Large Language Models (LLMs) have achieved remarkable progress across diverse domains, but continual adaptation to evolving tasks and environments remains a key challenge. Existing memory-augmented ap...
arXiv:2607. 13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.
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:2606. 06787v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge.
M-Plan is a closed‑loop multi‑agent system that combines long‑term and short‑term memory to improve large language model agents on long‑horizon, multi‑turn tasks. It uses task‑specific milestones and local hints to generate global‑local guidance, forming short‑term memory during execution, and then optimizes and stores relevant information in long‑term memory for future use. Experiments on ALFWorld, Webshop, and PDDL show that M‑Plan outperforms baseline methods in both accuracy and efficiency.
arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.
arXiv:2606. 26105v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong capabilities in short-context reasoning but degrade in performance over long conversational horizons due to context window limitations and inefficient token usage.
arXiv:2607. 24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model.
The paper introduces the Unified Memory Agent (UMA), a system that builds a query‑agnostic external memory from a data stream and reuses it across multiple question‑answering sessions. UMA employs a single policy to manage a structured Memory Bank via CRUD operations and uses Task‑Stratified GRPO to supervise memory maintenance based on QA trajectory rewards. The authors also present Ledger‑QA, a benchmark for long‑horizon state tracking, and demonstrate that UMA outperforms other methods on test‑time learning and accurate‑retrieval tasks, with UMA‑Specialist further improving performance after task adaptation.
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.
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.