❌

Normal view

Received — 27 May 2026 ⏭

Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hongbo Jin · Mingnan Zhu · Jingqi Tian · Xu Jiang · Zhongjing Du · Haoran Tang · Siyi Xie · Qiaoman Zhang · Jiayu Ding
26 May 2026 at 12:00
arXiv:2605.25354v1 Announce Type: new Abstract: While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamically extract, internalize, and apply new knowledge from complex, task-specific contexts. Recent evaluations on the CL-Bench reveal a critical capability gap: frontier models solve only 17.2% of context-dependent tasks on average.

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiaqi Liu · Shi Qiu · Mairui Li · Bingzhou Li · Haonian Ji · Siwei Han · Xinyu Ye · Peng Xia · Zihan Dong · Meng Chen · Congyu Zhang · Letian Zhang · Guiming Chen · Haoqin Tu · Xinyu Yang · Lu Feng · Xujiang Zhao · Haifeng Chen · Jiawei Zhou · Xiao Wang · Weitong Zhang · Hongtu Zhu · Yun Li · Jieru Mei · Hongliang Fei · Jiaheng Zhang · Linjie Li · Linjun Zhang · Yuyin Zhou · Sheng Wang · Caiming Xiong · James Zou · Zeyu Zheng · Cihang Xie · Mingyu Ding · Huaxiu Yao
26 May 2026 at 12:00
arXiv:2605.20025v2 Announce Type: replace Abstract: Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across cycles. Existing autonomous research systems often model this process as a linear pipeline: they rely on single-agent reasoning, stop when execution fails, and do not carry experience across runs. We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms: structured multi-agent debate for hypothesis generation and result analysis, a self-healing executor with a \textsc{Pivot}/\textsc{Refine} decision loop that transforms failures into information, verifiable result reporting that prevents fabricated numbers and hallucinated citations, human-in-the-loop collaboration with seven intervention modes spanning full autonomy to step-by-step oversight, and cross-run evolution that converts past mistakes into future safeguards. On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%. A human-in-the-loop ablation across seven intervention modes reveals that precise, targeted collaboration at high-leverage decision points consistently outperforms both full autonomy and exhaustive step-by-step oversight. We position AutoResearchClaw as a research amplifier that augments rather than replaces human scientific judgment. Code is available at https://github.com/aiming-lab/AutoResearchClaw.

hUCMSC-exosomes attenuate acute lung injury by inhibiting ferroptosis in pulmonary microvascular endothelial cells through ribosomal protein RPS11 upregulation

✇Omics In Lung
By: Anyun Ding · Mingou Yan · Yunong Li · Zhongyun Bi · Jingchun Song · Lin Zhao · Renyu Ding
23 May 2026 at 18:00

J Nanobiotechnology. 2026 May 22. doi: 10.1186/s12951-026-04565-1. Online ahead of print.

ABSTRACT

BACKGROUND: Human umbilical cord mesenchymal stem cell-derived exosomes (hUCMSC-Exos) are a promising treatment for acute lung injury (ALI)/acute respiratory distress syndrome (ARDS), but traditional delivery methods have limitations. Therefore, this study presents a noninvasive therapeutic approach for ALI/ARDS, offering new mechanistic insights and identifying potential therapeutic targets.

RESULTS: We established a nebulized LPS-induced ALI model that was characterized by diffuse lung injury and high homogeneity. Following inhalation, hUCMSC-Exos were observed to be internalized by pulmonary microvascular endothelial cells. Analysis revealed that hUCMSC-Exos alleviated ALI by reducing the severity of histological damage, pulmonary oedema, lung inflammation and ferroptosis. Additionally, hUCMSC-Exos improved the mitochondrial function of human pulmonary microvascular endothelial cells (HPMECs) via the transfer of mitochondrial components. Subsequent proteomic sequencing of mitochondria isolated from HPMECs receiving different treatments revealed the significant differential expression of ribosomal proteins among the groups. The most significantly upregulated protein, RPS11, was identified as a key mediator; its knockdown blocked the ability of hUCMSC-Exos to suppress ferroptosis and restore mitochondrial function in HPMECs. Mechanistically, hUCMSC-Exos exert their effects by enhancing mitochondria-encoded protein translation.

CONCLUSIONS: We report a mechanism whereby hUCMSC-Exos upregulate RPS11 to promote mitochondria-encoded protein translation, rescuing mitochondrial function, inhibiting ferroptosis in HPMECs, and ultimately alleviating ALI. Validated across multiple models and supported by multi-omics analyses, our findings collectively establish nebulized hUCMSC-Exos as a promising cell-free therapy targeting mitochondrial homeostasis in HPMECs for the treatment of ALI.

PMID:42174606 | DOI:10.1186/s12951-026-04565-1

Received — 4 April 2026 ⏭

Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiaqi Liu · Zipeng Ling · Shi Qiu · Yanqing Liu · Siwei Han · Peng Xia · Haoqin Tu · Zeyu Zheng · Cihang Xie · Charles Fleming · Mingyu Ding · Huaxiu Yao
3 April 2026 at 12:00
arXiv:2604.01007v2 Announce Type: replace Abstract: AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space spanning architecture, retrieval strategies, prompt engineering, and data pipelines; this space is too large and interconnected for manual exploration or traditional AutoML to explore effectively. We deploy an autonomous research pipeline to discover Omni-SimpleMem, a unified multimodal memory framework for lifelong AI agents. Starting from a na\"ive baseline (F1=0.117 on LoCoMo), the pipeline autonomously executes ${\sim}50$ experiments across two benchmarks, diagnosing failure modes, proposing architectural modifications, and repairing data pipeline bugs, all without human intervention in the inner loop. The resulting system achieves state-of-the-art on both benchmarks, improving F1 by +411% on LoCoMo (0.117$\to$0.598) and +214% on Mem-Gallery (0.254$\to$0.797) relative to the initial configurations. Critically, the most impactful discoveries are not hyperparameter adjustments: bug fixes (+175%), architectural changes (+44%), and prompt engineering (+188% on specific categories) each individually exceed the cumulative contribution of all hyperparameter tuning, demonstrating capabilities fundamentally beyond the reach of traditional AutoML. We provide a taxonomy of six discovery types and identify four properties that make multimodal memory particularly suited for autoresearch, offering guidance for applying autonomous research pipelines to other AI system domains. Code is available at this https://github.com/aiming-lab/SimpleMem.
Received — 2 April 2026 ⏭

DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yi Chen · Yuying Ge · Hui Zhou · Mingyu Ding · Yixiao Ge · Xihui Liu
1 April 2026 at 12:00
arXiv:2603.29844v1 Announce Type: cross Abstract: The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping vision-language features to low-level actions. This paradigm underutilizes the VLM's potential in high-level decision making and introduces training instability, frequently degrading its rich semantic representations. To address these limitations, we introduce DIAL, a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck. Specifically, a VLM-based System-2 performs latent world modeling by synthesizing latent visual foresight within the VLM's native feature space; this foresight explicitly encodes intent and serves as the structural bottleneck. A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions via latent inverse dynamics. To ensure optimization stability, we employ a two-stage training paradigm: a decoupled warmup phase where System-2 learns to predict latent futures while System-1 learns motor control under ground-truth future guidance within a unified feature space, followed by seamless end-to-end joint optimization. This enables action-aware gradients to refine the VLM backbone in a controlled manner, preserving pre-trained knowledge. Extensive experiments on the RoboCasa GR1 Tabletop benchmark show that DIAL establishes a new state-of-the-art, achieving superior performance with 10x fewer demonstrations than prior methods. Furthermore, by leveraging heterogeneous human demonstrations, DIAL learns physically grounded manipulation priors and exhibits robust zero-shot generalization to unseen objects and novel configurations during real-world deployment on a humanoid robot.
Received — 26 March 2026 ⏭

Hijacking ERAD for targeted degradation of transmembrane proteins

✇Cell
By: Haikun Song · Wei Wang · Tingfang Mei · Huiwen Zheng · Keni Ning · Xiaofan Liu · Siulam Cheung · Zhiyuan Cao · Danqi Sheng · Xiaohan Mai · Haoran Zhu · Guankai Guo · Shuaimeng Liu · Rongkai Wei · Qian Wang · Yu Cao · Yu Ding · Yiyan Fei · Rui Liu · Motoyuki Hattori · Chunquan Sheng · Boxun Lu
19 March 2026 at 08:00
Development of an ERAD-hijacking technology overcomes the challenges of current targeted protein degradation approaches to achieve degradation of transmembrane proteins.
Received — 17 February 2026 ⏭

SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chihao Shen · Connor Dilgren · Purva Chiniya · Luke Griffith · Yu Ding · Yizheng Chen
17 February 2026 at 13:00
arXiv:2504.21205v3 Announce Type: replace-cross Abstract: This paper introduces SecRepoBench, a benchmark to evaluate code agents on secure code completion in real-world repositories. SecRepoBench has 318 code completion tasks in 27 C/C++ repositories, covering 15 CWEs. We evaluate 29 standalone LLMs and 15 code agents across 3 state-of-the-art agent frameworks using our benchmark. We find that state-of-the-art LLMs struggle with generating correct and secure code completions. However, code agents significantly outperform standalone LLMs. We show that SecRepoBench is more difficult than the prior state-of-the-art benchmark. Finally, our comprehensive analysis provides insights into potential directions for enhancing the ability of code agents to write correct and secure code in real-world repositories.
There are no more articles
❌