The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2607. 12893v1 Announce Type: new Abstract: Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions.
arXiv:2608.21755v1 Announce Type: new Abstract: Long-horizon agents need memory that identifies relevant experience, resolves revisions, and exposes checkable provenance. We present ECHO (Embodied Co...
The paper introduces QEMem, a framework that rethinks how large language model agents use long‑term memory by constructing query‑specific evidence sets rather than relying on individual memory relevance. QEMem combines query‑guided discovery, source‑grounded reification into structured ViewCards, and sufficiency‑guided refinement to assemble comprehensive evidence from multiple memory granularities. Experiments show that QEMem achieves 91.43% LLM‑judge accuracy on LoCoMo with Claude Opus 4.5, surpassing leading baselines by significant margins and improving evidence coverage for cross‑session queries.
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.
The paper introduces a scale‑conditioned evaluation protocol for agent memory that measures how usable evidence degrades as irrelevant sessions accumulate. It logs memory trajectories and reports four diagnostics—budget‑compliant reliability, tail memory‑call burden, failure‑regime decomposition, and the usable‑scale boundary. Experiments on LongMemEval and LoCoMo show that reliability loss varies across memory interfaces and agents, highlighting that scalable‑memory claims must be conditioned on agent, interface, scale range, and interaction budget.
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.