Memory Tax: Dissecting the Net Value of Agent Memory
Memory Tax: Dissecting the Net Value of Agent Memory
Large-scale evaluations show that dedicated memory systems are often weaker than simple retrieval-enhanced generation. The Memory Benefit and Memory Tax framework is introduced to evaluate the net value. Memory is becoming increasingly common in long-term intelligent agents, but the net value of building memory compared to directly retrieving from raw history remains unclear.
Published on Oct 25
Authors:
,
,
,
,
,
,
,
,
,
Abstract
Large-scale evaluation reveals that dedicated memory systems often underperform naive retrieval-augmented generation, introducing a framework of memory benefit and memory tax to assess net value.
Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear. Through a large-scale evaluation across multiple benchmarks and model backbones, we find many dedicated memory systems underperform naive RAG in many cases, indicating a negative net value. Taking RAG as a reference, we dissect the net value of memory into the gains and losses over direct retrieval, termed memory benefit and memory tax. These gains and losses arise because memory process changes how the raw information is organized and accessed. We view such changes as the double-edged deviations from the raw history. They are originally designed and introduced to benefit the task, for example by reorganizing facts or distilling preferences, but some may also remove or obscure evidence, giving rise to memory tax. Since memory benefit reflects the expected gains of its design, we then focus more on the overlooked memory tax, study how it arises from the system and evaluation side, and generalize the concept to more application scenarios of memory. We hope the notion of memory tax can provide a new lens and shift more attention from standalone performance to the net value of memory, informing more reliable memory designs and evaluations. We will open-source the code and results to the community. Project Page: https://hexuan21.github.io/MemoryTax/
View arXiv page View PDF Project page GitHub 4 Add to collection
Get this paper in your agent:
hf papers read 2610.34073
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.34073 in a model README.md to link it from this page.
Datasets citing this paper 7
hexuan21/MemoryTax-Res-world-model-mem
Viewer • Updated 1 day ago • 546 • 43
hexuan21/MemoryTax-Res-Other
hexuan21/MemoryTax-Res-GPT-5-6-luna
hexuan21/MemoryTax-Res-Qwen3-6-27B
Updated 1 day ago • 27
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.34073 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co