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.
arXiv:2610.34073v1 Announce Type: new Abstract: Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear...
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memory architectures treat all memories as equally persistent and systematically contaminate retrieved context with outdated facts.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.
arXiv:2606. 26511v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time.
The paper evaluates the impact of adding a persistent memory tier to a multi‑agent large language model inference system. While decomposing long‑context inference across agents reduces the peak KV cache usage from about 35 MiB to 14.3 MiB per query, the persistent tier adds only a modest 0.368 MiB to the cache and shows no measurable accuracy improvement across eight dataset pairs. The authors argue that the lack of benefit is structural, as single‑question benchmarks do not provide informative recall opportunities, and they outline conditions and detection procedures for agent‑memory ablations.
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...
The paper introduces Causal Memory Policy (CMP), a framework that identifies the utility of memories in memory‑augmented language models by intervening on retrieval rather than on storage. CMP reserves fixed context slots for memories sampled with known propensities and estimates utility using self‑normalized inverse propensity weighting, providing unbiased estimates and exact variance. Experiments show that CMP improves discrimination between required and non‑required memories and reveals that identified utility alone is insufficient for retention decisions across unseen queries.
arXiv:2610.17763v1 Announce Type: new Abstract: Long-term memory supports agents across sessions. Repeated retrieval and write-back can let one historical claim occupy multiple retrieval positions an...
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: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:2609.25054v1 Announce Type: new Abstract: For a long-horizon LLM agent, the memory question is not what was once recorded but what \emph{currently holds}. Most designs answer it only indirectly...
The paper introduces a new retrieval method called Retrieval as Traversal, which treats memory retrieval as a persistent local traversal through an address space, separating content from address. It proposes a cost‑regularised indexing objective that balances information value against retrieval cost, encouraging complementary memories to be co‑retrievable while discouraging redundant ones. A simple fixed‑geometry implementation was tested on MiniGrid Memory, achieving a mean return of 0.95 after 0.59M steps with a five‑token context, outperforming Gaussian and categorical absolute addressing baselines.
The paper introduces JointCoreBench, a benchmark for evaluating memory selection in large language model agents, and JointCore, a cost‑ordered group‑deletion baseline that identifies minimal sufficient memory subsets. JointCore achieves perfect recovery of minimum‑cost sufficient sets across 6,912 conditions, cuts subset evaluations by 62.9%, and saves 87.8% of active memory usage. Experiments across multiple model families and tasks demonstrate that JointCore preserves full‑memory behavior while reducing model queries and cost‑aware recovery rates compared to singleton deletion.