The paper introduces OPSD, a method that uses on‑policy self‑distillation to train a context‑free student model from a teacher conditioned on user memory, combined with a verify‑then‑regenerate router that directs queries to either weight or text memory. OPSD enables weight memory to compete with or surpass traditional text‑based memory systems on the HaluMem benchmark, reducing token usage per query. The study also explores how different training recipes influence weight memory performance and offers guidance for integrating it with retrieval in persistent, multi‑session agent deployments.
arXiv:2507. 05257v4 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks.
The paper presents a comprehensive evaluation of 11 memory substrates for long‑horizon LLM agents, using a unified set of 26 performance and efficiency metrics across three backbone models and four benchmark suites. It finds that no single substrate consistently outperforms others; retrieval‑heavy substrates aid long‑context factual QA but can impair sequential decision‑making, and scalability can shift performance trade‑offs. The study demonstrates that selecting a memory substrate tailored to the operating regime yields better results than any fixed choice, offering empirical guidance for designing efficient, reliable, and regime‑aware long‑term memory systems.
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics.
arXiv:2608. 12720v1 Announce Type: cross Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely treated as evolvable components.
The paper introduces TokenWorth, a lightweight framework that learns the value of past experiences for self-improving agents operating under strict resource constraints. By using sparse execution feedback, TokenWorth guides both retrieval and memory management without updating the core model, enabling agents to adaptively reuse only the most beneficial experiences. Experiments on LifelongAgentBench show that TokenWorth outperforms existing lifelong-memory methods in task success while minimizing output tokens within the given budgets.
arXiv:2607. 13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
The paper introduces AMA, a framework that uses multiple agents—Constructor, Retriever, Judge, and Refresher—to manage memory for large language model agents. AMA’s hierarchical memory design dynamically adjusts retrieval granularity to match task complexity, while the Judge and Refresher ensure relevance, consistency, and timely updates. Experiments on long-context benchmarks show AMA outperforms existing baselines and cuts token usage by about 80% compared to full-context approaches.
The paper introduces AMBER, an append‑only memory framework for language‑model agents that interact over long horizons. AMBER lets agents jointly learn to reason, act, and write free‑form memory, guaranteeing retention by construction and enabling end‑to‑end reinforcement learning without extensive curated data. Experiments on WebArena Lite show AMBER outperforms overwrite‑based memory by 4.09 percentage points in average success and improves task completion rates in repeated runs.
MemoryArena is a new evaluation gym that benchmarks agent memory in interdependent multi‑session tasks. Unlike prior benchmarks that test memorization or single‑session action in isolation, MemoryArena requires agents to acquire memory while interacting with the environment and then use that memory to guide future decisions across a range of tasks such as web navigation, planning, information search, and formal reasoning. The benchmark reveals that agents excelling on existing long‑context memory tests perform poorly here, highlighting a gap in current memory evaluation methods.
Adaptive Memory Index Evolution for Agents (AMIE) is a lightweight plug‑in layer that evolves per‑memory access state from deployment retrievals without altering stored content or retraining the host memory system. It distills a semantic teacher’s keep/suppress judgments into a retrieval‑conditioned policy and accumulates selective actions into bounded state that reweights subsequent host retrievals. Across five retrieval‑based hosts and three benchmarks, trained AMIE improves downstream F1 or accuracy in all 15 comparisons (0.70–3.37 percentage points) and improves retrieval in all 10 comparisons, demonstrating that persistent memory access can be adapted independently of memory content.
arXiv:2607. 05794v1 Announce Type: new Abstract: Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a consumer of pre-selected evidence.