arXiv:2607. 25066v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate reasoning traces, actions, and tool observations that can eventually exceed a model's fixed context window.
arXiv:2608. 12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment state have changed.
arXiv:2609.40118v1 Announce Type: new Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compa...
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:2608. 02515v1 Announce Type: cross Abstract: Long-running assistants and agents consume interaction streams that eventually outgrow the context.
arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.
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.
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.
arXiv:2607. 05708v1 Announce Type: new Abstract: Recent LLM-based agent systems continuously accumulate context across multi-turn interactions, tool invocations, and cross-session workflows.
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:2608.21755v1 Announce Type: new Abstract: Long-horizon agents need memory that identifies relevant experience, resolves revisions, and exposes checkable provenance. We present ECHO (Embodied Co...
The paper introduces the Weighted Memory Tree (WMT), a hierarchical memory system for large language model agents that organizes execution histories into tasks, subtasks, and actions while assigning each memory a dynamic retention score. Event-based updates and selection-based decay allow WMT to preserve useful information, fold completed trajectories, suppress low-utility content, and retain access to folded context. Experiments on GAIA-Text with Qwen3-8B, Gemma 4 E4B, and Llama-3.1-8B show that WMT improves accuracy by an average of 9.97 percentage points and reduces prompt-token usage by 32.8%, while also limiting the persistence of unreliable information.
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.