The paper introduces a new failure mode in agentic memory systems called structurally indirect prerequisite eviction, where upstream memory blocks that are only weakly aligned with a query are prematurely discarded due to budget constraints. The authors define this failure operationally, present a deterministic benchmark and trace diagnostics, and evaluate a one‑hop graph‑aware rule called Dependency‑aware Semantic Garbage Collection (DSGC). DSGC dramatically improves full‑chain retention rates across different encoders, and the study identifies the budget and scaling regimes where the rule is effective or fails.
arXiv:2609.16073v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) serves as the primary memory architecture for long-horizon autonomous agents. However, treating shared memory as...
The paper critiques current agent memory benchmarks that rely on downstream QA accuracy, arguing they conflate memory correctness with retrieval and generation quality, leading to misleading results. It introduces FEB-30, a new benchmark of 30 fact‑evolution trajectories across six diagnostic categories and three difficulty levels, generated automatically to provide deterministic ground truth. Using FEB-30, the authors show a significant divergence between intrinsic and extrinsic evaluations, revealing that a representative memory system correctly classifies memory operations only 20% of the time—an error invisible to traditional QA metrics.
arXiv:2607. 09236v1 Announce Type: new Abstract: Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety.
arXiv:2606. 13177v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks.
MemCut introduces a benchmark to test user-requested forgetting in large language model agents, featuring 456 hand-designed secrets embedded in long-horizon conversations with fully annotated evidence trails. The benchmark defines two recovery metrics—native and residual—to assess how well secrets can be retrieved after deletion. Experiments across five memory designs and four LLMs show that deletion reduces native recovery more than residual recovery, highlighting candidate coverage as a key bottleneck.
arXiv:2610.15642v1 Announce Type: new Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively suf...
Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks. However, as interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence.
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.
arXiv:2607. 17545v1 Announce Type: new Abstract: Language agents depend on memory across interactions.
The paper introduces GRAPHSU, a graph‑guided selective unlearning method for language models that expands deletion beyond explicitly identified forget seeds. By constructing a weighted support‑route graph and propagating deletion pressure, GRAPHSU applies graded forgetting to high‑risk neighboring examples. Experiments on the TOFU and PISTOL benchmarks with GPT‑2 Medium and Llama‑3.2‑3B‑Instruct show that GRAPHSU achieves the lowest utility‑feasible soft leakage, reducing leakage by up to 49.5 percentage points compared to a seed‑only baseline.
The paper introduces a streaming-recall benchmark that separates retention and selection decisions for persistent agents. It shows that query‑aware selection boosts recall by 15.5 points when access is fixed, while mixed comparisons inflate gains due to changes in history access. The study finds that under bounded retention, failures stem from eviction rather than ranking errors, and that dense retrieval can outperform lexical retrieval on natural text.
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...