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.

A universal visual foundation model for computational cytopathology

Nature Cancer

By: Xueyi Zheng · Ke Zheng · Jue Wang · Xinke Zhang · Kai Li · Zihan Zhao · Chaofeng Li · Haohua Chen · Ruixuan Wang · Junpeng Lai · Bing Chu · Sha Fu · Dan Xie · Muyan Cai

18 September 2026 at 08:00

Nature Cancer, Published online: 18 September 2026; doi:10.1038/s43018-026-01240-0

Zheng, Zheng, Wang, Zhang et al. developed CROWN, a universal visual foundation model for cytopathology, which they benchmarked on more than 200 real-world cytology tasks across cohorts, including lymph node metastasis and cervical screening datasets.

PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement

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

By: Tianyidan Xie · Peiyu Wang · Hu Jiaxin · Yuyi Qian · Yuxuan Wang · Shenyi Wang · Rui Ma · Yanlun Peng · Lanjun Wang · Ying Tai · Jian Yang · Zili Yi

14 September 2026 at 12:00

arXiv:2604.23580v2 Announce Type: replace-cross Abstract: Translating natural-language descriptions of physical phenomena into executable simulation code requires both programming expertise and physical reasoning. Current large language models (LLMs) lack this combination: they frequently produce code that runs but simulates the wrong physics. We introduce PhysCodeBench, the first benchmark for this task, with 1,200 expert-validated examples spanning four physical domains. Its evaluation suite, PhysCodeEval, goes beyond executability and visual fidelity to measure physical correctness directly from the engine state via conservation-law residuals and expert-written assertions, and supports cross-engine evaluation to disentangle physics reasoning from API fluency. As a reference method, we propose the Self-Corrective Multi-Agent Refinement Framework (SMRF), which decouples physics-aware error correction from code generation through specialized agents. This design is motivated by our finding that targeted correction, rather than generic iterative refinement, is the key driver of physical accuracy. SMRF nearly triples the physical-assertion pass rate of the best proprietary baseline (70.6\% vs.\ 23.8\%) and retains its advantage under cross-engine transfer.

An engineered nanopore identifies saccharides, amino acids, peptides and ribonucleotides

Nature Biotechnology - Issue - nature.com science feeds

By: Lang Yao · Zixuan Wang · Jialu Chen · Wen Sun · Kefan Wang · Yunqi Xiao · Hanhan Zhang · Wenzheng Li · Yifan Wang · Lulu Zhao · Xinyi Dai · Lu Qian · Panke Zhang · Shuo Huang

14 September 2026 at 08:00

Nature Biotechnology, Published online: 14 September 2026; doi:10.1038/s41587-026-03308-9

Modified nanopore simultaneously identifies diverse biomolecules and their modifications.

CAFs shape the immunosuppressive microenvironment of pancreatic cancer through the Lin28b-STING Axis

(Multiomics OR Omics) AND (Pancreatic)

By: Minghe Fan · Ziyang Zhang · Wei Xu · Yuwei Liu · Ruoxuan Wang · Wenqin Hao · Sihan Huo · Yuyao Guo · Lina Wang · Ang Lv · Xiangyu Liu · Wei Wang · Chuanhui Han · Ying Zhao

3 September 2026 at 18:00

Nat Commun. 2026 Aug 7;17(1):9491. doi: 10.1038/s41467-026-76495-3.

ABSTRACT

Cancer-associated fibroblasts comprise diverse functionally distinct cellular subsets, with certain subpopulations exerting pivotal influence in shaping the pancreatic cancer immune microenvironment. Here we show that Lin28b⁺ cancer-associated fibroblasts contribute to establishing an immunologically cold tumor microenvironment in pancreatic ductal adenocarcinoma. Mechanistically, Lin28b directly binds to STING mRNA and promotes its degradation, thereby suppressing STING expression and downstream type I interferon signaling. Loss of Lin28b in cancer-associated fibroblasts activates the cGAS-STING-interferon signaling cascade, enhancing dendritic cell antigen presentation and CD8⁺ T cell cytotoxic function. Importantly, genetic inhibition of Lin28b in cancer-associated fibroblasts enhances sensitivity to anti-PD-L1 immune checkpoint blockade therapy. These findings reveal that targeting the Lin28b-STING axis represents a promising therapeutic strategy for overcoming the intrinsic resistance of pancreatic ductal adenocarcinoma to immunotherapy.

PMID:42693143 | PMC:PMC13542369 | DOI:10.1038/s41467-026-76495-3

Integrated single-cell multi-omics characterization reveals lipid-associated macrophage-mediated immunosuppression in neoadjuvant immunotherapy of hepatocellular carcinoma

Omics in Hepatocellular

By: Shengxuan Peng · Chang Liu · Junyu Long · Jincheng Tian · Han Li · Donghai Lu · Qihang Cao · Daolin Zhang · Qiao He · Jisen Jia · Yuxuan Wang · Zhaoru Dong · Haitao Zhao · Lei Zhao · Dongxu Wang · Tao Li

1 September 2026 at 18:00

Nat Commun. 2026 Jul 31;17(1):9381. doi: 10.1038/s41467-026-75949-y.

ABSTRACT

Hepatocellular carcinoma (HCC) is a cancer with high incidence and mortality rate. Although immune checkpoint inhibitors (ICIs) improved survival outcomes for HCC patients, limited objective response rate highlights the urgency of investigating determinants of immunotherapy. Here, we explore HCC resistance mechanisms following neoadjuvant αPD-1 immunotherapy by constructing a comprehensive multi-modal single-cell transcriptomic atlas consisting of 14 HCC patients treated with αPD-1 from our cohort (ClinicalTrials.gov ID: NCT06571396) and 60 external HCC cases with heterogeneous treatment backgrounds. Supervised by clinical outcomes of our cohort, we identify positive and negative regulators of immunotherapy within the tumor immune microenvironment (TIME), especially lipid-associated macrophages (LAM) with increased lipid metabolic state in non-responders and characterized by C1QA, FABP1, and APOA1 expression. We further show the presence, exogenous inducements and immunosuppressive functions of LAM, along with regulation strategies of its lipid-associated condition, including lycopene and chiglitazar. Furthermore, we construct interaction networks of immune regulators across responders and non-responders, showing distinct ligand-receptor landscapes with intervention targets. We reveal the TIME components including immunosuppressive LAMs that influence immunotherapy outcomes, thus providing evidence and insights for exploring immune landscape and therapeutic strategies for HCC immunotherapy. ClinicalTrials.gov ID: NCT06571396.

PMID:42680737 | PMC:PMC13534469 | DOI:10.1038/s41467-026-75949-y

ConceptM$^3$oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology

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

By: Xuan Wang · Zhongling Xu · Gopi Kannedhara · Joakim Nguyen · Jian Yu · Jinrui Fang · Abdurrahmaan Baghdadi · Tianlong Chen · Awais Naeem · Chandra Krishnan · Edward Castillo · Andrew H. Song · Ankita Shukla · Ying Ding · Nicholas Konz · Hairong Wang

26 May 2026 at 12:00

arXiv:2605.24399v1 Announce Type: new Abstract: Healthcare models are transitioning from unimodal prediction toward multimodal reasoning over heterogeneous diagnostic inputs. In computational pathology, for complex tumor subtypes where morphology alone can be challenging to distinguish, pathology reports and molecular measurements may provide additional diagnostic evidence alongside whole-slide images, yet existing models often fail to clarify how diverse signals assemble into recognizable diagnostic concepts. We propose ConceptM$^3$oE (Concept Multimodal MoE), which embeds concept formation directly within interaction-aware mixture-of-experts (MoE) pathways. The architecture decomposes evidence into modality-specific, redundant, and synergistic experts, which are then projected into structured concept bottlenecks mapping latent features to a hierarchy of morphology and biomarker concepts. To prevent the information loss typical of interpretable bottlenecks, we utilize residual pathways within each expert to allow task-relevant signals to flow both through the concepts and directly to the final task prediction, so that high performance is maintained alongside interpretability. Across an institutional pediatric brain tumor cohort and a public glioma cohort, the framework delivers competitive performance to unconstrained models while producing reasoning traces validated by an independent neuropathologist. In data-limited regimes, ConceptM$^3$oE improves limited-data performance, increasing macro-F1 from 56.41% to 66.70% at small training sizes compared to non-concept-informed baselines, while also showing faster training convergence consistent with the regularizing effect of concept learning. This work offers a scalable path toward high-performance medical AI that is inherently verifiable and better aligned with the complex decision-making of clinical practice.

Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics

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

By: Lianhao Zhou · Hongyi Ling · Cong Fu · Yepeng Huang · Michael Sun · Wendi Yu · Xiaoxuan Wang · Xiner Li · Xingyu Su · Junkai Zhang · Xiusi Chen · Chenxing Liang · Xiaofeng Qian · Heng Ji · Wei Wang · Marinka Zitnik · Shuiwang Ji

7 April 2026 at 12:00

arXiv:2510.09901v2 Announce Type: replace Abstract: Computing has long served as a cornerstone of scientific discovery. Recently, a paradigm shift has emerged with the rise of large language models (LLMs), introducing autonomous systems, referred to as agents, that accelerate discovery across varying levels of autonomy. These language agents provide a flexible and versatile framework that orchestrates interactions with human scientists, natural language, computer language and code, and physics. This paper presents our view and vision of LLM-based scientific agents and their growing role in transforming the scientific discovery lifecycle, from hypothesis discovery, experimental design and execution, to result analysis and refinement. We critically examine current methodologies, emphasizing key innovations, practical achievements, and outstanding limitations. Additionally, we identify open research challenges and outline promising directions for building more robust, generalizable, and adaptive scientific agents. Our analysis highlights the transformative potential of autonomous agents to accelerate scientific discovery across diverse domains.

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

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

By: Yufei Xu · Fanxu Meng · Fan Jiang · Yuxuan Wang · Ruijie Zhou · Zhaohui Wang · Jiexi Wu · Zhixin Pan · Xiaojuan Tang · Wenjie Pei · Tongxuan Liu · Di Yin · Xing Sun · Muhan Zhang

7 April 2026 at 12:00

arXiv:2603.28458v3 Announce Type: replace-cross Abstract: Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical key for each query through a lightweight indexer, then computing attention only on the selected subset. While the downstream sparse attention itself scales favorably, the indexer must still scan the entire prefix for every query, introducing an per-layer bottleneck that grows prohibitively with context length. We propose HISA (Hierarchical Indexed Sparse Attention), a plug-and-play replacement for the indexer that rewrites the search path from a flat token scan into a two-stage hierarchical procedure: (1) a block-level coarse filtering stage that scores pooled block representations to discard irrelevant regions, followed by (2) a token-level refinement stage that applies the original indexer exclusively within the retained candidate blocks. HISA preserves the identical token-level top-sparse pattern consumed by the downstream Sparse MLA operator and requires no additional training. On kernel-level benchmarks, HISA achieves up to speedup at 64K context. On Needle-in-a-Haystack and LongBench, we directly replace the indexer in DeepSeek-V3.2 and GLM-5 with our HISA indexer, without any finetuning. HISA closely matches the original DSA in quality, while substantially outperforming block-sparse baselines.

Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles

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

By: Qingyan Wei · Yaojie Zhang · Zhiyuan Liu · Puyu Zeng · Yuxuan Wang · Biqing Qi · Dongrui Liu · Linfeng Zhang

1 April 2026 at 12:00

arXiv:2506.10848v3 Announce Type: replace-cross Abstract: Diffusion-based language models (dLLMs) have emerged as a promising alternative to traditional autoregressive LLMs by enabling parallel token generation and significantly reducing inference latency. However, existing sampling strategies for dLLMs, such as confidence-based or semi-autoregressive decoding, often suffer from static behavior, leading to suboptimal efficiency and limited flexibility. In this paper, we propose SlowFast Sampling, a novel dynamic sampling strategy that adaptively alternates between exploratory and accelerated decoding stages. Our method is guided by three golden principles: certainty principle, convergence principle, and positional principle, which govern when and where tokens can be confidently and efficiently decoded. We further integrate our strategy with dLLM-Cache to reduce redundant computation. Extensive experiments across benchmarks and models show that SlowFast Sampling achieves up to 15.63$\times$ speedup on LLaDA with minimal accuracy drop, and up to 34.22$\times$ when combined with caching. Notably, our approach outperforms strong autoregressive baselines like LLaMA3 8B in throughput, demonstrating that well-designed sampling can unlock the full potential of dLLMs for fast and high-quality generation.

Gene regulatory landscape dissected by single-cell four-omics sequencing

Nature - Issue - nature.com science feeds

By: Yujie Chen · Zhiyuan Liu · Heming Xu · Jiayu Liu · Mengxuan Wang · Yi Chi · Boyuan Liang · Menghan Liu · Yongli Peng · Hao Ge · Dong Xing

1 April 2026 at 08:00

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10322-z

Combining single-cell parallel profiling of genome conformation, histone modifications, chromatin accessibility and gene expression reveals dynamics and intranuclear spatial clustering of epigenome profiles, enabling sophisticated analysis of the regulatory landscape across cell types and tissues.

Multi-omics analysis reveals AR as a potential prognostic factor and immune-related therapeutic target in gastric cancer

Omics in Gastric

By: Tianru Ben · Zonghao Liu · Shitong Cheng · Yanlu Bai · Linlin Gao · Jingya Zhang · Ruixuan Wang · Nan Xia

27 March 2026 at 18:00

Biochem Biophys Rep. 2026 Mar 16;46:102537. doi: 10.1016/j.bbrep.2026.102537. eCollection 2026 Jun.

ABSTRACT

BACKGROUND: Although studies have shown that the androgen receptor (AR) is associated with tumor progression and malignant regulation, its role in the tumor immune microenvironment and predictive value for prognosis and immunotherapy response in various cancer types have not been systematically analyzed.

METHODS: In this paper, multi-omics techniques was used to analyze AR comprehensively.

RESULTS: A comprehensive pan-cancer analysis revealed that the AR was expressed in a variety of tumors, especially as a risk factor for poor prognosis in gastric cancer. In addition, gene set enrichment analysis showed that the AR promotes cell proliferation and tumor cell invasion and regulates anti-tumor response. Immune score, immune cell infiltration, and anticancer immune cycle analysis showed that high AR levels were correlated with low infiltration of CD4⁺ T cells and NKT cells, high infiltration of Th2 cells and MDSCs, negatively correlated with antigen-presenting molecules, and positively correlated with various immune-negative regulatory molecules. Single-cell sequencing highlighted the heterogeneous expression of ARs in different cell types, particularly in epithelial cells, where high AR levels were associated with the enhanced activity of tumor-promoting pathways.

CONCLUSIONS: In conclusion, this study highlights the potential of the AR as a novel biomarker for gastric cancer prognosis and immunotherapy efficacy, expanding its applicability in the development of new antitumor drugs.

PMID:41890218 | PMC:PMC13014673 | DOI:10.1016/j.bbrep.2026.102537

SynLeaF: A Dual-Stage Multimodal Fusion Framework for Synthetic Lethality Prediction Across Pan- and Single-Cancer Contexts

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

By: Zheming Xing · Siyuan Zhou · Ruinan Wang · Rui Han · Shiming Zhang · Shiqu Chen · Yurui Huang · Jiahao Ma · Yifan Chen · Xuan Wang · Yadong Wang · Junyi Li

25 March 2026 at 12:00

arXiv:2603.22369v1 Announce Type: cross Abstract: Accurate prediction of synthetic lethality (SL) is important for guiding the development of cancer drugs and therapies. SL prediction faces significant challenges in the effective fusion of heterogeneous multi-source data. Existing multimodal methods often suffer from "modality laziness" due to disparate convergence speeds, which hinders the exploitation of complementary information. This is also one reason why most existing SL prediction models cannot perform well on both pan-cancer and single-cancer SL pair prediction. In this study, we propose SynLeaF, a dual-stage multimodal fusion framework for SL prediction across pan- and single-cancer contexts. The framework employs a VAE-based cross-encoder with a product of experts mechanism to fuse four omics data types (gene expression, mutation, methylation, and CNV), while simultaneously utilizing a relational graph convolutional network to capture structured gene representations from biomedical knowledge graphs. To mitigate modality laziness, SynLeaF introduces a dual-stage training mechanism employing featurelevel knowledge distillation with adaptive uni-modal teacher and ensemble strategies. In extensive experiments across eight specific cancer types and a pancancer dataset, SynLeaF achieves superior performance in 17 out of 19 scenarios. Ablation studies and gradient analyses further validate the critical contributions of the proposed fusion and distillation mechanisms to model robustness and generalization. To facilitate community use, a web server is available at https://synleaf.bioinformatics-lilab.cn.

DreamAudio: Customized Text-to-Audio Generation with Diffusion Models

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

By: Yi Yuan · Xubo Liu · Haohe Liu · Xiyuan Kang · Zhuo Chen · Yuxuan Wang · Mark D. Plumbley · Wenwu Wang

25 March 2026 at 12:00

arXiv:2509.06027v2 Announce Type: replace-cross Abstract: With the development of large-scale diffusion-based and language-modeling-based generative models, impressive progress has been achieved in text-to-audio generation. Despite producing high-quality outputs, existing text-to-audio models mainly aim to generate semantically aligned sound and fall short of controlling fine-grained acoustic characteristics of specific sounds. As a result, users who need specific sound content may find it difficult to generate the desired audio clips. In this paper, we present DreamAudio for customized text-to-audio generation (CTTA). Specifically, we introduce a new framework that is designed to enable the model to identify auditory information from user-provided reference concepts for audio generation. Given a few reference audio samples containing personalized audio events, our system can generate new audio samples that include these specific events. In addition, two types of datasets are developed for training and testing the proposed systems. The experiments show that DreamAudio generates audio samples that are highly consistent with the customized audio features and aligned well with the input text prompts. Furthermore, DreamAudio offers comparable performance in general text-to-audio tasks. We also provide a human-involved dataset containing audio events from real-world CTTA cases as the benchmark for customized generation tasks.

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

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

By: Xiaoxuan Wang · Han Zhang · Haixin Wang · Yidan Shi · Ruoyan Li · Kaiqiao Han · Chenyi Tong · Haoran Deng · Renliang Sun · Alexander Taylor · Yanqiao Zhu · Jason Cong · Yizhou Sun · Wei Wang

10 March 2026 at 12:00

arXiv:2602.21534v2 Announce Type: replace Abstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable, often leading to training collapse. This instability limits scalability to larger environments and longer interaction horizons, and constrains systematic exploration of algorithmic design choices. In this paper, we first propose ARLArena, a stable training recipe and systematic analysis framework that examines training stability in a controlled and reproducible setting. ARLArena first constructs a clean and standardized testbed. Then, we decompose policy gradient into four core design dimensions and assess the performance and stability of each dimension. Through this fine-grained analysis, we distill a unified perspective on ARL and propose SAMPO, a stable agentic policy optimization method designed to mitigate the dominant sources of instability in ARL. Empirically, SAMPO achieves consistently stable training and strong performance across diverse agentic tasks. Overall, this study provides a unifying policy gradient perspective for ARL and offers practical guidance for building stable and reproducible LLM-based agent training pipelines.

Order Is Not Layout: Order-to-Space Bias in Image Generation

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

By: Yongkang Zhang · Zonglin Zhao · Yuechen Zhang · Fei Ding · Pei Li · Wenxuan Wang

5 March 2026 at 13:00

arXiv:2603.03714v1 Announce Type: cross Abstract: We study a systematic bias in modern image generation models: the mention order of entities in text spuriously determines spatial layout and entity--role binding. We term this phenomenon Order-to-Space Bias (OTS) and show that it arises in both text-to-image and image-to-image generation, often overriding grounded cues and causing incorrect layouts or swapped assignments. To quantify OTS, we introduce OTS-Bench, which isolates order effects with paired prompts differing only in entity order and evaluates models along two dimensions: homogenization and correctness. Experiments show that Order-to-Space Bias (OTS) is widespread in modern image generation models, and provide evidence that it is primarily data-driven and manifests during the early stages of layout formation. Motivated by this insight, we show that both targeted fine-tuning and early-stage intervention strategies can substantially reduce OTS, while preserving generation quality.

Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety

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

By: Junliang Liu · Jingyu Xiao · Wenxin Tang · Zhixian Wang · Zipeng Xie · Wenxuan Wang · Minrui Zhang · Shuanghe Yu

5 March 2026 at 13:00

arXiv:2509.21782v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are increasingly deployed as the core reasoning engine for web-facing systems, powering GUI agents and front-end automation that must interpret page structure, select actionable widgets, and execute multi-step interactions reliably. However, existing benchmarks largely emphasize visual perception or UI code generation, showing insufficient evaluation on the reasoning, robustness and safety capability required for end-to-end web applications. To bridge the gap, we introduce a comprehensive web understanding benchmark, named WebRRSBench, that jointly evaluates Reasoning, Robustness, and Safety across eight tasks, such as position relationship reasoning, color robustness, and safety critical detection, etc. The benchmark is constructed from 729 websites and contains 3799 QA pairs that probe multi-step inference over page structure, text, widgets, and safety-critical interactions. To ensure reliable measurement, we adopt standardized prompts, a protocolized and deterministic evaluation pipeline, and multi-stage quality control combining automatic checks with targeted human verification. We evaluate 11 MLLMs on WebRRSBench. The results reveal significant gaps: models still struggle with compositional and cross-element reasoning over realistic layouts, show limited robustness when facing perturbations in user interfaces and content such as layout rearrangements or visual style shifts, and are rather conservative in recognizing and avoiding safety critical or irreversible actions. Our code and appendix are available at https: //github.com/annoy-worker/WebRSSBench.

Generalized Discrete Diffusion with Self-Correction

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

By: Linxuan Wang · Ziyi Wang · Yikun Bai · Wei Deng · Guang Lin · Qifan Song

4 March 2026 at 13:00

arXiv:2603.02230v1 Announce Type: cross Abstract: Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such approaches often suffer from limited generalization and may impair reasoning performance. GIDD pioneers pretraining-based self-correction via a multi-step BERT-style uniform-absorbing objective. However, GIDD relies on a continuous interpolation-based pipeline with opaque interactions between uniform transitions and absorbing masks, which complicates hyperparameter tuning and hinders practical performance. In this work, we propose a Self-Correcting Discrete Diffusion (SCDD) model to reformulate pretrained self-correction with explicit state transitions and learn directly in discrete time. Our framework also simplifies the training noise schedule, eliminates a redundant remasking step, and relies exclusively on uniform transitions to learn self-correction. Experiments at the GPT-2 scale demonstrate that our method enables more efficient parallel decoding while preserving generation quality.

TrustMH-Bench: A Comprehensive Benchmark for Evaluating the Trustworthiness of Large Language Models in Mental Health

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

By: Zixin Xiong · Ziteng Wang · Haotian Fan · Xinjie Zhang · Wenxuan Wang

4 March 2026 at 13:00

arXiv:2603.03047v1 Announce Type: cross Abstract: While Large Language Models (LLMs) demonstrate significant potential in providing accessible mental health support, their practical deployment raises critical trustworthiness concerns due to the domains high-stakes and safety-sensitive nature. Existing evaluation paradigms for general-purpose LLMs fail to capture mental health-specific requirements, highlighting an urgent need to prioritize and enhance their trustworthiness. To address this, we propose TrustMH-Bench, a holistic framework designed to systematically quantify the trustworthiness of mental health LLMs. By establishing a deep mapping from domain-specific norms to quantitative evaluation metrics, TrustMH-Bench evaluates models across eight core pillars: Reliability, Crisis Identification and Escalation, Safety, Fairness, Privacy, Robustness, Anti-sycophancy, and Ethics. We conduct extensive experiments across six general-purpose LLMs and six specialized mental health models. Experimental results indicate that the evaluated models underperform across various trustworthiness dimensions in mental health scenarios, revealing significant deficiencies. Notably, even generally powerful models (e.g., GPT-5.1) fail to maintain consistently high performance across all dimensions. Consequently, systematically improving the trustworthiness of LLMs has become a critical task. Our data and code are released.

Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context

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

By: Kai Ruan · Xuan Wang · Jixiang Hong · Peng Wang · Yang Liu · Hao Sun

24 February 2026 at 13:00

arXiv:2412.17596v4 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities in scientific tasks such as literature analysis and experimental design (e.g., accurately extracting key findings from papers or generating coherent experimental procedures), existing evaluation benchmarks primarily assess performance using rich contextual inputs. We introduce LiveIdeaBench, a comprehensive benchmark evaluating LLMs' scientific idea generation by assessing divergent thinking capabilities using single-keyword prompts. Drawing from Guilford's creativity theory, our benchmark employs a dynamic panel of state-of-the-art LLMs to assess generated ideas across five key dimensions: originality, feasibility, fluency, flexibility, and clarity. Through extensive experimentation with over 40 leading models across 1,180 keywords spanning 22 scientific domains, we reveal that the scientific idea generation capabilities measured by our benchmark, are poorly predicted by standard metrics of general intelligence. Our results demonstrate that models like QwQ-32B-preview achieve creative performance comparable to top-tier models such as claude-3.7-sonnet:thinking, despite significant gaps in their general intelligence scores. These findings highlight the need for specialized evaluation benchmarks for scientific idea generation and suggest that enhancing these idea generation capabilities in LLMs may require different training strategies than those used for improving general problem-solving abilities, potentially enabling a wider range of AI tools tailored for different stages of the scientific process.

Reading view