Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning

By: Wei Fan · Yining Zhou · Mufan Zhang · Yanbing Weng · Yiran HU · Tianshi Zheng · Baixuan Xu · Chunyang Li · Jianhui Yang · Haoran Li · Yangqiu Song

26 May 2026 at 12:00

arXiv:2605.25920v1 Announce Type: cross Abstract: While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint that applicable law must match the temporal context of each case, as retroactive application of statutes violates core legal principles and leads to erroneous conclusions. Our observations reveal that current legal LLMs suffer from temporal bias anchored to their training cutoff, while search agents rarely incorporate temporal constraints into queries, and that web search alone cannot provide the precise statute and precedent citations that legal reasoning demands. To address these challenges, we propose LegalSearch-R1, an end-to-end reinforcement learning framework that pairs local statute RAG for precise article matching with online web search for broader legal knowledge, trained on temporally-indexed data spanning multiple amendment periods to enforce temporal consistency. Extensive experiments on our benchmark covering 13 legal tasks demonstrate that our 7B-parameter agent outperforms state-of-the-art deep research frameworks and specialized legal LLMs by 12.9% to 29.8%, surpasses baselines by 57.7% to 80.3% on temporal consistency, and exhibits robust out-of-domain generalization. The code and data are available at https://github.com/AlexFanw/LegalSearch-R1.

Multi-omics integration and Mendelian randomization elucidate the PARP16-UPR axis driving chemoresistancein gastric cancer

Omics in Gastric

By: Shuchang Tao · Hui Yang

18 May 2026 at 18:00

Front Oncol. 2026 May 1;16:1785100. doi: 10.3389/fonc.2026.1785100. eCollection 2026.

ABSTRACT

BACKGROUND: Acquired resistance to cisplatin-based chemotherapy is common in patients with gastric cancer (GC) and significantly limits treatment efficacy. The aim of this study was to investigate molecular features associated with GC chemoresistance using an integrative multi-level analytical framework combined with Mendelian randomization (MR), followed by cellular validation of key candidates.

METHODS: Transcriptome datasets GSE14210 and GSE31811 were obtained from the Gene Expression Omnibus (GEO) database to identify differentially expressed genes (DEGs), followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses to explore potential pathways. A total of 113 machine learning model combinations were applied for feature selection. MR analysis integrating expression quantitative trait loci (eQTLs) and genome-wide association study (GWAS) data was conducted to assess causal relationships between candidate genes and chemoresistance. The single-cell dataset GSE183904 was used to examine cell-type-specific expression patterns. Cisplatin-resistant NCI-N87/DDP cells were then established in vitro, and qRT-PCR, Western blotting, and drug sensitivity assays were performed to evaluate gene expression and function. Pathway inhibitors were applied to test the reversal of resistance.

RESULTS: A total of 827 DEGs were identified, mainly enriched in immune response, ECM interactions, metabolic reprogramming, and signaling pathways such as PI3K-Akt and MAPK. Among the machine learning models, the Stepglm[both] + Random Forest (RF) model achieved the best performance [area under the curve (AUC) = 0.865] and identified several core candidate genes. MR analysis supported potential risk associations for TRABD, RXRA, DEFA4, PARP16, SLC12A9, and TMEM132A, with PARP16 consistently highlighted across transcriptomic, machine learning, and MR analyses. In vitro experiments showed that PARP16 expression was elevated by approximately 3.1-fold in NCI-N87/DDP cells, accompanied by activation of the unfolded protein response (UPR) and suppression of apoptosis, and an elevated cisplatin IC₅₀ of 11.82 μg/mL. Inhibition of the PARP16-UPR axis significantly reduced the IC₅₀ to 4.67 μg/mL and restored DNA damage and apoptosis, demonstrating synergistic effects.

CONCLUSIONS: PARP16 emerged as a key candidate associated with chemoresistance in GC. Its elevated expression in stem-like cell populations and resistant cell models was associated with UPR activation, and targeting the PARP16-UPR axis restored cisplatin sensitivity. Targeting the PARP16-UPR axis effectively reverses resistance, providing new insights and potential therapeutic strategies for overcoming chemoresistance in GC.

PMID:42147232 | PMC:PMC13175845 | DOI:10.3389/fonc.2026.1785100

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

Clinical application of base editing for treating β-thalassaemia

Nature - Issue - nature.com science feeds

By: Yongrong Lai · Rongrong Liu · Lijie Wang · Xu-Kai Ma · Yaliang Li · Gaohui Yang · Lingling Shi · Yi-Lin Guo · Zhenbin Wei · Xuemei Zhou · Wenchao Xu · Yaofeng Hou · Annarita Miccio · Bei Yang · Xiaodun Mou · Li Yang · Jia Chen

8 April 2026 at 08:00

Nature, Published online: 08 April 2026; doi:10.1038/s41586-026-10342-9

A clinical phase 1 trial of a single infusion of CS-101, CD34+ cells modified using a transformer base editor to reactivate fetal haemoglobin production, led to early and enduring transfusion independence in patients with β-thalassaemia.

Leptomeningeal metastatic cancer cells induce a permissive choroid plexus vasculature through extracellular-vesicle-derived 5-HIAA signaling

Nature Cancer

By: Yang Huang · Yifan Hou · Jiahui Yang · Wanqi Yang · Hanxin Liu · Haibao Peng · Xiaohui Li · Jiaxu Zhao · Ye Zhang · Rui Zeng · Youming Zeng · Cheng Li · Qiangqiang Zhang · Yudan Chi

3 April 2026 at 08:00

Nature Cancer, Published online: 03 April 2026; doi:10.1038/s43018-026-01145-y

Huang, Hou, Yang et al. demonstrate that leptomeningeal metastatic cells favor the formation of a premetastatic niche by remodeling the choroid plexus vasculature through the serotonin metabolite 5-hydroxyindoleacetic acid, which signals into endothelial cells through the aryl hydrocarbon receptor.

Visual-ERM: Reward Modeling for Visual Equivalence

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

By: Ziyu Liu · Shengyuan Ding · Xinyu Fang · Xuanlang Dai · Penghui Yang · Jianze Liang · Jiaqi Wang · Kai Chen · Dahua Lin · Yuhang Zang

16 March 2026 at 12:00

arXiv:2603.13224v1 Announce Type: cross Abstract: Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs) achieve strong results via supervised fine-tuning, reinforcement learning remains challenging due to misaligned reward signals. Existing rewards either rely on textual rules or coarse visual embedding similarity, both of which fail to capture fine-grained visual discrepancies and are vulnerable to reward hacking. We propose Visual Equivalence Reward Model (Visual-ERM), a multimodal generative reward model that provides fine-grained, interpretable, and task-agnostic feedback to evaluate vision-to-code quality directly in the rendered visual space. Integrated into RL, Visual-ERM improves Qwen3-VL-8B-Instruct by +8.4 on chart-to-code and yields consistent gains on table and SVG parsing (+2.7, +4.1 on average), and further strengthens test-time scaling via reflection and revision. We also introduce VisualCritic-RewardBench (VC-RewardBench), a benchmark for judging fine-grained image-to-image discrepancies on structured visual data, where Visual-ERM at 8B decisively outperforms Qwen3-VL-235B-Instruct and approaches leading closed-source models. Our results suggest that fine-grained visual reward supervision is both necessary and sufficient for vision-to-code RL, regardless of task specificity.

FCMBench: The First Large-scale Financial Credit Multimodal Benchmark for Real-world Applications

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

By: Yehui Yang · Dalu Yang · Fangxin Shang · Wenshuo Zhou · Jie Ren · Yifan Liu · Haojun Fei · Qing Yang · Yanwu Xu · Tao Chen

16 March 2026 at 12:00

arXiv:2601.00150v3 Announce Type: replace-cross Abstract: FCMBench is the first large-scale and privacy-compliant multimodal benchmark for real-world financial credit applications, covering tasks and robustness challenges from domain specific workflows and constraints. The current version of FCMBench covers 26 certificate types, with 5198 privacy-compliant images and 13806 paired VQA samples. It evaluates models on Perception and Reasoning tasks under real-world Robustness interferences, including 3 foundational perception tasks, 4 credit-specific reasoning tasks demanding decision-oriented visual evidence interpretation, and 10 real-world challenges for rigorous robustness stress testing. Moreover, FCMBench offers privacy-compliant realism with minimal leakage risk through in-house scenario-aware captures of manually synthesized templates, without any publicly released images. We conduct extensive evaluations of 28 state-of-the-art vision-language models spanning 14 AI companies and research institutes. Among them, Gemini 3 Pro achieves the best F1 score as a commercial model (65.16), Kimi-K2.5 achieves the best score as an open-source baseline (60.58). The mean and the std. of all tested models is 44.8 and 10.3 respectively, indicating that FCMBench is non-trivial and provides strong resolution for separating modern vision-language model capabilities. Robustness evaluations reveal that even top-performing models experience notable performance degradation under the designed challenges. We have open-sourced this benchmark to advance AI research in the credit domain and provide a domain-specific task for real-world AI applications.

STEM Faculty Perspectives on Generative AI in Higher Education

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

By: Akila de Silva · Isabel Hyo Jung Song · Hui Yang · Shah Rukh Humayoun

5 March 2026 at 13:00

arXiv:2603.04001v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) tools are increasingly present in higher education, yet their adoption has been largely student-driven, requiring instructors to respond to technologies already embedded in classroom practices. While some faculty have embraced GenAI for pedagogical purposes such as content generation, assessment support, and curriculum design, others approach these tools with caution, citing concerns about student learning, assessment validity, and academic integrity. Understanding faculty perspectives is therefore essential for informing effective pedagogical strategies and institutional policies. In this paper, we present findings from a focus group study with 29 STEM faculty members at a large public university in the United States. We examine how faculty integrate GenAI into their courses, the benefits and challenges they perceive for student learning, and the institutional support they identify as necessary for effective and responsible adoption. Our findings highlight key patterns in how STEM faculty engage with GenAI, reflecting both active adoption and cautious use. Faculty described a range of pedagogical applications alongside concerns about student learning, assessment, and academic integrity. Overall, the results suggest that effective integration of GenAI in higher education requires rethinking assessment, pedagogy, and institutional governance in addition to technical adoption.

SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance

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

By: Pengkun Jiao · Yiming Jin · Jianhui Yang · Chenhe Dong · Zerui Huang · Shaowei Yao · Xiaojiang Zhou · Dan Ou · Haihong Tang

5 March 2026 at 13:00

arXiv:2510.07972v2 Announce Type: replace Abstract: Query-product relevance prediction is a foundational technology in e-commerce search engines and has become increasingly important in AI-driven e-commerce. The recent emergence of LLMs, particularly their CoT reasoning capabilities, offers promising opportunities for developing relevance systems that are both more interpretable and more robust. However, existing training paradigms have notable limitations: SFT and DPO suffer from poor generalization on long-tail queries and from a lack of fine-grained, stepwise supervision to enforce rule-aligned reasoning. In contrast, reinforcement learning with verification rewards (RLVR) suffers from sparse feedback, which provides insufficient signal to correct erroneous intermediate steps, thereby undermining logical consistency and limiting performance in complex inference scenarios. To address these challenges, we introduce the Stepwise Hybrid Examination Reinforcement Learning framework for search relevance (SHE). At its core is Stepwise Reward Policy Optimization (SRPO), a reinforcement learning algorithm that leverages step-level rewards generated by a hybrid of a high-quality generative stepwise reward model and a human-annotated offline verifier, prioritizing learning from critical correct and incorrect reasoning steps. To bolster robustness and generalization, SHE further integrates a dual-strategy optimization: diversified data filtering, which broadens the exploration of reasoning trajectories to preempt policy entropy collapse, and a multi-stage curriculum learning protocol that systematically orchestrates progressive capability acquisition. Extensive experiments on real-world search benchmarks show that SHE improves both reasoning quality and relevance-prediction accuracy in large-scale e-commerce settings, outperforming SFT, DPO, GRPO, and other baselines, while also enhancing interpretability and robustness.

A Secure and Private Distributed Bayesian Federated Learning Design

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

By: Nuocheng Yang · Sihua Wang · Zhaohui Yang · Mingzhe Chen · Changchuan Yin · Kaibin Huang

24 February 2026 at 13:00

arXiv:2602.20003v1 Announce Type: cross Abstract: Distributed Federated Learning (DFL) enables decentralized model training across large-scale systems without a central parameter server. However, DFL faces three critical challenges: privacy leakage from honest-but-curious neighbors, slow convergence due to the lack of central coordination, and vulnerability to Byzantine adversaries aiming to degrade model accuracy. To address these issues, we propose a novel DFL framework that integrates Byzantine robustness, privacy preservation, and convergence acceleration. Within this framework, each device trains a local model using a Bayesian approach and independently selects an optimal subset of neighbors for posterior exchange. We formulate this neighbor selection as an optimization problem to minimize the global loss function under security and privacy constraints. Solving this problem is challenging because devices only possess partial network information, and the complex coupling between topology, security, and convergence remains unclear. To bridge this gap, we first analytically characterize the trade-offs between dynamic connectivity, Byzantine detection, privacy levels, and convergence speed. Leveraging these insights, we develop a fully distributed Graph Neural Network (GNN)-based Reinforcement Learning (RL) algorithm. This approach enables devices to make autonomous connection decisions based on local observations. Simulation results demonstrate that our method achieves superior robustness and efficiency with significantly lower overhead compared to traditional security and privacy schemes.

Reading view