❌

Normal view

Received — 27 May 2026 ⏭

OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search

✇cs.AI, q-bio.NC updates on arXiv.org
By: Erhan Zhang · Yiqun Chen · Zechun Niu · Wei Yang · Xiaochi Wei · Yan Gao · Yi Wu · Yao Hu · Jiaxin Mao
26 May 2026 at 12:00
arXiv:2604.03675v3 Announce Type: replace Abstract: Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm for search agents, yet outcome-only rewards are sparse and provide limited credit assignment for intermediate search actions. Existing process-reward methods therefore seek to densify supervision through proxy signals, external evaluators, or likelihood-based information gain. However, proxy rewards can deviate from the final outcome objective, while fixed evaluators can become stale as the search policy evolves, leading to unreliable process supervision. To address these challenges, we propose OASES, an Outcome-Aligned Search-Evaluation Supervision framework for agentic search. OASES derives outcome-aligned process rewards by evaluating how well each intermediate search state supports answering the original question. It further co-trains the search policy and the state evaluator on policy, allowing the evaluator to adapt to evolving search behavior and provide more reliable process rewards. Experiments on five multi-hop QA benchmarks show that OASES consistently outperforms strong RL baselines, with further analyses confirming the benefits of outcome-aligned process rewards and search-evaluation co-training.

EditCaption: Human-Refined SFT and HAE-DPO for Image Editing Instruction Synthesis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiangyuan Wang · Honghao Cai · Yunhao Bai · Chao Hui · Tianze Zhou · Haohua Chen · Hao Shi · Yuling Wu · Yao Hu · Xu Tang · Yibo Chen · Wei Zhu
26 May 2026 at 12:00
arXiv:2604.08213v2 Announce Type: replace-cross Abstract: High-quality source-target image pairs with precise editing instructions are essential for instruction-guided image editing, yet constructing such training triplets at scale remains costly. Recent pipelines often rely on vision-language models to synthesize editing instructions automatically, but we find that strong VLMs still struggle to describe visual transformations between image pairs. In particular, they exhibit three recurring failure modes: orientation inconsistency, viewpoint ambiguity, and missing fine-grained attributes. In a human evaluation on 400 image pairs, several open-source VLM baselines produce critical-error rates above 47\%, making many synthesized instructions unsuitable for downstream training. To address this, we propose EditCaption, a two-stage post-training pipeline for image editing instruction synthesis. First, we construct a 100K supervised fine-tuning dataset through GLM-based auto-captioning, EditScore filtering, and human refinement. Second, we collect 10K human-annotated preference pairs, where each rejected instruction is labeled with its primary error type and severity. Based on this dataset, we propose Hardness-Adaptive Error-Aware DPO (HAE-DPO), a task-adapted DPO objective that introduces an adaptive margin based on human-labeled severity, failure-mode type, and reference-model hardness. Experiments across three benchmarks demonstrate that our 235B model with SFT+HAE-DPO achieves state-of-the-art performance among open-source and closed models, scoring 4.720 on Eval-400, 4.672 on HQ-Edit, and 4.651 on ByteMorph-Bench -- surpassing Gemini-3-Pro on all three. Human evaluation confirms critical error rates drop from 47.75\% to 17.50\%, with correct rates improving from 41.75\% to 70.25\%, surpassing Gemini-3-Pro (66.00\%).

EBV strain interacts with host HLA to drive nasopharyngeal carcinoma risk

✇Nature - Issue - nature.com science feeds
By: Yanhong Chen · Jingtong Liang · Wanlin Zhang · Xinyu Zhang · Xinyi Zhang · Ching-Yuan Wang · Fei Yao · Shanshan Zhang · Xiang Zhou · Weimin Ye · Ruimei Feng · Yonglin Cai · Zhe Zhang · Mingfang Ji · Qian Cui · Xihong Lin · Jiesen Li · Jialei Xu · Qiuting Zhang · Qinyao Huang · Yingying Cheng · Yanran Luo · Xiaoping Ye · Qisheng Feng · Minzhong Tang · Mu-Sheng Zeng · Yi-Xin Zeng · Zhonghua Liu · Weiwei Zhai · Jianjun Liu · Miao Xu
15 April 2026 at 08:00

Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10416-8

A genome-to-genome association study identifies host and viral risk factors that interact to drive nasopharyngeal carcinoma endemicity in southern China.
Received — 8 April 2026 ⏭

PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training

✇cs.AI, q-bio.NC updates on arXiv.org
By: Erhan Zhang · Yiqun Chen · Zechun Niu · Wei Yang · Xiaochi Wei · Yan Gao · Yi Wu · Yao Hu · Jiaxin Mao
7 April 2026 at 12:00
arXiv:2604.03675v1 Announce Type: new Abstract: In agentic search, large language models (LLMs) are trained to perform multi-turn retrieval and reasoning for complex tasks such as multi-hop question answering (QA). However, current search-based Reinforcement Learning (RL) methods suffer from two core limitations: expensive long-horizon rollouts are under-utilized during training, and supervision is typically available only at the final answer, resulting in severe reward sparsity. We present Prefix-based Rollout reuse for Agentic search with Intermediate Step rEwards (PRAISE), a framework for improving both data efficiency and credit assignment in agentic search training. Given a complete search trajectory, PRAISE extracts prefix states at different search turns, elicits intermediate answers from them, and uses these prefixes both to construct additional training trajectories and to derive step-level rewards from performance differences across prefixes. Our method uses a single shared model for both search policy learning and prefix answer evaluation, enabling joint optimization without extra human annotations or a separate reward model. Experiments on multi-hop QA benchmarks show that PRAISE consistently improves performance over strong baselines.
Received — 2 April 2026 ⏭

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

Received — 26 March 2026 ⏭

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenxuan Huang · Yu Zeng · Qiuchen Wang · Zhen Fang · Shaosheng Cao · Zheng Chu · Qingyu Yin · Shuang Chen · Zhenfei Yin · Lin Chen · Zehui Chen · Xu Tang · Yao Hu · Shaohui Lin · Philip Torr · Feng Zhao · Wanli Ouyang
25 March 2026 at 12:00
arXiv:2601.22060v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowledge, prior work has proposed augmenting MLLMs by ``reasoning-then-tool-call'' for visual and textual search engines to obtain substantial gains on tasks requiring extensive factual information. However, these approaches typically define multimodal search in a naive setting, assuming that a single full-level or entity-level image query and few text query suffices to retrieve the key evidence needed to answer the question, which is unrealistic in real-world scenarios with substantial visual noise. Moreover, they are often limited in the reasoning depth and search breadth, making it difficult to solve complex questions that require aggregating evidence from diverse visual and textual sources. Building on this, we propose Vision-DeepResearch, which proposes one new multimodal deep-research paradigm, i.e., performs multi-turn, multi-entity and multi-scale visual and textual search to robustly hit real-world search engines under heavy noise. Our Vision-DeepResearch supports dozens of reasoning steps and hundreds of engine interactions, while internalizing deep-research capabilities into the MLLM via cold-start supervision and RL training, resulting in a strong end-to-end multimodal deep-research MLLM. It substantially outperforming existing multimodal deep-research MLLMs, and workflows built on strong closed-source foundation model such as GPT-5, Gemini-2.5-pro and Claude-4-Sonnet. The code will be released in https://github.com/Osilly/Vision-DeepResearch.

Effects of multisensory stimulation based on immersive virtual reality in postoperative neuropsychiatric recovery after gynecological laparoscopy

✇npj Digital Medicine
By: Jiang Liu · Yuxiu Liu · Liuna Bi · Li Zhao · Fuchan Hu · Mengyao Huang · Jingyuan Zhang · Xun Zhou · Ting Wang · Shirong Fang · Fengxian Zhang · Yuanjian Song
24 March 2026 at 08:00

npj Digital Medicine, Published online: 24 March 2026; doi:10.1038/s41746-026-02515-7

Effects of multisensory stimulation based on immersive virtual reality in postoperative neuropsychiatric recovery after gynecological laparoscopy
Received — 11 March 2026 ⏭

CryoNet.Refine: A One-step Diffusion Model for Rapid Refinement of Structural Models with Cryo-EM Density Map Restraints

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fuyao Huang · Xiaozhu Yu · Kui Xu · Qiangfeng Cliff Zhang
10 March 2026 at 12:00
arXiv:2602.22263v2 Announce Type: replace-cross Abstract: High-resolution structure determination by cryo-electron microscopy (cryo-EM) requires the accurate fitting of an atomic model into an experimental density map. Traditional refinement pipelines such as Phenix.real_space_refine and Rosetta are computationally expensive, demand extensive manual tuning, and present a significant bottleneck for researchers. We present CryoNet.Refine, an end-to-end deep learning framework that automates and accelerates molecular structure refinement. Our approach utilizes a one-step diffusion model that integrates a density-aware loss function with robust stereochemical restraints, enabling rapid optimization of a structure against experimental data. CryoNet.Refine provides a unified and versatile solution capable of refining protein complexes as well as DNA/RNA-protein complexes. In benchmarks against Phenix.real_space_refine, CryoNet.Refine consistently achieves substantial improvements in both model-map correlation and overall geometric quality metrics. By offering a scalable, automated, and powerful alternative, CryoNet.Refine aims to serve as an essential tool for next-generation cryo-EM structure refinement. Web server: https://cryonet.ai/refine; Source code: https://github.com/kuixu/cryonet.refine.
Received — 25 February 2026 ⏭

One Token Is Enough: Improving Diffusion Language Models with a Sink Token

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zihou Zhang · Zheyong Xie · Li Zhong · Haifeng Liu · Yao Hu · Shaosheng Cao
24 February 2026 at 13:00
arXiv:2601.19657v4 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) have emerged as a compelling alternative to autoregressive approaches, enabling parallel text generation with competitive performance. Despite these advantages, there is a critical instability in DLMs: the moving sink phenomenon. Our analysis indicates that sink tokens exhibit low-norm representations in the Transformer's value space, and that the moving sink phenomenon serves as a protective mechanism in DLMs to prevent excessive information mixing. However, their unpredictable positions across diffusion steps undermine inference robustness. To resolve this, we propose a simple but effective extra sink token implemented via a modified attention mask. Specifically, we introduce a special token constrained to attend solely to itself, while remaining globally visible to all other tokens. Experimental results demonstrate that introducing a single extra token stabilizes attention sinks, substantially improving model performance. Crucially, further analysis confirms that the effectiveness of this token is independent of its position and characterized by negligible semantic content, validating its role as a robust and dedicated structural sink.
There are no more articles
❌