arXiv:2606. 31121v1 Announce Type: new Abstract: Sequentially evolving LLM memory enables agents to reuse past experience, but existing systems usually deploy each locally generated memory update without checking whether it improves future behavior.
arXiv:2608. 03699v1 Announce Type: new Abstract: Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning.
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
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:2605.12978v2 Announce Type: replace Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolid...
arXiv:2606. 24040v1 Announce Type: cross Abstract: MeMo proposes language models with explicit multi-layer correlation matrix memories (CMMs), where memorization, retrieval, and forgetting are architectural operations.
arXiv:2608. 19652v1 Announce Type: new Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps.
AdaMem introduces adaptive memory policies that allow personalized agents to decide what information to write into long‑term memory based on user preferences for each interaction context. Each policy is updated from periodic feedback and controls subsequent memory writing, aiming to improve relevance and reduce unnecessary memory persistence. In experiments on AdaMem‑Bench, AdaMem raises QA accuracy from 80.0% to 84.35% while cutting persistent memory by 9.27%, though models still struggle to execute policies reliably.
arXiv:2608. 07429v1 Announce Type: new Abstract: Long-term memory enables language agents to reuse past facts, preferences, and task experience.
arXiv:2607. 01523v1 Announce Type: cross Abstract: Recurrent memory agents extend LLMs to arbitrarily long contexts by iteratively consolidating input into a fixed-size memory window.
As preferences, goals, and facts change, LLM agents must use the current state while earlier versions remain in context. Yet they can answer with an old value of the same variable, a failure that we c...
arXiv:2607. 04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval.
arXiv:2608. 03137v1 Announce Type: new Abstract: Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon interaction.