Pulse: Long-Horizon Tasks Need Streaming Personalization
cs.AI
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
- VideoLLM-online: Online Video Large Language Model for Streaming Video
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- LightMem: Lightweight and Efficient Memory-Augmented Generation
- WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
- Active Retrieval Augmented Generation
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
- StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
- Lost in the Middle: How Language Models Use Long Contexts
- Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
- MemGPT: Towards LLMs as Operating Systems
- Generative Agents: Interactive Simulacra of Human Behavior
- Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
- LaMP: When Large Language Models Meet Personalization
- RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents