Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

By: Wenhui Chen · Shiwen Cheng · Hao Dong · Chenda Duan · Ruixiang Feng · Zhong Guan · Boqiang Guo · Xueyuan Han · Haojie Hao · Liangmeng Huang · Zhelong Huang · Xinke Kong · Hongyu Li · Jiazheng Li · Junbo Li · Qingchuan Li · Yukun Lian · Chang Liu · Tianyu Liu · Zicheng Liu · Shuyi Ouyang · Yijun Pan · Kunyu Shi · Xiaojun Tang · Bingquan Wang · Kesu Wang · Yuchen Wang · Sibo Wei · Sicong Xie · Xiaoying Xing · Yi Xu · Zhijun Xu · Hongwei Xue · Qingcheng Zeng · Di Zhang · Guannan Zhang · Haochen Zhang · Tianlong Zhang · Tianyu Zhao · Tianyu Zhao · Yanjun Zheng · Jialong Zhu · Zijian Zou

14 September 2026 at 12:00

arXiv:2609.11977v1 Announce Type: new Abstract: Co-work agents execute complex workflows that combine information gathering, tool use, coding, and file manipulation across many model invocations. Because cost and latency accumulate over the full episode, their practical value depends not only on peak capability but also on how efficiently that capability is delivered. Yet many steps in everyday work emphasize state tracking, coordination, recovery, and follow-through rather than frontier-scale reasoning. We present Occamy-1.0, a cost-efficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint. We construct execution-grounded data and environments, capture replayable long-horizon trajectories across multiple harnesses, and use staged post-training to develop and consolidate complementary execution capabilities. Across a broad suite of co-work benchmarks, Occamy-1.0 is consistently among the strongest comparably sized models and remains competitive with substantially larger frontier systems on several tasks. Under our stated evaluation and pricing protocol, its aggregate performance across four representative benchmarks places it at the low-cost knee of the observed cost--performance Pareto frontier. Supporting evaluations in tool calling, coding, and instruction following further show that this specialization preserves broad agentic capability. We release the model weights and a subset of the training data to support research on practical co-work agents and agentic post-training.

Impact of LLM-supported patient education on patient perspectives and patient-reported outcomes: a mixed-methods systematic review

npj Digital Medicine

By: Jiayi Liu · Yanan Zhang · Honghao Lai · Min Han · Ning Ma · Sibo Du · Weilong Zhao · Danni Xia · Bo Tong · Yanru Liu · Bei Pan · Xiaoman Wang · Bingyi Wang · Xufei Luo · Yimeng Li · Janne Estill · Sheng Li · Hongfei Cui · Li Xiao · Long Ge

10 September 2026 at 08:00

npj Digital Medicine, Published online: 10 September 2026; doi:10.1038/s41746-026-03228-7

Impact of LLM-supported patient education on patient perspectives and patient-reported outcomes: a mixed-methods systematic review

Transduction Efficiency in Clinical CAR T-Cell Products: A Retrospective Study at a Single Center

Molecular Therapy Advances

By: Lipei Shao · Michaela Prochazkova · Yihua Cai · Kyu Lee Han · Kathryn Martin · Rongye Shi · Ruyan Yang · Jinxia Ma · Yanyan Zheng · Pamela Garces · Sue-Ellen Frodigh · Victoria Pham · Nan Zhang · Robert P. Somerville · David F. Stroncek · Ping Jin

2 September 2026 at 08:00

Transduction efficiency is a critical determinant of CAR T-cell manufacturing quality. Analysis of 204 clinical CAR T-cell products revealed that transduction efficiency is shaped primarily by manufacturing workflows and protocol-dependent starting material composition. Higher transduction efficiency was associated with early memory-like cellular states, providing insights into optimizing CAR T-cell.

Wuwei Huanglian Wan inhibits Helicobacter pylori and alleviates associated gastritis: host metabolic remodeling and altered IL-6/STAT3 signaling

Omics in Gastric

By: Wenxi Yang · Gengyuan Yu · Yanan Zhang · Dongsheng Ren · Yuying Li · Jin Yang · Meicun Yao

5 September 2026 at 18:00

J Ethnopharmacol. 2026 Sep 5;374(Pt 1):122370. doi: 10.1016/j.jep.2026.122370. Online ahead of print.

ABSTRACT

ETHNOPHARMACOLOGICAL RELEVANCE: Wuwei Huanglian Wan (WWHLW) is a traditional Tibetan medicine formula developed by Tibetan physician Takpe Pingcuo and officially documented in the Ministry of Health Drug Standards for Tibetan Medicines (Volume I, 1995). It has long been used for the treatment of gastrointestinal disorders, particularly conditions associated with gastrointestinal discomfort and inflammation. Given the overlap between its traditional indications and the clinical manifestations of H. pylori-associated gastritis (HAG), WWHLW represents a promising candidate for the management of H. pylori infection and related gastric inflammation. In addition, several constituent herbs of WWHLW have demonstrated anti-H. pylori and anti-inflammatory activities, providing a pharmacological basis for further investigating its therapeutic effects.

AIM OF THE STUDY: This study aimed to systematically evaluate the therapeutic effects of WWHLW against H. pylori infection and HAG, and to explore the biological processes associated with these effects through integrated multi-omics and experimental validation.

MATERIALS AND METHODS: The therapeutic effects of WWHLW were evaluated through in vitro antibacterial assays and an H. pylori-infected mouse model. UHPLC-HRMS/MS was employed for chemical profiling and identification of serum-absorbed constituents. Serum metabolomics, 16S rRNA gene sequencing, network pharmacology analysis, molecular docking analysis, and molecular biological analyses were integrated to investigate the metabolic, microbial, and signaling changes associated with its therapeutic activity.

RESULTS: WWHLW exhibited anti-H. pylori activity, with minimum inhibitory concentrations (MICs) of 0.2-0.5 mg/mL against both standard strains and multidrug-resistant clinical isolates. At MIC concentrations, WWHLW treatment altered the expression of multiple virulence-associated genes and reduced gastric H. pylori colonization by 93.8% in infected mice. UHPLC-HRMS/MS analysis putatively annotated 121 compounds in the WWHLW extracts, of which 10 prototype constituents were detected in serum after oral administration. Integrated metabolomics and network pharmacology analyses revealed alterations in lipid and amino acid-related metabolic pathways following WWHLW treatment. Gut microbiota analysis showed that WWHLW was associated with less pronounced alterations in microbial diversity and composition than antibiotic treatment. Correlation analysis further revealed statistical associations between microbial taxa and lipid and amino acid-related features. Experimental validation showed that WWHLW reduced inflammatory cytokine expression and suppressed STAT3 phosphorylation, consistent with altered IL-6/STAT3-related molecular changes.

CONCLUSIONS: WWHLW exhibits therapeutic potential against H. pylori infection and HAG through combined antibacterial, anti-inflammatory and metabolic regulatory effects. The protective activity of WWHLW was associated with reduced IL-6/STAT3 signaling, providing pharmacological evidence supporting its traditional use in gastrointestinal disorders.

PMID:42700849 | DOI:10.1016/j.jep.2026.122370

TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning

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

By: Muyu Pan · Shu Zhao · Nan Zhang · Philip Shin · Varun Parekh · Vijaykrishnan Narayanan · Rui Zhang

26 May 2026 at 12:00

arXiv:2605.25850v1 Announce Type: cross Abstract: This paper investigates large language model (LLM) abstention learning, specifically using ternary reward, which incentivize truthfulness in large language models. This paper extends that idea by moving from a ternary reward to a Trajectory-Informed advantage reweighting, dynamically re-weights the abstention reward during Group Relative Policy Optimization (GRPO) training. The objective of this work focuses on abstention learning instead of improving truthfulness, serving as an exploration into hallucination reduction. The novelty of this paper lies in methodological innovation, advantage re-weighting, and benchmark selection. Leveraging GRPO's multiple trajectories as a natural abstention signal, this method uses a reward signal to explore knowledge boundaries and encourage consistency. By demonstrating that trajectories can be used as a confidence indicator of the policy relative to the query, they are then used to dynamically calculate the abstention advantage. AbstentionBench is used as the evaluation benchmark, as this work aims to contribute to the field of abstention learning. All datasets on the benchmark were tested against this method and various baselines. Empirical results demonstrate that TIAR achieves state-of-the-art abstention F1 scores across five of six evaluation categories, outperforming the static ternary baseline on 17 of 31 benchmark datasets while fully preserving baseline accuracy.

Routing by Analogy: kNN-Augmented Expert Assignment for Mixture-of-Experts

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

By: Boxuan Lyu · Soichiro Murakami · Hidetaka Kamigaito · Peinan Zhang

26 May 2026 at 12:00

arXiv:2601.02144v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sparse subset of experts. Typically, this router is trained once and then frozen, rendering routing decisions brittle under distribution shifts. We address this limitation by introducing kNN-MoE, a retrieval-augmented routing framework that reuses locally optimal expert assignments from a memory of similar past cases. This memory is constructed offline by directly optimizing token-wise routing logits to maximize the likelihood on a reference set. Crucially, we use the average similarity of retrieved neighbors as a confidence-driven mixing coefficient, thus allowing the method to fall back to the frozen router when no relevant cases are found. Experiments show that kNN-MoE outperforms the zero-shot baseline and is competitive with computationally intensive supervised fine-tuning.

Pan-neurodegeneration proteomics reveals disease subtypes and molecular signatures

Cell

By: Him K. Shrestha · Huan Sun · Jay M. Yarbro · DongGeun Lee · Danting Liu · Erming Wang · Meghan McReynolds · Nan Zhang · Boer Xie · Shu Yang · Kaiwen Yu · Suresh Poudel · Yuxin Li · Zuo-Fei Yuan · Dehui Kong · Minghui Wang · Zhen Wang · Mingming Niu · Hong Wang · Masihuz Zaman · Ju Wang · David R. Vanderwall · Yu Sun · Zhiping Wu · Ping-Chung Chen · Bing Bai · Anthony A. High · Júlia Faura · Chunyu Liu · David A. Bennett · Erik C.B. Johnson · Nicholas T. Seyfried · Allan I. Levey · Vahram Haroutunian · Geidy E. Serrano · Thomas G. Beach · Michael DeTure · Takahisa Kanekiyo · Ronald C. Petersen · Guojun Bu · Pamela J. McLean · Dennis W. Dickson · Rosa Rademakers · Gang Yu · Xusheng Wang · Bin Zhang · Junmin Peng

23 March 2026 at 08:00

A pan-neurodegeneration atlas built from multilayer, deep proteomics of 2,279 brain samples across 6 major diseases integrates whole proteome, detergent-insoluble proteome, and posttranslational modifications to enable intra- and inter-disease comparisons to reveal disease-specific subtypes and dysregulated pathways, while identifying shared changes such as GPNMB upregulation and NPTX2 downregulation.

BAAI Cardiac Agent: An intelligent multimodal agent for automated reasoning and diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging

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

By: Taiping Qu · Hongkai Zhang · Lantian Zhang · Can Zhao · Nan Zhang · Hui Wang · Zhen Zhou · Mingye Zou · Kairui Bo · Pengfei Zhao · Xingxing Jin · Zixian Su · Kun Jiang · Huan Liu · Yu Du · Maozhou Wang · Ruifang Yan · Zhongyuan Wang · Tiejun Huang · Lei Xu · Henggui Zhang

7 April 2026 at 12:00

arXiv:2604.04078v1 Announce Type: cross Abstract: Cardiac magnetic resonance (CMR) is a cornerstone for diagnosing cardiovascular disease. However, it remains underutilized due to complex, time-consuming interpretation across multi-sequences, phases, quantitative measures that heavily reliant on specialized expertise. Here, we present BAAI Cardiac Agent, a multimodal intelligent system designed for end-to-end CMR interpretation. The agent integrates specialized cardiac expert models to perform automated segmentation of cardiac structures, functional quantification, tissue characterization and disease diagnosis, and generates structured clinical reports within a unified workflow. Evaluated on CMR datasets from two hospitals (2413 patients) spanning 7-types of major cardiovascular diseases, the agent achieved an area under the receiver-operating-characteristic curve exceeding 0.93 internally and 0.81 externally. In the task of estimating left ventricular function indices, the results generated by this system for core parameters such as ejection fraction, stroke volume, and left ventricular mass are highly consistent with clinical reports, with Pearson correlation coefficients all exceeding 0.90. The agent outperformed state-of-the-art models in segmentation and diagnostic tasks, and generated clinical reports showing high concordance with expert radiologists (six readers across three experience levels). By dynamically orchestrating expert models for coordinated multimodal analysis, this agent framework enables accurate, efficient CMR interpretation and highlights its potentials for complex clinical imaging workflows. Code is available at https://github.com/plantain-herb/Cardiac-Agent.

Agentization of Digital Assets for the Agentic Web: Concepts, Techniques, and Benchmark

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

By: Linyao Chen · Bo Huang · Qinlao Zhao · Shuai Shao · Zhi Han · Zicai Cui · Ziheng Zhang · Guangtao Zeng · Wenzheng Tang · Yikun Wang · Yuanjian Zhou · Zimian Peng · Yong Yu · Weiwen Liu · Hiroki Kobayashi · Weinan Zhang

7 April 2026 at 12:00

arXiv:2604.04226v1 Announce Type: cross Abstract: Agentic Web, as a new paradigm that redefines the internet through autonomous, goal-driven interactions, plays an important role in group intelligence. As the foundational semantic primitives of the Agentic Web, digital assets encapsulate interactive web elements into agents, which expand the capacities and coverage of agents in agentic web. The lack of automated methodologies for agent generation limits the wider usage of digital assets and the advancement of the Agentic Web. In this paper, we first formalize these challenges by strictly defining the A2A-Agentization process, decomposing it into critical stages and identifying key technical hurdles on top of the A2A protocol. Based on this framework, we develop an Agentization Agent to agentize digital assets for the Agentic Web. To rigorously evaluate this capability, we propose A2A-Agentization Bench, the first benchmark explicitly designed to evaluate agentization quality in terms of fidelity and interoperability. Our experiments demonstrate that our approach effectively activates the functional capabilities of digital assets and enables interoperable A2A multi-agent collaboration. We believe this work will further facilitate scalable and standardized integration of digital assets into the Agentic Web ecosystem.

Elevation of Liver Elastic Value Following Radiofrequency Ablation Reflected Neutrophils Mediated Abscopal Effect in Liver Cancer

Omics in Hepatocellular

By: Ke Lin · Jiayao Huang · Nan Zhang · Bin Qiao · Daopeng Yang · Jianping Guo · Xiaoyan Xie · Manxia Lin · Bowen Zhuang

25 March 2026 at 18:00

JHEP Rep. 2026 Mar 23:101824. doi: 10.1016/j.jhepr.2026.101824. Online ahead of print.

ABSTRACT

BACKGROUND & AIMS: Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality globally. Radiofrequency ablation (RFA) is a widely used treatment for HCC, but its efficacy is often limited by tumor relapse. Neutrophils, serve as a double-edged sword in tumor immunology, have recently been implicated in anti-tumor immunity post-RFA. Shear wave elastography (SWE) is a non-invasive examination for liver tissue, and associated with immune response. This study investigates the correlation between dynamic change of SWE values and neutrophils response following RFA, and explores potential adjuvant strategies for RFA.

METHODS: We conducted a comprehensive analysis using both clinical data from patients undergoing RFA (n=102) and experimental studies in mouse models (n=4-6 per group). Single-cell RNA sequencing (scRNA-seq) and multi-omics analyses including multiplex immunofluorescence staining and flow cytometric analysis were performed to identify neutrophil subsets. To assess the therapeutic potential of neutrophils-activating therapy for enhancing anti-tumor immunity post-RFA, we tested CD40 agonist in combination with RFA in preclinical models.

RESULTS: We noticed that rising liver SWE values following RFA were significantly associated with reduce relapse (n=102, p<0.001), and demonstrated that this phenomenon was linked to the inflammatory environment induced by the infiltration of neutrophils (2.5-fold increase, p<0.001). scRNA-seq analysis identified neutrophil subsets characterized by high expression of interferon-stimulated genes, which exhibited potent anti-tumor activity via nitric oxide. Importantly, treatment with CD40 agonist significantly augmented this immune response, leading to reduced tumor growth in mice (149.6±38.12 mm³ vs 23.92±4.43 mm³, p=0.008).

CONCLUSIONS: We linked clinical features to neutrophil-mediated immunity post-RFA. Neutrophil-activating therapy like CD40 agonists may prevent HCC relapse after RFA.

PMID:41881314 | DOI:10.1016/j.jhepr.2026.101824

Generalizing Dynamics Modeling More Easily from Representation Perspective

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

By: Yiming Wang · Zhengnan Zhang · Genghe Zhang · Jiawen Dan · Changchun Li · Chenlong Hu · Chris Nugent · Jun Liu · Ximing Li · Bo Yang

25 March 2026 at 12:00

arXiv:2603.22655v1 Announce Type: cross Abstract: Learning system dynamics from observations is a critical problem in many applications over various real-world complex systems, e.g., climate, ecology, and fluid systems. Recently, neural dynamics modeling method have become a prevalent solution that embeds the object's observations into a latent space before learning dynamics using neural methods such as neural Ordinary Differential Equations (ODE). Existing dynamics modeling methods induce a specific model for each observation of different complex systems, resulting in poor generalization across systems. Inspired by the great success of pre-trained models, we conduct a generalized Pre-trained Dynamics EncoDER (PDEDER) which can embed the original state observations into a latent space where the dynamics can be captured more easily. To conduct the generalized PDEDER, we pre-train any Pre-trained Language Model (PLM) by minimizing the Lyapunov exponent objective, which constrains the chaotic behavior of governing dynamics learned in the latent space. By penalizing the divergence of embedded observations, our PDEDER promotes locally stable and well-structured latent dynamics, thereby facilitating more effective dynamics modeling than in the original observation space. In addition, we incorporate reconstruction and forecasting objectives to mitigate the risk of obtaining an over-smoothed latent space. Specifically, we collect 152 sets of real-world and synthetic observations from 23 complex systems as pre-training corpora and employ them to pre-train PDEDER. Given any future dynamic observation, we can fine-tune PDEDER with any specific dynamics modeling method. We evaluate PDEDER on 12 dynamic systems by short/long-term forecasting under both in-domain and cross-domain settings, and the empirical results indicate the effectiveness and generalizability of PDEDER.

Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective

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

By: Liyuan Mao · Le Yu · Jing Zhou · Chujie Zheng · Bowen Yu · Chang Gao · Shixuan Liu · An Yang · Weinan Zhang · JunYang Lin

10 March 2026 at 12:00

arXiv:2603.08398v1 Announce Type: cross Abstract: In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity-akin to chameleons adapting their coloration to environmental cues-that can be exposed through token-conditional generation and stabilized via reinforcement learning. Specifically, by conditioning generation on carefully selected token prefixes sampled from responses exhibiting desired behaviors, LLMs seamlessly adapt their behavioral modes at inference time (e.g., switching from step-by-step reasoning to direct answering) without retraining. Based on this insight, we propose Token-Conditioned Reinforcement Learning (ToCoRL), a principled framework that leverages RL to internalize this chameleon-like plasticity, transforming transient inference-time adaptations into stable and learnable behavioral patterns. ToCoRL guides exploration with token-conditional generation and keep enhancing exploitation, enabling emergence of appropriate behaviors. Extensive experiments show that ToCoRL enables precise behavioral control without capability degradation. Notably, we show that large reasoning models, while performing strongly on complex mathematics, can be effectively adapted to excel at factual question answering, which was a capability previously hindered by their step-by-step reasoning patterns.

Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

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

By: Shuai Shao · Qihan Ren · Chen Qian · Boyi Wei · Dadi Guo · Jingyi Yang · Xinhao Song · Linfeng Zhang · Weinan Zhang · Dongrui Liu · Jing Shao

10 March 2026 at 12:00

arXiv:2509.26354v2 Announce Type: replace Abstract: Advances in Large Language Models (LLMs) have enabled a new class of self-evolving agents that autonomously improve through interaction with the environment, demonstrating strong capabilities. However, self-evolution also introduces novel risks overlooked by current safety research. In this work, we study the case where an agent's self-evolution deviates in unintended ways, leading to undesirable or even harmful outcomes. We refer to this as Misevolution. To provide a systematic investigation, we evaluate misevolution along four key evolutionary pathways: model, memory, tool, and workflow. Our empirical findings reveal that misevolution is a widespread risk, affecting agents built even on top-tier LLMs (e.g., Gemini-2.5-Pro). Different emergent risks are observed in the self-evolutionary process, such as the degradation of safety alignment after memory accumulation, or the unintended introduction of vulnerabilities in tool creation and reuse. To our knowledge, this is the first study to systematically conceptualize misevolution and provide empirical evidence of its occurrence, highlighting an urgent need for new safety paradigms for self-evolving agents. Finally, we discuss potential mitigation strategies to inspire further research on building safer and more trustworthy self-evolving agents. Our code and data are available at https://github.com/ShaoShuai0605/Misevolution . Warning: this paper includes examples that may be offensive or harmful in nature.

PEPA: a Persistently Autonomous Embodied Agent with Personalities

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

By: Kaige Liu · Yang Li · Lijun Zhu · Weinan Zhang

10 March 2026 at 12:00

arXiv:2603.00117v2 Announce Type: replace-cross Abstract: Living organisms exhibit persistent autonomy through internally generated goals and self-sustaining behavioral organization, yet current embodied agents remain driven by externally scripted objectives. This dependence on predefined task specifications limits their capacity for long-term deployment in dynamic, unstructured environments where continuous human intervention is impractical. We propose that personality traits provide an intrinsic organizational principle for achieving persistent autonomy. Analogous to genotypic biases shaping biological behavioral tendencies, personalities enable agents to autonomously generate goals and sustain behavioral evolution without external supervision. To realize this, we develop PEPA, a three-layer cognitive architecture that operates through three interacting systems: Sys3 autonomously synthesizes personality-aligned goals and refines them via episodic memory and daily self-reflection; Sys2 performs deliberative reasoning to translate goals into executable action plans; Sys1 grounds the agent in sensorimotor interaction, executing actions and recording experiences. We validate the framework through real-world deployment on a quadruped robot in a multi-floor office building. Operating without reliance on fixed task specifications, the robot autonomously arbitrates between user requests and personality-driven motivations, navigating elevators and exploring environments accordingly. Quantitative analysis across five distinct personality prototypes demonstrates stable, trait-aligned behaviors. The results confirm that personality-driven cognitive architectures enable sustained autonomous operation characteristic of persistent embodied systems. Code and demo videos are available at https://sites.google.com/view/pepa-persistent/.

Reading view