# VitaBench: Memory Lifecycles Beyond Retrieval

arXiv: https://arxiv.org/abs/2610.14731 · HTML: https://mlsanity.com/paper/2610.14731/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 24 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [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)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks](https://mlsanity.com/paper/2602.16313/) (2026)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models](https://mlsanity.com/paper/2505.22101/) (2025)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues](https://mlsanity.com/paper/2605.12493/) (2026)
- [Useful Memories Become Faulty When Continuously Updated by LLMs](https://mlsanity.com/paper/2605.12978/) (2026)
- [Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents](https://mlsanity.com/paper/2602.10715/) (2026)
- [The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context](https://mlsanity.com/paper/2602.12108/) (2026)
- [Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2602.08382/) (2026)
- [RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents](https://mlsanity.com/paper/2605.16045/) (2026)
- [From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents](https://mlsanity.com/paper/2608.10502/) (2026)
- [MemRefine: LLM-Guided Compression for Long-Term Agent Memory](https://mlsanity.com/paper/2606.13177/) (2026)
- [MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations](https://mlsanity.com/paper/2607.12893/) (2026)
- [Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents](https://mlsanity.com/paper/2607.13591/) (2026)
- [TEPA: Revoking Stale Memories for Conflict-Robust Language Agents](https://mlsanity.com/paper/2608.07429/) (2026)
- [Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory](https://mlsanity.com/paper/2607.17545/) (2026)
- [ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL](https://mlsanity.com/paper/2608.28476/) (2026)

## Abstract (arXiv)

Long-term memory benchmarks for language agents primarily evaluate whether information from earlier interactions can be retrieved and used when relevant. Persistent memory systems face an additional problem before future use is known: deciding whether a memory should remain exact, be compressed, consolidated, or deleted. Existing benchmarks capture long-range retrieval, temporal reasoning, evidence reuse, and incremental interaction, but do not directly evaluate these earlier representation decisions. We formalize memory lifecycle evaluation and introduce VitaBench, a benchmark that makes lifecycle decisions measurable through repeated memory reviews and full-horizon counterfactual evaluation. VitaBench contains a controlled Diagnostic tier that isolates future-use patterns and a Naturalistic tier that composes them into generated customer-service-style interaction streams. We characterize lifecycle decision structure with three diagnostics: lifecycle headroom, measuring the advantage of adaptive choices over the best fixed strategy; horizon reversal, measuring when short-horizon decisions change under delayed consequences; and optimal-action diversity, measuring whether different memory states favor different lifecycle operations. Across both tiers, VitaBench exhibits substantial lifecycle structure: lifecycle headroom is 1.364 in Diagnostic and 1.405 in Naturalistic, and 60.2% and 56.5% of states, respectively, change their preferred action between short and full horizons. A learned delayed lifecycle policy further improves over the best fixed strategy on VitaBench-Naturalistic, reaching 101.5 versus 83.4 joint utility. These results show that retrieving past information and deciding how it should persist are distinct evaluation problems, and that lifecycle management requires evaluation of the delayed consequences of representation decisions.