MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off

• URL: http://arxiv.org/abs/2608.04843v1
• Date: Wed, 05 Aug 2026 13:37:08 GMT
• Title: MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
• Abstract summary: Long-horizon LLM agents require memory systems that recover useful evidence from large interaction histories without passing excessive context.<n>We propose MemoryCPT, an end-to-end trainable agent memory pipeline that spans offline memory construction and online query-conditioned context generation.<n> Experiments on LoCoMo and LongMemEval show that MemoryCPT improves the cost-performance trade-off over the evaluated baselines.
• Score: 18.54644708989368
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-horizon LLM agents require memory systems that recover useful evidence from large interaction histories without passing excessive context to downstream models. Existing memory pipelines often rely on hand-crafted heuristics and repeated LLM calls, which can introduce redundant context and high inference cost. We propose MemoryCPT, an end-to-end trainable agent memory pipeline that spans offline memory construction and online query-conditioned context generation. MemoryCPT consists of two stages: Query-agnostic Distillation (QAD), which distills a modular memory-construction pipeline into a compact model using explicit reasoning traces; and Query-aware Retrieval and Summarization (QAR), which combines reciprocal rank fusion (RRF) with a LoRA-based summarizer trained via Group Relative Policy Optimization (GRPO) under a cost-aware reward. We further introduce Quality per Cost (QPC) to quantify answer quality per unit inference cost. Experiments on LoCoMo and LongMemEval show that MemoryCPT improves the cost-performance trade-off over the evaluated baselines, while ablation and sensitivity analyses characterize the contributions of its components and the effects of key design choices.

Related papers

• Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents [97.19033877543522]
  We present a controlled harness evaluation of memory substrates for memory-augmented agents.<n>We instrument 26 performance and efficiency metrics under a unified harness.<n>These findings motivate substrate routing as a necessary component of adaptive agent memory systems.
  arXiv  Detail & Related papers  (2026-08-15T03:29:48Z)
• MemRefine: LLM-Guided Compression for Long-Term Agent Memory [67.62350557461352]
  Large language model (LLM) agents are increasingly expected to operate over long-term interactions.<n>As interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence.<n>This is especially limiting on resource-constrained platforms with hard memory budgets.<n>We propose storage-budgeted memory management, the task of keeping an already constructed memory store within a fixed budget while preserving information useful for future interactions.
  arXiv  Detail & Related papers  (2026-06-11T10:46:17Z)
• Mem-$π$: Adaptive Memory through Learning When and What to Generate [65.31077328444077]
  We present a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand.<n>Mem-$$ consistently outperforms retrieval-based and prior RL-optimized memory baselines.
  arXiv  Detail & Related papers  (2026-05-20T17:51:05Z)
• MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution [52.29303869050117]
  Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction.<n>MemMA is a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths.
  arXiv  Detail & Related papers  (2026-03-19T10:15:59Z)
• Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents [0.0]
  Persistent AI systems face a choice between passing full conversation histories to a long-context large language model (LLM) and maintaining a dedicated memory system that extracts and retrieves structured facts.<n>We compare a fact-based memory system built on the Mem0 framework against long-context LLM inference on three memory-centric benchmarks.
  arXiv  Detail & Related papers  (2026-03-05T05:01:30Z)
• Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory [56.0946692457838]
  BudgetMem is a runtime agent memory framework for explicit, query-aware performance-cost control.<n>A lightweight router performs budget-tier routing across modules to balance task performance and memory construction cost.<n>Across LoCoMo, LongMemEval, and HotpotQA, BudgetMem surpasses strong baselines when performance is prioritized.
  arXiv  Detail & Related papers  (2026-02-05T18:57:09Z)
• Mem-T: Densifying Rewards for Long-Horizon Memory Agents [23.19373149519922]
  We introduce Mem-T, an autonomous memory agent that interfaces with a lightweight hierarchical memory database to perform dynamic updates and multi-turn retrieval over streaming inputs.<n>We also propose MoT-GRPO, a tree-guided reinforcement learning framework that transforms sparse terminal feedback into dense, step-wise supervision via memory operation tree backpropagation and hindsight credit assignment.
  arXiv  Detail & Related papers  (2026-01-30T14:23:33Z)
• MemRec: Collaborative Memory-Augmented Agentic Recommender System [57.548438733740504]
  We propose MemRec, a framework that architecturally decouples reasoning from memory management.<n>MemRec introduces a dedicated LM_Mem to manage a dynamic collaborative memory graph.<n>It achieves state-of-the-art performance on four benchmarks.
  arXiv  Detail & Related papers  (2026-01-13T18:51:16Z)
• SR-CIS: Self-Reflective Incremental System with Decoupled Memory and Reasoning [32.18013657468068]
  We propose the Self-Reflective Complementary Incremental System (SR-CIS) It consists of the Complementary Inference Module (CIM) and Complementary Memory Module (CMM) CMM consists of task-specific Short-Term Memory (STM) region and a universal Long-Term Memory (LTM) region. By storing textual descriptions of images during training and combining them with the Scenario Replay Module (SRM) post-training for memory combination, SR-CIS achieves stable incremental memory with limited storage requirements.
  arXiv  Detail & Related papers  (2024-08-04T09:09:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.