Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations
cs.AI, cs.IR, cs.SD, eess.AS
Submitted: 2026-09-26
Updated: 2026-09-26
Project page: https://voxpolymem.github.io/VoxPolyBench/demo
Terminology
Sources
- AFA: Identity-Aware Memory for Preventing Persona Confusion in Multi-User Dialogue
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- LightMem: Lightweight and Efficient Memory-Augmented Generation
- M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions
- Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
- Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
- Memory in the Age of AI Agents
- A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
- An LLM Benchmark for Addressee Recognition in Multi-modal Multi-party Dialogue
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
- HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding
- SimpleMem: Efficient Lifelong Memory for LLM Agents
- MemVerse: Multimodal Memory for Lifelong Learning Agents
- Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
- From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection