MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
cs.AI
Submitted: 2026-08-07
Updated: 2026-10-27
Code: https://github.com/Feld-maxiu/MemPrism
Project page: https://cfg-bench.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
- A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
- MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Qwen-Image Technical Report
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
- Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
- On the Structural Memory of LLM Agents
Related papers
- 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
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems