Preprint2002
Multiple model-based reinforcement learning
Unknown
Proposes a modular reinforcement learning architecture for nonlinear, nonstationary control tasks using multiple models.
0Jan 1, 2002Reinforcement Learning
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
9 papersPreprint2026
Development of FDD-ON: an Ontology for VAV HVAC System Fault Detection and Diagnostics
Yimin Chen, Brian Fricke, Bo Shen, et al.
This paper introduces FDD-ON, a modular and extensible ontology for VAV HVAC systems that formally represents fault types, symptoms, impacts, and their causal relations to enable interoperable fault detection and diagnostics.
0Jul 31, 2026
arXiv
Preprint2023
Openicl: An open-source framework for in-context learning
Unknown
OpenICL is an open-source framework that provides a modular and flexible interface for in-context learning research and practice.
0Jan 1, 2023In Context Learning
Preprint2025
Flashrag: A modular toolkit for efficient retrieval-augmented generation research
Unknown
FlashRAG is a modular toolkit that provides a comprehensive framework for efficient retrieval-augmented generation research, supporting both LLMs and MLLMs.
0Jan 1, 2025Large Language ModelsRetrieval Augmented Generation
Preprint2026
Lightweight llm agent memory with small language models
Unknown
LightMem is a lightweight memory system for LLM agents that uses Small Language Models to modularize memory retrieval, writing, and long-term storage, improving efficiency and performance.
0Jan 1, 2026Retrieval Augmented Generation
Preprint2026
AI agents: opportunity, hype, and the way through
Unknown
This paper argues that AI agents will evolve into modular research infrastructure that reliably connects databases, theory, experiments, and feedback, rather than remaining hype-driven autonomous systems.
0Jan 1, 2026
PreprintarXiv.org2025
Eliciting Reasoning with Cognitive Tools
Brown Ebouky, A. Bartezzaghi, Mattia Rigotti
This paper shows that equipping LLMs with a small set of cognitive tools—modular reasoning operations executed by the LLM itself—significantly boosts mathematical reasoning performance, e.g., GPT-4.1 pass@1 on AIME2024 rises from 32% to 53%.
5Jun 13, 2025Reinforcement LearningReasoning
arXiv
JournalPLoS Computational Biology2015
Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills
Kai Olav Ellefsen, Jean-Baptiste Mouret, Jeff Clune
This paper shows that evolving modular neural networks with connection costs reduces catastrophic forgetting, enabling faster learning of new skills while retaining old ones.
177Apr 2, 2015Reinforcement LearningNeural Networks
Preprint2025
Mirix: Multi-agent memory system for llm-based agents
Yu Wang, Xi Chen
MIRIX is a modular multi-agent memory system that enables LLM-based agents to overcome critical memory limitations.
0Jul 1, 2025
arXiv