Zero-Mem: Zero-Token Memory Operations for LLM Agents

• URL: http://arxiv.org/abs/2607.29377v1
• Date: Fri, 31 Jul 2026 13:01:06 GMT
• Title: Zero-Mem: Zero-Token Memory Operations for LLM Agents
• Abstract summary: Zero-Mem preserves original interaction traces as its source of record.<n>Zero-Mem achieves competitive performance across long-memory and long-context question-answering benchmarks.
• Score: 17.228305588778
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged details can obscure the original evidence. We ask whether structured memory access requires generation at all. Zero-Mem introduces \emph{zero-token memory operations}: no step outside final question answering invokes an LLM or consumes LLM input or output tokens; encoder computation is accounted for separately. Zero-Mem preserves original interaction traces as its source of record. It organizes the traces in two complementary ways. An entity--context graph exposes connections across interactions, while a temporal hierarchy preserves conversational locality and session state. For each query, Zero-Mem weighs the two views, retrieves from both, and follows their structure to recover supporting relations or surrounding context. Deterministic calibration first discards conflicting evidence and then keeps the reader's answer grounded in the retrieved traces. Only the final-QA reader invokes an LLM. Across long-memory and long-context question-answering benchmarks, Zero-Mem achieves competitive performance while eliminating LLM calls and LLM-token consumption from memory operations. With the same final-QA reader and context budget, it reduces memory-operation time cost by 57.6\% relative to the fastest compared baseline. Ablations support the contribution of the two views and their query-dependent coordination. Overall, the results show that structured agent memory need not generate an intermediate representation of the past. After peer review, the code and implementation details will be available at \textcolor{blue}{https://github.com/TheMoon0815/Zero-mem}.

Related papers

• Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering [42.31517185994942]
  RAG enables large language models to answer questions by accessing external knowledge.<n>Existing methods suffer from two key challenges: fragmented evidence scattered across temporally distant sessions, and noisy content within retrieved sessions that triggers the lost-in-the-middle effect.<n>We propose MemLoc, a unified Retrieve-Localize-Generate framework for long-term conversational memory QA.
  arXiv  Detail & Related papers  (2026-09-07T06:32:12Z)
• EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph [37.27140929522461]
  Existing methods compress interaction histories into summaries or other LLM-generated representations.<n>We propose EdgeMem, an agent-memory method built around a simple principle: preserve original interaction turns and organize them through complementary content.
  arXiv  Detail & Related papers  (2026-09-03T11:17:03Z)
• LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation [27.436221279026856]
  LycheeMemory V2 is an efficient long-term memory framework that replaces turn-level consolidation with semantic segment-level consolidation.<n>LycheeMemory achieves state-of-the-art performance using GPT-4.12% on LoCoMo and 92.20% on LongMemEval-S.
  arXiv  Detail & Related papers  (2026-08-13T09:13:15Z)
• LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory [10.916121108457537]
  We introduce LazyMem, which deferring all memory construction to query time.<n>On LongMemEval, LazyMem-4B achieves an LLM-judge accuracy of 0.85, outperforming the strongest non-oracle baseline.<n>It further generalizes to LoCoMo without target-domain training and reduces mean latency relative to the prior query-time baseline.
  arXiv  Detail & Related papers  (2026-07-17T12:49:57Z)
• Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents [72.3752981234916]
  Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.<n>We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process.<n>MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5-20%.
  arXiv  Detail & Related papers  (2026-07-15T08:32:40Z)
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations [50.24315431387575]
  We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations.<n>MemOps represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence.<n>Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals.
  arXiv  Detail & Related papers  (2026-07-14T15:33:44Z)
• Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory [19.802226925602927]
  Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions.<n>We propose Infini Memory, a maintainable text-based persistent memory architecture that treats agent memory as topic-structured documents.
  arXiv  Detail & Related papers  (2026-06-09T10:31:51Z)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents [16.625864201773343]
  RecMem stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval.<n>Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.
  arXiv  Detail & Related papers  (2026-05-15T15:17:36Z)
• Lightweight LLM Agent Memory with Small Language Models [27.343533336242913]
  LightMem is a lightweight memory system for better agent memory driven by Small Language Models (SLMs)<n>We organize memory into short-term memory (STM) for immediate conversational context, mid-term memory (MTM) for reusable interaction summaries, and long-term memory (LTM) for consolidated knowledge.<n>Experiments show gains across model scales, with an average F1 improvement of about 2.5 on LoCoMo, more effective and low median latency (83 ms retrieval; 581 ms end-to-end)
  arXiv  Detail & Related papers  (2026-04-09T04:51:07Z)
• LightMem: Lightweight and Efficient Memory-Augmented Generation [72.21680105265824]
  We introduce a new memory system called LightMem, which strikes a balance between the performance and efficiency of memory systems.<n>Inspired by the Atkinson-Shiffrin model of human memory, LightMem organizes memory into three complementary stages.<n>Experiments on LongMemEval with GPT and Qwen backbones show that LightMem outperforms strong baselines in accuracy (up to 10.9% gains) while reducing token usage by up to 117x.
  arXiv  Detail & Related papers  (2025-10-21T17:58:17Z)
• From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents [79.87304940020256]
  Large Language Models (LLMs) have been widely adopted in conversational agents.<n>MemGAS is a framework that enhances memory consolidation by constructing multi-granularity association, adaptive selection, and retrieval.<n> Experiments on four long-term memory benchmarks demonstrate that MemGAS outperforms state-of-the-art methods on both question answer and retrieval tasks.
  arXiv  Detail & Related papers  (2025-05-26T06:13:07Z)
• SCM: Enhancing Large Language Model with Self-Controlled Memory Framework [54.33686574304374]
  Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.<n>We propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information.
  arXiv  Detail & Related papers  (2023-04-26T07:25:31Z)

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.