❌

Normal view

Received today — 7 October 2026 ⏭

Multi-omics-driven personalized management of advanced HCC

✇Omics in Hepatocellular
By: Jianpeng Sheng · Jinyuan Song · Lin Wang · Junlei Zhang · Wei Zhang · Hang Shi · Yaxing Zhao · Chengxiang Guo · Jianghui Tang · Yongtao Ji · Taohong Li · Wei Shao · Xueli Bai · Qing Li · Tingbo Liang
2 October 2026 at 18:00

Cell Rep Med. 2026 Oct 2:103085. doi: 10.1016/j.xcrm.2026.103085. Online ahead of print.

ABSTRACT

Hepatocellular carcinoma (HCC) management is challenging due to its complex tumor microenvironment and poor treatment responses. Here, using tumor specimens from a prospective clinical trial of combined transarterial chemoembolization (TACE) with immune checkpoint blockade (ICB), we perform exhaustive multi-omics analysis including spatial proteomics and transcriptomics, single-cell RNA sequencing, and bulk transcriptomics. These analyses reveal that treatment response is associated with enrichment of anti-tumor T cell regions that are regulated by cGAS-STING activation within immune-suppressive epithelial cells. Conversely, fibrotic processes impede these pro-response processes. Based on these insights, we test triple combination therapy consisting of cGAS activation, immune checkpoint blockade, and anti-fibrosis strategies, which shows improved efficacy over dual therapy. To identify patients who would benefit, we construct a predictive model using a group sparse learning algorithm. Our findings provide a blueprint for crafting personalized HCC therapies using next-generation biomarkers.

PMID:42826719 | DOI:10.1016/j.xcrm.2026.103085

Multi-omics-driven personalized management of advanced HCC

✇(Multiomics OR Omics) AND (Pancreatic)
By: Jianpeng Sheng · Jinyuan Song · Lin Wang · Junlei Zhang · Wei Zhang · Hang Shi · Yaxing Zhao · Chengxiang Guo · Jianghui Tang · Yongtao Ji · Taohong Li · Wei Shao · Xueli Bai · Qing Li · Tingbo Liang
2 October 2026 at 18:00

Cell Rep Med. 2026 Oct 2:103085. doi: 10.1016/j.xcrm.2026.103085. Online ahead of print.

ABSTRACT

Hepatocellular carcinoma (HCC) management is challenging due to its complex tumor microenvironment and poor treatment responses. Here, using tumor specimens from a prospective clinical trial of combined transarterial chemoembolization (TACE) with immune checkpoint blockade (ICB), we perform exhaustive multi-omics analysis including spatial proteomics and transcriptomics, single-cell RNA sequencing, and bulk transcriptomics. These analyses reveal that treatment response is associated with enrichment of anti-tumor T cell regions that are regulated by cGAS-STING activation within immune-suppressive epithelial cells. Conversely, fibrotic processes impede these pro-response processes. Based on these insights, we test triple combination therapy consisting of cGAS activation, immune checkpoint blockade, and anti-fibrosis strategies, which shows improved efficacy over dual therapy. To identify patients who would benefit, we construct a predictive model using a group sparse learning algorithm. Our findings provide a blueprint for crafting personalized HCC therapies using next-generation biomarkers.

PMID:42826719 | DOI:10.1016/j.xcrm.2026.103085

Received — 15 September 2026 ⏭

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xianming Li · Zongxi Li · Tsz-fung Andrew Lee · Jing Li · Haoran Xie · Qing Li
14 September 2026 at 12:00
arXiv:2604.19254v2 Announce Type: replace-cross Abstract: Popular low-rank parameter-efficient fine-tuning (PEFT) methods represent adaptation as separate updates to selected backbone weights, without maintaining an explicit task-specific state that is updated and reused across depth. These updates also require the backbone at inference and therefore cannot operate as standalone predictors. We propose ShadowPEFT, which consolidates trainable adaptation into a modular shadow component centered on a compact shadow model and lightweight Transformer layer-specific coupling modules. A persistent shadow state refines the frozen backbone representations and is updated from them in an interactive manner. Because the shadow model is trained as a complete predictor, it can be detached for shadow-only inference without executing the base model and can be initialized from a pretrained model. Experiments on text and image generation and understanding benchmarks show that ShadowPEFT matches or outperforms LoRA and DoRA under comparable trainable-parameter budgets. Additional analyses on shadow pretraining, cross-dataset transfer, parameter scaling, inference latency, and system-level evaluation suggest that centralized layer-space adaptation is a competitive and flexible alternative to conventional low-rank PEFT.
Received — 13 September 2026 ⏭

A clinically-oriented foundation model for intraoperative pathology

✇Nature Medicine
By: Zihan Zhao · Fengtao Zhou · Ronggang Li · Bing Chu · Xinke Zhang · Xueyi Zheng · Ke Zheng · Xiaobo Wen · Jiabo Ma · Yihui Wang · Jiewei Chen · Chengyou Zheng · Jiangyu Zhang · Yongqin Wen · Jiajia Meng · Ziqi Zeng · Xiaoqing Li · Jing Li · Dan Xie · Yaping Ye · Yu Wang · Hao Chen · Muyan Cai
10 September 2026 at 08:00

Nature Medicine, Published online: 10 September 2026; doi:10.1038/s41591-026-04703-0

CRISP, a vision-based pathology foundation model developed exclusively from frozen section slides, supports treatment decision-making throughout the surgical workflow with superior performance to current foundation models and extensive validation, including in a prospective cohort.
Received — 10 September 2026 ⏭

Structured light–matter interaction in semiconductor cavity quantum electrodynamics

✇Nature Nanotechnology
By: Shunfa Liu · Jiantao Ma · Hanqing Liu · Yangpeng Wang · Xueshi Li · Haiqiao Ni · Zhichuan Niu · Kai Zou · Yun Meng · Xiaolong Hu · Xuehua Wang · Jin Liu
8 September 2026 at 08:00

Nature Nanotechnology, Published online: 08 September 2026; doi:10.1038/s41565-026-02275-1

Structured light–matter interaction at the single-photon level is demonstrated in a coupled quantum-dot–micropillar system, enabling cavity-enhanced single-photon emission with spin-locked orbital angular momentum and tunable spin–orbit entanglement.
Received — 27 May 2026 ⏭

Geometric Flow Matching for Molecular Conformation Generation via Manifold Decomposition

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yunqing Liu · Yi Zhou · Wenqi Fan
26 May 2026 at 12:00
arXiv:2605.25577v1 Announce Type: cross Abstract: The generation of accurate 3D molecular conformations is a pivotal challenge in computational chemistry and drug discovery. Recently, diffusion and flow matching models have achieved remarkable success. However, there is a critical misalignment between their mathematical formulation and the physical reality of molecules. Existing approaches predominantly treat molecules as unstructured point clouds in Cartesian space, overlooking the intrinsic hierarchical mechanics where bond lengths and bond angles are relatively stiff, whereas torsion angles constitute the dominant flexible degrees of freedom. This lack of manifold awareness forces models to relearn fundamental geometric constraints from scratch, often leading to physically implausible intermediate structures. To address this, we propose GO-Flow that aligns generative modeling with molecular geometry via manifold decomposition. Instead of forcing motion through Euclidean space, GO-Flow decomposes the generation process into three physically motivated subspaces: translation space with linear optimal transport, rotation space with geodesic flows on $SO(3)$, and conformation space with entropic optimal transport. This decomposition injects geometric inductive biases and makes the generative paths better aligned with molecular degrees of freedom. When combined with equivariant neural architectures, it encourages rotation-consistent generation and improves geometric validity. Extensive experiments on GEOM-Drugs and GEOM-QM9 demonstrate that GO-Flow achieves state-of-the-art generation quality. Notably, by learning straighter probability paths on the correct manifolds naturally, our method enables high-fidelity sampling with as few as 50 steps, effectively bridging the gap between structural precision and computational efficiency.

How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhitao Zhu · Xili Wang · Shizhe Wu · Jiawei Fu · Xiaoqing Liu
26 May 2026 at 12:00
arXiv:2605.25698v1 Announce Type: cross Abstract: High-quality data is scarce in large language model (LLM) training, yet how to schedule its use jointly with training dynamics lacks theoretical guidance. We extend functional scaling laws by incorporating a data-quality dimension, and solve the joint data-quality and batch-size scheduling problem in asymptotic closed form. The solution reveals two regimes and a dual role of high-quality data. In the noise-limited regime, high-quality data should be used as a signal amplifier: lowering the batch size converts cleaner data into more signal without amplifying noise. In the signal-limited regime, it should be used as a noise suppressor: late placement reduces terminal noise without sacrificing signal accumulation. Existing curriculum-style pipelines primarily exploit the second role by placing cleaner data late, but miss the first role because conventional decay schedules reduce update intensity exactly when high-quality data becomes available. Guided by this, we propose Drop-Stable-Rampup for LLM midtraining: upon the quality transition, drop the batch size, hold it stable to accumulate signal, then ramp up to suppress terminal noise. On a 15B Mixture-of-Experts model midtrained on 108B tokens, Drop-Stable-Rampup improves average accuracy over Warmup-Stable-Decay (WSD) by +1.70 and over Cosine-decay by +2.98, with particularly large gains on mathematical reasoning benchmarks such as GSM8K (+4.23) and MATH (+2.80).

SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sihang Jiang · Lipeng Ma · Zhonghua Hong · Keyi Wang · Zhiyu Lu · Tengfei Wang · Shisong Chen · Jinghao Zhang · Tianjun Pan · Weijia Li · Jiaqing Liang · Yanghua Xiao
26 May 2026 at 12:00
arXiv:2604.08988v3 Announce Type: replace Abstract: Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, failing to accumulate experience across task boundaries. This paper formalizes the Self-Evolving Agent (SEA) from the perspective of digital embodiment and continuous cross-task evolution, introduces the Evolutionary Flywheel as its minimal sufficient architecture, and presents SEA-Eval -- the first benchmark designed specifically for evaluating SEAs. Grounded in Flywheel theory, SEA-Eval establishes SR and T as primary metrics and, through sequential task stream design, is designed to quantify evolutionary gain, evolutionary stability, and implicit alignment convergence. Empirical evaluation reveals that, under comparable success rates, token consumption differs by up to 31.2 times between frameworks on individual tasks, with divergent evolutionary trajectories emerging under sequential analysis -- demonstrating that success rate alone creates a capability illusion and that the sequential convergence of $T$ is the key criterion for distinguishing genuine evolution from pseudo-evolution.

GPNMB Drives Brain Metastasis by Sculpting a Pathological Endothelial-Immune Interactome

✇Omics In Lung
By: Xuefei Liu · Jun Tan · Chun Wu · Guanyin Huang · Yixin Cheng · Jianyang Hu · Binyu Zhang · Mao Zhao · Boxi Zhao · Jingru Lian · Shuqian Zheng · Lin Zeng · Meng Xu · Yang Xu · Shan Zeng · Hao Yu · Hui Yang · Zhixiang Zuo · Chuanyu Liu · Weineng Feng · Weinan Guo · Chunying Li · Sai-Lan Liu · Qing Liu · Feiqiu Wen · Xin Hong
13 April 2026 at 18:00

Cancer Discov. 2026 Apr 15. doi: 10.1158/2159-8290.CD-25-1663. Online ahead of print.

ABSTRACT

Brain metastases (BM) remain a devastating disease with dismal prognosis. How circulating tumor cells (CTCs) penetrate the blood brain barrier (BBB) and reprogram the brain microenvironment remain unclear. Using spatially resolved multi-omic profiling of CTCs and brain metastases, integrated with experimental and clinical analyses, we identified Glycoprotein Non-Metastatic Melanoma Protein B (GPNMB) as a CTC-secreted driver of vascular disruption and brain colonization. CBX3 upregulation induced GPNMB expression, which bound endothelial EGFR, triggering CBL-mediated ubiquitination and degradation. Attenuated EGFR signaling suppressed FTO and disrupted endothelial junctions via YTHDF2-dependent TJP1 m6A methylation. Remarkably, GPNMB-induced BBB remodeling promoted immune infiltration via CXCL12-CXCR4 axis, and induced time course-dependent T cell exhaustion within the brain microenvironment. Clinically, elevated CBX3⁺GPNMB⁺ CTCs and plasma CXCL12 were significantly associated with BM progression in lung cancer and melanoma. Therapeutically, dual blockade of GPNMB and PD1 enhanced anti-BM efficacy in mice, unveiling GPNMB as a promising target for precision immunotherapy.

PMID:41973996 | DOI:10.1158/2159-8290.CD-25-1663

Received — 8 April 2026 ⏭

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shanglin Wu · Yuyang Luo · Yueqing Liang · Kaiwen Shi · Yanfang Ye · Ali Payani · Kai Shu
7 April 2026 at 12:00
arXiv:2604.03295v1 Announce Type: cross Abstract: Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time. Although prior work has studied these dimensions separately, their interaction under realistic cost constraints remains unclear. In this paper, we introduce a conceptual scaling view of multi-agent systems that jointly considers team size and lifelong learning ability, and we study how memory design shares this landscape. To this end, we propose \textbf{LLMA-Mem}, a lifelong memory framework for LLM multi-agent systems under flexible memory topologies. We evaluate LLMA-Mem on \textsc{MultiAgentBench} across coding, research, and database environments. Empirically, LLMA-Mem consistently improves long-horizon performance over baselines while reducing cost. Our analysis further reveals a non-monotonic scaling landscape: larger teams do not always produce better long-term performance, and smaller teams can outperform larger ones when memory better supports the reuse of experience. These findings position memory design as a practical path for scaling multi-agent systems more effectively and more efficiently over time.
Received — 4 April 2026 ⏭

Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiaqi Liu · Zipeng Ling · Shi Qiu · Yanqing Liu · Siwei Han · Peng Xia · Haoqin Tu · Zeyu Zheng · Cihang Xie · Charles Fleming · Mingyu Ding · Huaxiu Yao
3 April 2026 at 12:00
arXiv:2604.01007v2 Announce Type: replace Abstract: AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space spanning architecture, retrieval strategies, prompt engineering, and data pipelines; this space is too large and interconnected for manual exploration or traditional AutoML to explore effectively. We deploy an autonomous research pipeline to discover Omni-SimpleMem, a unified multimodal memory framework for lifelong AI agents. Starting from a na\"ive baseline (F1=0.117 on LoCoMo), the pipeline autonomously executes ${\sim}50$ experiments across two benchmarks, diagnosing failure modes, proposing architectural modifications, and repairing data pipeline bugs, all without human intervention in the inner loop. The resulting system achieves state-of-the-art on both benchmarks, improving F1 by +411% on LoCoMo (0.117$\to$0.598) and +214% on Mem-Gallery (0.254$\to$0.797) relative to the initial configurations. Critically, the most impactful discoveries are not hyperparameter adjustments: bug fixes (+175%), architectural changes (+44%), and prompt engineering (+188% on specific categories) each individually exceed the cumulative contribution of all hyperparameter tuning, demonstrating capabilities fundamentally beyond the reach of traditional AutoML. We provide a taxonomy of six discovery types and identify four properties that make multimodal memory particularly suited for autoresearch, offering guidance for applying autonomous research pipelines to other AI system domains. Code is available at this https://github.com/aiming-lab/SimpleMem.

Four Generations of Quantum Biomedical Sensors

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xin Jin · Priyam Srivastava · Ronghe Wang · Yuqing Li · Jonathan Beaumariage · Tom Purdy · M. V. Gurudev Dutt · Kang Kim · Kaushik Seshadreesan · Junyu Liu
3 April 2026 at 12:00
arXiv:2603.29944v2 Announce Type: replace-cross Abstract: Quantum sensing technologies offer transformative potential for ultra-sensitive biomedical sensing, yet their clinical translation remains constrained by classical noise limits and a reliance on macroscopic ensembles. We propose a unifying generational framework to organize the evolving landscape of quantum biosensors based on their utilization of quantum resources. First-generation devices utilize discrete energy levels for signal transduction but follow classical scaling laws. Second-generation sensors exploit quantum coherence to reach the standard quantum limit, while third-generation architectures leverage entanglement and spin squeezing to approach Heisenberg-limited precision. We further define an emerging fourth generation characterized by the end-to-end integration of quantum sensing with quantum learning and variational circuits, enabling adaptive inference directly within the quantum domain. By analyzing critical parameters such as bandwidth matching and sensor-tissue proximity, we identify key technological bottlenecks and propose a roadmap for transitioning from measuring physical observables to extracting structured biological information with quantum-enhanced intelligence.

Cell-type-specific transposon demethylation and TAD remodeling in aging mouse brain

✇Cell
By: Qiurui Zeng · Wenliang Wang · Wei Tian · Amit Klein · Anna Bartlett · Hanqing Liu · Joseph R. Nery · Rosa G. Castanon · Julia Osteen · Nicholas D. Johnson · Wubin Ding · Huaming Chen · Jordan Altshul · Mia Kenworthy · Cynthia Valadon · William Owens · Zhanghao Wu · Maria Luisa Amaral · Nathan R. Zemke · Yuru Song · Cindy Tatiana Báez-Becerra · Silvia Cho · Chumo Chen · Jackson Willier · Stella Cao · Jonathan Rink · Jasper Lee · Ariana Barcoma · Jessica Arzavala · Nora Emerson · Yuancheng Ryan Lu · Bing Ren · M. Margarita Behrens · Joseph R. Ecker
11 March 2026 at 08:00
A multi-omic single-cell atlas of the aging mouse brain reveals cell-type-specific transposon methylation changes, strengthening of 3D genome boundaries, and regionally heterogeneous aging signatures. These findings offer a resource to understand the molecular mechanisms of brain aging and guide future research on neurodegeneration.
Received — 2 April 2026 ⏭

Four Generations of Quantum Biomedical Sensors

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xin Jin · Priyam Srivastava · Ronghe Wang · Yuqing Li · Jonathan Beaumariage · Tom Purdy · M. V. Gurudev Dutt · Kang Kim · Kaushik Seshadreesan · Junyu Liu
1 April 2026 at 12:00
arXiv:2603.29944v1 Announce Type: cross Abstract: Quantum sensing technologies offer transformative potential for ultra-sensitive biomedical sensing, yet their clinical translation remains constrained by classical noise limits and a reliance on macroscopic ensembles. We propose a unifying generational framework to organize the evolving landscape of quantum biosensors based on their utilization of quantum resources. First-generation devices utilize discrete energy levels for signal transduction but follow classical scaling laws. Second-generation sensors exploit quantum coherence to reach the standard quantum limit, while third-generation architectures leverage entanglement and spin squeezing to approach Heisenberg-limited precision. We further define an emerging fourth generation characterized by the end-to-end integration of quantum sensing with quantum learning and variational circuits, enabling adaptive inference directly within the quantum domain. By analyzing critical parameters such as bandwidth matching and sensor-tissue proximity, we identify key technological bottlenecks and propose a roadmap for transitioning from measuring physical observables to extracting structured biological information with quantum-enhanced intelligence.

GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rui Xie · Zhi Gao · Chenrui Shi · Zirui Shang · Lu Chen · Qing Li
1 April 2026 at 12:00
arXiv:2603.26266v2 Announce Type: replace Abstract: Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to domain-specific software operation data during training, these agents exhibit significant domain bias - they lack familiarity with the specific operation workflows (planning) and UI element layouts (grounding) of particular applications, limiting their real-world task performance. In this paper, we present GUIDE (GUI Unbiasing via Instructional-Video Driven Expertise), a training-free, plug-and-play framework that resolves GUI agent domain bias by autonomously acquiring domain-specific expertise from web tutorial videos through a retrieval-augmented automated annotation pipeline. GUIDE introduces two key innovations. First, a subtitle-driven Video-RAG pipeline unlocks video semantics through subtitle analysis, performing progressive three-stage retrieval - domain classification, topic extraction, and relevance matching - to identify task-relevant tutorial videos. Second, a fully automated annotation pipeline built on an inverse dynamics paradigm feeds consecutive keyframes enhanced with UI element detection into VLMs, inferring the required planning and grounding knowledge that are injected into the agent's corresponding modules to address both manifestations of domain bias. Extensive experiments on OSWorld demonstrate GUIDE's generality as a plug-and-play component for both multi-agent systems and single-model agents. It consistently yields over 5% improvements and reduces execution steps - without modifying any model parameters or architecture - validating GUIDE as an architecture-agnostic enhancement to bridge GUI agent domain bias.

The 1000 Chinese Pangenome empowers medical and population genetics

✇Nature - Issue - nature.com science feeds
By: Yifei Wang · Zhongqu Duan · Dan Chen · Dandan Shi · Yi Ding · Zhibin Wang · Baoqing Li · Zhiyi Wang · Minmin Guo · Wen Yang · Junren Hou · Wenhao Chen · Yazhou Guo · Wenjie Wei · Yujie Cao · Xiwei Sun · Weiyang Bai · Mingdong Lu · Ting Qi · Xian Shen · Jian Yang
1 April 2026 at 08:00

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10315-y

Development of the pangenome-informed genome assembly (PIGA) workflow enabled the generation of 1,116 diploid genome assemblies (55 de novo and 1,061 pangenome-informed), representing an extensive resource of medically relevant genic variations.
Received — 26 March 2026 ⏭

Three Creates All: You Only Sample 3 Steps

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuren Cai · Guangyi Wang · Zongqing Li · Li Li · Zhihui Liu · Songzhi Su
25 March 2026 at 12:00
arXiv:2603.22375v1 Announce Type: cross Abstract: Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes a key bottleneck for few-step sampling. Motivated by layer-dependent denoising dynamics, we propose Multi-layer Time Embedding Optimization (MTEO), which freeze the pretrained diffusion backbone and distill a small set of step-wise, layer-wise time embeddings from reference trajectories. MTEO is plug-and-play with existing ODE solvers, adds no inference-time overhead, and trains only a tiny fraction of parameters. Extensive experiments across diverse datasets and backbones show state-of-the-art performance in the few-step sampling and substantially narrow the gap between distillation-based and lightweight methods. Code will be available.

From Context to Intent: Reasoning-Guided Function-Level Code Completion

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yanzhou Li · Tianlin Li · Yiran Zhang · Shangqing Liu · Aishan Liu · Xianglong Liu · Yang Liu
25 March 2026 at 12:00
arXiv:2508.09537v2 Announce Type: replace-cross Abstract: The growing capabilities of Large Language Models (LLMs) have led to their widespread adoption for function completion within code repositories. Recent studies on such tasks show promising results when explicit instructions, often in the form of docstrings, are available to guide the completion. However, in real-world scenarios, clear docstrings are frequently absent. Under such conditions, LLMs typically fail to produce accurate completions. To enable more automated and accurate function completion in such settings, we aim to enable LLMs to accurately infer the developer's intent prior to code completion. Our key insight is that the preceding code, namely the code context before the function to be completed, often contains valuable cues that help the model understand the intended functionality. However, inferring intent from such implicit context is non-trivial and constitutes a core challenge in function-level code completion. To tackle this challenge, inspired by how humans interpret context, we propose a reasoning-based prompting framework that guides LLMs to utilize these contextual cues to infer intent step by step. To incentivize LLMs to reason through the preceding code and infer intent, we further curate a dataset of 40k examples, each annotated with intermediate reasoning traces and corresponding docstrings. Extensive experiments on DevEval and ComplexCodeEval demonstrate consistent performance improvements across multiple models, achieving over 25% relative gains in pass@1 for both DeepSeekCoder and CodeLLaMA families. Building upon our framework, we further develop an intent-interactive platform that supports lightweight human feedback. This platform allows developers to select from a set of candidate intentions or edit the intent to better guide the model. Our experiments show that this interactive approach leads to further performance improvements.

The dual regulatory role of METTL14-mediated m<sup>6</sup>A modification in tumorigenesis and its underlying mechanisms

✇Omics in Hepatocellular
By: Yulan Yang · Lemuge Chao · Xudong Ao · Junqing Liang
20 March 2026 at 18:00

Front Oncol. 2026 Mar 4;16:1771313. doi: 10.3389/fonc.2026.1771313. eCollection 2026.

ABSTRACT

N6-methyladenosine (m6A), as the most abundant RNA epitranscriptional modification in eukaryotes, its key component of the methyltransferase complex, METTL14, not only cooperates in catalyzing m6A deposition but also has functions independent of methyltransferase activity. This article systematically reviews the dual regulatory role of METTL14 in tumors and its molecular mechanisms, mainly organizing the relevant research in a logical sequence of "tumor suppressive effect - tumor promoting effect - controversial or context-dependent". Studies have shown that METTL14 often plays a tumor suppressive role in tumors such as hepatocellular carcinoma and colorectal cancer, while in pancreatic cancer and nasopharyngeal carcinoma, it mostly promotes malignant progression, showing a high degree of context dependence. This article focuses on two key mechanisms: on the one hand, METTL14 precisely regulates the processing, stability, and function of non-coding RNAs (including miRNAs, lncRNAs, and circRNAs) through m6A modification, reshaping the competitive endogenous RNA (ceRNA) network; on the other hand, it shapes an immunosuppressive tumor microenvironment by directly upregulating immune checkpoints such as PD-L1, mediating metabolism-immune interactions, and regulating the function of immune cells. Its functional duality also stems from the selective regulation of key pathways such as PI3K/AKT, as well as the differential interpretation by different m6A readers (such as YTHDF2 and IGF2BPs). Given the close association of these mechanisms with clinical prognosis, the expression level of METTL14 shows significant potential as a prognostic marker and therapeutic target; in the future, it is necessary to combine single-cell multi-omics and other technologies to analyze its dynamic regulatory network in specific tumor contexts and explore precise treatment strategies based on synthetic lethality or targeting downstream effector molecules.

PMID:41858346 | PMC:PMC12995618 | DOI:10.3389/fonc.2026.1771313

❌