❌

Normal view

Received today — 7 October 2026 ⏭

TFAM loss drives oxaliplatin resistance by linking mtDNA release to STING–TBK1-mediated lysophagy

✇Oncogene - Issue - nature.com science feeds
By: Xiao-Xuan Wang · Xin-Han Wang · Zi-Hong Fan · Xiao-Feng Ding · Jian-Rui Zhong · Bing-Ming Zhu · Jie Lyu · Su-Jie Wang · Qing-Yu He · Yang Wang · Jing Zhang
2 October 2026 at 08:00

Oncogene, Published online: 02 October 2026; doi:10.1038/s41388-026-03990-8

Colorectal cancer is often treated with oxaliplatin, but many tumors become less responsive over time, making treatment harder. This study aimed to understand one way cancer cells escape oxaliplatin and to identify a possible way to restore drug response. The researchers studied colorectal cancer cells, drug-resistant cells, mouse tumor models, and tumor-like structures grown from patient samples. They found that oxaliplatin stress lowers a mitochondrial protein called TFAM. This allows mitochondrial DNA to leak into the cell fluid and switch on a survival signal involving TBK1. This signal helps cancer cells clear damaged cell parts and survive treatment. Blocking TBK1 reduced this protective response and made resistant tumors more sensitive to oxaliplatin. These findings suggest that combining oxaliplatin with a TBK1-blocking treatment may help overcome drug resistance in colorectal cancer in the future.

Two-dimensional materials for advanced back-end-of-line and wafer backside technologies

✇Nature Nanotechnology
By: Zhengpeng Wang · Jiechen Wang · Yue Cao · Hang-Ming Zhang · Yan Zeng · Sishuo Liu · Songqi Wang · Hehe Gong · Yuhao Zhang · Pingfan Wu · Liang Peng · Han Wang
17 September 2026 at 08:00

Nature Nanotechnology, Published online: 17 September 2026; doi:10.1038/s41565-026-02274-2

Two-dimensional materials offer low resistivity, strong thermal management and back-end-of-line compatibility, making them promising for advanced interconnects, backside power delivery and boosting efficiency in next-generation semiconductor chips.
Received — 15 September 2026 ⏭

SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zihan Wang · Yuqi Wang · Lei Gong · Cheng Tang · Wenqi Lou · Teng Wang · Chao Wang · Xuehai Zhou
14 September 2026 at 12:00
arXiv:2609.12978v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) creates a structural advantage for offloading: only a small fraction of activated experts need to reside in device memory, and if they can be loaded in time for computation, offloading can in principle approach full-load performance, where all model weights reside in device memory. Yet translating MoE's structural advantage into practical offloading gains remains challenging. We propose SeqMoE to bridge this gap. To maximize expert hits, we build predictive memory management: (i) Sequence-to-sequence prediction. We are the first to recast expert activation prediction as sequence modeling, enabling accurate multi-step, multi-layer forecasts that provide a long and reliable window for downstream decisions. (ii) Joint prefetch scheduling. We formulate prefetch scheduling as Job Sequencing with Deadlines to maximize expected expert hits and improve bandwidth efficiency. (iii) Forecast-driven caching. Leveraging the recursive nature of sequence modeling, we introduce a probabilistic Belady policy for future-aware eviction. To eliminate execution bottleneck, we develop (iv) Graph-compatible offloading runtime. We derive general runtime principles encompassing compute-transparent expert placement and synchronization-free orchestration disciplines for end-to-end graph capture. With 45% expert residency, SeqMoE averages a 96.97% hit rate and 80.22% of full-load performance, advancing the state of the art in MoE offloading.
Received — 13 September 2026 ⏭

Pan-cancer analysis identifies KANSL2 as a cell-cycle-associated regulator of tumor progression and immunity in liver hepatocellular carcinoma

✇Omics in Hepatocellular
By: Nanbin Liu · Kun Li · Junqiao Feng · Shan Wang · Ji Li · Wenbin Yang · Senyang Li · Keping Feng
11 September 2026 at 18:00

Clin Exp Med. 2026 Jul 26;26(1):329. doi: 10.1007/s10238-026-02264-7.

ABSTRACT

KANSL2, a core component of the NSL histone acetyltransferase complex, has been implicated in tumorigenesis. However, its pan-cancer relevance and functional role in liver hepatocellular carcinoma (LIHC) remain unclear. Multi-omics data from TCGA, GEO, and HPA were integrated to systematically evaluate KANSL2 expression, clinical significance, genomic alterations, and immune associations across cancers. Functional enrichment, immune infiltration analyses, and single-cell transcriptomics were performed. In vitro assays were conducted to validate the biological effects of KANSL2 in LIHC cells. KANSL2 is broadly upregulated across cancers and exhibits strong diagnostic performance. Elevated KANSL2 expression correlates with unfavorable prognosis, particularly in LIHC. Mechanistically, KANSL2 and its co-expressed genes are enriched in cell-cycle progression. KANSL2 expression is also closely associated with immune infiltration and immunoregulatory signaling within the tumor microenvironment, with single-cell data indicating preferential expression in proliferative T-cell subsets. Functional experiments demonstrate that KANSL2 silencing suppresses proliferation, migration, and invasion, and induces G2/M phase arrest in LIHC cells. Notably, its effects on apoptosis are limited, suggesting that KANSL2 primarily drives tumor progression through cell-cycle-dependent mechanisms. This study identifies KANSL2 as a key regulator of tumor progression and immune remodeling in LIHC. By promoting malignancy predominantly via cell-cycle control, KANSL2 represents a promising biomarker for diagnosis and prognosis, and a potential therapeutic target.

PMID:42726304 | PMC:PMC13569553 | DOI:10.1007/s10238-026-02264-7

Pan-cancer analysis identifies KANSL2 as a cell-cycle-associated regulator of tumor progression and immunity in liver hepatocellular carcinoma

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Nanbin Liu · Kun Li · Junqiao Feng · Shan Wang · Ji Li · Wenbin Yang · Senyang Li · Keping Feng
11 September 2026 at 18:00

Clin Exp Med. 2026 Jul 26;26(1):329. doi: 10.1007/s10238-026-02264-7.

ABSTRACT

KANSL2, a core component of the NSL histone acetyltransferase complex, has been implicated in tumorigenesis. However, its pan-cancer relevance and functional role in liver hepatocellular carcinoma (LIHC) remain unclear. Multi-omics data from TCGA, GEO, and HPA were integrated to systematically evaluate KANSL2 expression, clinical significance, genomic alterations, and immune associations across cancers. Functional enrichment, immune infiltration analyses, and single-cell transcriptomics were performed. In vitro assays were conducted to validate the biological effects of KANSL2 in LIHC cells. KANSL2 is broadly upregulated across cancers and exhibits strong diagnostic performance. Elevated KANSL2 expression correlates with unfavorable prognosis, particularly in LIHC. Mechanistically, KANSL2 and its co-expressed genes are enriched in cell-cycle progression. KANSL2 expression is also closely associated with immune infiltration and immunoregulatory signaling within the tumor microenvironment, with single-cell data indicating preferential expression in proliferative T-cell subsets. Functional experiments demonstrate that KANSL2 silencing suppresses proliferation, migration, and invasion, and induces G2/M phase arrest in LIHC cells. Notably, its effects on apoptosis are limited, suggesting that KANSL2 primarily drives tumor progression through cell-cycle-dependent mechanisms. This study identifies KANSL2 as a key regulator of tumor progression and immune remodeling in LIHC. By promoting malignancy predominantly via cell-cycle control, KANSL2 represents a promising biomarker for diagnosis and prognosis, and a potential therapeutic target.

PMID:42726304 | PMC:PMC13569553 | DOI:10.1007/s10238-026-02264-7

Received — 10 September 2026 ⏭

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Lin Shi (Audrey) · Haowei Lin (Audrey) · Zixuan Zhu (Audrey) · Xiaoyue Zhou (Audrey) · Xiang Li (Audrey) · Xiangning Lin (Audrey) · Yaxuan Deng (Audrey) · Han Xu (Audrey) · Yuangang Li (Audrey) · Shanda Li (Audrey) · Zizhao Chen (Audrey) · Hanwen Xing (Audrey) · Harsh Raj (Audrey) · Bo Chen (Audrey) · Quan Shi (Audrey) · Steven Dillmann (Audrey) · Yipeng Gao (Audrey) · Puneesh Khanna (Audrey) · Ruofan Lu (Audrey) · Chao Beyond Zhou (Audrey) · Michael Yang (Audrey) · Robert Zhang (Audrey) · Siyuan Chai (Audrey) · Jiayu Chang (Audrey) · Yizhao Chen (Audrey) · Xiaokun Chen (Audrey) · Yiwei Dai (Audrey) · Wenting Yang (Audrey) · Hange Liu (Audrey) · Minghao Liu (Audrey) · Zihan Wang (Audrey) · Adnan El Assadi (Audrey) · Benedikt Stroebl (Audrey) · E. Kelly Buchanan (Audrey) · Han Meng (Audrey) · Junwei He (Audrey) · Longxuan Yu (Audrey) · Radin Shayanfar (Audrey) · Yukyung Lee (Audrey) · Zhikang Dong (Audrey) · Allen G Hart (Audrey) · Anjiang Wei (Audrey) · Anurag Kashyap (Audrey) · Arpandeep Khatua (Audrey) · Audrey Jixin Zheng (Audrey) · Chengrui Ma (Aud
10 September 2026 at 12:00
arXiv:2609.04298v2 Announce Type: replace Abstract: Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of 8 models spanning capability tiers across 54 benchmarks; every model is run with Terminus-2 and with one of 3 native harnesses. This enables a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Index, a curated set of 82 difficult, diverse, and high-quality tasks spanning 29 benchmarks, refined from the adapted suite through difficulty filtering, AI and human audit, and an audit-and-fix loop. Harbor-Index preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; no evaluated model-harness configuration exceeds 30% pass rate, and the strongest (GPT-5.5 with Codex) reaches 28.0%. We release the adapters, evaluation results, in-depth analysis, and Harbor-Index as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.

Synergistic Vision-Language Reinforcement Enables Scalable On-Demand Analysis across Diverse Clinical Tasks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haonan Wang · Jiaji Mao · Lehan Wang · Qixiang Zhang · Marawan Elbatel · Yi Qin · Huijun Hu · Baoxun Li · Wenhui Deng · Weifeng Qin · Hongrui Li · Jialin Liang · Jun Shen · Xiaomeng Li
10 September 2026 at 12:00
arXiv:2505.03380v2 Announce Type: replace-cross Abstract: Accurate delineation of tumors and surrounding organs-at-risk is essential for radiotherapy, surgery and treatment response assessment, yet remains time-consuming and expertise-intensive. Existing artificial intelligence systems often require manual spatial prompts or task-specific retraining, while generic class labels provide limited semantic grounding for heterogeneous disease targets. Here we present SyRe, a promptable segmentation foundation model based on Synergistic vision-language Reinforcement. SyRe strengthens bidirectional interaction between visual and linguistic representations to improve semantically grounded spatial understanding. To support large-scale training, we introduce the Color Region Description strategy and construct SyReData, comprising 20 million image-mask-description triplets across 9 modalities and 229 segmentation tasks. Training with diversified prompt forms further enables open-ended prompting, invalid-prompt rejection and flexible switching between single- and multi-target analysis. SyRe achieves accurate text-prompted segmentation across diverse clinical scenarios, with particularly strong performance on disease-related targets. Across 28 unseen external datasets, including 20 cancer types and multinational in-house cohorts, SyRe generalizes robustly under real-world distribution shifts. SyRe-generated masks also preserve clinically relevant quantitative information in pathology and yield radiomics features that stratify survival and improve prognostic modeling across five retrospective CT and MRI tumor cohorts. Finally, clinician-in-the-loop refinement enables efficient case-level correction when greater precision is required. These results establish SyRe as a generalizable foundation for scalable quantitative oncology and clinician-guided segmentation refinement.

Instance-Aware Algorithm Selection for Maximum Clique via a Dual-Channel Graph Neural Architecture

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiang Li · Shanshan Wang · Chenglong Xiao
10 September 2026 at 12:00
arXiv:2508.08005v5 Announce Type: replace-cross Abstract: Although the Maximum Clique Problem (MCP) has been extensively studied and features a rich ecosystem of exact solvers, empirical evidence shows that solver performance varies substantially across graph families. Consequently, selecting an appropriate algorithm for a given instance remains an open and practically important challenge that has received little systematic attention. We address this gap by developing an instance-aware selection framework that systematically combines global statistical descriptors with learned topological representations. We construct a comprehensive benchmark by evaluating four state-of-the-art exact solvers on a diverse collection of graph instances and deriving both global statistical and local structural features. An evaluation of conventional classifiers establishes Random Forest as a strong baseline and reveals that connectivity and topological features are key predictors of performance. Motivated by these observations, we introduce a dual-channel architecture that jointly leverages a Graph Attention Network for capturing local neighborhood patterns and a Multilayer Perceptron for modeling global statistical features. Extensive experiments show that the proposed dual-channel model consistently surpasses classical baselines and the single-best solver, achieving 90.43% test accuracy. These findings demonstrate the value of integrating local topological encoding with global statistical cues for combinatorial algorithm selection. Code and models are available at: https://anonymous.4open.science/r/GAT-MLP-7E5F.

City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rui Liu · Steven Jige Quan · Zhong-Ren Peng · Zijun Yao · Han Wang · Pengyang Wang · Kunpeng Liu · Yanjie Fu · Dongjie Wang
10 September 2026 at 12:00
arXiv:2602.19326v3 Announce Type: replace-cross Abstract: Urban renewal requires incremental modifications to existing geospatial plans, yet manually updating complex layouts under spatial constraints is labor-intensive and error-prone. To tackle this, we propose CEAE, a hierarchical agentic framework that formulates urban renewal as machine-executable GeoJSON editing from natural-language instructions. CEAE decomposes instructions into hierarchical geometric intents, executing edits from coarse to fine while preserving spatial consistency through a self-reflective execution-validation loop. Experimental results show that CEAE outperforms baselines in execution validity, robustness, and geometric accuracy.
Received — 27 May 2026 ⏭

A Non-Canonical Role of SMAD4 in Regulating 3D Genome Architecture to Inhibit Lung Squamous Cell Carcinoma Development

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Qian Tang · Chen Lian · Xinyan Han · Xuhan Zhang · Zihan Wang · Boyu Wang · Taoyu Zhu · Xinrui Lin · Xiaolei Wang · Yaping Xu · Manyu Xiao · Zijin Wang · Junming Li · Silin Chen · Yunze Wang · Yufei Liu · Songsong Li · Zuolin Shen · Xi Lu · Xueqi Han · Yilu Zhou · Mingyang Xiao · Jiayi Ran · Xiaoran Cao · Xinyi Xu · Hugo Sámano-Sánchez · Alfredo Rodríguez · Lian Wang · Shuifang Chen · Zhanyu Xu · Shirong Zhang · Nuo Yang · Yong Tang · Jian Liu
26 May 2026 at 18:00

Adv Sci (Weinh). 2026 May 26:e75839. doi: 10.1002/advs.75839. Online ahead of print.

ABSTRACT

Lung squamous cell carcinoma (LUSC) lacks clearly defined key drivers and effective targeted therapies, reflecting an incomplete understanding of its molecular pathogenesis. Here, we identify SMAD4 as a critical regulator of three-dimensional (3D) genome organization in LUSC and uncover a mechanistic link between tumor suppressor loss and oncogenic transcriptional activation. By integrating clinical datasets, genetically engineered mouse models, human and murine LUSC cell lines, and multi-omics analyses, we demonstrate that SMAD4 deficiency promotes LUSC progression by unleashing EP300-mediated enhancer-promoter looping at the SOX2 locus. Mechanistically, SMAD4 does not directly bind SOX2 regulatory elements but instead constrains chromatin looping by sequestering EP300 away from loop anchor regions. Loss of SMAD4 leads to enhanced H3K27ac deposition, aberrant SOX2 activation, and increased LUSC tumor cell proliferation. Together, these findings reveal a non-canonical role for a transcription factor (e.g., SMAD4) in regulating dysregulated 3D genome architecture to inhibit tumor development.

PMID:42189071 | DOI:10.1002/advs.75839

A Non-Canonical Role of SMAD4 in Regulating 3D Genome Architecture to Inhibit Lung Squamous Cell Carcinoma Development

✇Omics In Lung
By: Qian Tang · Chen Lian · Xinyan Han · Xuhan Zhang · Zihan Wang · Boyu Wang · Taoyu Zhu · Xinrui Lin · Xiaolei Wang · Yaping Xu · Manyu Xiao · Zijin Wang · Junming Li · Silin Chen · Yunze Wang · Yufei Liu · Songsong Li · Zuolin Shen · Xi Lu · Xueqi Han · Yilu Zhou · Mingyang Xiao · Jiayi Ran · Xiaoran Cao · Xinyi Xu · Hugo Sámano-Sánchez · Alfredo Rodríguez · Lian Wang · Shuifang Chen · Zhanyu Xu · Shirong Zhang · Nuo Yang · Yong Tang · Jian Liu
26 May 2026 at 18:00

Adv Sci (Weinh). 2026 May 26:e75839. doi: 10.1002/advs.75839. Online ahead of print.

ABSTRACT

Lung squamous cell carcinoma (LUSC) lacks clearly defined key drivers and effective targeted therapies, reflecting an incomplete understanding of its molecular pathogenesis. Here, we identify SMAD4 as a critical regulator of three-dimensional (3D) genome organization in LUSC and uncover a mechanistic link between tumor suppressor loss and oncogenic transcriptional activation. By integrating clinical datasets, genetically engineered mouse models, human and murine LUSC cell lines, and multi-omics analyses, we demonstrate that SMAD4 deficiency promotes LUSC progression by unleashing EP300-mediated enhancer-promoter looping at the SOX2 locus. Mechanistically, SMAD4 does not directly bind SOX2 regulatory elements but instead constrains chromatin looping by sequestering EP300 away from loop anchor regions. Loss of SMAD4 leads to enhanced H3K27ac deposition, aberrant SOX2 activation, and increased LUSC tumor cell proliferation. Together, these findings reveal a non-canonical role for a transcription factor (e.g., SMAD4) in regulating dysregulated 3D genome architecture to inhibit tumor development.

PMID:42189071 | DOI:10.1002/advs.75839

Extracting Training Data from Diffusion Language Models via Infilling

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yihan Wang · N. Asokan
26 May 2026 at 12:00
arXiv:2605.24173v1 Announce Type: cross Abstract: Memorization in large language models has been studied almost exclusively through prefix-conditioned extraction, a natural choice for autoregressive models. However, diffusion language models (DLMs) can denoise masked tokens at arbitrary positions. Thus, prefix-only probing reveals only one facet of memorization in DLMs and significantly underestimates the risk of training-data extraction. In order to realistically model extractability of training data in DLMs, we introduce \emph{infilling extraction}, a data-extraction protocol parameterized by an arbitrary binary mask that subsumes prefix-only probing and accounts for the bidirectional inductive bias of DLMs. Instantiating it on LLaDA-8B and Dream-7B across five extraction modes, three training pipelines, and three corpora covering verbatim and partial leakage, we find that mask geometry governs extractability: edge-conditioned masks \emph{extract up to three times more} verbatim sequences than prefix-conditioned ones, and bidirectional access opens channels inaccessible in autoregressive models. In particular, we show that a realistic adversary with access to training data where personally identifiable information has been redacted, can even achieve higher recall on extracting redacted email addresses from DLMs than from scale-matched autoregressive models. Tunable parameters for decoding measurably affect extraction performance, while a follow-up supervised finetuning stage does not eliminate the prior memorization.

Explainable Retinal Imaging for Prediction of Multi-Organ Dysfunction in Type 2 Diabetes

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mini Han Wang · Liting Huang · Wei Hong · Boonthawan Wingwon
26 May 2026 at 12:00
arXiv:2605.24912v1 Announce Type: cross Abstract: Background: Type 2 diabetes mellitus (T2DM) is increasingly recognised as a systemic disease characterised by coordinated dysfunction across metabolic, renal, lipid, and inflammatory pathways. Existing clinical assessments often fail to capture this multi-dimensional burden. Methods: We conducted a retrospective study of 1,195 patients using routinely collected laboratory biomarkers. System-level abnormality indices were constructed to quantify organ-specific dysfunction, and multi-system involvement was defined as abnormalities in two or more systems. Supervised machine learning models, including logistic regression, random forest, and gradient boosting, were trained to predict multi-system dysregulation. Model interpretability was achieved using SHapley Additive exPlanations (SHAP). Results: The gradient boosting model demonstrated near-perfect discrimination (AUC = 1.000), significantly outperforming logistic regression (AUC = 0.925). Feature attribution analysis revealed that hyperglycaemia, renal impairment, dyslipidaemia, and inflammation were the dominant drivers of multi-system risk. Dose-response relationships observed in partial dependence analyses further supported the biological plausibility of model predictions. Conclusion: This study presents an interpretable, data-driven framework for quantifying systemic disease burden in T2DM. By linking routine biomarkers to multi-organ dysfunction, our approach provides both predictive accuracy and mechanistic insight, offering potential for improved risk stratification and precision medicine in diabetes care. The data and code used in this study are openly available on GitHub at: https://github.com/MiniHanWang/Type-2-Diabetes-1.git

Explainable Multi-Task Retinal Imaging Reveals Microvascular Signals for Systemic Risk Stratification in Type 2 Diabetes: A Pilot Study

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mini Han Wang · Liting Huang · Wei Hong · Boonthawan Wingwon
26 May 2026 at 12:00
arXiv:2605.24913v1 Announce Type: cross Abstract: Retinal imaging provides a non-invasive window into systemic microvascular health and has emerged as a potential biomarker for systemic diseases. However, whether retinal features encode biologically meaningful systemic signals that can be reliably interpreted using explainable artificial intelligence (XAI) remains unclear. An explainable multi-task deep learning framework was developed to investigate associations between retinal microvascular features and systemic abnormalities in Type 2 Diabetes Mellitus. A total of 11,011 fundus images from 2,719 individuals were analysed using a shared neural network with task-specific heads for glycaemic status, kidney abnormality, and multi-system involvement. Model interpretability was evaluated using Gradient-weighted Class Activation Mapping (Grad-CAM), anatomical masking, and vessel alignment analysis. The framework demonstrated task-dependent predictive performance, with the best discrimination observed for kidney abnormality (AUC up to 0.63), whereas glycaemic status prediction showed limited performance (AUC = 0.49-0.61). Explainability analyses consistently localized model attention to retinal vessels and peripapillary regions. Masking experiments showed that occlusion of vascular regions caused the greatest performance decline, indicating that retinal vessels were the primary predictive source. Different architectures exhibited heterogeneous attention patterns, suggesting multiple representational pathways for systemic signal encoding. This pilot study demonstrates that retinal microvascular features contain measurable signals associated with systemic abnormalities, particularly microvascular damage. By integrating multi-task learning with quantitative XAI validation, this framework advances retinal imaging toward interpretable digital biomarkers for systemic risk stratification in diabetes.

Simulating Human Memory with Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qihan Wang · Nicholas Tomlin · Michael Hu · Brian Dillon · Tal Linzen
26 May 2026 at 12:00
arXiv:2605.25680v1 Announce Type: cross Abstract: Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap, we run a series of classic memory experiments from psychology on both humans and language models. Across tasks, we find that out-of-the-box language models exhibit better memory than humans, even when prompted to imitate human behavior. We then show that better prompting strategies and the use of a compactor can cause language models to forget content in a more human-like way. Using these methods, we show preliminary evidence that language models with human-like memory constraints can function as more effective user simulators in a downstream education task. Finally, we release human reference data and benchmarks to support future work on simulating human memory with language models.

Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haibo Jin · Peng Kuang · Ye Yu · Xiaopeng Yuan · Haohan Wang
26 May 2026 at 12:00
arXiv:2602.03695v2 Announce Type: replace-cross Abstract: While existing multi-agent systems (MAS) can handle complex problems by enabling collaboration among multiple agents, they are often highly task-specific, relying on manually crafted agent roles and interaction prompts, which leads to increased architectural complexity and limited reusability across tasks. Moreover, most MAS communicate primarily through natural language, making them vulnerable to error accumulation and instability in long-context, multi-stage interactions within internal agent histories. In this work, we propose \textbf{Agent Primitives}, a set of reusable latent building blocks for LLM-based MAS. Inspired by neural network design, where complex models are built from reusable components, we observe that many existing MAS architectures can be decomposed into a small number of recurring internal computation patterns. Based on this observation, we instantiate three primitives: Review, Voting and Selection, and Planning and Execution. All primitives communicate internally via key-value (KV) cache, which improves both robustness and efficiency by mitigating information degradation across multi-stage interactions. To enable automatic system construction, an Organizer agent selects and composes primitives for each query, guided by a lightweight knowledge pool of previously successful configurations, forming a primitive-based MAS. Experiments show that primitives-based MAS improve average accuracy by 12.0-16.5\% over single-agent baselines, reduce token usage and inference latency by approximately 3$\times$-4$\times$ compared to text-based MAS, while incurring only 1.3$\times$-1.6$\times$ overhead relative to single-agent inference and providing more stable performance across model backbones.

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiaodong Lu · Xiaohan Wang · Jiajun Chai · Guojun Yin · Wei Lin · Zhijun Chen · Yu Luo · Fuzhen Zhuang · Yikun Ban · Deqing Wang
26 May 2026 at 12:00
arXiv:2602.08499v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner: responses of heterogeneous quality within each prompt are treated uniformly, and historical rollouts are discarded after a single use. This leads to noisy supervision, poor sample efficiency, and suboptimal policy updates. We address these issues by formulating rollout scheduling in RLVR as a contextual bandit problem and proposing a unified neural scheduling framework that adaptively selects high-value rollouts throughout training. Each rollout is treated as an arm whose reward is defined by the induced performance gain between consecutive optimization steps. The resulting scheduler supports both noise-aware intra-group selection and adaptive global reuse of historical rollouts within a single principled framework. We provide theoretical justification by deriving sublinear regret bounds and showing that enlarging the rollout buffer improves the achievable performance upper bound. Experiments on six mathematical reasoning benchmarks demonstrate consistent gains in performance and training efficiency across multiple RLVR optimization methods.

Fetal monitoring for high-risk pregnancies using a wearable ultrasound patch

✇Nature Biotechnology - Issue - nature.com science feeds
By: Geonho Park · Yizhou Bian · Hao Huang · Sai Zhou · Siyu Qin · Muyang Lin · Xinyi Yang · Aaron Lee · Anand Ramkumar · Mariana Tome · Jayne Lander · Xiangjun Chen · Shenghan Wang · Pranavi Bheemreddy · Liam Stanton · Ren Sheng · Guihuan Guo · Mabel Shehada · Ruotao Wang · Alexa Roa · Chengchangfeng Lu · Wentong Yue · Ray S. Wu · Xiaoxiang Gao · Hongjie Hu · Amer Yaghi · Mark Liu · Lawrence Impey · Sally L. Collins · Aris T. Papageorghiou · Louise C. Laurent · Keith A. Wear · Antoniya Georgieva · Sheng Xu
26 May 2026 at 08:00

Nature Biotechnology, Published online: 26 May 2026; doi:10.1038/s41587-026-03140-1

A wearable ultrasound device is optimized for continuous monitoring of pregnancies.

Multi-omics Analysis Reveals the Protection of a Quadruple Probiotic Mixture in Experimental Autoimmune Hepatitis

✇(Multiomics OR Omics) AND (Pancreatic)
By: Yu Chen · Shuhui Wang · Anzhuo Chen · Zhuoying Lin · Han Wang · Wanneng Li · Jun Liu · Jia Yao · Dean Tian · Yu Lei · Mei Liu
23 May 2026 at 18:00

Probiotics Antimicrob Proteins. 2026 May 23. doi: 10.1007/s12602-026-11062-2. Online ahead of print.

ABSTRACT

Autoimmune hepatitis (AIH) is a chronic progressive inflammatory liver disease with a rising global incidence. The treatment of AIH remains challenging because first-line drugs show limited efficacy and systemic side effects. Gut microbiota plays a crucial role in the pathogenesis of AIH, leading to growing interest in developing probiotic-based therapies. In this study, we used multi-omics analysis to investigate the therapeutic effects of a quadruple probiotic mixture (Probiotic-quad) consisting of Bifidobacterium infantis, Lactobacillus acidophilus, Enterococcus faecalis, and Bacillus cereus in a well-established chronic AIH murine model. Our results showed that Probiotic-quad treatment significantly alleviated AIH progression, as evidenced by lower serum liver enzyme levels, ameliorated hepatic inflammatory infiltration and histopathological damage. Metagenomic sequencing results showed that gut dysbiosis in AIH mice was partially reversed after Probiotic-quad administration. Additionally, the integrity of the intestinal epithelial barrier was restored, accompanied by a reduction in serum lipopolysaccharide levels. Untargeted metabolomic and transcriptomic analysis revealed that Probiotic-quad treatment was linked to alterations in hepatic metabolism, including the citrate cycle and tryptophan metabolism, and was associated with reduced activation of the NF-κB and NOD-like receptor signaling pathways. These findings suggest that Probiotic-quad treatment ameliorates AIH severity and is potentially associated with changes in hepatic immune responses, metabolism, gut microbiota, and intestinal barrier function, highlighting its potential as an adjuvant therapy for AIH.

PMID:42176246 | DOI:10.1007/s12602-026-11062-2

Ferroptosis and macrophage polarization: mechanisms, interplay, and implications for medical applications

✇Cell Death Discovery nature.com science feeds
By: Yajuan Zhao · Jianbin Fu · Ping Zhao · Yuan Jiang · Yuhan Wang · Yaopeng Zhang · Zhaorui Li · Yongjun Zhao · Niannian Li · Bao Lang · Yanhua Luo
23 May 2026 at 08:00

Cell Death Discovery, Published online: 23 May 2026; doi:10.1038/s41420-026-03147-2

Ferroptosis and macrophage polarization: mechanisms, interplay, and implications for medical applications
❌