MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval
cs.CL, cs.LG
Submitted: 2026-09-02
Updated: 2026-09-02
Comments: 8 pages, 2 figures, 4 tables
License: http://creativecommons.org/licenses/by/4.0/
The gist: Long-term LLM agents must preserve information across interactions while distinguishing repeated evidence, historical states, updates, and unresolved contradictions.
Terminology
Abstract
Long-term LLM agents must preserve information across interactions while distinguishing repeated evidence, historical states, updates, and unresolved contradictions. Existing textual memory systems retrieve semantically relevant memories efficiently but often leave these relationships implicit, whereas richer structured approaches model them through global graphs, hierarchical abstractions, or reflection at greater complexity. We introduce MemoryLACE (MemLACE), a lightweight memory framework that explicitly models the lifecycle of textual evidence through sparse merge, supersession, and contradiction relations while preserving atomic natural-language memories and their provenance. Rather than retrieving memories independently, MemLACE reconstructs relation-aware evidence units that expose current, historical, supporting, and conflicting evidence for downstream reasoning. Across BEAM and StructMemEval, using open-weight and proprietary LLM backbones, MemLACE achieves the highest overall performance in same-backbone comparisons while reducing end-to-end runtime on BEAM by 66.6% relative to Hindsight, the strongest reported reflective-memory baseline. Ablation studies identify lifecycle expansion and temporal awareness as the principal contributors to these gains. Together, the results demonstrate that explicitly modeling the local lifecycle of textual evidence is sufficient to substantially improve long-term memory reasoning without requiring comprehensive knowledge graphs or global reflection.
Sources
- Memory in the Age of AI Agents
- Generative Agents: Interactive Simulacra of Human Behavior
- MemGPT: Towards LLMs as Operating Systems
- SimpleMem: Efficient Lifelong Memory for LLM Agents
- On Memory Construction and Retrieval for Personalized Conversational Agents
- A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents
- TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
- HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents
- Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
- Evaluating Memory Structure in LLM Agents
- Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- MemOS: A Memory OS for AI System
- Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering