The paper introduces TRACE, a Transparent Reasoning Architecture for Credible Execution, which provides an explainable AI-based decision framework for autonomous robots. TRACE structures decision-making into four auditable layers—Semantic Perception, Belief Reasoning, Action Synthesis, and Execution Verification—to ensure every action can be traced back to sensor evidence through documented causal chains. Experimental results on warehouse robot navigation show high evidence traceability (98.6%), temporal continuity (99.0%), and decision reconstructability (98.1%) across 500 simulated decision cycles.
By Cagri Temel
The paper investigates how vision‑language models (VLMs) perceive uncertainty in visualizations and make decisions based on visual data. Two studies were conducted: one on agents’ ability to quantify uncertainty in charts, and another on their decision‑making when presented with images. Results show GPT‑4o best perceives uncertainty in pie and bar charts, while agents align most closely with rational decision theory when uncertainty is shown via circle charts, icon arrays, or text.
By Keyty Loza, Shayan Monadjemi
arXiv:2205. 04599v2 Announce Type: replace-cross Abstract: Explainable Artificial Intelligence (XAI) is essential for trustworthy AI in healthcare, yet many existing methods rely on technical explanations that are difficult for clinicians and patients to interpret.
By Mohammad Eslami, Solale Tabarestani, Saber Kazeminasab, Ehsan Adeli, Glyn Elwyn, Tobias Elze, Mengyu Wang, Nazlee Zebardast, Lucia Sobrin, Nassir Navab, Daniel Shu Wei Ting, Malek Adjouadi
arXiv:2606. 15767v1 Announce Type: cross Abstract: Understanding when and why deep neural networks are uncertain is crucial for deploying reliable machine learning systems in safety-critical domains.
By Dong Hyun Jeong, Feng Chen, Jin-Hee Cho, Lance M. Kaplan, Audun J{\o}sang, Soo-Yeon Ji
arXiv:2607. 19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios.
By Gjergji Kasneci, Enkelejda Kasneci
The paper examines a trace‑completeness assumption in language‑enabled robot systems that combine semantic‑graph planning with temporal‑logic safety monitors. By auditing RoboGuard, the authors compare the monitor’s verdict on a surface plan with its verdict on a graph‑refined trace under the same LTL specification. Their evaluation of 28 controlled cases and 14 end‑to‑end scenarios shows that all targeted abstraction cases exhibit the predicted surface‑versus‑refined discrepancy, while controls behave as expected, suggesting that graph‑based trace refinement can serve as a lightweight mitigation and diagnostic tool for physical‑AI safety monitors.
By Stabak Das, Priyesh Ranjan, Xiangfang Li, Lijun Qian
arXiv:2607. 18325v1 Announce Type: cross Abstract: Modern safety-critical systems increasingly rely on human-robot interaction to reduce disaster risk and support decision-making during emergencies.
By Murali Indukuri, Mohammad Eskandari, Sree Nitya Kollu, Stephanie Lukin, Cynthia Matuszek
arXiv:2607. 17861v1 Announce Type: cross Abstract: Establishing interpretable decision-making processes in long-horizon robotic manipulation is critical for enabling reliable human oversight and intervention.
By Yongyan Wen, Feifan Liu, Jinyi Chen, Bo An, Peng Liu, Siyuan Li
arXiv:2606. 15563v1 Announce Type: new Abstract: AI systems increasingly delegate decisions to specialized models, evaluators, tools, and supervisory controllers.
By Carlos R. B. Azevedo
arXiv:2606. 26614v1 Announce Type: cross Abstract: Large language model (LLM) agents enable natural language interaction for scientific visualization (SciVis).
By Kuangshi Ai, Patrick Phuoc Do, Chaoli Wang
GuardEn is an executable safeguard framework that transforms complex safety policies into atomic propositions via Safety‑Rule Compilation and models their composition as executable code. At inference, Scene‑Grounded Execution uses visual scene graphs to instantiate these propositions, allowing rule‑grounded and interpretable safety reasoning. Experiments on SafetyVisionBench show GuardEn improves F1 by an average of 9.8 points over the strongest baseline.
By Jisoo Kim (Sungkyunkwan University), TaeYoon Kwack (Sungkyunkwan University), Jinwoo Jang (Sungkyunkwan University), Honguk Woo (Sungkyunkwan University)
This paper proposes the Bayesian Expected Uncertainty Reduction (B-EUR) model, which formalizes the value of trying a candidate design action as its expected reduction of epistemic uncertainty about action--outcome relations. The model addresses one part of the Uncertainty Driven Action (UDA) model's open question concerning how changes in uncertainty perception determine action selection.