{"total":13,"items":[{"citing_arxiv_id":"2606.30266","ref_index":11,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation","primary_cat":"cs.LG","submitted_at":"2026-06-29T13:14:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Proposes LoRA-based mixture-of-experts with autoencoder routing for continual bidirectional motion-language learning, reporting near-zero forgetting on a 5-task HumanML3D benchmark derived via semantic clustering.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25198","ref_index":46,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","primary_cat":"cs.AI","submitted_at":"2026-06-23T21:44:08+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Heuresis evaluates six search strategies for LLM research agents and shows they steer ideas along quality-diversity-novelty axes but fail to generate novel ideas that match or exceed known high-performing recipes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22449","ref_index":17,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence","primary_cat":"cs.AI","submitted_at":"2026-06-21T11:46:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Proposes a self-evolving cognitive framework integrating causal world modeling, intervention-driven reasoning, and continual refinement for embodied scientific intelligence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18003","ref_index":3,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift","primary_cat":"cs.LG","submitted_at":"2026-06-16T14:50:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"C2FL proposes spatial clustering plus continual learning techniques inside federated learning to maintain performance under combined spatial heterogeneity and temporal drift.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20638","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents","primary_cat":"cs.AI","submitted_at":"2026-06-02T14:40:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"RIZZ is a continual adaptation framework for black-box LLM agents that uses dynamically spawned memory branches, context-aware routing, verifier-gated updates, and prompt compilation to control interference across nonstationary inputs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28577","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Continual Model Routing in Evolving Model Hubs","primary_cat":"cs.AI","submitted_at":"2026-05-27T15:00:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Formalizes continual model routing (CMR), releases CMRBench with over 2000 models, and presents CARvE which outperforms retrieval, fine-tuning and adapter-merging baselines on model/family/domain accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23061","ref_index":11,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Anytime Training with Schedule-Free Spectral Optimization","primary_cat":"cs.LG","submitted_at":"2026-05-21T21:50:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SF-NorMuon is a new schedule-free spectral optimizer that closes the gap with tuned AdamW on 125M-772M parameter models across 1-8x Chinchilla horizons while providing stationarity guarantees.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18903","ref_index":36,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","primary_cat":"cs.LG","submitted_at":"2026-05-17T13:26:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Formalizes Reasoning Portability (RP) and proposes RDB-CL to modulate per-sample KL regularization in RLVR for MLLM continual learning, achieving +12.0% Last accuracy over vanilla RLVR baseline by preserving reusable reasoning on high-RP samples.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14588","ref_index":15,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Silent Collapse in Recursive Learning Systems","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:59:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Silent collapse in recursive learning contracts internal distributions like entropy and diversity despite stable metrics, preceded by three precursors that enable the MTR monitoring framework to intervene early.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00324","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale","primary_cat":"cs.IR","submitted_at":"2026-05-01T01:03:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"IEFF enables retrain-free feature efficiency rollouts in ranking systems by elastically controlling feature coverage at serving time, achieving 5x faster rollouts, zero retraining GPU cost, and 50-55% less performance degradation than abrupt feature removal.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17698","ref_index":69,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability","primary_cat":"cs.LG","submitted_at":"2026-04-20T01:24:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08059","ref_index":21,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study","primary_cat":"cs.RO","submitted_at":"2026-04-09T10:18:51+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2312.03732","ref_index":19,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","primary_cat":"cs.CL","submitted_at":"2023-11-28T03:23:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LoRA adapters should be scaled by 1/sqrt(rank) rather than 1/rank to stabilize learning and enable effective use of higher ranks during fine-tuning of large language models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}