{"work":{"id":"4519e90e-26c9-43ef-a89b-c8e8a8378280","openalex_id":"https://openalex.org/W7118560772","doi":"10.48550/arxiv.2601.01885","arxiv_id":"2601.01885","raw_key":null,"title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","authors":null,"authors_text":"Yi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan, Jiaqi Feng, Yunfei Li, Libing Wu","year":2026,"venue":"cs.CL","abstract":"Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components, relying on heuristics or auxiliary controllers, which limits adaptability and end-to-end optimization. In this paper, we propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy. AgeMem exposes memory operations as tool-based actions, enabling the LLM agent to autonomously decide what and when to store, retrieve, update, summarize, or discard information. To train such unified behaviors, we propose a three-stage progressive reinforcement learning strategy and design a step-wise GRPO to address sparse and discontinuous rewards induced by memory operations. Experiments on five long-horizon benchmarks demonstrate that AgeMem consistently outperforms strong memory-augmented baselines across multiple LLM backbones, achieving improved task performance, higher-quality long-term memory, and more efficient context usage.","external_url":"https://arxiv.org/abs/2601.01885","cited_by_count":0,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2601.01885","created_at":"2026-05-09T06:20:42.300212+00:00","updated_at":"2026-08-05T02:49:54.815029+00:00","title_quality_ok":true,"display_title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","render_title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents"},"hub":{"state":{"work_id":"4519e90e-26c9-43ef-a89b-c8e8a8378280","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":31,"external_cited_by_count":0,"distinct_field_count":6,"first_pith_cited_at":"2026-04-03T04:26:56+00:00","last_pith_cited_at":"2026-07-07T03:47:12+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-23T22:59:27.970266+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":5},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":5},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}