arXiv Computation and Language
Memory Tax: Dissecting the Net Value of Agent Memory
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Sep 10
When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
arXiv Machine Learning
Jul 10
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
arXiv:2607. 08032v1 Announce Type: new Abstract: Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions.
arXiv AI
Oct 15
Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents
arXiv:2610.18052v1 Announce Type: new Abstract: Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users...
arXiv Machine Learning
Jun 25
Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory
arXiv:2606. 25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights.
Hugging Face Trending Papers
4d ago
Top-$k$ Retrieval Leaves Memory Value Undetermined
The paper examines how a memory‑augmented agent can determine the value of its memories using only retrieval logs. It shows that top‑k retrieval fails to assign any value to memories regardless of the number of episodes logged, and that a single question can determine at most one memory’s value. To address this, the authors propose LEDGER, which estimates determined Shapley values with confidence intervals, merges memories with identical histories, and strategically retrieves to increase determinability, achieving a substantial rise in determined memories on HotpotQA and LoCoMo.
Hugging Face Trending Papers
Aug 5
Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems
LLM agents that persist across sessions accumulate stored memories whose validity varies enormously by content type, yet existing memory architectures treat all memories as equally persistent and systematically contaminate retrieved context with outdated facts. We show that per-memory, type-conditioned temporal decay, a property of western scrub jay episodic memory, can be operationalized as an auto-classified coefficient $π_i$ in an external LLM-agent memory store, yielding ScrubJay-MEM: each memory is encoded as a jointly-bound What--Where--When tuple with an estimated perishability $π_i$ and utility horizon $τ_i$, retrieved by query-adaptive scoring, and revised retroactively at $O(1)$ LLM calls per update.