Lifecycle

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 68

All topics

Evolve: A Persistent Knowledge Lifecycle for Small Language Models
Apr 25, 2026Dikran HovagimianLarge Language Model Memory Retrievers
Independent Researcher
Unlocking the Forecasting Economy: A Suite of Datasets for the Full Lifecycle of Prediction Market: [Experiments & Analysis]
Apr 22, 2026Huaiyu Jia, Luofeng Zhou, Wentao Zhang +3Data-Driven Forecasting Lifecycle
Nanyang Technological University Singapore, Singapore
Cold-Start Forecasting of New Product Life-Cycles via Conditional Diffusion Models
Apr 22, 2026Ruihan Zhou, Zishi Zhang, Jinhui Han +2Conditional Distribution Lifecycle
Guanghua School of Management, Peking University, Beijing 100871, China · Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology, Hong Kong SAR, China
Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
Apr 17, 2026Xing Zhang, Guanghui Wang, Yanwei Cui +4Large Language Model Agents Long-Term Agent Memory
AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China.
Autogenesis: A Self-Evolving Agent Protocol
Apr 16, 2026Wentao Zhang, Zhe Zhao, Haibin Wen +4Self-Evolving Agents Alphaevolve
Nanyang Technological University · Stanford University · City University of Hong Kong +1
Agentic AI-RAN: Enabling Intent-Driven, Explainable and Self-Evolving Open RAN Intelligence
Feb 27, 2026Zhizhou He, Yang Luo, Xinkai Liu +4Self-Evolving Agents Lifecycle
5G/6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, UK · 6G Research Center, Khalifa University, Abu Dhabi, UAE
CIRCLE: A Framework for Evaluating AI from a Real-World Lens
Feb 27, 2026Reva Schwartz, Carina Westling, Morgan Briggs +12Artificial Intelligence Evaluation Lifecycle
Civitaas Insights · Bournemouth University · Independent Researcher +11
Is Knowledge Distillation Actually Greener? A Case Study in Machine Translation
Feb 10, 2026Joseph Attieh, Timothee Mickus, Anne-Laure Ligozat +2Knowledge Distillation Machine Translation
University of Helsinki · Université Paris-Saclay, CNRS, LISN

Apr 25, 2026, cs.LGJ/K move · Enter open · S save

Evolve: A Persistent Knowledge Lifecycle for Small Language Models

Dikran Hovagimian

Independent Researcher

Large Language Model Memory Retrievers Reusable Knowledge Lifecycle

Open paper AskPDF arXiv

Evolve pairs a small local language model with a persistent, teacher-compiled knowledge store -- refined through sleep consolidation and usage-driven refresh -- to deliver substantial accuracy gains over the model's parametric baseline while amortizing teacher costs through cross-query knowledge reuse. Rather than retrieving document fragments at query time, Evolve constructs a store of semantically coherent sections compiled by teacher models at natural conceptual boundaries; new sections are staged on acquisition, consolidated offline through teacher-mediated merging, and refreshed inline when expired. A 2B-parameter local model handles classification and generation; large teacher models are invoked only for knowledge operations. Across 750 benchmark queries spanning custom specialist questions, NaturalQuestions, and TriviaQA, the 2B model augmented by Evolve improves from 20-33% baseline accuracy to 60-84% (+40-52pp) while reducing teacher invocations by over 50% through reuse. Post-consolidation compresses the knowledge store by 31-33.5% across three independent benchmarks while preserving accuracy; section-based retrieval outperforms chunk-based retrieval by 5-9pp across every lifecycle condition. The architecture supports two generation modes over the same lifecycle -- suppress (strict section-only grounding, auditable) and augment (section-supplemented responses).

Momentum

Related topics

Latest papers 68