{"total":11,"items":[{"citing_arxiv_id":"2606.24985","ref_index":111,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","primary_cat":"cs.LG","submitted_at":"2026-06-23T14:24:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11169","ref_index":79,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents","primary_cat":"cs.AI","submitted_at":"2026-05-11T19:28:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10936","ref_index":82,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Personal Visual Context Learning in Large Multimodal Models","primary_cat":"cs.CV","submitted_at":"2026-05-11T17:59:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces Personal VCL formalization and benchmark revealing LMM context gaps, plus an Agentic Context Bank baseline that boosts personalized visual reasoning.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"personal items, and knows exactly how they like their fried eggs cooked. Equipped with this visual memory, AI assistants can answer personalized queries and provide active guidance for the user, such as pinpointing where they left their water bottle or alerting if the egg is getting overcooked compared to their usual standard. This vision fundamentally rests on the broader challenge of model personalization [82]. In the text domain, the established mechanism for personalizing LLMs [63, 42, 53, 62, 64] relies on retrieving relevant written information about the user and prepending it to the prompt to guide generation. In this paper, we explore the direct visual analog of this paradigm. As illustrated in Fig. 1, a user's visual history consists of the long, continuous egocentric stream captured over time, from which relevant"},{"citing_arxiv_id":"2605.09359","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Skill-R1: Agent Skill Evolution via Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-05-10T06:19:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Skill-R1 applies bi-level group-relative policy optimization to evolve skills recurrently from verified outcomes, yielding gains over baselines on multi-step tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08526","ref_index":74,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck","primary_cat":"cs.LG","submitted_at":"2026-05-08T22:17:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18955","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Assessing Capabilities of Large Language Models in Social Media Analytics: A Multi-task Quest","primary_cat":"cs.CL","submitted_at":"2026-04-21T01:05:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLMs show mixed results on authorship verification, post generation, and attribute inference from Twitter data, with new frameworks and user studies establishing benchmarks for these analytics tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13074","ref_index":49,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PersonaVLM: Long-Term Personalized Multimodal LLMs","primary_cat":"cs.CL","submitted_at":"2026-03-20T17:59:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PersonaVLM adds memory extraction, multi-turn retrieval-based reasoning, and personality inference to multimodal LLMs, yielding 22.4% gains on a new long-term personalization benchmark and outperforming GPT-4o.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.16120","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users","primary_cat":"cs.CL","submitted_at":"2026-03-17T04:59:32+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Personalized deep research systems need evaluation with real users because LLM judges overlook nuanced errors that matter to researchers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.02845","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents","primary_cat":"cs.CL","submitted_at":"2026-01-06T09:24:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TiMem introduces a Temporal Memory Tree that consolidates conversational history into hierarchical persona representations, reaching 75.30% on LoCoMo and 76.88% on LongMemEval-S while cutting recalled length by 52%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.04465","ref_index":110,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents","primary_cat":"cs.HC","submitted_at":"2025-10-06T03:38:54+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A 3x3 between-subjects experiment finds that risk-contingent autonomy in LLM agents attenuates personalization's negative effects on privacy concerns and trust via increased perceived control.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.21046","ref_index":284,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","primary_cat":"cs.AI","submitted_at":"2025-07-28T17:59:05+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}