Can Agent Memory Systems Track Evolving State?

• URL: http://arxiv.org/abs/2608.19652v1
• Date: Thu, 20 Aug 2026 05:41:23 GMT
• Title: Can Agent Memory Systems Track Evolving State?
• Abstract summary: We argue an effective memory system must track the evolving state of the world.<n>As facts, constraints, and decisions are revised over a long interaction, answers must reflect the current state and not a superseded one.<n>We define this capability as state tracking and instantiate it in StateMemBench.
• Score: 19.24558136812374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmarks focus largely on recall-shaped tasks, we argue an effective memory system must track the evolving state of the world; as facts, constraints, and decisions are revised over a long interaction, answers must reflect the current state and not a superseded one. We define this capability as state tracking and instantiate it in StateMemBench, a benchmark of 234 multi-session scenarios spanning two conversation-length regimes. Its closed-pool grading scores whether an answer reflects the current state, the superseded state, or fails otherwise, separating state-tracking failures from other errors by construction. Our analysis shows that this task is challenging for existing memory systems, retrieval-augmented baselines, and long-context baselines. We then present StateMem, a state-first memory method that explicitly tracks supersession and relational dependencies, and show it improves current-state accuracy over the strongest same-backbone baseline by 1.8x (0.205 -> 0.363) on DeepSeek-V4-Flash and over the strongest memory system by 1.6x (0.149 -> 0.233) on Qwen-3.5-9B, while remaining competitive with the long-context baselines. Finally, we show the same state approach can be applied as a lightweight single-call wrapper over existing memory systems, lifting current-state accuracy by +32 to +67 points on StateMemBench across six memory and retrieval backends. A length- and cost-matched control attributes +15 to +32 of those points to state structure rather than added context.

Related papers

• LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference [6.324239367257621]
  Long-running assistants and agents consume computation streams that eventually outgrow the context.<n>Existing context retention, summarization, and retrieval preserve access to selected history, but do not provide a persistent state over the full lifecycle when working context changes.<n>We introduce an intrinsic memory method, textbfLiveMem, which augments a pretrained full-attention LLM with a memory state that preserves the historical information over the whole lifecycle.
  arXiv  Detail & Related papers  (2026-08-03T17:12:05Z)
• 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)
• A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory [7.7803190371583]
  We study emphghost memory, a state coordination failure in which old, current, and transition facts coexist in the memory bank, remain mixed during retrieval, and mislead the answer model.<n>We propose ATMA, a state aware overlay for existing memory systems. ATMA keeps superseded and transition records in the bank, and exposes current, historical, and transition labels to QA.
  arXiv  Detail & Related papers  (2026-07-02T09:28:29Z)
• GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents [61.50171793000712]
  GateMem is a benchmark for multi-principal shared-memory agents.<n>It spans medical, office, education, and household domains.<n>No method simultaneously achieves strong utility, robust access control, and reliable forgetting.
  arXiv  Detail & Related papers  (2026-06-17T09:06:15Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory [3.263386002412657]
  Long-running AI agents need persistent memory.<n>Current agent memory systems and database paradigms treat memory as storage.<n>In our vision, long-term agent memory is a new data-management workload.
  arXiv  Detail & Related papers  (2026-05-25T18:22:42Z)
• EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective [21.66000179149483]
  EvoMemBench is a unified benchmark organized along two axes: memory scope and memory content.<n>We compare 15 representative memory methods with strong long-context baselines under a standardized protocol.<n>Results show that current memory systems are still far from a general solution.
  arXiv  Detail & Related papers  (2026-05-18T13:54:38Z)
• Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory [50.857546269660276]
  We introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving large language models (LLMs) memory.<n>Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference.
  arXiv  Detail & Related papers  (2026-05-14T20:15:22Z)
• RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design [77.30163153176954]
  RMBench is a simulation benchmark comprising 9 manipulation tasks that span multiple levels of memory complexity.<n>Mem-0 is a modular manipulation policy with explicit memory components designed to support controlled ablation studies.<n>We identify memory-related limitations in existing policies and provide empirical insights into how architectural design choices influence memory performance.
  arXiv  Detail & Related papers  (2026-03-01T18:59:59Z)
• Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects [11.300084544174894]
  We present Hindsight, a memory architecture that treats agent memory as a structured, first-class substrate for reasoning.<n>It supports three core operations -- retain, recall, and reflect -- that govern how information is added, accessed, and updated.<n>Hindsight with an open-source 20B model lifts overall accuracy from 39% to 83.6% over a full-context baseline.
  arXiv  Detail & Related papers  (2025-12-14T19:47:23Z)

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.