❌

Normal view

Received — 29 October 2025 ⏭ Favourites

Tongyi DeepResearch Technical Report

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tongyi DeepResearch Team · Baixuan Li · Bo Zhang · Dingchu Zhang · Fei Huang · Guangyu Li · Guoxin Chen · Huifeng Yin · Jialong Wu · Jingren Zhou · Kuan Li · Liangcai Su · Litu Ou · Liwen Zhang · Pengjun Xie · Rui Ye · Wenbiao Yin · Xinmiao Yu · Xinyu Wang · Xixi Wu · Xuanzhong Chen · Yida Zhao · Zhen Zhang · Zhengwei Tao · Zhongwang Zhang · Zile Qiao · Chenxi Wang · Donglei Yu · Gang Fu · Haiyang Shen · Jiayin Yang · Jun Lin · Junkai Zhang · Kui Zeng · Li Yang · Hailong Yin · Maojia Song · Ming Yan · Peng Xia · Qian Xiao · Rui Min · Ruixue Ding · Runnan Fang · Shaowei Chen · Shen Huang · Shihang Wang · Shihao Cai · Weizhou Shen · Xiaobin Wang · Xin Guan · Xinyu Geng · Yingcheng Shi · Yuning Wu · Zhuo Chen · Zijian Li · Yong Jiang
29 October 2025 at 12:00
arXiv:2510.24701v1 Announce Type: cross Abstract: We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework that combines agentic mid-training and agentic post-training, enabling scalable reasoning and information seeking across complex tasks. We design a highly scalable data synthesis pipeline that is fully automatic, without relying on costly human annotation, and empowers all training stages. By constructing customized environments for each stage, our system enables stable and consistent interactions throughout. Tongyi DeepResearch, featuring 30.5 billion total parameters, with only 3.3 billion activated per token, achieves state-of-the-art performance across a range of agentic deep research benchmarks, including Humanity's Last Exam, BrowseComp, BrowseComp-ZH, WebWalkerQA, xbench-DeepSearch, FRAMES and xbench-DeepSearch-2510. We open-source the model, framework, and complete solutions to empower the community.
Received — 28 October 2025 ⏭ Favourites

Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zihao Li · Weiwei Yi · Jiahong Chen
27 October 2025 at 12:00
arXiv:2509.13345v2 Announce Type: replace-cross Abstract: Hallucination in generative AI is often treated as a technical failure to produce factually correct output. Yet this framing underrepresents the broader significance of hallucinated content in language models, which may appear fluent, persuasive, and contextually appropriate while conveying distortions that escape conventional accuracy checks. This paper critically examines how regulatory and evaluation frameworks have inherited a narrow view of hallucination, one that prioritises surface verifiability over deeper questions of meaning, influence, and impact. We propose a layered approach to understanding hallucination risks, encompassing epistemic instability, user misdirection, and social-scale effects. Drawing on interdisciplinary sources and examining instruments such as the EU AI Act and the GDPR, we show that current governance models struggle to address hallucination when it manifests as ambiguity, bias reinforcement, or normative convergence. Rather than improving factual precision alone, we argue for regulatory responses that account for languages generative nature, the asymmetries between system and user, and the shifting boundaries between information, persuasion, and harm.
Received — 15 July 2025 ⏭ Favourites

Cancer-Associated Fibroblasts: Heterogeneity, Cancer Pathogenesis, and Therapeutic Targets

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yutao Li · Qingyun Liu · Xilin Jing · Yuqi Wang · Xiaohua Jia · Xing Yang · Kezhong Chen
14 July 2025 at 18:00

MedComm (2020). 2025 Jul 11;6(7):e70292. doi: 10.1002/mco2.70292. eCollection 2025 Jul.

ABSTRACT

Cancer-associated fibroblasts (CAFs) are functionally diverse stromal regulators that orchestrate tumor progression, metastasis, and therapy resistance through dynamic crosstalk within the tumor microenvironment (TME). Recent advances in single-cell multiomics and spatial transcriptomics have identified conserved CAF subtypes with distinct molecular signatures, spatial distributions, and context-dependent roles, highlighting their dual capacity to promote immunosuppression or restrain tumor growth. However, therapeutic strategies struggle to reconcile this functional duality, hindering clinical translation. This review systematically categorizes CAF subtypes by origin, biomarkers, and TME-specific functions, focusing on their roles in chemoresistance, maintenance of stemness, and formation of immunosuppressive niches. We evaluate emerging targeting approaches, including selective depletion of tumor-promoting subsets (e.g., fibroblast activation protein+ CAFs), epigenetic reprogramming toward antitumor phenotypes, and inhibition of CXCL12/CXCR4 or transforming growth factor-beta signaling pathways. Spatial multiomics-driven combinatorial therapies, such as the synergistic use of CAFs and immune checkpoint inhibitors, are highlighted as strategies to overcome microenvironment-driven resistance. By integrating CAF biology with translational advances, this work provides a roadmap for developing subtype-specific biomarkers and precision stromal therapies, directly informing efforts to disrupt tumor-stroma coevolution. Key concepts include spatial transcriptomics, stromal reprogramming, and tumor-stroma coevolution, offering actionable insights for both mechanistic research and clinical innovation.

PMID:40656546 | PMC:PMC12246558 | DOI:10.1002/mco2.70292

There are no more articles
❌