Topic
survey
New Survey Maps How Evidence Tracing and Execution Provenance Can Make LLM Agents Trustworthy
A new survey from arXiv explores evidence tracing and execution provenance as key mechanisms for ensuring trustworthiness in LLM-based agents. The paper defines a unified framework connecting retrieval grounding, tool-use safety, memory lineage, and failure diagnosis, and reviews benchmarks and open challenges.
3D Skeleton Person Re-Identification Survey Reveals Taxonomy, Advances, and Interdisciplinary Potential
A new survey on 3D skeleton based person re-identification (SRID) provides a comprehensive taxonomy, covering hand-crafted, sequence-based, and graph-based modeling approaches, along with supervised, self-supervised, and unsupervised learning paradigms. The paper reviews state-of-the-art methods, evaluates them on standard benchmarks, and discusses key challenges and interdisciplinary prospects, with potential applications in security, biometrics, and beyond.
Medical Image Segmentation Survey: U-Net, Transformers, SAM and Clinical Translation Challenges
A new arXiv survey systematically reviews medical image segmentation methods based on U-Net, Transformer, and SAM architectures. It covers public datasets, evaluation metrics, and key challenges, aiming to guide future research and clinical adoption. The authors have made all related resources publicly available on GitHub.
Survey on Medical Embodied AI Highlights Integration of Perception, Decision-Making, and Action
A systematic survey of medical embodied AI examines its core components — perception, decision-making, and action — and their coordinated integration for real-world clinical workflows. The paper reviews representative applications, datasets, and challenges, highlighting the need for unified system-level organization beyond individual functional aspects.
New Survey Maps Agentic Security: Applications, Threats, and Defenses for Autonomous AI
A new survey from arXiv provides the first holistic overview of agentic security, covering how LLM-based agents are used in cybersecurity, their vulnerabilities, and countermeasures. The analysis of over 260 papers reveals that agentic systems are structurally fragile and require defenses spanning the full agent lifecycle.
AI-Driven Test Case Generation from Natural Language: Survey Reveals Six Quality Gaps and Research Roadmap
A systematic review of 21 primary studies on AI-driven test case generation from natural language requirements reveals that no existing approach simultaneously satisfies six key quality dimensions: automation, ambiguity handling, domain applicability, traceability, evaluation thoroughness, and hallucination control. The survey synthesizes three evolutionary eras and proposes four actionable research guidelines targeting hallucination, traceability, complexity sensitivity, and compliance.
Large Language Models as Optimizers: Survey of Direct vs. Tool-Augmented Approaches and Performance Frontiers
A new survey categorizes LLM-based optimization into direct, tool-augmented, and tool-creating paradigms. It identifies a critical reasoning gap in current architectures and discusses trade-offs between future potential and auditability.
Technology 89% of UK adults unfamiliar with data centers, survey finds knowledge gap
A survey by SEC Newgate found that 89% of UK adults are unfamiliar with data centers, with 14% never having heard of them. However, when provided with factual information, positive sentiment rose from 35% to 61%, and support for building new data centres increased from 54% to 73%. The research highlights a public knowledge gap at a time when the UK is making major digital growth decisions.
Technology Nearly Half of UK Adults Would Eliminate Generative AI If They Could, Survey Fin
A new YouGov survey reveals that 42% of British adults would eliminate generative AI if possible, with younger citizens aged 18-24 most opposed. Public trust has fallen since ChatGPT's launch, and environmental concerns fuel opposition to data centers. Enterprise leaders deploying AI must navigate this scepticism.
Business New Survey Reveals 'Forgotten' Remote Colleagues and Tech Failures Plague Hybrid
A new Jabra survey reveals that around half of remote workers feel excluded in hybrid meetings due to poor technology. 75% of hybrid meetings experience technical failures, adding 11 minutes per meeting. Women and junior workers are more affected.