❌

Normal view

Received — 4 April 2026 ⏭

DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval

✇cs.AI, q-bio.NC updates on arXiv.org
By: Duolin Sun · Meixiu Long · Dan Yang · Junjie Wang · Yecheng Luo · Yue Shen · Jian Wang · Hualei Zhou · Chunxiao Guo · Peng Wei · Jiahai Wang · Jinjie Gu
3 April 2026 at 12:00
arXiv:2508.07995v5 Announce Type: replace-cross Abstract: Retrieval-augmented generation has achieved strong performance on knowledge-intensive tasks where query-document relevance can be identified through direct lexical or semantic matches. However, many real-world queries involve abstract reasoning, analogical thinking, or multi-step inference, which existing retrievers often struggle to capture. To address this challenge, we present DIVER, a retrieval pipeline designed for reasoning-intensive information retrieval. It consists of four components. The document preprocessing stage enhances readability and preserves content by cleaning noisy texts and segmenting long documents. The query expansion stage leverages large language models to iteratively refine user queries with explicit reasoning and evidence from retrieved documents. The retrieval stage employs a model fine-tuned on synthetic data spanning medical and mathematical domains, along with hard negatives, enabling effective handling of reasoning-intensive queries. Finally, the reranking stage combines pointwise and listwise strategies to produce both fine-grained and globally consistent rankings. On the BRIGHT benchmark, DIVER achieves state-of-the-art nDCG@10 scores of 46.8 overall and 31.9 on original queries, consistently outperforming competitive reasoning-aware models. These results demonstrate the effectiveness of reasoning-aware retrieval strategies in complex real-world tasks.
Received — 2 April 2026 ⏭

Ophiopogon japonicus polysaccharide ameliorates pulmonary fibrosis via gut microbiota-metabolite crosstalk

✇Omics In Lung
By: Pei-Pei Zhang · Ming-Yang Cui · Yue Shen · Bo Han · Wei Yu · Tian-Tian Wei · Ke-Wu Zeng · Peng-Fei Tu
30 March 2026 at 18:00

Microb Pathog. 2026 Mar 28;215:108464. doi: 10.1016/j.micpath.2026.108464. Online ahead of print.

ABSTRACT

Despite the clinical application of Ophiopogon japonicus in idiopathic pulmonary fibrosis (PF), its key anti-fibrotic components and underlying mechanisms remain poorly defined. Using a bleomycin-induced murine PF model, we systematically compared the efficacy of the total extract (OJTE), polysaccharides (OJTP), saponins (OJTS), and flavonoids (OJTF). The active component was further investigated via integrated metagenomics and metabolomics (serum/feces) to decipher the gut-lung axis mechanism. All O. japonicus components attenuated lung injury and collagen deposition, with OJTP demonstrating the most potent efficacy (reducing lung hydroxyproline content by 42.12% (p < 0.01) compared to the model group). Multi-omics analysis revealed that OJTP remodeled the gut microbiota, notably enriching probiotic strains such as Muribaculaceae bacterium (log2FC = 2.17) and Duncaniella muricolitica (log2FC = 2.06), as well as the polysaccharide-utilizing species Prevotella sp. MGM2 (log2FC = 2.79). Concomitantly, OJTP significantly altered host metabolism, upregulating key metabolites including urobilinogen (p < 0.0001) and 5-amino valeric acid betaine (5-AVAB, p < 0.002). These metabolites are implicated in porphyrin and amino acid metabolism, respectively. Correlation networks further established strong associations between these OJTP-modulated microbes and metabolites. Our study first identifies OJTP as the primary bioactive component of O. japonicus against PF. We propose a novel trans-organ mechanism wherein OJTP ameliorates PF via orchestrating a "gut microbiota-metabolite" axis, highlighting the therapeutic potential of targeting polysaccharide-probiotic synergy.

PMID:41912071 | DOI:10.1016/j.micpath.2026.108464

Ophiopogon japonicus Polysaccharide Ameliorates Pulmonary Fibrosis via Gut Microbiota-Metabolite Crosstalk

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Pei-Pei Zhang · Ming-Yang Cui · Yue Shen · Bo Han · Wei Yu · Tian-Tian Wei · Ke-Wu Zeng · Peng-Fei Tu
30 March 2026 at 18:00

Microb Pathog. 2026 Mar 28:108464. doi: 10.1016/j.micpath.2026.108464. Online ahead of print.

ABSTRACT

Despite the clinical application of Ophiopogon japonicus in idiopathic pulmonary fibrosis (PF), its key anti-fibrotic components and underlying mechanisms remain poorly defined. Using a bleomycin-induced murine PF model, we systematically compared the efficacy of the total extract (OJTE), polysaccharides (OJTP), saponins (OJTS), and flavonoids (OJTF). The active component was further investigated via integrated metagenomics and metabolomics (serum/feces) to decipher the gut-lung axis mechanism. All O. japonicus components attenuated lung injury and collagen deposition, with OJTP demonstrating the most potent efficacy (reducing lung hydroxyproline content by 42.12% (p < 0.01) compared to the model group). Multi-omics analysis revealed that OJTP remodeled the gut microbiota, notably enriching probiotic strains such as Muribaculaceae bacterium (log2FC = 2.17) and Duncaniella muricolitica (log2FC = 2.06), as well as the polysaccharide-utilizing species Prevotella sp. MGM2 (log2FC = 2.79). Concomitantly, OJTP significantly altered host metabolism, upregulating key metabolites including urobilinogen (p < 0.0001) and 5-amino valeric acid betaine (5-AVAB, p < 0.002). These metabolites are implicated in porphyrin and amino acid metabolism, respectively. Correlation networks further established strong associations between these OJTP-modulated microbes and metabolites. Our study first identifies OJTP as the primary bioactive component of O. japonicus against PF. We propose a novel trans-organ mechanism wherein OJTP ameliorates PF via orchestrating a "gut microbiota-metabolite" axis, highlighting the therapeutic potential of targeting polysaccharide-probiotic synergy.

PMID:41912071 | DOI:10.1016/j.micpath.2026.108464

Received — 5 March 2026 ⏭

See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zongru Wu · Rui Mao · Zhiyuan Tian · Pengzhou Cheng · Tianjie Ju · Zheng Wu · Lingzhong Dong · Haiyue Sheng · Zhuosheng Zhang · Gongshen Liu
5 March 2026 at 13:00
arXiv:2509.13615v4 Announce Type: replace Abstract: The advent of multimodal agents facilitates effective interaction within graphical user interface (GUI), especially in ubiquitous GUI control. However, their inability to reliably execute toggle control instructions remains a key bottleneck. To investigate this, we construct a state control benchmark with binary toggle instructions derived from public datasets. Evaluation results of existing agents demonstrate their notable unreliability, particularly when the current toggle state already matches the desired state. To address the challenge, we propose State-aware Reasoning (StaR), a multimodal reasoning method that enables agents to perceive the current toggle state, infer the desired state from the instruction, and act accordingly. Experiments on four multimodal agents demonstrate that StaR can improve toggle instruction execution accuracy by over 30\%. Further evaluations on three public agentic benchmarks show that StaR also enhances general agentic task performance. Finally, evaluations on a dynamic environment highlight the potential of StaR for real-world applications. Code and benchmark: https://github.com/ZrW00/StaR.

See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zongru Wu · Rui Mao · Zhiyuan Tian · Pengzhou Cheng · Tianjie Ju · Zheng Wu · Lingzhong Dong · Haiyue Sheng · Zhuosheng Zhang · Gongshen Liu
4 March 2026 at 13:00
arXiv:2509.13615v3 Announce Type: replace Abstract: The advent of multimodal agents facilitates effective interaction within graphical user interface (GUI), especially in ubiquitous GUI control. However, their inability to reliably execute toggle control instructions remains a key bottleneck. To investigate this, we construct a state control benchmark with binary toggle instructions derived from public datasets. Evaluation results of existing agents demonstrate their notable unreliability, particularly when the current toggle state already matches the desired state. To address the challenge, we propose State-aware Reasoning (StaR), a multimodal reasoning method that enables agents to perceive the current toggle state, infer the desired state from the instruction, and act accordingly. Experiments on four multimodal agents demonstrate that StaR can improve toggle instruction execution accuracy by over 30\%. Further evaluations on three public agentic benchmarks show that StaR also enhances general agentic task performance. Finally, evaluations on a dynamic environment highlight the potential of StaR for real-world applications. Code and benchmark: https://github.com/ZrW00/StaR.

MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Siqi Ma · Jiajie Huang · Fan Zhang · Yue Shen · Jinlin Wu · Guohui Fan · Zhu Zhang · Zelin Zang
4 March 2026 at 13:00
arXiv:2509.23725v3 Announce Type: replace Abstract: Answering complex medical questions requires not only domain expertise and patient-specific information, but also structured and multi-perspective reasoning. Existing multi-agent approaches often rely on fixed roles or shallow interaction prompts, limiting their ability to detect and resolve fine-grained logical inconsistencies. To address this, we propose \textsc{MedLA}, a logic-driven multi-agent framework built on large language models. Each agent organizes its reasoning process into an explicit logical tree based on syllogistic triads (major premise, minor premise, and conclusion), enabling transparent inference and premise-level alignment. Agents engage in a multi-round, graph-guided discussion to compare and iteratively refine their logic trees, achieving consensus through error correction and contradiction resolution. We demonstrate that \textsc{MedLA} consistently outperforms both static role-based systems and single-agent baselines on challenging benchmarks such as MedDDx and standard medical QA tasks. Furthermore, \textsc{MedLA} scales effectively across both open-source and commercial LLM backbones, achieving state-of-the-art performance and offering a generalizable paradigm for trustworthy medical reasoning.
There are no more articles
❌