❌

Normal view

Received — 27 May 2026 ⏭

Coupled Variational Reinforcement Learning for Language Model General Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xueru Wen · Jie Lou · Yanjiang Liu · Hongyu Lin · Ben He · Xianpei Han · Le Sun · Yaojie Lu · Debing Zhang
26 May 2026 at 12:00
arXiv:2512.12576v3 Announce Type: replace-cross Abstract: While reinforcement learning has achieved impressive progress in language model reasoning, it is constrained by the requirement for verifiable rewards. Recent verifier-free RL methods address this limitation by utilizing the probabilities that LLMs generate reference answers as reward signals. However, these approaches typically sample reasoning traces conditioned only on the question. This design decouples reasoning-trace sampling from answer information, leading to inefficient exploration and incoherence between traces and final answers. In this paper, we propose \textit{\b{Co}upled \b{V}ariational \b{R}einforcement \b{L}earning} (CoVRL), which bridges variational inference and reinforcement learning by coupling prior and posterior distributions through a hybrid sampling strategy. By constructing and optimizing a composite distribution that integrates these two distributions, CoVRL enables efficient exploration while preserving strong thought-answer coherence. Extensive experiments on mathematical and general reasoning benchmarks show that CoVRL improves performance by 12.4\% over the base model and achieves an additional 2.3\% improvement over state-of-the-art verifier-free RL baselines, providing a principled framework for enhancing the general reasoning capabilities of language models.
Received — 13 April 2026 ⏭

Characterization and regulatory mechanism evaluation of C8orf33 in hepatocellular carcinoma through multiomics profiling

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Wei Gao · Siyi Xing · Mingjiang Liu · Xing Xie · Mei Feng · Zhipeng Quan · Housheng Wang · Zhilong He · Qianxin Hu · Huizhao Su · Shuiping Yu · Zeyuan Li
11 April 2026 at 18:00

Discov Oncol. 2026 Apr 11. doi: 10.1007/s12672-026-04951-z. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) is a major cause of cancer-related mortality. Chromosome 8 open reading frame 33 (C8orf33) has been noted as a potential oncogenic factor in several cancers, but its biological roles and regulatory mechanism in HCC microenvironment remain unknown.

METHODS: We integrated bulk RNA sequencing, single-cell RNA sequencing (scRNA-seq), and spatial transcriptomics (ST) to characterize the expression landscape of C8orf33. We then performed C8orf33 loss-of-function studies in HCC cell lines, including in vitro phenotypic assays and subcutaneous xenografts.

RESULTS: C8orf33 was broadly overexpressed and associated with unfavorable prognosis across multiple Cancers. In HCC, higher C8orf33 aligned with advanced stage and shorter overall survival. C8orf33 knockdown reduced proliferation and migration, impaired tumorigenic capacity, and increased apoptosis. ScRNA-seq analyses identified a malignant population of Epi3 with high C8orf33 expression. Cell-cell communication analysis suggested that C8orf33-high Epi3 state was associated with an enriched MIF-CD74/CXCR4/CD44 signaling program toward macrophage populations with M2-like features. ST analyses further confirmed the colocalization of C8orf33 with malignant features in tumor cores. In Huh7 cells, C8orf33 knockdown was accompanied by reduced mRNA and protein levels of MIF and its receptor components. Consistently, xenografts derived from C8orf33-silenced cells showed lower expression of these MIF-axis components and reduced infiltration of CD163 and CD206-positive macrophages.

CONCLUSION: These results support a tumor-promoting association of C8orf33 in HCC and suggest a potential link to macrophage-associated immunomodulatory features, nominating C8orf33 as a candidate biomarker and therapeutic target.

PMID:41965457 | DOI:10.1007/s12672-026-04951-z

Characterization and regulatory mechanism evaluation of C8orf33 in hepatocellular carcinoma through multiomics profiling

✇Omics in Hepatocellular
By: Wei Gao · Siyi Xing · Mingjiang Liu · Xing Xie · Mei Feng · Zhipeng Quan · Housheng Wang · Zhilong He · Qianxin Hu · Huizhao Su · Shuiping Yu · Zeyuan Li
11 April 2026 at 18:00

Discov Oncol. 2026 Apr 11. doi: 10.1007/s12672-026-04951-z. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) is a major cause of cancer-related mortality. Chromosome 8 open reading frame 33 (C8orf33) has been noted as a potential oncogenic factor in several cancers, but its biological roles and regulatory mechanism in HCC microenvironment remain unknown.

METHODS: We integrated bulk RNA sequencing, single-cell RNA sequencing (scRNA-seq), and spatial transcriptomics (ST) to characterize the expression landscape of C8orf33. We then performed C8orf33 loss-of-function studies in HCC cell lines, including in vitro phenotypic assays and subcutaneous xenografts.

RESULTS: C8orf33 was broadly overexpressed and associated with unfavorable prognosis across multiple Cancers. In HCC, higher C8orf33 aligned with advanced stage and shorter overall survival. C8orf33 knockdown reduced proliferation and migration, impaired tumorigenic capacity, and increased apoptosis. ScRNA-seq analyses identified a malignant population of Epi3 with high C8orf33 expression. Cell-cell communication analysis suggested that C8orf33-high Epi3 state was associated with an enriched MIF-CD74/CXCR4/CD44 signaling program toward macrophage populations with M2-like features. ST analyses further confirmed the colocalization of C8orf33 with malignant features in tumor cores. In Huh7 cells, C8orf33 knockdown was accompanied by reduced mRNA and protein levels of MIF and its receptor components. Consistently, xenografts derived from C8orf33-silenced cells showed lower expression of these MIF-axis components and reduced infiltration of CD163 and CD206-positive macrophages.

CONCLUSION: These results support a tumor-promoting association of C8orf33 in HCC and suggest a potential link to macrophage-associated immunomodulatory features, nominating C8orf33 as a candidate biomarker and therapeutic target.

PMID:41965457 | DOI:10.1007/s12672-026-04951-z

Received — 8 April 2026 ⏭

XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xingrui Wang · Jiang Liu · Chao Huang · Xiaodong Yu · Ze Wang · Ximeng Sun · Jialian Wu · Alan Yuille · Emad Barsoum · Zicheng Liu
7 April 2026 at 12:00
arXiv:2510.15148v2 Announce Type: replace-cross Abstract: Omni-modal large language models (OLLMs) aim to unify audio, vision, and text understanding within a single framework. While existing benchmarks primarily evaluate general cross-modal question-answering ability, it remains unclear whether OLLMs achieve modality-invariant reasoning or exhibit modality-specific biases. We introduce XModBench, a large-scale tri-modal benchmark explicitly designed to measure cross-modal consistency. XModBench comprises 60,828 multiple-choice questions spanning five task families and systematically covers all six modality compositions in question-answer pairs, enabling fine-grained diagnosis of an OLLM's modality-invariant reasoning, modality disparity, and directional imbalance. Experiments show that even the strongest model, Gemini 2.5 Pro, (i) struggles with spatial and temporal reasoning, achieving less than 60% accuracy, (ii) reveals persistent modality disparities, with performance dropping substantially when the same semantic content is conveyed through audio rather than text, and (iii) shows systematic directional imbalance, exhibiting lower consistency when vision serves as context compared to text. These findings indicate that current OLLMs remain far from truly modality-invariant reasoning and position XModBench as a fundamental diagnostic tool for evaluating and improving cross-modal competence. All data and evaluation tools will be available at https://xingruiwang.github.io/projects/XModBench/.
Received — 4 April 2026 ⏭

World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuejiang Liu · Fan Feng · Lingjing Kong · Weifeng Lu · Jinzhou Tang · Kun Zhang · Kevin Murphy · Chelsea Finn · Yilun Du
3 April 2026 at 12:00
arXiv:2604.01985v1 Announce Type: cross Abstract: General-purpose world models promise scalable policy evaluation, optimization, and planning, yet achieving the required level of robustness remains challenging. Unlike policy learning, which primarily focuses on optimal actions, a world model must be reliable over a much broader range of suboptimal actions, which are often insufficiently covered by action-labeled interaction data. To address this challenge, we propose World Action Verifier (WAV), a framework that enables world models to identify their own prediction errors and self-improve. The key idea is to decompose action-conditioned state prediction into two factors -- state plausibility and action reachability -- and verify each separately. We show that these verification problems can be substantially easier than predicting future states due to two underlying asymmetries: the broader availability of action-free data and the lower dimensionality of action-relevant features. Leveraging these asymmetries, we augment a world model with (i) a diverse subgoal generator obtained from video corpora and (ii) a sparse inverse model that infers actions from a subset of state features. By enforcing cycle consistency among generated subgoals, inferred actions, and forward rollouts, WAV provides an effective verification mechanism in under-explored regimes, where existing methods typically fail. Across nine tasks spanning MiniGrid, RoboMimic, and ManiSkill, our method achieves 2x higher sample efficiency while improving downstream policy performance by 18%.
Received — 26 March 2026 ⏭

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 ⏭

AI Agents, Language, Deep Learning and the Next Revolution in Science

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ke Li · Beijiang Liu · Bruce Mellado · Changzheng Yuan · Zhengde Zhang
10 March 2026 at 12:00
arXiv:2603.07940v1 Announce Type: cross Abstract: Modern science is reaching a critical inflection point. Instruments across disciplines, from particle physics and astronomy to genomics and climate modeling, now produce data of such scale, diversity, and interdependence that traditional analytical methods can no longer keep pace. This growing imbalance between data generation and data understanding signals the need for a new scientific paradigm. We propose that intelligent, human-supervised AI agents operating over deep-learning algorithms, represent the next evolution of the scientific method. Built upon large language models and multimodal learning, these agents can interpret scientific intent, design and execute analytical workflows, and ensure traceability through domain-specific languages that preserve human oversight and accountability. Particle physics, a historic incubator of computational innovation, offers the ideal testbed for this transition. At the Institute of High Energy Physics of the Chinese Academy of Sciences, the Dr. Sai system embodies this vision, a multi-agent reasoning framework deployed within collider research at the CEPC. This emerging approach does not replace human scientists but extends their cognitive reach, enabling discovery to scale with complexity and redefining how knowledge itself is produced in the age of intelligent machines. The significance of this paradigm transcends particle physics, offering a blueprint for all data-driven sciences facing the same complexity ceiling.
Received — 25 February 2026 ⏭

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.
There are no more articles
❌