arXiv:2607. 26637v1 Announce Type: cross Abstract: Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, and reorganizes through generic file tools.
arXiv:2606. 04315v1 Announce Type: new Abstract: LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems.
Agent Zero Memory is a provenance‑aware long‑term memory system for large language model agents that distills user interactions into three parallel memory structures: an episodic timeline, an associative entity‑event knowledge graph, and a semantic, citation‑locked hierarchical documentary memory. Retrieval is performed via an intent gate, source router, and concurrent searches across the three systems, producing integrated, cited answers that exclude fabrication and require evidence the reader has opened. The system achieves state‑of‑the‑art performance on LongMemEval (95.60%) and LoCoMo (93.60%) while offering a favorable accuracy‑cost‑latency trade‑off across multiple backbone LLMs.
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.
The paper introduces Just-in-Time Memory (JitMem), a system that defers memory curation until a task is read, allowing a curator to synthesize task‑specific memory payloads based on the current query. Unlike traditional write‑time curation, JitMem retains raw trajectories and trains the curator using immediate task success, avoiding long‑horizon credit‑assignment issues. Experiments on ALFWorld, WebShop, and τ²‑bench show JitMem consistently outperforms both no‑memory agents and existing write‑time memory methods, with improvements of up to 16.3 absolute success‑rate points. whyItMatters":"By curating memory at read time, JitMem enables more effective, task‑adaptive recall that directly improves agent performance across diverse benchmarks."
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. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations.
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.
Mnemon is a memory agent that stores conversations as raw, dated records and uses a fast System 1 decision model (Jev) to quickly judge the relevance of records, while a slow System 2 LLM plans searches and composes answers. The agent consolidates records into topic timelines and value histories in the background, enabling efficient retrieval without rewriting conversations into structured formats. Experiments show Mnemon achieving high scores on LoCoMo and LongMemEval‑S with low context length and cost, and Jev outperforming LLMs in evidence separation and speed.
arXiv:2607. 20972v1 Announce Type: new Abstract: Coding agents ship with one kind of memory: documents.
arXiv:2608.31057v1 Announce Type: new Abstract: Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles a...
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.
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:2607. 13157v1 Announce Type: new Abstract: Agent memory is a systems problem for long-horizon agents.