Can Large Language Model Agents Learn by Watching Tutorial Videos?
cs.LG, cs.AI, cs.CL, cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- See-Control: A Multimodal Agent Framework for Smartphone Interaction with a Robotic Arm
- A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Agent Workflow Memory
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- FLEX: Continuous Agent Evolution via Forward Learning from Experience
- Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- XSkill: Continual Learning from Experience and Skills in Multimodal Agents
- DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
- Memento 2: Learning by Stateful Reflective Memory
- Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
- RT-1: Robotics Transformer for Real-World Control at Scale
- Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
- VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos
- Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition
- The information bottleneck method
- ChessQA: Evaluating Large Language Models for Chess Understanding
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis