❌

Reading view

↗️

The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Oleg Romanchuk Β· Roman Bondar
arXiv:2601.15059v1 Announce Type: new Abstract: Modern CI/CD pipelines integrating agent-generated code exhibit a structural failure in responsibility attribution. Decisions are executed through formally correct approval processes, yet no entity possesses both the authority to approve those decisions and the epistemic capacity to meaningfully understand their basis. We define this condition as responsibility vacuum: a state in which decisions occur, but responsibility cannot be attributed because authority and verification capacity do not coincide. We show that this is not a process deviation or technical defect, but a structural property of deployments where decision generation throughput exceeds bounded human verification capacity. We identify a scaling limit under standard deployment assumptions, including parallel agent generation, CI-based validation, and individualized human approval gates. Beyond a throughput threshold, verification ceases to function as a decision criterion and is replaced by ritualized approval based on proxy signals. Personalized responsibility becomes structurally unattainable in this regime. We further characterize a CI amplification dynamic, whereby increasing automated validation coverage raises proxy signal density without restoring human capacity. Under fixed time and attention constraints, this accelerates cognitive offloading in the broad sense and widens the gap between formal approval and epistemic understanding. Additional automation therefore amplifies, rather than mitigates, the responsibility vacuum. We conclude that unless organizations explicitly redesign decision boundaries or reassign responsibility away from individual decisions toward batch- or system-level ownership, responsibility vacuum remains an invisible but persistent failure mode in scaled agent deployments.
  •  
  • ↗️
↗️

Towards Execution-Grounded Automated AI Research

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Chenglei Si Β· Zitong Yang Β· Yejin Choi Β· Emmanuel Cand\`es Β· Diyi Yang Β· Tatsunori Hashimoto
arXiv:2601.14525v1 Announce Type: cross Abstract: Automated AI research holds great potential to accelerate scientific discovery. However, current LLMs often generate plausible-looking but ineffective ideas. Execution grounding may help, but it is unclear whether automated execution is feasible and whether LLMs can learn from the execution feedback. To investigate these, we first build an automated executor to implement ideas and launch large-scale parallel GPU experiments to verify their effectiveness. We then convert two realistic research problems - LLM pre-training and post-training - into execution environments and demonstrate that our automated executor can implement a large fraction of the ideas sampled from frontier LLMs. We analyze two methods to learn from the execution feedback: evolutionary search and reinforcement learning. Execution-guided evolutionary search is sample-efficient: it finds a method that significantly outperforms the GRPO baseline (69.4% vs 48.0%) on post-training, and finds a pre-training recipe that outperforms the nanoGPT baseline (19.7 minutes vs 35.9 minutes) on pre-training, all within just ten search epochs. Frontier LLMs often generate meaningful algorithmic ideas during search, but they tend to saturate early and only occasionally exhibit scaling trends. Reinforcement learning from execution reward, on the other hand, suffers from mode collapse. It successfully improves the average reward of the ideator model but not the upper-bound, due to models converging on simple ideas. We thoroughly analyze the executed ideas and training dynamics to facilitate future efforts towards execution-grounded automated AI research.
  •  
  • ↗️
↗️

Automated Rubrics for Reliable Evaluation of Medical Dialogue Systems

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Yinzhu Chen Β· Abdine Maiga Β· Hossein A. Rahmani Β· Emine Yilmaz
arXiv:2601.15161v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are particularly challenging as they often manifest as subtle clinical errors that evade detection by generic metrics, while expert-authored fine-grained rubrics remain costly to construct and difficult to scale. In this paper, we propose a retrieval-augmented multi-agent framework designed to automate the generation of instance-specific evaluation rubrics. Our approach grounds evaluation in authoritative medical evidence by decomposing retrieved content into atomic facts and synthesizing them with user interaction constraints to form verifiable, fine-grained evaluation criteria. Evaluated on HealthBench, our framework achieves a Clinical Intent Alignment (CIA) score of 60.12%, a statistically significant improvement over the GPT-4o baseline (55.16%). In discriminative tests, our rubrics yield a mean score delta ($\mu_{\Delta} = 8.658$) and an AUROC of 0.977, nearly doubling the quality separation achieved by GPT-4o baseline (4.972). Beyond evaluation, our rubrics effectively guide response refinement, improving quality by 9.2% (from 59.0% to 68.2%). This provides a scalable and transparent foundation for both evaluating and improving medical LLMs. The code is available at https://anonymous.4open.science/r/Automated-Rubric-Generation-AF3C/.
  •  
  • ↗️
↗️

Towards AI Transparency and Accountability: A Global Framework for Exchanging Information on AI Systems

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Warren Buckley Β· Adrian Byrne Β· Nicholas Perello Β· Cyrus Cousins Β· Taha Yasseri Β· Yair Zick Β· Przemyslaw Grabowicz
arXiv:2307.13658v3 Announce Type: replace-cross Abstract: We propose that future AI transparency and accountability regulations are based on an open global standard for exchanging information about AI systems, which allows co-existence of potentially conflicting local regulations. Then, we discuss key components of a lightweight and effective AI transparency and/or accountability regulation. To prevent overregulation, the proposed approach encourages collaboration between regulators and industry to create a scalable and cost-efficient mutually beneficial solution. This includes using automated assessments and benchmarks with results transparently communicated through AI cards in an open AI register to facilitate meaningful public comparisons of competing AI systems. Such AI cards should report standardized measures tailored to the specific high-risk applications of AI systems and could be used for conformity assessments under AI transparency and accountability policies such as the European Union's AI Act.
  •  
  • ↗️
↗️

PPGFlowECG: Latent Rectified Flow with Cross-Modal Encoding for PPG-Guided ECG Generation and Cardiovascular Disease Detection

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Xiaocheng Fang Β· Jiarui Jin Β· Haoyu Wang Β· Che Liu Β· Jieyi Cai Β· Yujie Xiao Β· Guangkun Nie Β· Bo Liu Β· Shun Huang Β· Hongyan Li Β· Shenda Hong
arXiv:2509.19774v2 Announce Type: replace-cross Abstract: Electrocardiography (ECG) is the clinical gold standard for cardiovascular disease (CVD) assessment, yet continuous monitoring is constrained by the need for dedicated hardware and trained personnel. Photoplethysmography (PPG) is ubiquitous in wearable devices and readily scalable, but it lacks electrophysiological specificity, limiting diagnostic reliability. While generative methods aim to translate PPG into clinically useful ECG signals, existing approaches are limited by the misalignment of physiological semantics in generative models and the complexity of modeling in high-dimensional signals. To address these limitations, we propose PPGFlowECG, a two-stage framework that aligns PPG and ECG in a shared latent space using the CardioAlign Encoder and then synthesizes ECGs with latent rectified flow. We further provide a formal analysis of this coupling, showing that the CardioAlign Encoder is necessary to guarantee stable and semantically consistent ECG synthesis under our formulation. Extensive experiments on four datasets demonstrate improved synthesis fidelity and downstream diagnostic utility. These results indicate that PPGFlowECG supports scalable, wearable-first CVD screening when standard ECG acquisition is unavailable.
  •  
  • ↗️
↗️

Large language models improve transferability of electronic health record-based predictions across countries and coding systems

βœ‡npj Digital Medicine
By: Matthias Kirchler Β· Matteo Ferro Β· Veronica Lorenzini Β· Robin P. van de Water Β· Andrea Ganna Β· Christoph Lippert

npj Digital Medicine, Published online: 22 January 2026; doi:10.1038/s41746-026-02363-5

Large language models improve transferability of electronic health record-based predictions across countries and coding systems
  •  
  • ↗️
↗️

Multimodal AI generates virtual population for tumor microenvironment modeling

βœ‡Cell
By: Jeya Maria Jose Valanarasu Β· Hanwen Xu Β· Naoto Usuyama Β· Chanwoo Kim Β· Cliff Wong Β· Peniel Argaw Β· Racheli Ben Shimol Β· Angela Crabtree Β· Kevin Matlock Β· Alexandra Q. Bartlett Β· Jaspreet Bagga Β· Yu Gu Β· Sheng Zhang Β· Tristan Naumann Β· Bernard A. Fox Β· Bill Wright Β· Ari Robicsek Β· Brian Piening Β· Carlo Bifulco Β· Sheng Wang Β· Hoifung Poon
GigaTIME leverages multimodal AI to generate virtual multiplex immunofluorescence (mIF) profiles from standard H&E slides, enabling comprehensive tumor immune microenvironment modeling across a large (>14,000) and diverse patient population. This virtual approach unlocks new opportunities for large-scale clinical discoveries that were previously hindered by the scarcity of mIF data.
  •  
  • ↗️
↗️

Research progress in diagnosis and treatment of pancreatic cancer with mismatch repair and microsatellite instability

βœ‡(Multiomics OR Omics) AND (Pancreatic)
By: Hang Yin Β· Yong Liu Β· Jiatong Chen Β· Zhuang Li Β· Yue Pan Β· Feng Zhu

Clin Transl Oncol. 2026 Jan 21. doi: 10.1007/s12094-025-04214-3. Online ahead of print.

ABSTRACT

Pancreatic cancer (PC), predominantly pancreatic ductal adenocarcinoma, remains one of the most lethal malignancies, largely due to late diagnosis and intrinsic resistance to conventional therapies. In recent years, mismatch repair deficiency (dMMR) and microsatellite instability-high (MSI-H) have emerged as clinically actionable biomarkers in a small but distinct subset of PC, accounting for approximately 1-2% of cases. These tumors display unique molecular characteristics, including a high prevalence of wild-type KRAS and TP53, elevated tumor mutational burden, and recurrent kinase fusions, which together confer enhanced immunogenicity and increased sensitivity to immune checkpoint inhibitors (ICIs). In addition to their therapeutic relevance, dMMR/MSI-H status has important diagnostic implications for the identification of Lynch syndrome-associated pancreatic cancers, informing genetic counseling and familial risk assessment. This review summarizes current understanding of the molecular basis of mismatch repair deficiency and microsatellite instability in PC, evaluates available diagnostic approaches such as immunohistochemistry, polymerase chain reaction, and next-generation sequencing, and discusses the prognostic and predictive significance of dMMR/MSI-H status. Emerging clinical evidence supporting the use of ICIs in selected patients across neoadjuvant, adjuvant, and advanced disease settings is also reviewed, along with challenges related to assay discordance, tumor heterogeneity, and immunotherapy resistance. Finally, future directions are highlighted, emphasizing the need for standardized testing algorithms, integration of multi-omics and spatial profiling technologies, and prospective clinical studies to optimize precision treatment strategies for this rare but clinically meaningful subtype of pancreatic cancer.

PMID:41563663 | DOI:10.1007/s12094-025-04214-3

  •  
  • ↗️
↗️

United multi-omics and machine learning refine regulatory T cell-defined hepatocellular carcinoma subtypes

βœ‡Omics in Hepatocellular
By: Wanli Zhang Β· Chengdong Liu Β· Aishun Jin Β· Meiying Shen

iScience. 2025 Dec 3;29(1):114328. doi: 10.1016/j.isci.2025.114328. eCollection 2026 Jan 16.

ABSTRACT

Hepatocellular carcinoma (HCC) is highly heterogeneous and aggressive, and the absence of precision individual treatment regimen enables repeated immune escape. Exploiting regulatory T cell (Treg) marker genes as key classifiers, we used 10 clustering algorithms to integrate the multi-omics HCC patient data and combined them with 10 machine learning (ML) algorithms to delineate molecular subtypes predictive of prognosis and immune response. We identified two cancer subtypes (CSs) that are associated with prognosis, with the second subtype (CS2) showing the most favorable prognostic outcomes. Subsequently, 9 key genes were screened for HCC model scoring, stratifying patients into low-risk (good prognosis, responsive to immunotherapy) and high-risk (poor outcome, not responsive to immunotherapy) groups. The high-risk group may be effective against the mTOR inhibitor AZD8055. Comprehensive multi-omics data and multiple ML algorithms offer key insights into HCC occurrence and evolution, with model scores guiding patient prognosis and treatment clinically.

PMID:41561382 | PMC:PMC12814435 | DOI:10.1016/j.isci.2025.114328

  •  
  • ↗️
↗️

Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Gourab K Patro Β· Himanshi Agrawal Β· Himanshu Gharat Β· Supriya Panigrahi Β· Nim Sherpa Β· Vishal Vaddina Β· Dagnachew Birru
arXiv:2601.13122v1 Announce Type: new Abstract: Modern general-purpose AI systems made using large language and vision models, are capable of performing a range of tasks like writing text articles, generating and debugging codes, querying databases, and translating from one language to another, which has made them quite popular across industries. However, there are risks like hallucinations, toxicity, and stereotypes in their output that make them untrustworthy. We review various risks and vulnerabilities of modern general-purpose AI along eight widely accepted responsible AI (RAI) principles (fairness, privacy, explainability, robustness, safety, truthfulness, governance, and sustainability) and compare how they are non-existent or less severe and easily mitigable in traditional task-specific counterparts. We argue that this is due to the non-deterministically high Degree of Freedom in output (DoFo) of general-purpose AI (unlike the deterministically constant or low DoFo of traditional task-specific AI systems), and there is a need to rethink our approach to RAI for general-purpose AI. Following this, we derive C2V2 (Control, Consistency, Value, Veracity) desiderata to meet the RAI requirements for future general-purpose AI systems, and discuss how recent efforts in AI alignment, retrieval-augmented generation, reasoning enhancements, etc. fare along one or more of the desiderata. We believe that the goal of developing responsible general-purpose AI can be achieved by formally modeling application- or domain-dependent RAI requirements along C2V2 dimensions, and taking a system design approach to suitably combine various techniques to meet the desiderata.
  •  
  • ↗️
↗️

DeepEvidence: Empowering Biomedical Discovery with Deep Knowledge Graph Research

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Zifeng Wang Β· Zheng Chen Β· Ziwei Yang Β· Xuan Wang Β· Qiao Jin Β· Yifan Peng Β· Zhiyong Lu Β· Jimeng Sun
arXiv:2601.11560v1 Announce Type: cross Abstract: Biomedical knowledge graphs (KGs) encode vast, heterogeneous information spanning literature, genes, pathways, drugs, diseases, and clinical trials, but leveraging them collectively for scientific discovery remains difficult. Their structural differences, continual evolution, and limited cross-resource alignment require substantial manual integration, limiting the depth and scale of knowledge exploration. We introduce DeepEvidence, an AI-agent framework designed to perform Deep Research across various heterogeneous biomedical KGs. Unlike generic Deep Research systems that rely primarily on internet-scale text, DeepEvidence incorporates specialized knowledge-graph tooling and coordinated exploration strategies to systematically bridge heterogeneous resources. At its core is an orchestrator that directs two complementary agents: Breadth-First ReSearch (BFRS) for broad, multi-graph entity search, and Depth-First ReSearch (DFRS) for multi-hop, evidence-focused reasoning. An internal, incrementally built evidence graph provides a structured record of retrieved entities, relations, and supporting evidence. To operate at scale, DeepEvidence includes unified interfaces for querying diverse biomedical APIs and an execution sandbox that enables programmatic data retrieval, extraction, and analysis. Across established deep-reasoning benchmarks and four key stages of the biomedical discovery lifecycle: drug discovery, pre-clinical experimentation, clinical trial development, and evidence-based medicine, DeepEvidence demonstrates substantial gains in systematic exploration and evidence synthesis. These results highlight the potential of knowledge-graph-driven Deep Research to accelerate biomedical discovery.
  •  
  • ↗️
↗️

Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Sravanthi Machcha Β· Sushrita Yerra Β· Sahil Gupta Β· Aishwarya Sahoo Β· Sharmin Sultana Β· Hong Yu Β· Zonghai Yao
arXiv:2601.12471v1 Announce Type: cross Abstract: Current evaluation of large language models (LLMs) overwhelmingly prioritizes accuracy; however, in real-world and safety-critical applications, the ability to abstain when uncertain is equally vital for trustworthy deployment. We introduce MedAbstain, a unified benchmark and evaluation protocol for abstention in medical multiple-choice question answering (MCQA) -- a discrete-choice setting that generalizes to agentic action selection -- integrating conformal prediction, adversarial question perturbations, and explicit abstention options. Our systematic evaluation of both open- and closed-source LLMs reveals that even state-of-the-art, high-accuracy models often fail to abstain with uncertain. Notably, providing explicit abstention options consistently increases model uncertainty and safer abstention, far more than input perturbations, while scaling model size or advanced prompting brings little improvement. These findings highlight the central role of abstention mechanisms for trustworthy LLM deployment and offer practical guidance for improving safety in high-stakes applications.
  •  
  • ↗️
↗️

A Cloud-based Multi-Agentic Workflow for Science

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Anurag Acharya Β· Timothy Vega Β· Rizwan A. Ashraf Β· Anshu Sharma Β· Derek Parker Β· Robert Rallo
arXiv:2601.12607v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become ubiquitous across various scientific domains, their lack of ability to perform complex tasks like running simulations or to make complex decisions limits their utility. LLM-based agents bridge this gap due to their ability to call external resources and tools and thus are now rapidly gaining popularity. However, coming up with a workflow that can balance the models, cloud providers, and external resources is very challenging, making implementing an agentic system more of a hindrance than a help. In this work, we present a domain-agnostic, model-independent workflow for an agentic framework that can act as a scientific assistant while being run entirely on cloud. Built with a supervisor agent marshaling an array of agents with individual capabilities, our framework brings together straightforward tasks like literature review and data analysis with more complex ones like simulation runs. We describe the framework here in full, including a proof-of-concept system we built to accelerate the study of Catalysts, which is highly important in the field of Chemistry and Material Science. We report the cost to operate and use this framework, including the breakdown of the cost by services use. We also evaluate our system on a custom-curated synthetic benchmark and a popular Chemistry benchmark, and also perform expert validation of the system. The results show that our system is able to route the task to the correct agent 90% of the time and successfully complete the assigned task 97.5% of the time for the synthetic tasks and 91% of the time for real-world tasks, while still achieving better or comparable accuracy to most frontier models, showing that this is a viable framework for other scientific domains to replicate.
  •  
  • ↗️
↗️

SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Xiaohan Huang Β· Meng Xiao Β· Chuan Qin Β· Qingqing Long Β· Jinmiao Chen Β· Yuanchun Zhou Β· Hengshu Zhu
arXiv:2601.12805v1 Announce Type: cross Abstract: Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks. However, their ability to reliably reason from gene-level knowledge to functional understanding, However, their ability to reliably reason from gene-level knowledge to functional understanding, a core requirement for knowledge-enhanced cell atlas interpretation, remains largely underexplored. To address this gap, we introduce SciHorizon-GENE, a large-scale gene-centric benchmark constructed from authoritative biological databases. The benchmark integrates curated knowledge for over 190K human genes and comprises more than 540K questions covering diverse gene-to-function reasoning scenarios relevant to cell type annotation, functional interpretation, and mechanism-oriented analysis. Motivated by behavioral patterns observed in preliminary examinations, SciHorizon-GENE evaluates LLMs along four biologically critical perspectives: research attention sensitivity, hallucination tendency, answer completeness, and literature influence, explicitly targeting failure modes that limit the safe adoption of LLMs in biological interpretation pipelines. We systematically evaluate a wide range of state-of-the-art general-purpose and biomedical LLMs, revealing substantial heterogeneity in gene-level reasoning capabilities and persistent challenges in generating faithful, complete, and literature-grounded functional interpretations. Our benchmark establishes a systematic foundation for analyzing LLM behavior at the gene scale and offers insights for model selection and development, with direct relevance to knowledge-enhanced biological interpretation.
  •  
  • ↗️
↗️

SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Tim Baumg\"artner, Iryna Gurevych
arXiv:2601.12910v1 Announce Type: cross Abstract: We present SciCoQA, a dataset for detecting discrepancies between scientific publications and their codebases to ensure faithful implementations. We construct SciCoQA from GitHub issues and reproducibility papers, and to scale our dataset, we propose a synthetic data generation method for constructing paper-code discrepancies. We analyze the paper-code discrepancies in detail and propose discrepancy types and categories to better understand the occurring mismatches. In total, our dataset consists of 611 paper-code discrepancies (81 real, 530 synthetic), spanning diverse computational science disciplines, including AI, Physics, Quantitative Biology, and others. Our evaluation of 21 LLMs highlights the difficulty of SciCoQA, particularly for instances involving omitted paper details, long-context inputs, and data outside the models' pre-training corpus. The best performing model in our evaluation, GPT-5, can only detect 45.7\% of real-world paper-code discrepancies.
  •  
  • ↗️
↗️

AI-generated data contamination erodes pathological variability and diagnostic reliability

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Hongyu He Β· Shaowen Xiang Β· Ye Zhang Β· Yingtao Zhu Β· Jin Zhang Β· Hao Deng Β· Emily Alsentzer Β· Qingyu Chen Β· Kun-Hsing Yu Β· Andrew Marmenshall Β· Tingting Chen Β· Srinivas Anumasa Β· Daniel Ebner Β· Dean Ho Β· Kee Yuan Ngiam Β· Ching-Yu Cheng Β· Dianbo Liu
arXiv:2601.12946v1 Announce Type: cross Abstract: Generative artificial intelligence (AI) is rapidly populating medical records with synthetic content, creating a feedback loop where future models are increasingly at risk of training on uncurated AI-generated data. However, the clinical consequences of this AI-generated data contamination remain unexplored. Here, we show that in the absence of mandatory human verification, this self-referential cycle drives a rapid erosion of pathological variability and diagnostic reliability. By analysing more than 800,000 synthetic data points across clinical text generation, vision-language reporting, and medical image synthesis, we find that models progressively converge toward generic phenotypes regardless of the model architecture. Specifically, rare but critical findings, including pneumothorax and effusions, vanish from the synthetic content generated by AI models, while demographic representations skew heavily toward middle-aged male phenotypes. Crucially, this degradation is masked by false diagnostic confidence; models continue to issue reassuring reports while failing to detect life-threatening pathology, with false reassurance rates tripling to 40%. Blinded physician evaluation confirms that this decoupling of confidence and accuracy renders AI-generated documentation clinically useless after just two generations. We systematically evaluate three mitigation strategies, finding that while synthetic volume scaling fails to prevent collapse, mixing real data with quality-aware filtering effectively preserves diversity. Ultimately, our results suggest that without policy-mandated human oversight, the deployment of generative AI threatens to degrade the very healthcare data ecosystems it relies upon.
  •  
  • ↗️
↗️

Multi-objective fluorescent molecule design with a data-physics dual-driven generative framework

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Yanheng Li Β· Zhichen Pu Β· Lijiang Yang Β· Zehao Zhou Β· Yi Qin Gao
arXiv:2601.13564v1 Announce Type: cross Abstract: Designing fluorescent small molecules with tailored optical and physicochemical properties requires navigating vast, underexplored chemical space while satisfying multiple objectives and constraints. Conventional generate-score-screen approaches become impractical under such realistic design specifications, owing to their low search efficiency, unreliable generalizability of machine-learning prediction, and the prohibitive cost of quantum chemical calculation. Here we present LUMOS, a data-and-physics driven framework for inverse design of fluorescent molecules. LUMOS couples generator and predictor within a shared latent representation, enabling direct specification-to-molecule design and efficient exploration. Moreover, LUMOS combines neural networks with a fast time-dependent density functional theory (TD-DFT) calculation workflow to build a suite of complementary predictors spanning different trade-offs in speed, accuracy, and generalizability, enabling reliable property prediction across diverse scenarios. Finally, LUMOS employs a property-guided diffusion model integrated with multi-objective evolutionary algorithms, enabling de novo design and molecular optimization under multiple objectives and constraints. Across comprehensive benchmarks, LUMOS consistently outperforms baseline models in terms of accuracy, generalizability and physical plausibility for fluorescence property prediction, and demonstrates superior performance in multi-objective scaffold- and fragment-level molecular optimization. Further validation using TD-DFT and molecular dynamics (MD) simulations demonstrates that LUMOS can generate valid fluorophores that meet various target specifications. Overall, these results establish LUMOS as a data-physics dual-driven framework for general fluorophore inverse design.
  •  
  • ↗️
↗️

Temporal-Spatial Decouple before Act: Disentangled Representation Learning for Multimodal Sentiment Analysis

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Chunlei Meng Β· Ziyang Zhou Β· Lucas He Β· Xiaojing Du Β· Chun Ouyang Β· Zhongxue Gan
arXiv:2601.13659v1 Announce Type: cross Abstract: Multimodal Sentiment Analysis integrates Linguistic, Visual, and Acoustic. Mainstream approaches based on modality-invariant and modality-specific factorization or on complex fusion still rely on spatiotemporal mixed modeling. This ignores spatiotemporal heterogeneity, leading to spatiotemporal information asymmetry and thus limited performance. Hence, we propose TSDA, Temporal-Spatial Decouple before Act, which explicitly decouples each modality into temporal dynamics and spatial structural context before any interaction. For every modality, a temporal encoder and a spatial encoder project signals into separate temporal and spatial body. Factor-Consistent Cross-Modal Alignment then aligns temporal features only with their temporal counterparts across modalities, and spatial features only with their spatial counterparts. Factor specific supervision and decorrelation regularization reduce cross factor leakage while preserving complementarity. A Gated Recouple module subsequently recouples the aligned streams for task. Extensive experiments show that TSDA outperforms baselines. Ablation analysis studies confirm the necessity and interpretability of the design.
  •  
  • ↗️
↗️

Who Should Have Surgery? A Comparative Study of GenAI vs Supervised ML for CRS Surgical Outcome Prediction

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Sayeed Shafayet Chowdhury Β· Snehasis Mukhopadhyay Β· Shiaofen Fang Β· Vijay R. Ramakrishnan
arXiv:2601.13710v1 Announce Type: cross Abstract: Artificial intelligence has reshaped medical imaging, yet the use of AI on clinical data for prospective decision support remains limited. We study pre-operative prediction of clinically meaningful improvement in chronic rhinosinusitis (CRS), defining success as a more than 8.9-point reduction in SNOT-22 at 6 months (MCID). In a prospectively collected cohort where all patients underwent surgery, we ask whether models using only pre-operative clinical data could have identified those who would have poor outcomes, i.e. those who should have avoided surgery. We benchmark supervised ML (logistic regression, tree ensembles, and an in-house MLP) against generative AI (ChatGPT, Claude, Gemini, Perplexity), giving each the same structured inputs and constraining outputs to binary recommendations with confidence. Our best ML model (MLP) achieves 85 % accuracy with superior calibration and decision-curve net benefit. GenAI models underperform on discrimination and calibration across zero-shot setting. Notably, GenAI justifications align with clinician heuristics and the MLP's feature importance, repeatedly highlighting baseline SNOT-22, CT/endoscopy severity, polyp phenotype, and physchology/pain comorbidities. We provide a reproducible tabular-to-GenAI evaluation protocol and subgroup analyses. Findings support an ML-first, GenAI- augmented workflow: deploy calibrated ML for primary triage of surgical candidacy, with GenAI as an explainer to enhance transparency and shared decision-making.
  •  
  • ↗️
↗️

A Survey of AI Scientists

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Guiyao Tie Β· Pan Zhou Β· Lichao Sun
arXiv:2510.23045v5 Announce Type: replace Abstract: Artificial intelligence is undergoing a profound transition from a computational instrument to an autonomous originator of scientific knowledge. This emerging paradigm, the AI scientist, is architected to emulate the complete scientific workflow-from initial hypothesis generation to the final synthesis of publishable findings-thereby promising to fundamentally reshape the pace and scale of discovery. However, the rapid and unstructured proliferation of these systems has created a fragmented research landscape, obscuring overarching methodological principles and developmental trends. This survey provides a systematic and comprehensive synthesis of this domain by introducing a unified, six-stage methodological framework that deconstructs the end-to-end scientific process into: Literature Review, Idea Generation, Experimental Preparation, Experimental Execution, Scientific Writing, and Paper Generation. Through this analytical lens, we chart the field's evolution from early Foundational Modules (2022-2023) to integrated Closed-Loop Systems (2024), and finally to the current frontier of Scalability, Impact, and Human-AI Collaboration (2025-present). By rigorously synthesizing these developments, this survey not only clarifies the current state of autonomous science but also provides a critical roadmap for overcoming remaining challenges in robustness and governance, ultimately guiding the next generation of systems toward becoming trustworthy and indispensable partners in human scientific inquiry.
  •  
  • ↗️
❌