{"total":12,"items":[{"citing_arxiv_id":"2606.08723","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Text to Discovery: How Large Language Models Are Accelerating and Complicating Research Across Scientific and Humanistic Disciplines","primary_cat":"cs.DL","submitted_at":"2026-06-07T16:38:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"LLMs accelerate research workflows from idea generation to writing but introduce challenges like hallucination, bias, opacity, and ten systemic risks requiring new governance frameworks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03876","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members","primary_cat":"cs.HC","submitted_at":"2026-06-02T16:46:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Redesigned LLM summaries of older adults' tracking data, structured as multi-layer narratives, were rated higher in satisfaction, helpfulness, trust, and willingness by 11 remote family members in a survey.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29483","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data","primary_cat":"cs.AI","submitted_at":"2026-05-28T07:10:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VitalAgent adds longitudinal memory and tool-augmented reasoning to an agent for reactive QA and proactive monitoring on ECG/PPG streams, reporting >25% gains over baselines on a new 1,862-pair + 90-hour benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27466","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems","primary_cat":"cs.MA","submitted_at":"2026-05-26T08:10:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AgensFlow learns coordination policies from task trajectories and outperforms fixed pipelines on distributed-systems incident and security-advisory tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21295","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:25:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09579","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Biosignal Fingerprinting: A Cross-Modal PPG-ECG Foundation Model","primary_cat":"cs.LG","submitted_at":"2026-05-10T14:40:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A cross-modal masked autoencoder creates reusable biosignal fingerprints that match or exceed specialist models on seven cardiovascular tasks using only single-modality input.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00468","ref_index":70,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?","primary_cat":"cs.CL","submitted_at":"2026-05-01T07:11:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Personalized LLM-generated plain language summaries improve lay readers' comprehension and quality ratings but increase risks of reinforcing biases and introducing hallucinations compared to static expert summaries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23938","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Authority Inversion in LLM-Mediated Ubiquitous Systems: When Models Trust Users Over Sensors","primary_cat":"cs.AI","submitted_at":"2026-04-28T04:59:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LLMs exhibit authority inversion by prioritizing natural-language user claims over numerical sensor data in conflicts, diagnosed with new geometric metrics and mitigated via layer-level calibration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10172","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Wearable AI in the Era of Large Sensor Models","primary_cat":"eess.SP","submitted_at":"2026-04-11T11:41:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Large Sensor Models trained on large-scale multimodal wearable data can provide a scalable, general framework for wearable AI by learning transferable representations across modalities and tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.02501","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook","primary_cat":"eess.SP","submitted_at":"2026-04-02T20:09:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"ECG foundation models for signal interpretation and medical LLMs for reasoning can be integrated into agentic systems for real-time cardiovascular intelligence on edge devices.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"These challenges motivate the need for more generalizable and clinical knowledge-aware modeling paradigms for cardiovascular intelligence [10]. Lately, Large Language Models (LLMs) and Foundation Models (FMs) have emerged as transformative paradigms in artificial intelligence, enabling scalable representation learning and reasoning across various sub-disciplines of health domain [11, 12]. Specialized LLMs such as Med-PaLM, Med-Gemma, BioGPT, MEDITRON, and Med42 have demonstrated strong capabilities in clinical question answering, reasoning, report generation, and knowledge synthesis [13-17]. However, these medical LLMs are predominantly trained on textual cor- pora-including biomedical literature and electronic health arXiv:2604."},{"citing_arxiv_id":"2406.06543","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SparrowSNN: A Hardware/software Co-design for Energy Efficient ECG Classification","primary_cat":"cs.AR","submitted_at":"2024-05-06T10:30:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SparrowSNN introduces SSF activation, a tunable hybrid ANN-SNN, and reconfigurable ASIC achieving SOTA accuracy on MIT-BIH ECG with 20-100x lower energy than prior ultra-low-power solutions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2401.05459","ref_index":191,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","primary_cat":"cs.HC","submitted_at":"2024-01-10T09:25:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"This survey discusses key components and challenges for Personal LLM Agents and reviews solutions for their capability, efficiency, and security.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"There is also research examining the relationship between sensor data and user career advancement [195], as well as a study that predicts user life satisfaction [196]. Furthermore, specific states of users have been a focus, including studies on the perception of mental illnesses [197, 198], such as one that predicts and analyzes schizophrenia [199], depression [190], and another that detects habits like smoking [ 200]. Lifelo et al. [191] utilized LLM to conduct psychological disorder analysis for a highly rare African language. Additionally, Ouyang and Srivastava[201] attempt to extract higher-level perceptual information from simple data. Long-term sensing involve deep and abstract information, containing the profound logic behind user behavior. These pieces of information are often more subtle, making perception and maintenance challenging."}],"limit":50,"offset":0}