❌

Normal view

Received — 18 November 2025 ⏭ Favourites

CLINB: A Climate Intelligence Benchmark for Foundational Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Michelle Chen Huebscher · Katharine Mach · Aleksandar Stani\'c · Markus Leippold · Ben Gaiarin · Zeke Hausfather · Elisa Rawat · Erich Fischer · Massimiliano Ciaramita · Joeri Rogelj · Christian Buck · Lierni Sestorain Saralegui · Reto Knutti
18 November 2025 at 13:00
arXiv:2511.11597v1 Announce Type: new Abstract: Evaluating how Large Language Models (LLMs) handle complex, specialized knowledge remains a critical challenge. We address this through the lens of climate change by introducing CLINB, a benchmark that assesses models on open-ended, grounded, multimodal question answering tasks with clear requirements for knowledge quality and evidential support. CLINB relies on a dataset of real users' questions and evaluation rubrics curated by leading climate scientists. We implement and validate a model-based evaluation process and evaluate several frontier models. Our findings reveal a critical dichotomy. Frontier models demonstrate remarkable knowledge synthesis capabilities, often exhibiting PhD-level understanding and presentation quality. They outperform "hybrid" answers curated by domain experts assisted by weaker models. However, this performance is countered by failures in grounding. The quality of evidence varies, with substantial hallucination rates for references and images. We argue that bridging this gap between knowledge synthesis and verifiable attribution is essential for the deployment of AI in scientific workflows and that reliable, interpretable benchmarks like CLINB are needed to progress towards building trustworthy AI systems.

End to End AI System for Surgical Gesture Sequence Recognition and Clinical Outcome Prediction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xi Li · Nicholas Matsumoto · Ujjwal Pasupulety · Atharva Deo · Cherine Yang · Jay Moran · Miguel E. Hernandez · Peter Wager · Jasmine Lin · Jeanine Kim · Alvin C. Goh · Christian Wagner · Geoffrey A. Sonn · Andrew J. Hung
18 November 2025 at 13:00
arXiv:2511.11899v1 Announce Type: new Abstract: Fine-grained analysis of intraoperative behavior and its impact on patient outcomes remain a longstanding challenge. We present Frame-to-Outcome (F2O), an end-to-end system that translates tissue dissection videos into gesture sequences and uncovers patterns associated with postoperative outcomes. Leveraging transformer-based spatial and temporal modeling and frame-wise classification, F2O robustly detects consecutive short (~2 seconds) gestures in the nerve-sparing step of robot-assisted radical prostatectomy (AUC: 0.80 frame-level; 0.81 video-level). F2O-derived features (gesture frequency, duration, and transitions) predicted postoperative outcomes with accuracy comparable to human annotations (0.79 vs. 0.75; overlapping 95% CI). Across 25 shared features, effect size directions were concordant with small differences (~ 0.07), and strong correlation (r = 0.96, p

UpBench: A Dynamically Evolving Real-World Labor-Market Agentic Benchmark Framework Built for Human-Centric AI

✇cs.AI, q-bio.NC updates on arXiv.org
By: Darvin Yi · Teng Liu · Mattie Terzolo · Lance Hasson · Ayan Sinh · Pablo Mendes · Andrew Rabinovich
18 November 2025 at 13:00
arXiv:2511.12306v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly undertake digital work, reliable frameworks are needed to evaluate their real-world competence, adaptability, and capacity for human collaboration. Existing benchmarks remain largely static, synthetic, or domain-limited, providing limited insight into how agents perform in dynamic, economically meaningful environments. We introduce UpBench, a dynamically evolving benchmark grounded in real jobs drawn from the global Upwork labor marketplace. Each task corresponds to a verified client transaction, anchoring evaluation in genuine work activity and financial outcomes. UpBench employs a rubric-based evaluation framework, in which expert freelancers decompose each job into detailed, verifiable acceptance criteria and assess AI submissions with per-criterion feedback. This structure enables fine-grained analysis of model strengths, weaknesses, and instruction-following fidelity beyond binary pass/fail metrics. Human expertise is integrated throughout the data pipeline (from job curation and rubric construction to evaluation) ensuring fidelity to real professional standards and supporting research on human-AI collaboration. By regularly refreshing tasks to reflect the evolving nature of online work, UpBench provides a scalable, human-centered foundation for evaluating agentic systems in authentic labor-market contexts, offering a path toward a collaborative framework, where AI amplifies human capability through partnership rather than replacement.

Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Decision Making

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dylan M. Asmar · Mykel J. Kochenderfer
18 November 2025 at 13:00
arXiv:2511.12378v1 Announce Type: new Abstract: Autonomous agents operating in sequential decision-making tasks under uncertainty can benefit from external action suggestions, which provide valuable guidance but inherently vary in reliability. Existing methods for incorporating such advice typically assume static and known suggester quality parameters, limiting practical deployment. We introduce a framework that dynamically learns and adapts to varying suggester reliability in partially observable environments. First, we integrate suggester quality directly into the agent's belief representation, enabling agents to infer and adjust their reliance on suggestions through Bayesian inference over suggester types. Second, we introduce an explicit ``ask'' action allowing agents to strategically request suggestions at critical moments, balancing informational gains against acquisition costs. Experimental evaluation demonstrates robust performance across varying suggester qualities, adaptation to changing reliability, and strategic management of suggestion requests. This work provides a foundation for adaptive human-agent collaboration by addressing suggestion uncertainty in uncertain environments.

Multi-agent Self-triage System with Medical Flowcharts

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yujia Liu · Sophia Yu · Hongyue Jin · Jessica Wen · Alexander Qian · Terrence Lee · Mattheus Ramsis · Gi Won Choi · Lianhui Qin · Xin Liu · Edward J. Wang
18 November 2025 at 13:00
arXiv:2511.12439v1 Announce Type: new Abstract: Online health resources and large language models (LLMs) are increasingly used as a first point of contact for medical decision-making, yet their reliability in healthcare remains limited by low accuracy, lack of transparency, and susceptibility to unverified information. We introduce a proof-of-concept conversational self-triage system that guides LLMs with 100 clinically validated flowcharts from the American Medical Association, providing a structured and auditable framework for patient decision support. The system leverages a multi-agent framework consisting of a retrieval agent, a decision agent, and a chat agent to identify the most relevant flowchart, interpret patient responses, and deliver personalized, patient-friendly recommendations, respectively. Performance was evaluated at scale using synthetic datasets of simulated conversations. The system achieved 95.29% top-3 accuracy in flowchart retrieval (N=2,000) and 99.10% accuracy in flowchart navigation across varied conversational styles and conditions (N=37,200). By combining the flexibility of free-text interaction with the rigor of standardized clinical protocols, this approach demonstrates the feasibility of transparent, accurate, and generalizable AI-assisted self-triage, with potential to support informed patient decision-making while improving healthcare resource utilization.

MiniGPT-Pancreas: Multimodal Large Language Model for Pancreas Cancer Classification and Detection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Andrea Moglia · Elia Clement Nastasio · Luca Mainardi · Pietro Cerveri
18 November 2025 at 13:00
arXiv:2412.15925v1 Announce Type: cross Abstract: Problem: Pancreas radiological imaging is challenging due to the small size, blurred boundaries, and variability of shape and position of the organ among patients. Goal: In this work we present MiniGPT-Pancreas, a Multimodal Large Language Model (MLLM), as an interactive chatbot to support clinicians in pancreas cancer diagnosis by integrating visual and textual information. Methods: MiniGPT-v2, a general-purpose MLLM, was fine-tuned in a cascaded way for pancreas detection, tumor classification, and tumor detection with multimodal prompts combining questions and computed tomography scans from the National Institute of Health (NIH), and Medical Segmentation Decathlon (MSD) datasets. The AbdomenCT-1k dataset was used to detect the liver, spleen, kidney, and pancreas. Results: MiniGPT-Pancreas achieved an Intersection over Union (IoU) of 0.595 and 0.550 for the detection of pancreas on NIH and MSD datasets, respectively. For the pancreas cancer classification task on the MSD dataset, accuracy, precision, and recall were 0.876, 0.874, and 0.878, respectively. When evaluating MiniGPT-Pancreas on the AbdomenCT-1k dataset for multi-organ detection, the IoU was 0.8399 for the liver, 0.722 for the kidney, 0.705 for the spleen, and 0.497 for the pancreas. For the pancreas tumor detection task, the IoU score was 0.168 on the MSD dataset. Conclusions: MiniGPT-Pancreas represents a promising solution to support clinicians in the classification of pancreas images with pancreas tumors. Future research is needed to improve the score on the detection task, especially for pancreas tumors.

MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mohammad Karami · Mohammad Reza Nemati · Aidin Kazemi · Ali Mikaeili Barzili · Hamid Azadegan · Behzad Moshiri
18 November 2025 at 13:00
arXiv:2511.11625v1 Announce Type: cross Abstract: Artificial intelligence (AI) has shown great potential in medical imaging, particularly for brain tumor detection using Magnetic Resonance Imaging (MRI). However, the models remain vulnerable at inference time when they are trained collaboratively through Federated Learning (FL), an approach adopted to protect patient privacy. Adversarial attacks can subtly alter medical scans in ways invisible to the human eye yet powerful enough to mislead AI models, potentially causing serious misdiagnoses. Existing defenses often assume centralized data and struggle to cope with the decentralized and diverse nature of federated medical settings. In this work, we present MedFedPure, a personalized federated learning defense framework designed to protect diagnostic AI models at inference time without compromising privacy or accuracy. MedFedPure combines three key elements: (1) a personalized FL model that adapts to the unique data distribution of each institution; (2) a Masked Autoencoder (MAE) that detects suspicious inputs by exposing hidden perturbations; and (3) an adaptive diffusion-based purification module that selectively cleans only the flagged scans before classification. Together, these steps offer robust protection while preserving the integrity of normal, benign images. We evaluated MedFedPure on the Br35H brain MRI dataset. The results show a significant gain in adversarial robustness, improving performance from 49.50% to 87.33% under strong attacks, while maintaining a high clean accuracy of 97.67%. By operating locally and in real time during diagnosis, our framework provides a practical path to deploying secure, trustworthy, and privacy-preserving AI tools in clinical workflows. Index Terms: cancer, tumor detection, federated learning, masked autoencoder, diffusion, privacy

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jingwei Song · Wanyi Chen · Xinyuan Song · Max · Chris Tong · Gufeng Chen · Tianyi Zhao · Eric Yang · Bill Shi · Lynn Ai
18 November 2025 at 13:00
arXiv:2511.11733v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in decentralized settings, where network latency often dominates compute, remains under-characterized. We present Decentralized Speculative Decoding (DSD), a plug-and-play framework for decentralized inference that turns communication delay into useful computation by verifying multiple candidate tokens in parallel across distributed nodes. We further introduce an adaptive speculative verification strategy that adjusts acceptance thresholds by token-level semantic importance, delivering an additional 15% to 20% end-to-end speedup without retraining. In theory, DSD reduces cross-node communication cost by approximately (N-1)t1(k-1)/k, where t1 is per-link latency and k is the average number of tokens accepted per round. In practice, DSD achieves up to 2.56x speedup on HumanEval and 2.59x on GSM8K, surpassing the Eagle3 baseline while preserving accuracy. These results show that adapting speculative decoding for decentralized execution provides a system-level optimization that converts network stalls into throughput, enabling faster distributed LLM inference with no model retraining or architectural changes.

Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sebasti\'an Andr\'es Cajas Ord\'o\~nez · Luis Fernando Torres Torres · Mackenzie J. Meni · Carlos Andr\'es Duran Paredes · Eric Arazo · Cristian Bosch · Ricardo Simon Carbajo · Yuan Lai · Leo Anthony Celi
18 November 2025 at 13:00
arXiv:2511.11743v1 Announce Type: cross Abstract: Deploying deep neural networks on resource-constrained devices faces two critical challenges: maintaining accuracy under aggressive quantization while ensuring predictable inference latency. We present a curiosity-driven quantized Mixture-of-Experts framework that addresses both through Bayesian epistemic uncertainty-based routing across heterogeneous experts (BitNet ternary, 1-16 bit BitLinear, post-training quantization). Evaluated on audio classification benchmarks (ESC-50, Quinn, UrbanSound8K), our 4-bit quantization maintains 99.9 percent of 16-bit accuracy (0.858 vs 0.859 F1) with 4x compression and 41 percent energy savings versus 8-bit. Crucially, curiosity-driven routing reduces MoE latency variance by 82 percent (p = 0.008, Levene's test) from 230 ms to 29 ms standard deviation, enabling stable inference for battery-constrained devices. Statistical analysis confirms 4-bit/8-bit achieve practical equivalence with full precision (p > 0.05), while MoE architectures introduce 11 percent latency overhead (p

Real-Time Speech Enhancement via a Hybrid ViT: A Dual-Input Acoustic-Image Feature Fusion

✇cs.AI, q-bio.NC updates on arXiv.org
By: Behnaz Bahmei · Siamak Arzanpour · Elina Birmingham
18 November 2025 at 13:00
arXiv:2511.11825v1 Announce Type: cross Abstract: Speech quality and intelligibility are significantly degraded in noisy environments. This paper presents a novel transformer-based learning framework to address the single-channel noise suppression problem for real-time applications. Although existing deep learning networks have shown remarkable improvements in handling stationary noise, their performance often diminishes in real-world environments characterized by non-stationary noise (e.g., dog barking, baby crying). The proposed dual-input acoustic-image feature fusion using a hybrid ViT framework effectively models both temporal and spectral dependencies in noisy signals. Designed for real-world audio environments, the proposed framework is computationally lightweight and suitable for implementation on embedded devices. To evaluate its effectiveness, four standard and commonly used quality measurements, namely PESQ, STOI, Seg SNR, and LLR, are utilized. Experimental results obtained using the Librispeech dataset as the clean speech source and the UrbanSound8K and Google Audioset datasets as the noise sources, demonstrate that the proposed method significantly improves noise reduction, speech intelligibility, and perceptual quality compared to the noisy input signal, achieving performance close to the clean reference.

Securing Generative AI in Healthcare: A Zero-Trust Architecture Powered by Confidential Computing on Google Cloud

✇cs.AI, q-bio.NC updates on arXiv.org
By: Adaobi Amanna · Ishana Shinde
18 November 2025 at 13:00
arXiv:2511.11836v1 Announce Type: cross Abstract: The integration of Generative Artificial Intelligence (GenAI) in healthcare is impeded by significant security challenges unaddressed by traditional frameworks, precisely the data-in-use gap where sensitive patient data and proprietary AI models are exposed during active processing. To address this, the paper proposes the Confidential Zero-Trust Framework (CZF), a novel security paradigm that synergistically combines Zero-Trust Architecture for granular access control with the hardware-enforced data isolation of Confidential Computing. We detailed a multi-tiered architectural blueprint for implementing the CZF on Google Cloud and analyzed its efficacy against real-world threats. The CZF provides a defense-in-depth architecture where data remains encrypted while in-use within a hardware-based Trusted Execution Environment (TEE). The framework's use of remote attestation offers cryptographic proof of workload integrity, transforming compliance from a procedural exercise into a verifiable technical fact and enabling secure, multi-party collaborations previously blocked by security and intellectual property concerns. By closing the data-in-use gap and enforcing Zero-Trust principles, the CZF provides a robust and verifiable framework that establishes the necessary foundation of trust to enable the responsible adoption of transformative AI technologies in healthcare.

EgoEMS: A High-Fidelity Multimodal Egocentric Dataset for Cognitive Assistance in Emergency Medical Services

✇cs.AI, q-bio.NC updates on arXiv.org
By: Keshara Weerasinghe · Xueren Ge · Tessa Heick · Lahiru Nuwan Wijayasingha · Anthony Cortez · Abhishek Satpathy · John Stankovic · Homa Alemzadeh
18 November 2025 at 13:00
arXiv:2511.09894v2 Announce Type: replace Abstract: Emergency Medical Services (EMS) are critical to patient survival in emergencies, but first responders often face intense cognitive demands in high-stakes situations. AI cognitive assistants, acting as virtual partners, have the potential to ease this burden by supporting real-time data collection and decision making. In pursuit of this vision, we introduce EgoEMS, the first end-to-end, high-fidelity, multimodal, multiperson dataset capturing over 20 hours of realistic, procedural EMS activities from an egocentric view in 233 simulated emergency scenarios performed by 62 participants, including 46 EMS professionals. Developed in collaboration with EMS experts and aligned with national standards, EgoEMS is captured using an open-source, low-cost, and replicable data collection system and is annotated with keysteps, timestamped audio transcripts with speaker diarization, action quality metrics, and bounding boxes with segmentation masks. Emphasizing realism, the dataset includes responder-patient interactions reflecting real-world emergency dynamics. We also present a suite of benchmarks for real-time multimodal keystep recognition and action quality estimation, essential for developing AI support tools for EMS. We hope EgoEMS inspires the research community to push the boundaries of intelligent EMS systems and ultimately contribute to improved patient outcomes.

A Workflow for Full Traceability of AI Decisions

✇cs.AI, q-bio.NC updates on arXiv.org
By: Julius Wenzel · Syeda Umaima Alam · Andreas Schmidt · Hanwei Zhang · Holger Hermanns
18 November 2025 at 13:00
arXiv:2511.11275v2 Announce Type: replace Abstract: An ever increasing number of high-stake decisions are made or assisted by automated systems employing brittle artificial intelligence technology. There is a substantial risk that some of these decision induce harm to people, by infringing their well-being or their fundamental human rights. The state-of-the-art in AI systems makes little effort with respect to appropriate documentation of the decision process. This obstructs the ability to trace what went into a decision, which in turn is a prerequisite to any attempt of reconstructing a responsibility chain. Specifically, such traceability is linked to a documentation that will stand up in court when determining the cause of some AI-based decision that inadvertently or intentionally violates the law. This paper takes a radical, yet practical, approach to this problem, by enforcing the documentation of each and every component that goes into the training or inference of an automated decision. As such, it presents the first running workflow supporting the generation of tamper-proof, verifiable and exhaustive traces of AI decisions. In doing so, we expand the DBOM concept into an effective running workflow leveraging confidential computing technology. We demonstrate the inner workings of the workflow in the development of an app to tell poisonous and edible mushrooms apart, meant as a playful example of high-stake decision support.

A large language model-based approach to quantifying the effects of social determinants in liver transplant decisions

✇npj Digital Medicine
By: Emily Robitschek · Asal Bastani · Kathryn Horwath · Savyon Sordean · Mark J. Pletcher · Jennifer C. Lai · Sergio Galletta · Elliott Ash · Jin Ge · Irene Y. Chen
17 November 2025 at 08:00

npj Digital Medicine, Published online: 17 November 2025; doi:10.1038/s41746-025-02025-y

A large language model-based approach to quantifying the effects of social determinants in liver transplant decisions

Methods for Analytical Validation of Novel Digital Clinical Measures: Implementation Feasibility Evaluation Using Real-World Datasets

✇Journal of Medical Internet Research
By: Simon Turner · Lysbeth Floden · Leif Simmatis · Piper Fromy · Joss Langford · Eric J Daza · Andrew Potter · Kathleen Troeger · the STAGES cohort investigator group
18 November 2025 at 04:00
Background: Sensor-based digital health technologies (sDHTs) are increasingly used to support scientific and clinical decision-making. The digital measures (DMs) they generate offer significant potential to accelerate the drug development timeline, decrease clinical trial costs, and improve access to care. However, choosing appropriate statistical methodology when conducting analytical validation (AV) of a DM is complicated, particularly for novel DMs, for which appropriate, established reference measures may not exist. More understanding of, and a standardization of approach to, AV in these scenarios is needed. Objective: In a prior simulation study, three statistical methods were tested for their ability to estimate a simulated relationship between a sDHT-derived DM and several clinical outcome assessment (COA) reference measures. The aim of this work was to assess the feasibility of these methods’ implementation in real data, and to examine the impact of AV study design factors on the relationships estimated. Methods: Four real-world datasets, captured using sDHTs, were used to prepare hypothetical AV studies that represented a range of scenarios with respect to three key study design properties: temporal coherence, construct coherence and data completeness. For each hypothetical study, two-factor, correlated-factors confirmatory factor analysis (CFA) models, and a combination of simple and multiple linear regression models, were built using the DM and reference measure data. The factor correlation, R2 and adjusted R2 statistics were calculated, in addition to the Pearson Correlation Coefficients (PCCs). Results: The majority of CFA models exhibited an acceptable fit according to the majority of the fit statistics employed, and each model was able to estimate a factor correlation. For each model, these correlations were greater than or equal to the corresponding PCC in magnitude. Correlations were strongest in the hypothetical studies with strong temporal and construct coherence. Conclusions: The performance of the measures shown in this work supports the feasibility of the selected statistical methods when implemented in real-world data. Our findings in particular support the use of CFA to assess the relationship between a novel digital measure and a COA reference measure. The observed impact of AV study design factors on the relationships estimated allowed the authors to determine practical recommendations to aid in appropriate study design for AV of novel digital measures. By utilizing a standardized methodology for evaluating novel digital measures, sDHT developers, biostatisticians and clinical researchers will be able to navigate the complex validation landscape more easily, with more certainty, and with more tools at their disposal, expediting the pathway to validation and regulatory review.

The gut microbiome and gastrointestinal cancers: mechanisms, biomarkers and therapeutic opportunities

✇Omics in Gastric
By: Sarbjeet Kaur Makkar · Kumar S Bishnupuri
17 November 2025 at 19:00

Front Physiol. 2025 Oct 30;16:1676796. doi: 10.3389/fphys.2025.1676796. eCollection 2025.

ABSTRACT

Gastrointestinal (GI) cancers remain a leading global cause of cancer-related mortality, significantly impacting public health and healthcare systems worldwide. Emerging evidence underscores the critical role of gut microbiome dysbiosis-characterized by disrupted microbial diversity and function-in GI carcinogenesis. Utilizing recent advancements in multi-omics technologies and sophisticated computational biology, researchers have elucidated distinct microbial signatures associated with colorectal, gastric, hepatobiliary, pancreatic, and esophageal cancers. This review comprehensively analyzes the primary mechanisms through which gut microbes contribute to cancer development and progression, encompassing genotoxicity, chronic inflammation, metabolic dysregulation, epigenetic modifications, and immunomodulation. Moreover, we explore innovative microbiome-derived biomarkers for potential clinical applications, including early diagnosis, prognosis assessment, and therapeutic response prediction. The intricate interactions between microbiota and standard cancer therapies-chemotherapy, immunotherapy, and radiation therapy-are discussed, highlighting microbiome influences on therapeutic efficacy and adverse effect profiles. We also critically assess the impact of modifiable factors such as diet, medications, lifestyle, and environmental exposures on microbiome composition and cancer risk. The review evaluates emerging therapeutic interventions, including dietary modifications, probiotics, prebiotics, fecal microbiota transplantation (FMT), and engineered live biotherapeutics. Despite notable advancements, significant hurdles remain, including clarifying causality, methodological standardization, and equitable global research representation. Addressing these challenges, we propose a strategic research agenda aimed at harnessing microbiome insights to advance precision oncology and improve GI cancer outcomes globally.

PMID:41245267 | PMC:PMC12611654 | DOI:10.3389/fphys.2025.1676796

The gut microbiome and gastrointestinal cancers: mechanisms, biomarkers and therapeutic opportunities

✇(Multiomics OR Omics) AND (Pancreatic)
By: Sarbjeet Kaur Makkar · Kumar S Bishnupuri
17 November 2025 at 19:00

Front Physiol. 2025 Oct 30;16:1676796. doi: 10.3389/fphys.2025.1676796. eCollection 2025.

ABSTRACT

Gastrointestinal (GI) cancers remain a leading global cause of cancer-related mortality, significantly impacting public health and healthcare systems worldwide. Emerging evidence underscores the critical role of gut microbiome dysbiosis-characterized by disrupted microbial diversity and function-in GI carcinogenesis. Utilizing recent advancements in multi-omics technologies and sophisticated computational biology, researchers have elucidated distinct microbial signatures associated with colorectal, gastric, hepatobiliary, pancreatic, and esophageal cancers. This review comprehensively analyzes the primary mechanisms through which gut microbes contribute to cancer development and progression, encompassing genotoxicity, chronic inflammation, metabolic dysregulation, epigenetic modifications, and immunomodulation. Moreover, we explore innovative microbiome-derived biomarkers for potential clinical applications, including early diagnosis, prognosis assessment, and therapeutic response prediction. The intricate interactions between microbiota and standard cancer therapies-chemotherapy, immunotherapy, and radiation therapy-are discussed, highlighting microbiome influences on therapeutic efficacy and adverse effect profiles. We also critically assess the impact of modifiable factors such as diet, medications, lifestyle, and environmental exposures on microbiome composition and cancer risk. The review evaluates emerging therapeutic interventions, including dietary modifications, probiotics, prebiotics, fecal microbiota transplantation (FMT), and engineered live biotherapeutics. Despite notable advancements, significant hurdles remain, including clarifying causality, methodological standardization, and equitable global research representation. Addressing these challenges, we propose a strategic research agenda aimed at harnessing microbiome insights to advance precision oncology and improve GI cancer outcomes globally.

PMID:41245267 | PMC:PMC12611654 | DOI:10.3389/fphys.2025.1676796

Received — 17 November 2025 ⏭ Favourites
Received — 14 November 2025 ⏭ Favourites

Benevolent Dictators? On LLM Agent Behavior in Dictator Games

✇cs.AI, q-bio.NC updates on arXiv.org
By: Andreas Einwiller · Kanishka Ghosh Dastidar · Artur Romazanov · Annette Hautli-Janisz · Michael Granitzer · Florian Lemmerich
13 November 2025 at 13:00
arXiv:2511.08721v1 Announce Type: cross Abstract: In behavioral sciences, experiments such as the ultimatum game are conducted to assess preferences for fairness or self-interest of study participants. In the dictator game, a simplified version of the ultimatum game where only one of two players makes a single decision, the dictator unilaterally decides how to split a fixed sum of money between themselves and the other player. Although recent studies have explored behavioral patterns of AI agents based on Large Language Models (LLMs) instructed to adopt different personas, we question the robustness of these results. In particular, many of these studies overlook the role of the system prompt - the underlying instructions that shape the model's behavior - and do not account for how sensitive results can be to slight changes in prompts. However, a robust baseline is essential when studying highly complex behavioral aspects of LLMs. To overcome previous limitations, we propose the LLM agent behavior study (LLM-ABS) framework to (i) explore how different system prompts influence model behavior, (ii) get more reliable insights into agent preferences by using neutral prompt variations, and (iii) analyze linguistic features in responses to open-ended instructions by LLM agents to better understand the reasoning behind their behavior. We found that agents often exhibit a strong preference for fairness, as well as a significant impact of the system prompt on their behavior. From a linguistic perspective, we identify that models express their responses differently. Although prompt sensitivity remains a persistent challenge, our proposed framework demonstrates a robust foundation for LLM agent behavior studies. Our code artifacts are available at https://github.com/andreaseinwiller/LLM-ABS.

AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rohan Kadekodi · Zhan Jin · Keisuke Kamahori · Yile Gu · Sean Khatiri · Noah H. Bayindirli · Sergey Gorbunov · Baris Kasikci
13 November 2025 at 13:00
arXiv:2510.00229v4 Announce Type: replace Abstract: The deployment of Large Language Models (LLMs) as agentic orchestrators has revolutionized task automation, but the need for privacy-preserving, cost-effective solutions demands on-device inference capabilities. However, local LLMs consistently underperform compared to frontier models in tool calling scenarios, struggling with both tool selection from large tool sets and accurate argument generation for complex parameter structures. We introduce a methodology that disaggregates a tool-calling task into two distinct subtasks: tool selection and argument generation. We propose "decoupled fine-tuning", a novel post-training approach that employs LoRA fine-tuning to create dedicated LoRA adapters for tool selection and tool-specific argument generation using separate loss masking for each of the subtasks. Furthermore, we present AgentFlux, an inference framework that leverages the LoRA adapters created using decoupled fine-tuning to perform efficient agent orchestration with the help of local models on end-user devices. AgentFlux decomposes the tool-call generation step into tool selection and argument generation, and dynamically loads the corresponding LoRA adapters to generate tool calls. Additionally, AgentFlux implements hierarchical orchestration to restrict the number of tools required for tool selection. Our experiments on the MCP-Bench benchmark demonstrate that the Qwen-2.5-7B model trained using decoupled fine-tuning improves the tool calling accuracy of the base model by 46%, and outperforms other local reasoning, non-reasoning and fine-tuned models of similar size in all cases, and models that are 2x larger, in most cases.
❌