❌

Normal view

Received — 26 March 2026 ⏭

WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fangyuan Li · Pengfei Li · Shijie Wang · Junqi Gao · Jianxing Liu · Biqing Qi · Yuqiang Li
25 March 2026 at 12:00
arXiv:2603.22352v1 Announce Type: cross Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while corpus-grounded approaches rely on curated data environments. We present \textbf{WIST}, a \textbf{W}eb-grounded \textbf{I}terative \textbf{S}elf-play \textbf{T}ree framework for domain-targeted reasoning improvement that learns directly from the open web without requiring any pre-arranged domain corpus. WIST incrementally expands a domain tree for exploration, and retrieves and cleans path-consistent web corpus to construct a controllable training environment. It then performs Challenger--Solver self-play with verifiable rewards, and feeds learnability signals back to update node posteriors and guide subsequent exploration through an adaptive curriculum. Across four backbones, WIST consistently improves over the base models and typically outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines, with the Overall gains reaching \textbf{+9.8} (\textit{Qwen3-4B-Base}) and \textbf{+9.7} (\textit{OctoThinker-8B}). WIST is also domain-steerable, improving \textit{Qwen3-8B-Base} by \textbf{+14.79} in medicine and \textit{Qwen3-4B-Base} by \textbf{+5.28} on PhyBench. Ablations further confirm the importance of WIST's key components for stable open-web learning. Our Code is available at https://github.com/lfy-123/WIST.

CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Max Fu, Justin Yu, Karim El-Refai, Ethan Kou, Haoru Xue, Huang Huang, Wenli Xiao, Guanzhi Wang, Fei-Fei Li, Guanya Shi, Jiajun Wu, Shankar Sastry, Yuke Zhu, Ken Goldberg, Linxi "Jim" Fan
25 March 2026 at 12:00
arXiv:2603.22435v1 Announce Type: cross Abstract: "Code-as-Policy" considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored. We present CaP-X, an open-access framework for systematically studying Code-as-Policy agents in robot manipulation. At its core is CaP-Gym, an interactive environment in which agents control robots by synthesizing and executing programs that compose perception and control primitives. Building on this foundation, CaP-Bench evaluates frontier language and vision-language models across varying levels of abstraction, interaction, and perceptual grounding. Across 12 models, CaP-Bench reveals a consistent trend: performance improves with human-crafted abstractions but degrades as these priors are removed, exposing a dependence on designer scaffolding. At the same time, we observe that this gap can be mitigated through scaling agentic test-time computation--through multi-turn interaction, structured execution feedback, visual differencing, automatic skill synthesis, and ensembled reasoning--substantially improves robustness even when agents operate over low-level primitives. These findings allow us to derive CaP-Agent0, a training-free framework that recovers human-level reliability on several manipulation tasks in simulation and on real embodiments. We further introduce CaP-RL, showing reinforcement learning with verifiable rewards improves success rates and transfers from sim2real with minimal gap. Together, CaP-X provides a principled, open-access platform for advancing embodied coding agents.

Inactivating <i>SnRK1β1A</i> promotes broad-spectrum disease resistance in rice

✇Nature - Issue - nature.com science feeds
By: Guixin Yuan · Xunli Lu · Xingbin Wang · Mengfei Li · Shiwei Wang · Zhaoxiang Huang · Zhigang Li · Fengrui Zhang · Xin Zhang · Jun Yang · Hailong Guo · Vijai Bhadauria · Wang-Sheng Zhu · Wensheng Zhao · Meng Yuan · Jian-Min Zhou · You-Liang Peng
25 March 2026 at 08:00

Nature, Published online: 25 March 2026; doi:10.1038/s41586-026-10273-5

SnRK1β1A in rice promotes susceptibility to multiple fungal diseases, and disrupting this infection-inducible gene confers broad-spectrum resistance without compromising growth or yield under normal field conditions.
Received — 17 March 2026 ⏭

daVinci-Env: Open SWE Environment Synthesis at Scale

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dayuan Fu · Shenyu Wu · Yunze Wu · Zerui Peng · Yaxing Huang · Jie Sun · Ji Zeng · Mohan Jiang · Lin Zhang · Yukun Li · Jiarui Hu · Liming Liu · Jinlong Hou · Pengfei Liu
16 March 2026 at 12:00
arXiv:2603.13023v1 Announce Type: cross Abstract: Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for iterative code editing, test execution, and solution refinement. However, existing open-source datasets remain limited in scale and repository diversity, while industrial solutions are opaque with unreleased infrastructure, creating a prohibitive barrier for most academic research groups. We present OpenSWE, the largest fully transparent framework for SWE agent training in Python, comprising 45,320 executable Docker environments spanning over 12.8k repositories, with all Dockerfiles, evaluation scripts, and infrastructure fully open-sourced for reproducibility. OpenSWE is built through a multi-agent synthesis pipeline deployed across a 64-node distributed cluster, automating repository exploration, Dockerfile construction, evaluation script generation, and iterative test analysis. Beyond scale, we propose a quality-centric filtering pipeline that characterizes the inherent difficulty of each environment, filtering out instances that are either unsolvable or insufficiently challenging and retaining only those that maximize learning efficiency. With $891K spent on environment construction and an additional $576K on trajectory sampling and difficulty-aware curation, the entire project represents a total investment of approximately $1.47 million, yielding about 13,000 curated trajectories from roughly 9,000 quality guaranteed environments. Extensive experiments validate OpenSWE's effectiveness: OpenSWE-32B and OpenSWE-72B achieve 62.4% and 66.0% on SWE-bench Verified, establishing SOTA among Qwen2.5 series. Moreover, SWE-focused training yields substantial out-of-domain improvements, including up to 12 points on mathematical reasoning and 5 points on science benchmarks, without degrading factual recall.
Received — 14 March 2026 ⏭

Autophagy-centered regulation of PI3K/Akt/mTOR and MAPK signaling by traditional Chinese medicine in gastric cancer

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Lujia Chen · Guonong He · Hongfei Liu
13 March 2026 at 18:00

Tissue Cell. 2026 Mar 10;101:103409. doi: 10.1016/j.tice.2026.103409. Online ahead of print.

ABSTRACT

Gastric cancer (GC) remains a major global health burden, with high incidence and mortality rates, particularly in East Asia, driven by factors such as Helicobacter pylori infection, dietary risks, and genetic predispositions. Conventional treatments like surgery and chemotherapy are limited by resistance, toxicity, and poor outcomes in advanced stages. The PI3K/Akt/mTOR and MAPK signaling pathways are central to GC pathogenesis, promoting proliferation, survival, metabolic reprogramming, epithelial-mesenchymal transition (EMT), and metastasis through aberrations like PIK3CA mutations, PTEN loss, and KRAS alterations. These pathways exhibit extensive crosstalk, contributing to therapeutic resistance. This review explores the regulatory effects of Traditional Chinese Medicine (TCM) on these pathways in GC, grounded in TCM principles such as Qi deficiency, Damp-Heat, and disharmony of the Spleen and Stomach. Single herbal monomers (e.g., curcumin, berberine, resveratrol) inhibit PI3K/Akt/mTOR by upregulating PTEN and suppressing mTOR, inducing autophagy and apoptosis. Classical herbs like Huangqin and Huanglian modulate Akt and ERK phosphorylation, while compound formulas (e.g., Banxia Xiexin Decoction, Sijunzi Decoction) synergistically target both pathways, reversing EMT and chemoresistance. TCM addresses crosstalk by disrupting feedback loops and reducing inflammation, enhancing efficacy in combination with Western therapies like chemotherapy and immunotherapy. Network pharmacology and multi-omics analyses reveal TCM's multitarget mechanisms, aligning with ZHENG-based personalization. Challenges include research variability, standardization issues, and incomplete mechanistic validation. Future directions emphasize high-quality trials, omics integration, and precision TCM for clinical translation. TCM offers low-toxicity, holistic options for integrative GC management, potentially improving survival and quality of life.

PMID:41825157 | DOI:10.1016/j.tice.2026.103409

Autophagy-centered regulation of PI3K/Akt/mTOR and MAPK signaling by traditional Chinese medicine in gastric cancer

✇Omics in Gastric
By: Lujia Chen · Guonong He · Hongfei Liu
13 March 2026 at 18:00

Tissue Cell. 2026 Mar 10;101:103409. doi: 10.1016/j.tice.2026.103409. Online ahead of print.

ABSTRACT

Gastric cancer (GC) remains a major global health burden, with high incidence and mortality rates, particularly in East Asia, driven by factors such as Helicobacter pylori infection, dietary risks, and genetic predispositions. Conventional treatments like surgery and chemotherapy are limited by resistance, toxicity, and poor outcomes in advanced stages. The PI3K/Akt/mTOR and MAPK signaling pathways are central to GC pathogenesis, promoting proliferation, survival, metabolic reprogramming, epithelial-mesenchymal transition (EMT), and metastasis through aberrations like PIK3CA mutations, PTEN loss, and KRAS alterations. These pathways exhibit extensive crosstalk, contributing to therapeutic resistance. This review explores the regulatory effects of Traditional Chinese Medicine (TCM) on these pathways in GC, grounded in TCM principles such as Qi deficiency, Damp-Heat, and disharmony of the Spleen and Stomach. Single herbal monomers (e.g., curcumin, berberine, resveratrol) inhibit PI3K/Akt/mTOR by upregulating PTEN and suppressing mTOR, inducing autophagy and apoptosis. Classical herbs like Huangqin and Huanglian modulate Akt and ERK phosphorylation, while compound formulas (e.g., Banxia Xiexin Decoction, Sijunzi Decoction) synergistically target both pathways, reversing EMT and chemoresistance. TCM addresses crosstalk by disrupting feedback loops and reducing inflammation, enhancing efficacy in combination with Western therapies like chemotherapy and immunotherapy. Network pharmacology and multi-omics analyses reveal TCM's multitarget mechanisms, aligning with ZHENG-based personalization. Challenges include research variability, standardization issues, and incomplete mechanistic validation. Future directions emphasize high-quality trials, omics integration, and precision TCM for clinical translation. TCM offers low-toxicity, holistic options for integrative GC management, potentially improving survival and quality of life.

PMID:41825157 | DOI:10.1016/j.tice.2026.103409

Risk-adaptive therapy guided by dynamic ctDNA in nasopharyngeal carcinoma

✇Nature - Issue - nature.com science feeds
By: Jiawei Lv · Dan-Xue Zheng · Jin-Hui Liang · Ning Zhang · Zu-Lu Ye · Xu-Dong Xu · Melvin. L. K. Chua · Lu-Lu Zhang · Zi-Ming Du · Zi-Chen Zhang · Wen-Fei Li · Ling-Long Tang · Lei Chen · Yan-Ping Mao · Rui Guo · Yu-Pei Chen · Li Lin · Yuan Zhang · Xu Liu · Cheng Xu · Zhi-Xuan Li · Ling-Xin Xu · Pan-Yang Yang · Kun Chen · Deng Bin · Tian-Sheng Gao · Jian-Ye Yan · Lu-Si Chen · Shao Hui Huang · Hong-Yun Zhao · Shu-Bin Hong · Yu-Sheng Jie · Hui-Ling Huang · Xu-Hua Tang · Jing-Ping Yun · Li-Zhi Liu · Li Tian · Hao-Jiang Li · Ji-Bin Li · Guan-Qun Zhou · Jun Ma · Ying Sun
11 March 2026 at 08:00

Nature, Published online: 11 March 2026; doi:10.1038/s41586-026-10244-w

A clinical trial testing whether monitoring ctDNA clearance during treatment for nasopharyngeal cancer could be used to inform decisions about an individual’s subsequent therapeutic programme shows promising results.
Received — 11 March 2026 ⏭

RedSage: A Cybersecurity Generalist LLM

✇cs.AI, q-bio.NC updates on arXiv.org
By: Naufal Suryanto · Muzammal Naseer · Pengfei Li · Syed Talal Wasim · Jinhui Yi · Juergen Gall · Paolo Ceravolo · Ernesto Damiani
10 March 2026 at 12:00
arXiv:2601.22159v2 Announce Type: replace-cross Abstract: Cybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks or on open models lacking domain adaptation. To bridge this gap, we curate 11.8B tokens of cybersecurity-focused continual pretraining data via large-scale web filtering and manual collection of high-quality resources, spanning 28.6K documents across frameworks, offensive techniques, and security tools. Building on this, we design an agentic augmentation pipeline that simulates expert workflows to generate 266K multi-turn cybersecurity samples for supervised fine-tuning. Combined with general open-source LLM data, these resources enable the training of RedSage, an open-source, locally deployable cybersecurity assistant with domain-aware pretraining and post-training. To rigorously evaluate the models, we introduce RedSage-Bench, a benchmark with 30K multiple-choice and 240 open-ended Q&A items covering cybersecurity knowledge, skills, and tool expertise. RedSage is further evaluated on established cybersecurity benchmarks (e.g., CTI-Bench, CyberMetric, SECURE) and general LLM benchmarks to assess broader generalization. At the 8B scale, RedSage achieves consistently better results, surpassing the baseline models by up to +5.59 points on cybersecurity benchmarks and +5.05 points on Open LLM Leaderboard tasks. These findings demonstrate that domain-aware agentic augmentation and pre/post-training can not only enhance cybersecurity-specific expertise but also help to improve general reasoning and instruction-following. All models, datasets, and code are publicly available.
Received — 5 March 2026 ⏭
  • ✇cs.AI, q-bio.NC updates on arXiv.org
  • Efficient Agent Training for Computer Use Yanheng He · Jiahe Jin · Pengfei Liu
    arXiv:2505.13909v2 Announce Type: replace Abstract: Scaling up high-quality trajectory data has long been a critical bottleneck for developing human-like computer use agents. We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale human demonstrations. Starting with just 312 human-annotated computer use trajectories, we further augment them by synthesizing diverse alternative action decisions with Claude 3.7 Sonnet. Trained on these enri
     
  • 🏷️
  • ↗️

Efficient Agent Training for Computer Use

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yanheng He · Jiahe Jin · Pengfei Liu
4 March 2026 at 13:00
arXiv:2505.13909v2 Announce Type: replace Abstract: Scaling up high-quality trajectory data has long been a critical bottleneck for developing human-like computer use agents. We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale human demonstrations. Starting with just 312 human-annotated computer use trajectories, we further augment them by synthesizing diverse alternative action decisions with Claude 3.7 Sonnet. Trained on these enriched trajectories, our PC Agent-E model achieved a remarkable 141 relative improvement, and even surpassed the Claude 3.7 Sonnet by 10% in relative terms on WindowsAgentArena-V2, an improved benchmark we also released. By integrating robust human computer use skills with automated AI data synthesis capabilities, our method not only brought substantial improvements over training on human trajectories alone, but also significantly surpassed direct distillation from Claude 3.7 Sonnet. Code, data and models are available at https://github.com/GAIR-NLP/PC-Agent-E

Reducing Belief Deviation in Reinforcement Learning for Active Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Deyu Zou · Yongqiang Chen · Jianxiang Wang · Haochen Yang · Mufei Li · James Cheng · Pan Li · Yu Gong
4 March 2026 at 13:00
arXiv:2510.12264v2 Announce Type: replace Abstract: Active reasoning requires large language model (LLM) agents to interact with external sources and strategically gather information to solve problems in multiple turns. Central to this process is belief tracking: maintaining an accurate representation of the underlying state and uncertainty in understanding and solving the problem. However, due to limited reasoning capabilities, LLM-based agents often suffer belief deviation: their internal beliefs drift from the true problem state, leading to loss of state awareness and uninformative or repetitive actions. Once this happens, errors compound in the trajectories used for reinforcement learning (RL), leading to misattributed credits and limited exploration. To address this issue, we propose to track belief deviation and develop $\mathbf{T^3}$, a simple yet principled method that detects excessive deviation and truncates training trajectories to suppress uninformative tail effects. Hence, $\mathbf{T^3}$ preserves credits for informative prefixes and systematically improves policy optimization. Across 5 challenging tasks, $\mathbf{T^3}$ consistently enhances training stability and yields performance gains of up to 30 points while cutting token cost by up to 34%. These results highlight belief control as a key principle for building robust LLM agents capable of active reasoning.
Received — 25 February 2026 ⏭

Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yi Yang · Xueqi Li · Yiyang Chen · Jin Song · Yihan Wang · Zipeng Xiao · Jiadi Su · You Qiaoben · Pengfei Liu · Zhijie Deng
24 February 2026 at 13:00
arXiv:2511.16175v2 Announce Type: replace-cross Abstract: Recent advances in Vision-Language-Action (VLA) models demonstrate that visual signals can effectively complement sparse action supervisions. However, letting VLA directly predict high-dimensional visual states can distribute model capacity and incur prohibitive training cost, while compressing visual states into more compact supervisory signals inevitably incurs information bottlenecks. Moreover, existing methods often suffer from poor comprehension and reasoning capabilities due to the neglect of language supervision. This paper introduces Mantis, a novel framework featuring a Disentangled Visual Foresight (DVF) to tackle these issues. Specifically, Mantis decouples visual foresight prediction from the backbone with the combination of meta queries and a diffusion Transformer (DiT) head. With the current visual state provided to the DiT via a residual connection, a simple next-state prediction objective enables the meta queries to automatically capture the latent actions that delineate the visual trajectory, and hence boost the learning of explicit actions. The disentanglement reduces the burden of the VLA backbone, enabling it to maintain comprehension and reasoning capabilities through language supervision. Empirically, pretrained on human manipulation videos, robot demonstrations, and image-text pairs, Mantis achieves a 96.7% success rate on LIBERO benchmark after fine-tuning, surpassing powerful baselines while exhibiting high convergence speed. Real-world evaluations show that Mantis outperforms $\pi_{0.5}$, a leading open-source VLA model, particularly in instruction-following capability, generalization to unseen instructions, and reasoning ability. Code and weights are released to support the open-source community.

Generative Reasoning Re-ranker

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mingfu Liang · Yufei Li · Jay Xu · Kavosh Asadi · Xi Liu · Shuo Gu · Kaushik Rangadurai · Frank Shyu · Shuaiwen Wang · Song Yang · Zhijing Li · Jiang Liu · Mengying Sun · Fei Tian · Xiaohan Wei · Chonglin Sun · Jacob Tao · Shike Mei · Wenlin Chen · Santanu Kolay · Sandeep Pandey · Hamed Firooz · Luke Simon
24 February 2026 at 13:00
arXiv:2602.07774v4 Announce Type: replace-cross Abstract: Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on retrieval and ranking, while the reranking phase, critical for refining final recommendations, is largely overlooked; (2) LLMs are typically used in zero-shot or supervised fine-tuning settings, leaving their reasoning abilities, especially those enhanced through reinforcement learning (RL) and high-quality reasoning data, underexploited; (3) items are commonly represented by non-semantic IDs, creating major scalability challenges in industrial systems with billions of identifiers. To address these gaps, we propose the Generative Reasoning Reranker (GR2), an end-to-end framework with a three-stage training pipeline tailored for reranking. First, a pretrained LLM is mid-trained on semantic IDs encoded from non-semantic IDs via a tokenizer achieving $\ge$99% uniqueness. Next, a stronger larger-scale LLM generates high-quality reasoning traces through carefully designed prompting and rejection sampling, which are used for supervised fine-tuning to impart foundational reasoning skills. Finally, we apply Decoupled Clip and Dynamic sAmpling Policy Optimization (DAPO), enabling scalable RL supervision with verifiable rewards designed specifically for reranking. Experiments on two real-world datasets demonstrate GR2's effectiveness: it surpasses the state-of-the-art OneRec-Think by 2.4% in Recall@5 and 1.3% in NDCG@5. Ablations confirm that advanced reasoning traces yield substantial gains across metrics. We further find that RL reward design is crucial in reranking: LLMs tend to exploit reward hacking by preserving item order, motivating conditional verifiable rewards to mitigate this behavior and optimize reranking performance.
Received — 17 February 2026 ⏭

Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xinjie Shen · Mufei Li · Pan Li
17 February 2026 at 13:00
arXiv:2510.02356v3 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) in embodied agents creates an urgent need to measure their privacy awareness in the physical world. Existing evaluation methods, however, are confined to natural language based scenarios. To bridge this gap, we introduce EAPrivacy, a comprehensive evaluation benchmark designed to quantify the physical-world privacy awareness of LLM-powered agents. EAPrivacy utilizes procedurally generated scenarios across four tiers to test an agent's ability to handle sensitive objects, adapt to changing environments, balance task execution with privacy constraints, and resolve conflicts with social norms. Our measurements reveal a critical deficit in current models. The top-performing model, Gemini 2.5 Pro, achieved only 59\% accuracy in scenarios involving changing physical environments. Furthermore, when a task was accompanied by a privacy request, models prioritized completion over the constraint in up to 86\% of cases. In high-stakes situations pitting privacy against critical social norms, leading models like GPT-4o and Claude-3.5-haiku disregarded the social norm over 15\% of the time. These findings, demonstrated by our benchmark, underscore a fundamental misalignment in LLMs regarding physically grounded privacy and establish the need for more robust, physically-aware alignment. Codes and datasets will be available at https://github.com/Graph-COM/EAPrivacy.
There are no more articles
❌