On Using Machine Learning to Early Detect Catastrophic Failures in Marine Diesel Engines

By: Francesco Maione · Paolo Lino · Giuseppe Giannino · Guido Maione

16 March 2026 at 12:00

arXiv:2603.12733v1 Announce Type: new Abstract: Catastrophic failures of marine engines imply severe loss of functionality and destroy or damage the systems irreversibly. Being sudden and often unpredictable events, they pose a severe threat to navigation, crew, and passengers. The abrupt nature makes early detection the only effective countermeasure. However, research has concentrated on modeling the gradual degradation of components, with limited attention to sudden and anomalous phenomena. This work proposes a new method for early detection of catastrophic failures. Based on real data from a failed engine, the approach evaluates the derivatives of the deviation between actual sensor readings and expected values of engine variables. Predictions are obtained by a Random Forest, which is the most suitable Machine Learning algorithm among the tested ones. Traditional methods focus on deviations of monitored signals, whereas the proposed approach employs the derivatives of the deviations to provide earlier indications of abnormal dynamics, and to alert that a rapid and dangerous event is breaking out within the system. The method allows the detection of anomalies before measurements reach critical thresholds and alarms are triggered, which is the common method in industry. Consequently, operators can be warned in advance and shut down the engine, then prevent damage and unexpected power loss. Moreover, they have the time to safely change the ship route and avoid potential obstacles. Simulation results conf irm the effectiveness of the proposed approach in anticipating occurrence of catastrophic failures. Validation on real-world data further reinforces the robustness and practical applicability of the method. It is worth noting that data acquisition to train the predictive algorithm is not a problem, since a Deep Learning-based data augmentation procedure is used.

Test-Time Strategies for More Efficient and Accurate Agentic RAG

cs.AI, q-bio.NC updates on arXiv.org

By: Brian Zhang · Deepti Guntur · Zhiyang Zuo · Abhinav Sharma · Shreyas Chaudhari · Wenlong Zhao · Franck Dernoncourt · Puneet Mathur · Ryan Rossi · Nedim Lipka

16 March 2026 at 12:00

arXiv:2603.12396v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iteratively, have been proposed to address these complexities. However, such approaches can introduce inefficiencies, including repetitive retrieval of previously processed information and challenges in contextualizing retrieved results effectively within the current generation prompt. Such issues can lead to unnecessary retrieval turns, suboptimal reasoning, inaccurate answers, and increased token consumption. In this paper, we investigate test-time modifications to the Search-R1 pipeline to mitigate these identified shortcomings. Specifically, we explore the integration of two components and their combination: a contextualization module to better integrate relevant information from retrieved documents into reasoning, and a de-duplication module that replaces previously retrieved documents with the next most relevant ones. We evaluate our approaches using the HotpotQA (Yang et al., 2018) and the Natural Questions (Kwiatkowski et al., 2019) datasets, reporting the exact match (EM) score, an LLM-as-a-Judge assessment of answer correctness, and the average number of turns. Our best-performing variant, utilizing GPT-4.1-mini for contextualization, achieves a 5.6% increase in EM score and reduces the number of turns by 10.5% compared to the Search-R1 baseline, demonstrating improved answer accuracy and retrieval efficiency.

Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies

cs.AI, q-bio.NC updates on arXiv.org

By: Siddharth Srikanth · Freddie Liang · Sophie Hsu · Varun Bhatt · Shihan Zhao · Henry Chen · Bryon Tjanaka · Minjune Hwang · Akanksha Saran · Daniel Seita · Aaquib Tabrez · Stefanos Nikolaidis

16 March 2026 at 12:00

arXiv:2603.12510v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have significant potential to enable general-purpose robotic systems for a range of vision-language tasks. However, the performance of VLA-based robots is highly sensitive to the precise wording of language instructions, and it remains difficult to predict when such robots will fail. To improve the robustness of VLAs to different wordings, we present Q-DIG (Quality Diversity for Diverse Instruction Generation), which performs red-teaming by scalably identifying diverse natural language task descriptions that induce failures while remaining task-relevant. Q-DIG integrates Quality Diversity (QD) techniques with Vision-Language Models (VLMs) to generate a broad spectrum of adversarial instructions that expose meaningful vulnerabilities in VLA behavior. Our results across multiple simulation benchmarks show that Q-DIG finds more diverse and meaningful failure modes compared to baseline methods, and that fine-tuning VLAs on the generated instructions improves task success rates. Furthermore, results from a user study highlight that Q-DIG generates prompts judged to be more natural and human-like than those from baselines. Finally, real-world evaluations of Q-DIG prompts show results consistent with simulation, and fine-tuning VLAs on the generated prompts further success rates on unseen instructions. Together, these findings suggest that Q-DIG is a promising approach for identifying vulnerabilities and improving the robustness of VLA-based robots. Our anonymous project website is at qdigvla.github.io.

Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages

cs.AI, q-bio.NC updates on arXiv.org

By: Vishnu Teja Kunde · Fatemeh Doudi · Mahdi Farahbakhsh · Dileep Kalathil · Krishna Narayanan · Jean-Francois Chamberland

16 March 2026 at 12:00

arXiv:2603.12554v1 Announce Type: cross Abstract: Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing approaches therefore rely on surrogate likelihoods or heuristic approximations, which can introduce bias and obscure the sequential structure of denoising. We formulate diffusion-based sequence generation as a finite-horizon Markov decision process over the denoising trajectory and derive an exact, unbiased policy gradient that decomposes over denoising steps and is expressed in terms of intermediate advantages, without requiring explicit evaluation of the sequence likelihood. To obtain a practical and compute-efficient estimator, we (i) select denoising steps for policy updates via an entropy-guided approximation bound, and (ii) estimate intermediate advantages using a one-step denoising reward naturally provided by the diffusion model, avoiding costly multi-step rollouts. Experiments on coding and logical reasoning benchmarks demonstrate state-of-the-art results, with strong competitive performance on mathematical reasoning, outperforming existing RL post-training approaches for DLMs. Code is available at https://github.com/vishnutez/egspo-dllm-rl.

Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation

16 March 2026 at 12:00

arXiv:2603.12581v1 Announce Type: cross Abstract: Although diffusion models have achieved remarkable progress in multi-modal magnetic resonance imaging (MRI) translation tasks, existing methods still tend to suffer from anatomical inconsistencies or degraded texture details when handling arbitrary missing-modality scenarios. To address these issues, we propose a latent diffusion-based multi-modal MRI translation framework, termed MSG-LDM. By leveraging the available modalities, the proposed method infers complete structural information, which preserves reliable boundary details. Specifically, we introduce a style--structure disentanglement mechanism in the latent space, which explicitly separates modality-specific style features from shared structural representations, and jointly models low-frequency anatomical layouts and high-frequency boundary details in a multi-scale feature space. During the structure disentanglement stage, high-frequency structural information is explicitly incorporated to enhance feature representations, guiding the model to focus on fine-grained structural cues while learning modality-invariant low-frequency anatomical representations. Furthermore, to reduce interference from modality-specific styles and improve the stability of structure representations, we design a style consistency loss and a structure-aware loss. Extensive experiments on the BraTS2020 and WMH datasets demonstrate that the proposed method outperforms existing MRI synthesis approaches, particularly in reconstructing complete structures. The source code is publicly available at https://github.com/ziyi-start/MSG-LDM.

Competition-Aware CPC Forecasting with Near-Market Coverage

cs.AI, q-bio.NC updates on arXiv.org

By: Sebastian Frey · Edoardo Beccari · Maximilian Kranz · Nicol\`o Alberto Pellizzari · Ali Mete Karaman · Qiwei Han · Maximilian Kaiser

16 March 2026 at 12:00

arXiv:2603.13059v1 Announce Type: cross Abstract: Cost-per-click (CPC) in paid search is a volatile auction outcome generated by a competitive landscape that is only partially observable from any single advertiser's history. Using Google Ads auction logs from a concentrated car-rental market (2021--2023), we forecast weekly CPC for 1,811 keyword series and approximate latent competition through complementary signals derived from keyword text, CPC trajectories, and geographic market structure. We construct (i) semantic neighborhoods and a semantic keyword graph from pretrained transformer-based representations of keyword text, (ii) behavioral neighborhoods via Dynamic Time Warping (DTW) alignment of CPC trajectories, and (iii) geographic-intent covariates capturing localized demand and marketplace heterogeneity. We extensively evaluate these signals both as stand-alone covariates and as relational priors in spatiotemporal graph forecasters, benchmarking them against strong statistical, neural, and time-series foundation-model baselines. Across methods, competition-aware augmentation improves stability and error profiles at business-relevant medium and longer horizons, where competitive regimes shift and volatility is most consequential. The results show that broad market-outcome coverage, combined with keyword-derived semantic and geographic priors, provides a scalable way to approximate latent competition and improve CPC forecasting in auction-driven markets.

A mathematical theory for understanding when abstract representations emerge in neural networks

cs.AI, q-bio.NC updates on arXiv.org

By: Bin Wang · W. Jeffrey Johnston · Stefano Fusi

16 March 2026 at 12:00

arXiv:2510.09816v2 Announce Type: replace Abstract: Recent experiments in neuroscience reveal that task-relevant variables are often encoded in approximately orthogonal subspaces of neural population activity. These disentangled, or abstract, representations have been observed in multiple brain areas and across different species. These representations have been shown to support out of distribution generalization and rapid learning of novel tasks. The mechanisms by which these representations emerge remain poorly understood, especially in the case of supervised task behavior. Here, we show mathematically that abstract representations of latent variables are guaranteed to appear in the hidden layer of feedforward nonlinear networks when they are trained on tasks that depend directly on these latent variables. These learned abstract representations reflect the semantics of the input stimuli. To show this, we reformulate the usual optimization over the network weights into a mean field optimization problem over the distribution of neural preactivations. We then apply this framework to finite-width ReLU networks and show that the hidden layer of these networks will exhibit an abstract representation at all global minima of the task objective. Finally, we extend our findings to two broad families of activation functions as well as deep feedforward architectures. Together, our results provide an explanation for the widely observed abstract representations in both the brain and artificial neural networks. In addition, the general framework that we develop here provides a mathematically tractable toolkit for understanding the emergence of different kinds of representations in task-optimized, feature-learning network models.

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

cs.AI, q-bio.NC updates on arXiv.org

By: Usman Anwar · Julianna Piskorz · David D. Baek · David Africa · Jim Weatherall · Max Tegmark · Christian Schroeder de Witt · Mihaela van der Schaar · David Krueger

16 March 2026 at 12:00

arXiv:2602.23163v2 Announce Type: replace Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to detect and quantify such behaviours are lacking. Classical definitions of steganography, and detection methods based on them, require a known reference distribution of non-steganographic signals. For the case of steganographic reasoning in LLMs, knowing such a reference distribution is not feasible; this renders these approaches inapplicable. We propose an alternative, \textbf{decision-theoretic view of steganography}. Our central insight is that steganography creates an asymmetry in usable information between agents who can and cannot decode the hidden content (present within a steganographic signal), and this otherwise latent asymmetry can be inferred from the agents' observable actions. To formalise this perspective, we introduce generalised $\mathcal{V}$-information: a utilitarian framework for measuring the amount of usable information within some input. We use this to define the \textbf{steganographic gap} -- a measure that quantifies steganography by comparing the downstream utility of the steganographic signal to agents that can and cannot decode the hidden content. We empirically validate our formalism, and show that it can be used to detect, quantify, and mitigate steganographic reasoning in LLMs.

Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models

cs.AI, q-bio.NC updates on arXiv.org

By: Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Sch\"olkopf, Mario Fritz

16 March 2026 at 12:00

arXiv:2502.21123v5 Announce Type: replace-cross Abstract: Ensuring trustworthiness in machine learning (ML) systems is crucial as they become increasingly embedded in high-stakes domains. This paper advocates for integrating causal methods into machine learning to navigate the trade-offs among key principles of trustworthy ML, including fairness, privacy, robustness, accuracy, and explainability. While these objectives should ideally be satisfied simultaneously, they are often addressed in isolation, leading to conflicts and suboptimal solutions. Drawing on existing applications of causality in ML that successfully align goals such as fairness and accuracy or privacy and robustness, this paper argues that a causal approach is essential for balancing multiple competing objectives in both trustworthy ML and foundation models. Beyond highlighting these trade-offs, we examine how causality can be practically integrated into ML and foundation models, offering solutions to enhance their reliability and interpretability. Finally, we discuss the challenges, limitations, and opportunities in adopting causal frameworks, paving the way for more accountable and ethically sound AI systems.

DriveMind: A Dual Visual Language Model-based Reinforcement Learning Framework for Autonomous Driving

cs.AI, q-bio.NC updates on arXiv.org

By: Dawood Wasif · Terrence J. Moore · Chandan K. Reddy · Frederica Free-Nelson · Seunghyun Yoon · Hyuk Lim · Dan Dongseong Kim · Jin-Hee Cho

16 March 2026 at 12:00

arXiv:2506.00819v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving systems map sensor data directly to control commands, but remain opaque, lack interpretability, and offer no formal safety guarantees. While recent vision-language-guided reinforcement learning (RL) methods introduce semantic feedback, they often rely on static prompts and fixed objectives, limiting adaptability to dynamic driving scenes. We present DriveMind, a unified semantic reward framework that integrates: (i) a contrastive Vision-Language Model (VLM) encoder for stepwise semantic anchoring; (ii) a novelty-triggered VLM encoder-decoder, fine-tuned via chain-of-thought (CoT) distillation, for dynamic prompt generation upon semantic drift; (iii) a hierarchical safety module enforcing kinematic constraints (e.g., speed, lane centering, stability); and (iv) a compact predictive world model to reward alignment with anticipated ideal states. DriveMind achieves 19.4 +/- 2.3 km/h average speed, 0.98 +/- 0.03 route completion, and near-zero collisions in CARLA Town 2, outperforming baselines by over 4% in success rate. Its semantic reward generalizes zero-shot to real dash-cam data with minimal distributional shift, demonstrating robust cross-domain alignment and potential for real-world deployment.

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling

cs.AI, q-bio.NC updates on arXiv.org

By: Jonas Ngnaw\'e · Maxime Heuillet · Sabyasachi Sahoo · Yann Pequignot · Ola Ahmad · Audrey Durand · Fr\'ed\'eric Precioso · Christian Gagn\'e

16 March 2026 at 12:00

arXiv:2509.23325v3 Announce Type: replace-cross Abstract: Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples, remains challenging. Despite the abundance of non-robust pretrained models in open-source repositories, their potential for RFT is less understood. We address this knowledge gap by systematically examining RFT from such non-robust models. Our experiments reveal that fine-tuning non-robust models with a robust objective, even under small perturbations, can lead to poor performance, a phenomenon that we dub suboptimal transfer. In challenging scenarios (eg, difficult tasks, high perturbation), the resulting performance can be so low that it may be considered a transfer failure. We find that fine-tuning using a robust objective impedes task adaptation at the beginning of training and eventually prevents optimal transfer. However, we propose a novel heuristic, Epsilon-Scheduling, a schedule over perturbation strength used during training that promotes optimal transfer. Additionally, we introduce expected robustness, a metric that captures performance across a range of perturbations, providing a more comprehensive evaluation of the accuracy-robustness trade-off for diverse models at test time. Extensive experiments on a wide range of configurations (six pretrained models and five datasets) show that Epsilon-Scheduling successfully prevents suboptimal transfer and consistently improves expected robustness.

RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation

cs.AI, q-bio.NC updates on arXiv.org

By: Yash Jangir · Yidi Zhang · Pang-Chi Lo · Kashu Yamazaki · Chenyu Zhang · Kuan-Hsun Tu · Tsung-Wei Ke · Lei Ke · Yonatan Bisk · Katerina Fragkiadaki

16 March 2026 at 12:00

arXiv:2510.23571v2 Announce Type: replace-cross Abstract: The pursuit of robot generalists, agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is labor-intensive, slow, unsafe at scale, and difficult to reproduce. As policies expand in scope and complexity, these barriers only intensify, since defining "success" in robotics often hinges on nuanced human judgments of execution quality. We introduce RobotArena Infinity, a new benchmarking framework that overcomes these challenges by shifting vision-language-action (VLA) evaluation into large-scale simulated environments augmented with online human feedback. Leveraging advances in vision-language models, 2D-to-3D generative modeling, and differentiable rendering, our approach automatically converts video demonstrations from widely used robot datasets into simulated counterparts. Within these digital twins, we assess VLA policies using both automated vision-language-model-guided scoring and scalable human preference judgments collected from crowdworkers, transforming human involvement from tedious scene setup, resetting, and safety supervision into lightweight preference comparisons. To measure robustness, we systematically perturb simulated environments along multiple axes, including textures and object placements, stress-testing policy generalization under controlled variation. The result is a continuously evolving, reproducible, and scalable benchmark for real-world-trained robot manipulation policies, addressing a critical missing capability in today's robotics landscape.

Retrofitters, pragmatists and activists: Public interest litigation for accountable automated decision-making

cs.AI, q-bio.NC updates on arXiv.org

By: Henry Fraser · Zahra Stardust

16 March 2026 at 12:00

arXiv:2511.03211v3 Announce Type: replace-cross Abstract: This paper examines the role of public interest litigation in promoting accountability for AI and automated decision-making (ADM) in Australia. Since ADM regulation faces geopolitical headwinds, effective governance will have to rely at least in part on the enforcement of existing laws. Drawing on interviews with Australian public interest litigators, technology policy activists, and technology law scholars, the paper positions public interest litigation as part of a larger ecosystem for transparency, accountability and justice with respect to ADM. It builds on one participant's characterisation of litigation about ADM as an exercise in legal retrofitting: adapting old laws to new circumstances. The paper's primary contribution is to aggregate, organise and present original insights on pragmatic strategies and tactics for effective public interest litigation about ADM. Naturally, it also contends with the limits of these strategies, and of the Australian legal system. Where limits are, however, capable of being overcome, the paper presents findings on urgent needs: the enabling institutional arrangements without which effective litigation and accountability will falter. The paper is relevant to law and technology scholars; individuals and groups harmed by ADM; public interest litigators and technology lawyers; civil society and advocacy organisations; and policymakers.

SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling

cs.AI, q-bio.NC updates on arXiv.org

By: Elisabetta Fedele · Francis Engelmann · Ian Huang · Or Litany · Marc Pollefeys · Leonidas Guibas

16 March 2026 at 12:00

arXiv:2512.05343v2 Announce Type: replace-cross Abstract: Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing approaches predominantly rely on text or image prompts, which often fall short in geometric specificity: language can be ambiguous, and images are difficult to manipulate. In this work, we introduce SpaceControl, a training-free test-time method for explicit spatial control of 3D asset generation. Our approach accepts a wide range of geometric inputs, from coarse primitives to detailed meshes, and integrates seamlessly with modern generative models without requiring any additional training. A control parameter lets users trade off between geometric fidelity and output realism. Extensive quantitative evaluation and user studies demonstrate that SpaceControl outperforms both training-based and optimization-based baselines in geometric faithfulness while preserving high visual quality. Finally, we present an interactive interface for real-time superquadric editing and direct 3D asset generation, enabling seamless use in creative workflows. Project page: https://spacecontrol3d.github.io/.

IROSA: Interactive Robot Skill Adaptation using Natural Language

cs.AI, q-bio.NC updates on arXiv.org

By: Markus Knauer, Samuel Bustamante, Thomas Eiband, Alin Albu-Sch\"affer, Freek Stulp, Jo\~ao Silv\'erio

16 March 2026 at 12:00

arXiv:2603.03897v2 Announce Type: replace-cross Abstract: Foundation models have demonstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for robot skill adaptation from limited data. Combining these approaches holds significant promise for direct application to robotics, yet this combination has received limited attention, particularly for industrial deployment. We present a novel framework that enables open-vocabulary skill adaptation through a tool-based architecture, maintaining a protective abstraction layer between the language model and robot hardware. Our approach leverages pre-trained LLMs to select and parameterize specific tools for adapting robot skills without requiring fine-tuning or direct model-to-robot interaction. We demonstrate the framework on a 7-DoF torque-controlled robot performing an industrial bearing ring insertion task, showing successful skill adaptation through natural language commands for speed adjustment, trajectory correction, and obstacle avoidance while maintaining safety, transparency, and interpretability.

Liquid Biopsy in Non-Metastatic Prostate Cancer: Clinical Evidence and Future Directions

MRD

By: Maria Chiara Sighinolfi · Giuseppe Pallotta · Marzia Del Re · Koosha Moosavi · Or Schubert · Francesco Rossi · Filippo Gavi · Simone Assumma · Enrico Panio · Angelo Totaro · Filippo Turri · Mauro Ragonese · Nazario Foschi · Pierluigi Russo · Ela Patel · Carlo Gandi · Giuseppe Palermo · Eros Scarciglia · Francesco Pinto · Simona Presutti · Marcio Covas Moschovas · Angelo Minucci · Roberto Iacovelli · Chiara Ciccarese · Luca Tagliaferri · Francesco Pierconti · Camilla Nero · Gian Franco Zannoni · Bernardo Rocco

14 March 2026 at 18:00

Cancers (Basel). 2026 Feb 28;18(5):800. doi: 10.3390/cancers18050800.

ABSTRACT

BACKGROUND AND OBJECTIVE: Liquid biopsy has transformed the management of advanced prostate cancer, yet its clinical role in non-metastatic disease remains uncertain. Conventional biomarkers such as PSA, imaging, and pathology have limited ability to capture minimal residual disease and biological aggressiveness. The objective of this review was to critically evaluate the current evidence on circulating tumor cells (CTCs) and circulating tumor DNA (ctDNA) in non-metastatic prostate cancer, focusing on feasibility, prognostic value, and potential clinical applications.

METHODS: A narrative review of PubMed-indexed original studies evaluating liquid biopsy in clinically localized or non-metastatic prostate cancer was performed. Eligible studies included patients treated with curative-intent local therapy or experiencing biochemical recurrence without radiologic metastases. Study designs were predominantly prospective or retrospective observational cohorts. Liquid biopsy analytes included CTCs and ctDNA assessed from peripheral blood plasma using EpCAM-based enrichment, targeted next-generation sequencing, whole-genome sequencing, or ultra-sensitive tumor-informed assays. Primary outcomes included detection rates, associations with clinicopathologic features, biochemical recurrence, metastasis-free survival, and overall survival. Key Findings and Limitations: Across 11 studies, CTC detection using EpCAM-based platforms was infrequent in localized disease and biochemical recurrence and showed limited prognostic value (10-11% in preoperative settings). In contrast, ctDNA was detectable in a minority of patients but consistently identified biologically aggressive disease and a higher risk of recurrence when present, particularly using tumor-informed ultra-sensitive assays. Limitations include low detection rates, heterogeneous methodologies, small sample sizes, and predominantly exploratory study designs.

CONCLUSIONS AND CLINICAL IMPLICATIONS: Currently, its most promising application is not broad screening, but as a selective, biology-driven tool for detecting minimal residual disease and refining risk assessment. CtDNA acts as a biological risk modifier, potentially guiding the escalation or de-escalation of adjuvant therapy. However, prospective biomarker-driven trials are required to validate these strategies before routine clinical implementation.

PMID:41827734 | PMC:PMC12984391 | DOI:10.3390/cancers18050800