Hierarchical Belief Modeling for Zero-Shot Opponent Adaptation in Partially Observable Multi-Agent Navigation

By: Kowei Shih · Lu Cheng · Zeyu Wang · Yeyun Xu · Kejian Tong

14 September 2026 at 12:00

arXiv:2609.12422v1 Announce Type: new Abstract: Lux AI Season 3 requires agents to act under partial observability, randomized episode level dynamics, and a best of five match structure that rewards both tactical execution and fast adaptation. We present HORIZON, a hierarchical agent that combines symmetry aware spatial perception, dual memory belief tracking, relic centric graph attention, information gain driven exploration, and an opponent conditioned policy mixture. HORIZON separates short horizon control from cross match meta reasoning, while auxiliary belief and world model objectives stabilize learning. Trained with PPO in a large scale JAX simulator, the resulting agent explicitly infers hidden game parameters and opponent style. Experiments show consistent gains in match win rate, episode win rate, adaptation gain, and league rating over strong recurrent and feed forward baselines.

FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data

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

By: Zhenghang Song · Tang Qian · Lu Chen · Yushuai Li · Zhengke Hu · Bingbing Fang · Yumeng Song · Junbo Zhao · Sheng Zhang · Tianyi Li

14 September 2026 at 12:00

arXiv:2603.16513v4 Announce Type: replace-cross Abstract: Structured data is widely used in domains such as healthcare, finance, and scientific data management. Recent studies on structured data foundation models (SFMs) aim to support data analysis and mining tasks over such data, but still face scalability and generalization challenges when applied to real-world enterprise databases. First, many SFMs rely on full self-attention, which introduces an O(N^2) computational bottleneck and limits the number of tuples that can be processed jointly. Second, directly replacing attention with linear-complexity sequence models may conflict with the permutation-invariant nature of structured data, introducing artificial order bias and degrading representation quality. Moreover, models trained only on synthetic data may struggle to generalize to the heavy-tailed and heterogeneous distributions commonly found in real-world databases. To address these challenges, we propose FEAT, a linear-complexity foundation model for extremely large structured data. FEAT replaces quadratic attention with a multi-layer dual-axis encoding architecture. It integrates an adaptive-fusion bidirectional state-space model (AFBM) with convolutional gated linear attention (Conv-GLA), enabling cross-tuple contextualization in O(N) time while supporting permutation-invariant representation learning. To improve robustness under real-world data skewness, FEAT further adopts a hybrid structural causal pre-training pipeline with a robust reconstruction objective. Experiments on 12 real-world database benchmarks show that FEAT consistently outperforms representative SFMs on zero-shot tasks and scales linearly with structured-data sample length, achieving up to 50x faster inference latency.

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.

A clinically derived lipid-endothelial signature links serum multi-omics to immune exclusion and clinical stratification in hepatocellular carcinoma

Omics in Hepatocellular

By: Luxi Yang · Qiaoying Jin · Lu Chen · Yating Liu · Yumin Li

2 September 2026 at 18:00

Ther Adv Med Oncol. 2026 Aug 31;18:17588359261481797. doi: 10.1177/17588359261481797. eCollection 2026.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) is driven by extensive metabolic reprogramming, vascular remodeling, and immune microenvironmental dysfunction. Although numerous stratification signatures have been proposed, few are grounded in clinically derived serum multi-omics and biologically linked to endothelial remodeling, endothelial regulation, and immune exclusion.

OBJECTIVES: This study aimed to identify a serum-derived lipid-endothelial program associated with immune exclusion and clinical stratification in HCC.

DESIGN: A translational multi-omics study integrating clinically collected serum samples, public transcriptomic cohorts, single-cell RNA sequencing, and experimental validation.

METHODS: Proteomic and metabolomic sequencing was performed on serum samples from patients with HCC and normal controls. Dysregulated pathways were integrated with transcriptomic data from TCGA-LIHC and ICGC-LIRI-JP cohorts to identify genes jointly associated with lipid metabolism and leukocyte transendothelial migration. A risk score was calculated using the expression of PON1, TXNRD1, CLDN4, CLDN6, CYP2C9, and CTSA. Higher expression of TXNRD1, CLDN4, CLDN6, and CTSA contributed to a higher risk score, whereas PON1 and CYP2C9 contributed protective coefficients. Immune contexture, tumor mutation burden, and exploratory therapeutic sensitivity patterns were further evaluated using transcriptome-based drug sensitivity prediction, followed by single-cell RNA sequencing and experimental expression validation.

RESULTS: Serum multi-omics analysis revealed prominent dysregulation of lipid metabolic pathways and leukocyte transendothelial migration-related processes in HCC. Integrative analysis identified a six-gene lipid-endothelial signature (PON1, TXNRD1, CLDN4, CLDN6, CYP2C9, and CTSA) that stratified patients into high- and low-risk groups. In the TCGA-LIHC cohort, high-risk patients had significantly poorer overall survival than low-risk patients (log-rank P < 0.0001), and this survival-stratifying association was externally supported in the ICGC-LIRI-JP cohort (log-rank P = 0.016). The high-risk phenotype was associated with immune-excluded features, distinct somatic mutation patterns, and altered predicted sensitivity to several selected anticancer agents. Single-cell analysis and experimental assays further supported the association between the six-gene program, malignant epithelial states, endothelial-related remodeling, and immune microenvironmental heterogeneity.

CONCLUSION: This study defines a clinically derived lipid-endothelial program associated with immune exclusion, adverse prognosis, and potential differences in therapeutic vulnerability in HCC. The proposed signature provides a biologically informed framework for prognostic assessment and may support future evaluation of targeted interventions in HCC.

PMID:42682961 | PMC:PMC13530516 | DOI:10.1177/17588359261481797

Emotional intelligence in large language models is fragmented across perception, cognition, and interaction

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

By: Minghao Lv · Lu Chen · Enchang Zhang · Anji Zhou · Xiaoran Xue · Hanyi Zhang · Fenghua Tang · Zhuo Rachel Han · Mengyue Wu

26 May 2026 at 12:00

arXiv:2605.24686v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence (EI) becomes a critical frontier for safety and alignment. Current benchmarks often conflate superficial politeness with deep affective reasoning, failing to distinguish between perceptual accuracy and interactive efficacy. Here, we introduce FACET (Functional Affective Competence and Empathy Test), a psychometrically grounded framework comprising 480 expert-crafted items. Unlike previous metrics, FACET is theoretically anchored in the Mayer-Salovey-Caruso four-branch ability model, operationalizing EI through perception, facilitation, understanding, and management of emotions. Through an evaluation of nine frontier models (including GPT-5, Claude-Sonnet-4), we demonstrate that emotional intelligence is not a monolithic capability but is fragmented across cognitive and interactive dimensions. While frontier models demonstrate robust proficiency in objective emotion recognition and social reasoning, this does not consistently translate to interactive success. We categorize these discrepancies into three distinct performance profiles: cognitive-dominant, interactive-dominant, and context-dependent. These typologies indicate that emotional skills do not scale uniformly with general intelligence or model size; rather, they are shaped by specific alignment paradigms. Notably, we identify hidden emotion recognition as a universal performance bottleneck across all architectures. Our results suggest that current RLHF processes may optimize for "stochastic empathy", a statistical mimicry of emotional syntax, at the expense of integrated affective reasoning. These findings challenge the assumption of linear emotional scaling and provide a rigorous roadmap for developing socially aware agents capable of genuine clinical resonance.

Adaptive Stopping for Multi-Turn LLM Reasoning

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

By: Xiaofan Zhou · Huy Nguyen · Bo Yu · Chenxi Liu · Lu Cheng

7 April 2026 at 12:00

arXiv:2604.01413v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by iteratively retrieving information, reasoning, or acting, but introduce a key challenge: \textbf{When should the model stop?} Existing approaches rely on heuristic stopping rules or fixed turn budgets and provide no formal guarantees that the final prediction still contains the correct answer. This limitation is particularly problematic in high-stakes domains such as finance and healthcare, where unnecessary turns increase cost and latency, while stopping too early risks incorrect decisions. Conformal prediction (CP) provides formal coverage guarantees, but existing LLM-CP methods only apply to a single model output and cannot handle multi-turn pipelines with adaptive stopping. To address this gap, we propose Multi-Turn Language Models with Conformal Prediction (MiCP), the first CP framework for multi-turn reasoning. MiCP allocates different error budgets across turns, enabling the model to stop early while maintaining an overall coverage guarantee. We demonstrate MiCP on adaptive RAG and ReAct, where it achieves the target coverage on both single-hop and multi-hop question answering benchmarks while reducing the number of turns, inference cost, and prediction set size. We further introduce a new metric that jointly evaluates coverage validity and answering efficiency.

Adaptive Stopping for Multi-Turn LLM Reasoning

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

By: Xiaofan Zhou · Huy Nguyen · Bo Yu · Chenxi Liu · Lu Cheng

3 April 2026 at 12:00

arXiv:2604.01413v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by iteratively retrieving information, reasoning, or acting, but introduce a key challenge: \textbf{When should the model stop?} Existing approaches rely on heuristic stopping rules or fixed turn budgets and provide no formal guarantees that the final prediction still contains the correct answer. This limitation is particularly problematic in high-stakes domains such as finance and healthcare, where unnecessary turns increase cost and latency, while stopping too early risks incorrect decisions. Conformal prediction (CP) provides formal coverage guarantees, but existing LLM-CP methods only apply to a single model output and cannot handle multi-turn pipelines with adaptive stopping. To address this gap, we propose Multi-Turn Language Models with Conformal Prediction (MiCP), the first CP framework for multi-turn reasoning. MiCP allocates different error budgets across turns, enabling the model to stop early while maintaining an overall coverage guarantee. We demonstrate MiCP on adaptive RAG and ReAct, where it achieves the target coverage on both single-hop and multi-hop question answering benchmarks while reducing the number of turns, inference cost, and prediction set size. We further introduce a new metric that jointly evaluates coverage validity and answering efficiency.

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.

Unraveling the role of cuproptosis in pulmonary fibrosis pathogenesis and prognosis: an integrative single-cell transcriptomics and microarray analysis

Omics In Lung

By: Mengting Chen · Jialu Chen · Jiaxiang Zhang · Yong Zhu · Xiaoxiao Meng · Zhengfeng Yang · Ruilan Wang

13 March 2026 at 18:00

Mol Cell Biochem. 2026 Mar 13. doi: 10.1007/s11010-026-05510-4. Online ahead of print.

ABSTRACT

Pulmonary fibrosis (PF), a progressive interstitial lung disease with elusive pathogenesis, remains a therapeutic challenge. Emerging evidence suggests cuproptosis-a copper-dependent cell death pathway-may play a regulatory role in disease progression. This study aims to elucidate cuproptosis's biological function and establish a prognostic model for PF. Through integrative analysis of single-cell RNA-seq data from bleomycin (BLM)-induced mouse models and bulk RNA-seq data from idiopathic pulmonary fibrosis (IPF) patients, we identified cuproptosis-related genes (CRGs) using LASSO regression and Cox regression. A novel 4-CRG signature (LIAS, LIPT1, ATP7A, PDHB) was constructed to stratify patients into distinct risk groups in the GSE70866 cohort, where high-risk individuals exhibited poorer survival and enhanced extracellular matrix/lipid metabolism activity via GO/KEGG analysis. Experimental validation in BLM-induced mouse models, TGF-β1-stimulated fibroblast-to-myofibroblast transition assays, and human IPF specimens demonstrated significant downregulation of CRGs through qRT-PCR and immunohistochemical analyses. Functional assays revealed impaired cell viability and elevated cuproptosis markers in fibrotic microenvironments. Our findings establish an inverse correlation between cuproptosis and PF progression, and propose a robust risk-score model for clinical prognosis prediction. This multi-omics approach provides new insights into copper-mediated regulatory mechanisms in fibrogenesis.

PMID:41824199 | DOI:10.1007/s11010-026-05510-4

A Novel Multi-Agent Architecture to Reduce Hallucinations of Large Language Models in Multi-Step Structural Modeling

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

By: Ziheng Geng · Jiachen Liu · Ran Cao · Lu Cheng · Dan M. Frangopol · Minghui Cheng

10 March 2026 at 12:00

arXiv:2603.07728v1 Announce Type: new Abstract: Large language models (LLMs) such as GPT and Gemini have demonstrated remarkable capabilities in contextual understanding and reasoning. The strong performance of LLMs has sparked growing interest in leveraging them to automate tasks traditionally dependent on human expertise. Recently, LLMs have been integrated into intelligent agents capable of operating structural analysis software (e.g., OpenSees) to construct structural models and perform analyses. However, existing LLMs are limited in handling multi-step structural modeling due to frequent hallucinations and error accumulation during long-sequence operations. To this end, this study presents a novel multi-agent architecture to automate the structural modeling and analysis using OpenSeesPy. First, problem analysis and construction planning agents extract key parameters from user descriptions and formulate a stepwise modeling plan. Node and element agents then operate in parallel to assemble the frame geometry, followed by a load assignment agent. The resulting geometric and load information is translated into executable OpenSeesPy scripts by code translation agents. The proposed architecture is evaluated on a benchmark of 20 frame problems over ten repeated trials, achieving 100% accuracy in 18 cases and 90% in the remaining two. The architecture also significantly improves computational efficiency and demonstrates scalability to larger structural systems.

SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems

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

By: Haochang Hao · Yifan Xu · Xinzhuo Li · Yingqiang Ge · Lu Cheng

5 March 2026 at 13:00

arXiv:2603.03536v1 Announce Type: cross Abstract: Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which recommendation outputs may negatively impact users by violating personalized safety constraints, when individualized safety sensitivities -- such as trauma triggers, self-harm history, or phobias -- are implicitly inferred from the conversation but not respected during recommendation. We formalize this challenge as personalized CRS safety and introduce SafeRec, a new benchmark dataset designed to systematically evaluate safety risks in LLM-based CRS under user-specific constraints. To further address this problem, we propose SafeCRS, a safety-aware training framework that integrates Safe Supervised Fine-Tuning (Safe-SFT) with Safe Group reward-Decoupled Normalization Policy Optimization (Safe-GDPO) to jointly optimize recommendation quality and personalized safety alignment. Extensive experiments on SafeRec demonstrate that SafeCRS reduces safety violation rates by up to 96.5% relative to the strongest recommendation-quality baseline while maintaining competitive recommendation quality. Warning: This paper contains potentially harmful and offensive content.

Reading view