Unmasking FCGR2B as a high-grade serous ovarian cancer specific marker of immune suppression and tumor progression through multi-omics mining

By: Jialu Zhou · Tao Zeng · Mingxia Ye · Mingxia Li · Liang Wen · Xinyi Liu · Zhe Zhang · Yuanguang Meng

4 April 2026 at 18:00

Transl Oncol. 2026 Apr 3;67:102748. doi: 10.1016/j.tranon.2026.102748. Online ahead of print.

ABSTRACT

BACKGROUND: Epithelial ovarian cancer (EOC) encompasses five major histological subtypes with marked genetic, immunological, and clinical heterogeneity. While genome-wide association studies (GWAS) have identified subtype-specific risk loci, a critical gap remains in understanding how plasma proteins influence immune-cell traits and contribute to EOC pathogenesis.

METHODS: We integrated subtype-stratified GWAS data from two EOC cohorts with plasma proteomics and immune-cell traits to construct protein-immune-EOC regulatory landscapes using a three-stage Mendelian randomization framework. Single-cell RNA-seq and multiplex immunofluorescence were employed to delineate the cellular distribution and spatial context of causal proteins. Subsequent analyses characterized immune infiltration, macrophage polarization, and clinicopathological associations. Drug-gene correlations were used to identify potential therapeutic targets, and transcriptomic analyses were applied to delineate the underlying transcriptional landscape.

RESULTS: We identified 20 subtype-specific protein-immune-EOC regulatory axes, with FCGR2B emerging as a causal plasma protein in immune regulation and high-grade serous ovarian cancer (HGSOC) progression. FCGR2B was highly expressed in tumor-associated macrophages and was associated with an M2-like polarization phenotype. Functional characterization revealed that FCGR2B was associated with shorter progression-free survival and an immunosuppressive tumor microenvironment. Transcriptomic analyses revealed altered NF-κB signaling upon FCGR2B knockdown, and drug-response data suggested a potential association between high FCGR2B expression and sensitivity to NF-κB inhibitors.

CONCLUSIONS: These findings delineate subtype-specific genetically informed protein-immune regulatory landscapes in EOC and identify FCGR2B as a key immunoregulatory and prognostic biomarker in HGSOC, suggesting FCGR2B as a potential therapeutic vulnerability that warrants further investigation.

PMID:41934917 | DOI:10.1016/j.tranon.2026.102748

Metabolite-gated vascular contractility switch: OXGR1 activation mechanism enables agonist therapy for rosacea erythema

Cell

By: Wenqin Xiao · Yan Zhu · Xinjie Tang · Kongkai Zhu · Weifeng Zhang · Mengting Chen · Kui Cai · San Xu · Zheng Wu · Mei Wang · Jiayi Liu · Linglong Long · Zixin Tan · Aike Wu · Songqi Zhou · Zhixiang Zhao · Yan Tang · Yingxue Huang · Ben Wang · Fangfen Liu · Qian Wang · Fan Yang · Dan Jian · Wei Shi · Hongfu Xie · Xiang Chen · Lulu Guo · Zhili Deng · Jinpeng Sun · Ji Li

5 March 2026 at 08:00

Xiao et al. identify α-KG as a rosacea-associated metabolite that activates the OXGR1-Gq-MYL9 axis in the vascular smooth muscle cells to boost contractility and suppress pathological vasodilation underlying erythema. Cryo-EM reveals a bipartite-acid pocket of OXGR1 that enables structure-guided development of A-1, a selective agonist that alleviates erythema in rosacea-like models.

GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification

cs.AI, q-bio.NC updates on arXiv.org

By: Iordanis Fostiropoulos · Muhammad Rafay Azhar · Abdalaziz Sawwan · Boyu Fang · Yuchen Liu · Jiayi Liu · Hanchao Yu · Qi Guo · Jianyu Wang · Fei Liu · Xiangjun Fan

1 April 2026 at 12:00

arXiv:2603.29112v1 Announce Type: new Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in recommendation systems. Unlike traditional RecSys benchmarks that focus on item prediction accuracy, our benchmark evaluates how well LLMs can extract and verify user interests from engagement data. We propose two novel metric families: Interest Groundedness (IG), decomposed into precision and recall components to separately penalize hallucinated interest categories and reward coverage, and Interest Specificity (IS), which assesses the distinctiveness of verified LLM-predicted user profiles. We release a synthetic dataset constructed on real user interactions on a global short-form video platform. Our dataset contains both implicit and explicit engagement signals and rich textual descriptions. We validate our dataset fidelity against user surveys, and evaluate eight open-weight LLMs spanning 7B to 120B parameters. Our findings reveal performance bottlenecks in current LLMs, particularly their limited ability to accurately count and attribute engagement signals across heterogeneous interaction types.

Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs

cs.AI, q-bio.NC updates on arXiv.org

By: Yi Liu

1 April 2026 at 12:00

arXiv:2603.28823v1 Announce Type: cross Abstract: Scaling laws relate model quality to compute budget (FLOPs), but practitioners face wall-clock time constraints, not compute budgets. We study optimal model sizing under fixed time budgets from 5 minutes to 24 hours on consumer GPUs (RTX 4090). Across 70+ runs spanning 50M--1031M parameters, we find: (1)~at each time budget a U-shaped curve emerges where too-small models overfit and too-large models undertrain; (2)~optimal model size follows $N^* \propto t^{0.60}$, growing \emph{faster} than Chinchilla's $N^* \propto C^{0.50}$, with $\alpha = 0.60 \pm 0.07$ robustly exceeding compute-optimal across all sensitivity analyses; (3)~a \emph{dual U-shape mechanism}: short-budget U-curves arise from compute bottlenecks, while long-budget U-curves emerge from data bottlenecks (overfitting), with an intermediate regime where the U-curve temporarily disappears. These findings have immediate implications for researchers training on consumer hardware, where wall-clock time -- not FLOPs -- is the binding constraint. We release all code, logs, and 70+ experimental configurations.

Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification

cs.AI, q-bio.NC updates on arXiv.org

By: Guan Wang · Shuyin Xia · Lei Qian · Guoyin Wang · Yi Liu · Yi Wang · Wei Wang

1 April 2026 at 12:00

arXiv:2603.29148v1 Announce Type: cross Abstract: Graph Convolutional Network (GCN) is a model that can effectively handle graph data tasks and has been successfully applied. However, for large-scale graph datasets, GCN still faces the challenge of high computational overhead, especially when the number of convolutional layers in the graph is large. Currently, there are many advanced methods that use various sampling techniques or graph coarsening techniques to alleviate the inconvenience caused during training. However, among these methods, some ignore the multi-granularity information in the graph structure, and the time complexity of some coarsening methods is still relatively high. In response to these issues, based on our previous work, in this paper, we propose a new framework called Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification. Specifically, this method first uses a multi-granularity granular-ball graph coarsening algorithm to coarsen the original graph to obtain many subgraphs. The time complexity of this stage is linear and much lower than that of the exiting graph coarsening methods. Then, subgraphs composed of these granular-balls are randomly sampled to form minibatches for training GCN. Our algorithm can adaptively and significantly reduce the scale of the original graph, thereby enhancing the training efficiency and scalability of GCN. Ultimately, the experimental results of node classification on multiple datasets demonstrate that the method proposed in this paper exhibits superior performance. The code is available at https://anonymous.4open.science/r/1-141D/.

Electric dipole moment drives the dynamics of the TNFR1 complex I signalosome

Nature - Issue - nature.com science feeds

By: Jianping Liu · Jing Zhao · Jiayang Gao · Kun Zhao · Yaoyao Han · Jing Yang · Zefei Li · Jianyu Ye · Ziyu Sun · Fengyi Wang · Xinyi Liu · Zekai Li · Siyu Ji · Bo Liu · Cong Liu · Yixiao Zhang · Junying Yuan · James J. Chou

1 April 2026 at 08:00

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10304-1

Long-range interactions mediated by protein electric dipole moments have a role in driving the assembly and disassembly of super-signalling complex I for promoting NF-κB signalling.

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

cs.AI, q-bio.NC updates on arXiv.org

By: Xiangyi Li · Wenbo Chen · Yimin Liu · Shenghan Zheng · Xiaokun Chen · Yifeng He · Yubo Li · Bingran You · Haotian Shen · Jiankai Sun · Shuyi Wang · Binxu Li · Qunhong Zeng · Di Wang · Xuandong Zhao · Yuanli Wang · Roey Ben Chaim · Zonglin Di · Yipeng Gao · Junwei He · Yizhuo He · Liqiang Jing · Luyang Kong · Xin Lan · Jiachen Li · Songlin Li · Yijiang Li · Yueqian Lin · Xinyi Liu · Xuanqing Liu · Haoran Lyu · Ze Ma · Bowei Wang · Runhui Wang · Tianyu Wang · Wengao Ye · Yue Zhang · Hanwen Xing · Yiqi Xue · Steven Dillmann · Han-chung Lee

16 March 2026 at 12:00

arXiv:2602.12670v3 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers. Each task is evaluated under three conditions: no Skills, curated Skills, and self-generated Skills. We test 7 agent-model configurations over 7,308 trajectories. Curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain (+4.5pp for Software Engineering to +51.9pp for Healthcare) and 16 of 84 tasks show negative deltas. Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming. Focused Skills with 2--3 modules outperform comprehensive documentation, and smaller models with Skills can match larger models without them.

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos

cs.AI, q-bio.NC updates on arXiv.org

By: Wenqi Liu · Yunxiao Wang · Shijie Ma · Meng Liu · Qile Su · Tianke Zhang · Haonan Fan · Changyi Liu · Kaiyu Jiang · Jiankang Chen · Kaiyu Tang · Bin Wen · Fan Yang · Tingting Gao · Han Li · Yinwei Wei · Xuemeng Song

16 March 2026 at 12:00

arXiv:2602.07801v3 Announce Type: replace-cross Abstract: In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding.

Profiling of the mycobiome and metabolome: a comparative study of benign pulmonary nodules and lung adenocarcinoma

Pulmonary nodule

By: Weiyi Zhang · Yuan Dong · Fangyan Chen · Fang Wang · Jiahui Li · Chunxi Liu · Tianyi Liu · Li Han · Xiaodong Jia

11 March 2026 at 18:00

Front Cell Infect Microbiol. 2026 Feb 23;16:1732958. doi: 10.3389/fcimb.2026.1732958. eCollection 2026.

ABSTRACT

INTRODUCTION: Lung adenocarcinoma (LUAD), the most common subtype of non-small cell lung cancer, is a form of malignant pulmonary nodule that requires clinical differentiation from benign pulmonary nodules (BPN). The mechanisms underlying the development of LUAD are complex, and effective non-invasive methods for differentiating BPN from LUAD are lacking. This study aimed not only to distinguish BPN from LUAD using gut fungi and serum metabolites, but also to establish an integrated network of gut fungi-metabolite-cytokine interactions.

METHODS: Fecal and serum samples from individuals with BPN and patients with LUAD were subjected to internal transcribed spacer sequencing, ultra-performance liquid chromatography-tandem mass spectrometry, and multiplex Luminex assays to quantify gut fungi, metabolites, and cytokines, respectively.

RESULTS: A significant difference in gut fungal communities was observed between the BPN and LUAD groups. Multiple genera and species were more abundant in LUAD than in BPN. Docosapentaenoic acid n-6 (DPAn-6), indole-3-propionic acid (IPA), and interferon-γ-induced protein 10 (IP-10) were significantly elevated in the LUAD group. The integrated model established using a combination of gut fungi and metabolites demonstrated excellent performance in distinguishing BPN from LUAD. A network of interactions was established among differentially abundant gut fungi, serum metabolites, and cytokines.

CONCLUSION: Our study identifies a novel panel of fungal and metabolite biomarkers for differentiating between BPN and LUAD, and constructs a multi-omics network that provides new insights into investigating the mechanistic role of gut mycobiota dysbiosis in LUAD.

PMID:41809995 | PMC:PMC12968269 | DOI:10.3389/fcimb.2026.1732958

Large Language Model for Discrete Optimization Problems: Evaluation and Step-by-step Reasoning

cs.AI, q-bio.NC updates on arXiv.org

By: Tianhao Qian · Guilin Qi · Z. Y. Wu · Ran Gu · Xuanyi Liu · Canchen Lyu

10 March 2026 at 12:00

arXiv:2603.07733v1 Announce Type: new Abstract: This work investigated the capabilities of different models, including the Llama-3 series of models and CHATGPT, with different forms of expression in solving discrete optimization problems by testing natural language datasets. In contrast to formal datasets with a limited scope of parameters, our dataset included a variety of problem types in discrete optimization problems and featured a wide range of parameter magnitudes, including instances with large parameter sets, integrated with augmented data. It aimed to (1) provide an overview of LLMs' ability in large-scale problems, (2) offer suggestions to those who want to solve discrete optimization problems automatically, and (3) regard the performance as a benchmark for future research. These datasets included original, expanded and augmented datasets. Among these three datasets, the original and augmented ones aimed for evaluation while the expanded one may help finetune a new model. In the experiment, comparisons were made between strong and week models, CoT methods and No-CoT methods on various datasets. The result showed that stronger model performed better reasonably. Contrary to general agreement, it also showed that CoT technique was not always effective regarding the capability of models and disordered datasets improved performance of models on easy to-understand problems, even though they were sometimes with high variance, a manifestation of instability. Therefore, for those who seek to enhance the automatic resolution of discrete optimization problems, it is recommended to consult the results, including the line charts presented in the Appendix, as well as the conclusions drawn in this study for relevant suggestions.

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

cs.AI, q-bio.NC updates on arXiv.org

By: Xiangyi Li · Wenbo Chen · Yimin Liu · Shenghan Zheng · Xiaokun Chen · Yifeng He · Yubo Li · Bingran You · Haotian Shen · Jiankai Sun · Shuyi Wang · Binxu Li · Qunhong Zeng · Di Wang · Xuandong Zhao · Yuanli Wang · Roey Ben Chaim · Zonglin Di · Yipeng Gao · Junwei He · Yizhuo He · Liqiang Jing · Luyang Kong · Xin Lan · Jiachen Li · Songlin Li · Yijiang Li · Yueqian Lin · Xinyi Liu · Xuanqing Liu · Haoran Lyu · Ze Ma · Bowei Wang · Runhui Wang · Tianyu Wang · Wengao Ye · Yue Zhang · Hanwen Xing · Yiqi Xue · Steven Dillmann · Han-chung Lee

10 March 2026 at 12:00

arXiv:2602.12670v2 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers. Each task is evaluated under three conditions: no Skills, curated Skills, and self-generated Skills. We test 7 agent-model configurations over 7,308 trajectories. Curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain (+4.5pp for Software Engineering to +51.9pp for Healthcare) and 16 of 84 tasks show negative deltas. Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming. Focused Skills with 2--3 modules outperform comprehensive documentation, and smaller models with Skills can match larger models without them.

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning

cs.AI, q-bio.NC updates on arXiv.org

By: Chuang Zhang · Zizhen Zhu · Yihao Wei · Bing Tian · Junyi Liu · Henan Wang · Xavier Wang · Yaxiao Liu

5 March 2026 at 13:00

arXiv:2603.03752v1 Announce Type: cross Abstract: Large language models (LLMs) demonstrate superior reasoning capabilities compared to small language models (SLMs), but incur substantially higher costs. We propose COllaborative REAsoner (COREA), a system that cascades an SLM with an LLM to achieve a balance between accuracy and cost in complex reasoning tasks. COREA first attempts to answer questions using the SLM, which outputs both an answer and a verbalized confidence score. Questions with confidence below a predefined threshold are deferred to the LLM for more accurate resolution. We introduce a reinforcement learning-based training algorithm that aligns the SLM's confidence through an additional confidence calibration reward. Extensive experiments demonstrate that our method jointly improves the SLM's reasoning ability and confidence calibration across diverse datasets and model backbones. Compared to using the LLM alone, COREA reduces cost by 21.5% and 16.8% on out-of-domain math and non-math datasets, respectively, with only an absolute pass@1 drop within 2%.

DisenReason: Behavior Disentanglement and Latent Reasoning for Shared-Account Sequential Recommendation

cs.AI, q-bio.NC updates on arXiv.org

By: Jiawei Cheng · Min Gao · Zongwei Wang · Xiaofei Zhu · Zhiyi Liu · Wentao Li · Wei Li · Huan Wu

5 March 2026 at 13:00

arXiv:2603.03782v1 Announce Type: cross Abstract: Shared-account usage is common on streaming and e-commerce platforms, where multiple users share one account. Existing shared-account sequential recommendation (SSR) methods often assume a fixed number of latent users per account, limiting their ability to adapt to diverse sharing patterns and reducing recommendation accuracy. Recent latent reasoning technique applied in sequential recommendation (SR) generate intermediate embeddings from the user embedding (e.g, last item embedding) to uncover users' potential interests, which inspires us to treat the problem of inferring the number of latent users as generating a series of intermediate embeddings, shifting from inferring preferences behind user to inferring the users behind account. However, the last item cannot be directly used for reasoning in SSR, as it can only represent the behavior of the most recent latent user, rather than the collective behavior of the entire account. To address this, we propose DisenReason, a two-stage reasoning method tailored to SSR. DisenReason combines behavior disentanglement stage from frequency-domain perspective to create a collective and unified account behavior representation, which serves as a pivot for latent user reasoning stage to infer the number of users behind the account. Experiments on four benchmark datasets show that DisenReason consistently outperforms all state-of-the-art baselines across four benchmark datasets, achieving relative improvements of up to 12.56\% in MRR@5 and 6.06\% in Recall@20.

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos

cs.AI, q-bio.NC updates on arXiv.org

By: Wenqi Liu · Yunxiao Wang · Shijie Ma · Meng Liu · Qile Su · Tianke Zhang · Haonan Fan · Changyi Liu · Kaiyu Jiang · Jiankang Chen · Kaiyu Tang · Bin Wen · Fan Yang · Tingting Gao · Han Li · Yinwei Wei · Xuemeng Song

4 March 2026 at 13:00

arXiv:2602.07801v2 Announce Type: replace-cross Abstract: In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding.

CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG

cs.AI, q-bio.NC updates on arXiv.org

By: Xiaobin Wong · Zhonghua Zhao · Haoran Guo · Zhengyi Liu · Yu Wu · Feng Yan · Zhiren Wang · Sen Song

24 February 2026 at 13:00

arXiv:2602.19138v1 Announce Type: new Abstract: EEG-based neural decoding models often fail to generalize across acquisition sites due to structured, site-dependent biases implicitly exploited during training. We reformulate cross-site clinical EEG learning as a bias-factorized generalization problem, in which domain shifts arise from multiple interacting sources. We identify three fundamental bias factors and propose a general training framework that mitigates their influence through data standardization and representation-level constraints. We construct a standardized multi-site EEG benchmark for Major Depressive Disorder and introduce CRCC, a two-stage training paradigm combining encoder-decoder pretraining with joint fine-tuning via cross-subject/site contrastive learning and site-adversarial optimization. CRCC consistently outperforms state-of-the-art baselines and achieves a 10.7 percentage-point improvement in balanced accuracy under strict zero-shot site transfer, demonstrating robust generalization to unseen environments.

FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations

cs.AI, q-bio.NC updates on arXiv.org

By: Yixing Peng · Licheng Zhang · Shancheng Fang · Yi Liu · Peijian Gu · Quan Wang

24 February 2026 at 13:00

arXiv:2602.18437v1 Announce Type: cross Abstract: Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the user query, which degrades answer quality and robustness in real-world settings with noisy or irrelevant retrieved content. Moreover, the prevailing single-pass paradigm struggles to deliver optimal answers in long-form generation that requiring multiple citations. To address these limitations, we propose FineRef, a framework based on Fine-grained error Reflection, which explicitly teaches the model to self-identify and correct two key citation errors, mismatch and irrelevance, on a per-citation basis. FineRef follows a two-stage training strategy. The first stage instills an "attempt-reflect-correct" behavioral pattern via supervised fine-tuning, using fine-grained and controllable reflection data constructed by specialized lightweight models. An online self-reflective bootstrapping strategy is designed to improve generalization by iteratively enriching training data with verified, self-improving examples. To further enhance the self-reflection and correction capability, the second stage applies process-level reinforcement learning with a multi-dimensional reward scheme that promotes reflection accuracy, answer quality, and correction gain. Experiments on the ALCE benchmark demonstrate that FineRef significantly improves both citation performance and answer accuracy. Our 7B model outperforms GPT-4 by up to 18% in Citation F1 and 4% in EM Recall, while also surpassing the state-of-the-art model across key evaluation metrics. FineRef also exhibits strong generalization and robustness in domain transfer settings and noisy retrieval scenarios.

MAS-on-the-Fly: Dynamic Adaptation of LLM-based Multi-Agent Systems at Test Time

cs.AI, q-bio.NC updates on arXiv.org

By: Guangyi Liu · Haojun Lin · Huan Zeng · Heng Wang · Quanming Yao

17 February 2026 at 13:00

arXiv:2602.13671v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation, lacking dynamic adaptability after deployment. Inspired by how biological systems adapt, we introduce MASFly, a novel multi-agent framework enabling dynamic adaptation at test time. To adapt system generation, MASFly employs a retrieval-augmented SOP instantiation mechanism that leverages a self-constructed repository of successful collaboration patterns, enabling the LLM to assemble customized MASs for new queries. For adaptive execution, MASFly incorporates an experience-guided supervision mechanism, where a dedicated Watcher agent monitors system behaviors with reference to a personalized experience pool and provides real-time interventions. Extensive experiments demonstrate that MASFly achieves state-of-the-art performance, most notably a 61.7% success rate on the TravelPlanner benchmark, while exhibiting strong task adaptability and robustness.

Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design

cs.AI, q-bio.NC updates on arXiv.org

By: Bojian Hou · Xiaolong Liu · Xiaoyi Liu · Jiaqi Xu · Yasmine Badr · Mengyue Hang · Sudhanshu Chanpuriya · Junqing Zhou · Yuhang Yang · Han Xu · Qiuling Suo · Laming Chen · Yuxi Hu · Jiasheng Zhang · Huaqing Xiong · Yuzhen Huang · Chao Chen · Yue Dong · Yi Yang · Shuo Chang · Xiaorui Gan · Wenlin Chen · Santanu Kolay · Darren Liu · Jade Nie · Chunzhi Yang · Ellie Wen · Jiyan Yang · Huayu Li

17 February 2026 at 13:00

arXiv:2602.10016v2 Announce Type: replace-cross Abstract: Deriving predictable scaling laws that govern the relationship between model performance and computational investment is crucial for designing and allocating resources in massive-scale recommendation systems. While such laws are established for large language models, they remain challenging for recommendation systems, especially those processing both user history and context features. We identify poor scaling efficiency as the main barrier to predictable power-law scaling, stemming from inefficient modules with low Model FLOPs Utilization (MFU) and suboptimal resource allocation. We introduce Kunlun, a scalable architecture that systematically improves model efficiency and resource allocation. Our low-level optimizations include Generalized Dot-Product Attention (GDPA), Hierarchical Seed Pooling (HSP), and Sliding Window Attention. Our high-level innovations feature Computation Skip (CompSkip) and Event-level Personalization. These advances increase MFU from 17% to 37% on NVIDIA B200 GPUs and double scaling efficiency over state-of-the-art methods. Kunlun is now deployed in major Meta Ads models, delivering significant production impact.

Reading view