The paper investigates how agent memory contributes to reliable handling of unanswerable questions (UAQs) within a unified Retrieval-Augmented Generation (RAG) framework. Four memory methods were evaluated across three UAQ datasets and two base models, revealing that memory can improve UAQ performance in selective settings but the gains are fragile under dataset shift. Procedural and rule-based memories, especially when combined with complementary behavioral signals, provide the most reliable support, indicating that effective UAQ memory relies more on transferable behavioral guidance than on sheer volume of stored experience.
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
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.
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:2606. 29030v1 Announce Type: new Abstract: AI agents extend conventional large language model (LLM) applications by integrating language understanding with task execution, external tool use, and memory mechanisms.
The paper investigates how large language model agents can over-rely on agentic memory, a phenomenon where retrieved memories distort inference even when they are correctly stored and retrieved. It shows that memory is helpful when past experience fully transfers to the current task but becomes misleading under partial query-memory overlap, a pattern confirmed by controlled experiments. To address this, the authors propose MEMTRIM, a plug‑and‑play framework that indexes memory evidence at write time and limits its reuse at read time, thereby reducing over-reliance without retraining and preserving useful memory benefits across models and memory architectures.
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.
The paper investigates how large language model (LLM) agents can improve performance by storing and reusing experience in external memory. It identifies a problem called error reproduction, where mistakes in stored abstractions propagate through cycles of abstraction, execution, and re-abstraction, leading to persistent errors. To mitigate this, the authors propose Anti-Persistence, a memory design that retains raw trajectories and outcomes but reconstructs task-specific guidance on demand, discarding it after use. Experiments across multiple benchmarks show that Anti-Persistence yields higher held‑out success rates and lower LLM‑call costs compared to other memory designs, supporting the idea of separating experience accumulation from abstraction persistence.
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.
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 RD-Forget, a training‑free framework that separates what a persistent language agent stores from what it uses at answer time. It keeps a source archive of all observations while a query‑conditioned memory view filters evidence relevant to the current question, using a frozen language‑model curator to group facts into semantic slots and preserve multi‑hop relations. The approach employs rate‑distortion principles to stay within a memory budget and demonstrates improvements across conversational memory, knowledge updating, fact consolidation, long‑context reasoning, and personalization tasks.
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.
Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experiences more persistent, compact, and retrievable, but retrieval alone does not ensure that a memory provides valid evidence for the current query.