# EMIR2: Evolution-Aware Memory with Intent-Guided Multi-Round Retrieval

arXiv: https://arxiv.org/abs/2609.32584 · HTML: https://mlsanity.com/paper/2609.32584/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems](https://mlsanity.com/paper/2506.07398/) (2025)
- [On Memory Construction and Retrieval for Personalized Conversational Agents](https://mlsanity.com/paper/2502.05589/) (2025)
- [MemInsight: Autonomous Memory Augmentation for LLM Agents](https://mlsanity.com/paper/2503.21760/) (2025)
- [Lifelong Learning of Large Language Model based Agents: A Roadmap](https://mlsanity.com/paper/2501.07278/) (2025)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation](https://mlsanity.com/paper/2502.20640/) (2025)
- [MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts](https://mlsanity.com/paper/2605.20926/) (2026)
- [Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents](https://mlsanity.com/paper/2606.06036/) (2026)
- [Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory](https://mlsanity.com/paper/2602.15313/) (2026)

## Abstract (arXiv)

Long-term memory enables large language model (LLM) agents to leverage historical interactions for future tasks. However, existing memory systems struggle to utilize continuously evolving historical information, as they often rely on static memory representations and single-round retrieval strategies, failing to track factual changes or integrate distributed evidence across long-term interactions. To address these challenges, we propose textscEMIR2, an Evolution-Aware Memory framework with Intent-Guided Multi-Round Retrieval, enabling LLM agents to maintain evolving historical knowledge and adaptively retrieve relevant evidence. Specifically, textscEMIR2 constructs a State-Evolving Memory Graph (SEMG) that represents long-term memory as evolving knowledge states supported by temporal event trajectories and evidential associations. By maintaining semantic states through evidence-based updates, SEMG preserves historical evolution and enables evidence tracing under complex and conflicting scenarios. Building upon this, we introduce an intent-guided multi-round retrieval mechanism that iteratively identifies missing evidence and expands retrieval based on accumulated information. Experiments on LoCoMo and MemConflict demonstrate that textscEMIR2 improves long-term memory utilization, dynamic and static conflict handling, and complex retrieval performance, achieving relative improvements of more than 12% in certain categories. These results highlight the effectiveness of jointly modeling memory evolution and adaptive evidence acquisition for long-term agent interactions.