# When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents

arXiv: https://arxiv.org/abs/2609.05441 · HTML: https://mlsanity.com/paper/2609.05441/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 17 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [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)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs](https://mlsanity.com/paper/2510.27246/) (2025)
- [HaluMem: Evaluating Hallucinations in Memory Systems of Agents](https://mlsanity.com/paper/2511.03506/) (2025)
- [RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction](https://mlsanity.com/paper/2601.06966/) (2026)

## Built on by (most cited first, 1 of 1)

- [When Evidence Changes: Evaluating Memory Repair and Re-reading in Language-Model Agents](https://mlsanity.com/paper/2610.03902/) (2026)

## Abstract (arXiv)

Long-term memory for LLM agents is evaluated today by conversational recall benchmarks (LoCoMo, LongMemEval), which measure question answering over dialogue history, not whether remembered facts change what a tool-using agent does. We present MERIT (Memory Evaluation for Realistic Instrumented Tasks), a benchmark and harness that measures the marginal utility of memory for task-executing agents under explicit cost accounting. MERIT provides episodic tool-use tasks in three domains whose dependence on earlier-episode facts is verified by an automated leak check; a difficulty ladder ending in updated-fact recall; controlled memory corruption; and full token and dollar metering of every memory operation. Across 23,440 scored episodes (42.57), a two-generation pilot on gpt-4.1-mini and a preregistered 3-model x 3-seed grid (GPT-4.1, Claude Haiku 4.5; memory side held fixed), memory lifts dependent-task success from a leak-verified floor of 0.00 to 0.55-1.00. On updated facts, embedding retrieval collapses unpredictably (0.30-0.95 across models; max seed gap 0.45), and agents act on a correctly retrieved value only 55% of the time, while update-on-write stores (a structured fact store and, notably, LLM summarization) remain at 0.70-1.00; the hybrid is worse than the fact store alone. A latest-generation spot-check (Claude Sonnet 5, gated on a clean full-replay control) reproduces the pattern. Swapping a memory's implementation moves task success by up to 60 points, and full replay is never economical: the best condition per domain delivers 2.7-3.9x its marginal utility per dollar. We release the benchmark, harness, and all traces.