❌

Normal view

Received — 27 May 2026 ⏭

PANDO: Efficient Multimodal AI Agents via Online Skill Distillation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yubo Li · Yidi Miao · Yuntian Shen · Yuxin Liu
26 May 2026 at 12:00
arXiv:2605.24785v2 Announce Type: new Abstract: Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist model stacks. This raises a central question: can a web agent become more efficient as it accumulates experience, rather than more expensive? We first analyze trajectories from VisualWebArena and identify three recurring sources of inefficiency: repeat-action loops, hidden discovery costs, and low prompt-cache reuse. We then introduce PANDO, a single-rollout online skill-distillation framework that maintains a structured Skill Library and combines progress reflection, confidence-based skill demotion, hierarchical routing, visual compression, and cache-aware prompting. On the full set of 910 VisualWebArena tasks, PANDO achieves a 58.3% success rate, outperforming SGV (54.0%) and our WALT reproduction (45.2%), while using 58% fewer tokens than SGV and 61% fewer tokens than WALT, without any pre-evaluation discovery budget. A 300-task ablation further shows that rules and routines provide most of the success gains, while routing, compression, and cache-aware prompting convert the larger skill library into lower marginal token cost. Finally, we introduce three trajectory-level efficiency metrics -- Action Repetition Rate, Step Overhead Ratio, and Prompt Cache Utilization -- to make efficiency visible beyond terminal success.

SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guohong Liu · Jialei Ye · Pengzhi Gao · Wei Liu · Jian Luan · Yunxin Liu · Yuanchun Li
26 May 2026 at 12:00
arXiv:2605.25160v1 Announce Type: new Abstract: Mobile GUI agents powered by large language models have progressed rapidly, creating urgent needs for realistic and comprehensive evaluation. Existing benchmarks prioritize reproducibility but are often limited to open-source apps or file-operation tasks for the difficulty of constructing rewards on real applications, leaving a gap between benchmark settings and real-world usage. Moreover, most benchmarks focus on basic grounding and navigation, with limited coverage of complex, long-horizon interactions. To address these limitations, we introduce SimuWoB, a fully synthetic benchmark for mobile GUI agents with 120 challenging tasks spanning diverse types and difficulty levels. We build a robust virtual environment generation framework that synthesizes high-fidelity tasks and environments, and automatically provides valid rewards for each task. Each environment is deployed as a backend-free webpage accessible via URL, enabling efficient and reproducible evaluation. We conduct comprehensive experiments on several state-of-the-art mobile GUI agents. The average success rate is only 27.92%, dropping to 17.82% on long-horizon tasks, which reveals substantial weaknesses in current agents under complex scenarios. Evaluation result comparison with real-world sample tasks demonstrate that agent assessments based on our synthetic environment generalize well. We further provide diagnostic insights across key capability dimensions and discuss implications for future mobile GUI agent development.

A SAUR gene enhances maize drought resilience by promoting silk elongation

✇Nature - Issue - nature.com science feeds
By: Chaohui Zhu · Zhirui Yang · Shiping Yang · Xueyan Zhou · Boxin Liu · Tian Tian · Bochen Zhao · Yingying Xie · Yujun Liu · Jinkui Cheng · Huaijun Tang · Yanjun Zhang · Xiaoqing Xie · Lei Zhang · Cheng Liu · Xingrong Wang · Shengxue Liu · Feng Qin
20 May 2026 at 08:00

Nature, Published online: 20 May 2026; doi:10.1038/s41586-026-10566-9

The Small Auxin Up RNA (SAUR) protein ZmSAUR72 in maize (Zea mays) promotes silk growth via regulation of H+-ATPase activity, and is a key determinant of the anthesis-silking interval and thus resilience to drought.
Received — 4 April 2026 ⏭

Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ha Min Son · Huan Ren · Xin Liu · Zhe Zhao
3 April 2026 at 12:00
arXiv:2510.08640v3 Announce Type: replace-cross Abstract: Android is the largest mobile platform, yet automatically building applications remains a practical challenge. While Large Language Models (LLMs) show promise for code repair, their use for fixing Android build errors remains underexplored. To address this gap, we first introduce AndroidBuildBench, a benchmark of 1,019 build failures curated from the commit histories of 43 open-source Android projects. Each problem is paired with a verified solution from a subsequent commit, ensuring that fixes are feasible. Second, we propose GradleFixer, an LLM agent with domain-specific tools for inspecting and manipulating the Gradle build environment. GradleFixer achieves a resolve rate of 81.4% (pass@1), significantly outperforming a state-of-the-art coding agent that relies on a general-purpose shell. GradleFixer's success suggests that while LLMs possess the high-level knowledge to solve these failures, they struggle to translate this knowledge into effective low-level actions using a general-purpose shell. We demonstrate the effectiveness of a strategy we term Tool Bridging, which replaces general-purpose shell commands with domain-aware abstractions. We hypothesize this approach works through two mechanisms: 1) it provides tools in an API-like format that LLMs use more reliably, and 2) it constrains the action space to relevant operations. This approach bridges the gap between the model's high-level reasoning and effective low-level execution.

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.
Received — 2 April 2026 ⏭

A monocyte-centered framework for predicting immunochemotherapy efficacy in lung squamous cell carcinoma patients

✇Omics In Lung
By: Jiangnan Zhao · Zijin Wang · Manyu Xiao · Yeyuan Zhang · Boxin Liu · Silin Chen · Yiping Tian · Dongqing Lv · Pingli Wang · Hai Song · Yuefeng Wu · Jian Liu · Kai Wang
30 March 2026 at 18:00

EMBO Mol Med. 2026 Mar 30. doi: 10.1038/s44321-026-00410-y. Online ahead of print.

ABSTRACT

Lung cancer is the leading cause of cancer-related mortality worldwide, with lung squamous cell carcinoma (LUSC) comprising 20-30% of cases. Immunochemotherapy (IC) is the standard first-line treatment for advanced LUSC, yet reliable predictors of therapeutic response remain unavailable. Using single-cell multi-omics profiling of paired pre- and post-treatment tumor and blood samples, we observed that patients responding to IC exhibited significantly higher baseline levels of peripheral blood monocytes, tumor-infiltrating classical monocytes, and APOBEC3A+ monocytes across both compartments compared with non-responders. These associations were independently validated in additional cohorts using routine complete blood count testing and multiplex immunofluorescence analysis of native tumor tissues. Our findings reveal monocyte-related parameters as clinically accessible indicators that link systemic immunity with the tumor microenvironment and hold promise for predicting IC responsiveness in patients with LUSC.

PMID:41912871 | DOI:10.1038/s44321-026-00410-y

A monocyte-centered framework for predicting immunochemotherapy efficacy in lung squamous cell carcinoma patients

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Jiangnan Zhao · Zijin Wang · Manyu Xiao · Yeyuan Zhang · Boxin Liu · Silin Chen · Yiping Tian · Dongqing Lv · Pingli Wang · Hai Song · Yuefeng Wu · Jian Liu · Kai Wang
30 March 2026 at 18:00

EMBO Mol Med. 2026 Mar 30. doi: 10.1038/s44321-026-00410-y. Online ahead of print.

ABSTRACT

Lung cancer is the leading cause of cancer-related mortality worldwide, with lung squamous cell carcinoma (LUSC) comprising 20-30% of cases. Immunochemotherapy (IC) is the standard first-line treatment for advanced LUSC, yet reliable predictors of therapeutic response remain unavailable. Using single-cell multi-omics profiling of paired pre- and post-treatment tumor and blood samples, we observed that patients responding to IC exhibited significantly higher baseline levels of peripheral blood monocytes, tumor-infiltrating classical monocytes, and APOBEC3A+ monocytes across both compartments compared with non-responders. These associations were independently validated in additional cohorts using routine complete blood count testing and multiplex immunofluorescence analysis of native tumor tissues. Our findings reveal monocyte-related parameters as clinically accessible indicators that link systemic immunity with the tumor microenvironment and hold promise for predicting IC responsiveness in patients with LUSC.

PMID:41912871 | DOI:10.1038/s44321-026-00410-y

Received — 17 March 2026 ⏭

MetaKE: Meta-learning Aligned Knowledge Editing via Bi-level Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shuxin Liu · Ou Wu
16 March 2026 at 12:00
arXiv:2603.12677v1 Announce Type: cross Abstract: Knowledge editing (KE) aims to precisely rectify specific knowledge in Large Language Models (LLMs) without disrupting general capabilities. State-of-the-art methods suffer from an open-loop control mismatch. We identify a critical "Semantic-Execution Disconnect": the semantic target is derived independently without feedback from the downstream's feasible region. This misalignment often causes valid semantic targets to fall within the prohibited space, resulting in gradient truncation and editing failure. To bridge this gap, we propose MetaKE (Meta-learning Aligned Knowledge Editing), a new framework that reframes KE as a bi-level optimization problem. Departing from static calculation, MetaKE treats the edit target as a learnable meta-parameter: the upper-level optimizer seeks a feasible target to maximize post-edit performance, while the lower-level solver executes the editing. To address the challenge of differentiating through complex solvers, we derive a Structural Gradient Proxy, which explicitly backpropagates editability constraints to the target learning phase. Theoretical analysis demonstrates that MetaKE automatically aligns the edit direction with the model's feasible manifold. Extensive experiments confirm that MetaKE significantly outperforms strong baselines, offering a new perspective on knowledge editing.

Insulin resistance prediction from wearables and routine blood biomarkers

✇Nature - Issue - nature.com science feeds
By: Ahmed A. Metwally · A. Ali Heydari · Daniel McDuff · Alexandru Solot · Zeinab Esmaeilpour · Anthony Z. Faranesh · Menglian Zhou · Girish Narayanswamy · Maxwell A. Xu · Xin Liu · Yuzhe Yang · David B. Savage · Mark Malhotra · Conor Heneghan · Shwetak Patel · Cathy Speed · Javier L. Prieto
16 March 2026 at 08:00

Nature, Published online: 16 March 2026; doi:10.1038/s41586-026-10179-2

A machine-learning model that integrates data from wearable devices (such as smartwatches) with blood biomarkers and demographic data can predict whether someone has insulin resistance, enabling timely lifestyle interventions to prevent progression to type 2 diabetes.
Received — 11 March 2026 ⏭

Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiaoyang Hou · Junqi Liu · Chence Shi · Xin Liu · Zhi Yang · Jian Tang
10 March 2026 at 12:00
arXiv:2603.06748v1 Announce Type: cross Abstract: Protein sequence design must balance designability, defined as the ability to recover a target backbone, with multiple, often competing, developability properties such as solubility, thermostability, and expression. Existing approaches address these properties through post hoc mutation, inference-time biasing, or retraining on property-specific subsets, yet they are target dependent and demand substantial domain expertise or careful hyperparameter tuning. In this paper, we introduce ProtAlign, a multi-objective preference alignment framework that fine-tunes pretrained inverse folding models to satisfy diverse developability objectives while preserving structural fidelity. ProtAlign employs a semi-online Direct Preference Optimization strategy with a flexible preference margin to mitigate conflicts among competing objectives and constructs preference pairs using in silico property predictors. Applied to the widely used ProteinMPNN backbone, the resulting model MoMPNN enhances developability without compromising designability across tasks including sequence design for CATH 4.3 crystal structures, de novo generated backbones, and real-world binder design scenarios, making it an appealing framework for practical protein sequence design.

How Well Do Multimodal Models Reason on ECG Signals?

✇cs.AI, q-bio.NC updates on arXiv.org
By: Maxwell A. Xu · Harish Haresamudram · Catherine W. Liu · Patrick Langer · Jathurshan Pradeepkumar · Wanting Mao · Sunita J. Ferns · Aradhana Verma · Jimeng Sun · Paul Schmiedmayer · Xin Liu · Daniel McDuff · Emily B. Fox · James M. Rehg
10 March 2026 at 12:00
arXiv:2603.00312v2 Announce Type: replace Abstract: While multimodal large language models offer a promising solution to the "black box" nature of health AI by generating interpretable reasoning traces, verifying the validity of these traces remains a critical challenge. Existing evaluation methods are either unscalable, relying on manual clinician review, or superficial, utilizing proxy metrics (e.g. QA) that fail to capture the semantic correctness of clinical logic. In this work, we introduce a reproducible framework for evaluating reasoning in ECG signals. We propose decomposing reasoning into two distinct, components: (i) Perception, the accurate identification of patterns within the raw signal, and (ii) Deduction, the logical application of domain knowledge to those patterns. To evaluate Perception, we employ an agentic framework that generates code to empirically verify the temporal structures described in the reasoning trace. To evaluate Deduction, we measure the alignment of the model's logic against a structured database of established clinical criteria in a retrieval-based approach. This dual-verification method enables the scalable assessment of "true" reasoning capabilities.
There are no more articles
❌