arXiv:2606. 06448v1 Announce Type: new Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories.
arXiv:2606. 04315v1 Announce Type: new Abstract: LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems.
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.
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
arXiv:2606. 28434v1 Announce Type: cross Abstract: Long-horizon software engineering agents often need to manage lengthy and noisy interaction histories under limited context budgets.
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.
The paper introduces StructMemEval, a benchmark designed to assess how well large language model (LLM) agents can organize their long‑term memory rather than merely recall facts. It compiles tasks that humans typically solve by structuring knowledge—such as transaction ledgers, to‑do lists, and trees—and evaluates agents on these. Experiments show that simple retrieval‑augmented LLMs struggle with such organization tasks, while memory‑augmented agents perform better when explicitly prompted to structure their memory, yet many modern LLMs still fail to recognize memory structures without prompting.
arXiv:2606. 06090v1 Announce Type: new Abstract: LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade.
arXiv:2607. 21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs.
arXiv:2607. 13157v1 Announce Type: new Abstract: Agent memory is a systems problem for long-horizon agents.
arXiv:2607. 20495v1 Announce Type: new Abstract: Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries.
arXiv:2607. 09493v1 Announce Type: new Abstract: Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive.
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.