❌

Normal view

Received — 27 May 2026 ⏭

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yusong Lin · Xinyuan Liang · Haiyang Wang · Qipeng Gu · Siqi Cheng · Jiangui Chen · Shuzhe Wu · Feiyang Pan · Lue Fan · Sanyuan Zhao · Dandan Tu
26 May 2026 at 12:00
arXiv:2605.26086v1 Announce Type: new Abstract: Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate over only narrow slices of that world, limiting context-sensitive reasoning and effective assistance. Existing benchmarks similarly provide only partial user state and therefore fail to capture performance in such a broad, always-on setting. To address this gap, we introduce Claw-Anything, a benchmark that expands agent context along three dimensions: long-horizon activity histories, interdependent backend services, and integrated GUI and CLI interaction across multiple devices. To instantiate this setting, we simulate months of user activity through multi-round event injection, producing complex world states and realistic noise, including irrelevant events and conflicting signals. Agents must reason over rich contextual environments while remaining robust to such noise. This expanded scope also enables the evaluation of proactive assistance, requiring agents to anticipate user needs and deliver timely recommendations. Experiments show that GPT-5.5 achieves only 34.5% pass@1, substantially below prior benchmarks, underscoring a gap between current agent capabilities and the demands of always-on personal assistance. Alongside the benchmark, we release an automated data-generation pipeline that yields 2,000 training environments and improves the base model by 23.7%, demonstrating its utility of scalable data infrastructure.

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dingbang Wu · Rui Hao · Haiyang Wang · Shuzhe Wu · Han Xiao · Zhenghong Li · Bojiang Zhou · Zheng Ju · Zichen Liu · Lue Fan · Zhaoxiang Zhang
26 May 2026 at 12:00
arXiv:2605.26114v1 Announce Type: new Abstract: We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating proprietary backends. It enables two capabilities previously out of reach for everyday apps: verifiable outcome signals through deterministic state-based judging over structured JSON state, and scalable online RL through low-cost parallel rollouts. The full environment state is captured, configured, forked, and compared as structured JSON, and a single server can host hundreds of parallel instances, with about 400 MB memory per instance and about 3 s cold start. A layered state model and a declarative task-definition framework keep state programmability and task creation practical at scale, and a single programmatic judging mechanism delivers both deterministic evaluation verdicts and dense RL rewards. The accompanying MobileGym-Bench provides 416 parameterized task templates, including 256 test and 160 train templates, over 28 apps, with deterministic judges and a structured AnswerSheet protocol that avoids free-text matching failures. In a Sim-to-Real case study, GRPO on Qwen3-VL-4B-Instruct gains +12.8 percentage points on the 256-task test set, and on a 59-task real-device signal subset, real-device execution retains 95.1% of the simulation-side training gain. Project page: https://mobilegym.github.io.

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhaoyang Wang · Canwen Xu · Boyi Liu · Yite Wang · Siwei Han · Zhewei Yao · Huaxiu Yao · Yuxiong He
26 May 2026 at 12:00
arXiv:2602.10090v3 Announce Type: replace Abstract: Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training is limited by the lack of diverse and reliable environments. In this paper, we propose Agent World Model (AWM), a fully synthetic environment generation pipeline. Using this pipeline, we scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets and obtain high-quality observations. Notably, these environments are code-driven and backed by databases, providing more reliable and consistent state transitions than environments simulated by LLMs. Moreover, they enable more efficient agent interaction compared with collecting trajectories from realistic environments. To demonstrate the effectiveness of this resource, we perform large-scale reinforcement learning for multi-turn tool-use agents. Thanks to the fully executable environments and accessible database states, we can also design reliable reward functions. Experiments on three benchmarks show that training exclusively in synthetic environments, rather than benchmark-specific ones, yields strong out-of-distribution generalization. The code is available at https://github.com/Snowflake-Labs/agent-world-model.

HiTeC: Hierarchical Contrastive Learning on Text-Attributed Hypergraph with Semantic-Aware Augmentation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mengting Pan · Fan Li · Chen Chen · Xiaoyang Wang · Wenjie Zhang
26 May 2026 at 12:00
arXiv:2508.03104v3 Announce Type: replace-cross Abstract: Contrastive learning (CL) has become a dominant paradigm for self-supervised hypergraph learning, enabling effective training without costly labels. However, node entities in real-world hypergraphs are often associated with rich textual information, which has been largely ignored in prior works. Directly applying existing CL-based methods to such text-attributed hypergraphs (TAHGs) leads to three key limitations: (1) The common use of graph-agnostic text encoders fails to capture the correlations between textual semantics and hypergraph topology, resulting in less expressive representations. (2) Their reliance on random data augmentations introduces noise and weakens the contrastive signals. (3) The primary focus on node- and hyperedge-level contrastive signals limits the ability to capture long-range dependencies, which is essential for effective representation learning. To address these challenges, we introduce HiTeC, a two-stage hierarchical contrastive learning framework for effective self-supervised learning on TAHGs. In the first stage, we pre-train the text encoder with a structure-aware contrastive objective to overcome the graph-agnostic nature of conventional methods. In the second stage, we begin by introducing semantic-aware augmentations, including structure-contextualized text augmentation and semantic-aware hyperedge dropping, to facilitate informative view generation. Subsequently, we propose a multi-scale contrastive loss with an $s$-walk-based subgraph-level objective to capture long-range dependencies. Extensive experiments on six real-world datasets validate the effectiveness of our proposed method.

Multi-omics analysis identified serum B4GALT1 as a prognostic factor for small cell lung cancer

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Chenyang Wang · Xiaoyue Zhu · Yiheng Shi · Guirong Wang · Teng Ma
25 May 2026 at 18:00

J Thorac Dis. 2026 Apr 30;18(4):353. doi: 10.21037/jtd-2025-1-2610. Epub 2026 Mar 20.

ABSTRACT

BACKGROUND: Small cell lung cancer (SCLC) is an aggressive neuroendocrine tumor characterized by rapid progression, early metastasis, and high mortality, with limited effective long-term treatment options. B4GALT1, a β-1,4-galactosyltransferase, has been implicated in the malignant progression of various cancers, but its specific role and underlying mechanisms in SCLC remain largely unexplored. We conducted a multi-omics analysis and clinical sample study to explore the function of B4GALT1 in SCLC.

METHODS: This study comprehensively investigated the expression pattern, functional significance, and clinical relevance of B4GALT1 in SCLC. We conducted multi-omics analyses, including single-cell data processing, InferCNV analysis, and immune infiltration analysis, to explore the association between B4GALT1 and the immune microenvironment of SCLC and patient survival. To determine B4GALT1 as a potential circulating biomarker, quantitative data-independent acquisition (DIA) proteomics analysis was performed on serum samples from SCLC patients and healthy controls. Enzyme-linked immunosorbent assay (ELISA) was used to further verify the differential expression of serum B4GALT1 in a larger cohort of SCLC patients, to evaluate its diagnostic, prognostic, and treatment response predictive value.

RESULTS: Multi-omics analysis revealed that B4GALT1 expression was significantly associated with patient survival. The expression of B4GALT1 positively correlated with macrophage infiltration in the tumor and negatively correlated with CD4+ T cells in the tumor. There was a negative correlation in inactivated naïve B cells, eosinophils, and CD4 naïve T cells, while it showed a positive correlation in dendritic cells, M0/M1/M2 macrophages, natural killer (NK) cells, CD8 T cells, follicular helper T cells, and regulatory T cells. ELISA results showed that serum protein B4GALT1 expression was higher in patients with SCLC than in healthy controls. Elevated serum B4GALT1 protein levels correlated with poor treatment outcomes in patients with SCLC undergoing chemoradiotherapy.

CONCLUSIONS: Our findings establish B4GALT1 as a critical prognostic, diagnostic, and predictive biomarker in SCLC, with its expression closely linked to the tumor immune microenvironment and treatment response. Targeting B4GALT1 or its related pathways may represent a novel therapeutic strategy, and serum B4GALT1 holds promise as a liquid biopsy marker for SCLC patient stratification, monitoring, and guiding treatment decisions.

PMID:42182735 | PMC:PMC13190155 | DOI:10.21037/jtd-2025-1-2610

Multi-omics analysis identified serum B4GALT1 as a prognostic factor for small cell lung cancer

✇Omics In Lung
By: Chenyang Wang · Xiaoyue Zhu · Yiheng Shi · Guirong Wang · Teng Ma
25 May 2026 at 18:00

J Thorac Dis. 2026 Apr 30;18(4):353. doi: 10.21037/jtd-2025-1-2610. Epub 2026 Mar 20.

ABSTRACT

BACKGROUND: Small cell lung cancer (SCLC) is an aggressive neuroendocrine tumor characterized by rapid progression, early metastasis, and high mortality, with limited effective long-term treatment options. B4GALT1, a β-1,4-galactosyltransferase, has been implicated in the malignant progression of various cancers, but its specific role and underlying mechanisms in SCLC remain largely unexplored. We conducted a multi-omics analysis and clinical sample study to explore the function of B4GALT1 in SCLC.

METHODS: This study comprehensively investigated the expression pattern, functional significance, and clinical relevance of B4GALT1 in SCLC. We conducted multi-omics analyses, including single-cell data processing, InferCNV analysis, and immune infiltration analysis, to explore the association between B4GALT1 and the immune microenvironment of SCLC and patient survival. To determine B4GALT1 as a potential circulating biomarker, quantitative data-independent acquisition (DIA) proteomics analysis was performed on serum samples from SCLC patients and healthy controls. Enzyme-linked immunosorbent assay (ELISA) was used to further verify the differential expression of serum B4GALT1 in a larger cohort of SCLC patients, to evaluate its diagnostic, prognostic, and treatment response predictive value.

RESULTS: Multi-omics analysis revealed that B4GALT1 expression was significantly associated with patient survival. The expression of B4GALT1 positively correlated with macrophage infiltration in the tumor and negatively correlated with CD4+ T cells in the tumor. There was a negative correlation in inactivated naïve B cells, eosinophils, and CD4 naïve T cells, while it showed a positive correlation in dendritic cells, M0/M1/M2 macrophages, natural killer (NK) cells, CD8 T cells, follicular helper T cells, and regulatory T cells. ELISA results showed that serum protein B4GALT1 expression was higher in patients with SCLC than in healthy controls. Elevated serum B4GALT1 protein levels correlated with poor treatment outcomes in patients with SCLC undergoing chemoradiotherapy.

CONCLUSIONS: Our findings establish B4GALT1 as a critical prognostic, diagnostic, and predictive biomarker in SCLC, with its expression closely linked to the tumor immune microenvironment and treatment response. Targeting B4GALT1 or its related pathways may represent a novel therapeutic strategy, and serum B4GALT1 holds promise as a liquid biopsy marker for SCLC patient stratification, monitoring, and guiding treatment decisions.

PMID:42182735 | PMC:PMC13190155 | DOI:10.21037/jtd-2025-1-2610

There are no more articles
❌