual details to ground their evolving reasoning states. To overcome this, we propose V-Reflection, a framework that transforms the MLLM into an active interrogator through a "think-then-look" visual reflection mechanism. During reasoning, latent states function as dynamic probes that actively interrogate the visual feature space, grounding each reasoning step for task-critical evidence. Our approach employs a two-stage distillation strategy. First, the Box-Guided Compression (BCM) module establishes stable pixel-to-latent targets through explicit spatial grounding. Next, a Dynamic Autoregressive Compression (DAC) module maps the model's hidden states into dynamic probes that interrogate the global visual feature map. By distilling the spatial expertise of the BCM teacher into the DAC student, V-Reflection internalizes the ability to localize task-critical evidence. During inference, both modules remain entirely inactive, maintaining a purely end-to-end autoregressive decoding in the latent space with optimal efficiency. Extensive experiments demonstrate the effectiveness of our V-Reflection across six perception-intensive benchmarks, significantly narrowing the fine-grained perception gap. Visualizations confirm that latent reasoning autonomously localizes task-critical visual evidence.
❌