AdaMEM: Test-Time Adaptive Memory for Language Agents

• URL: http://arxiv.org/abs/2606.05684v1
• Date: Thu, 04 Jun 2026 04:06:08 GMT
• Title: AdaMEM: Test-Time Adaptive Memory for Language Agents
• Abstract summary: We propose the Adaptive Memory Agent (AdaMEM), a novel framework for agent test-time adaptation.<n>Without updating model parameters online, AdaMEM adapts agent behavior via a hybrid memory architecture.<n>AdaMEM significantly outperforms static memory baselines, achieving relative gains of up to 13% on ALFWorld and 11% on WebShop.
• Score: 27.178795834085296
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A central challenge for language agents is utilizing past experience to adapt to dynamic test-time conditions. While recent work demonstrates the promise of agentic memory mechanisms, most systems restrict retrieval to episode initiation. Consequently, agents are forced to rely on static guidance that becomes increasingly misaligned as long-horizon tasks unfold. To address this rigidity, we propose the Adaptive Memory Agent (AdaMEM), a novel framework for agent test-time adaptation. Without updating model parameters online, AdaMEM adapts agent behavior via a hybrid memory architecture: it maintains a long-term trajectory memory of raw experiences collected offline while generating dynamic short-term strategy memory on-the-fly to guide decision-making. This mechanism enables the trade-off between token efficiency and adaptability across varying inference-time compute levels. Empirically, AdaMEM significantly outperforms static memory baselines, achieving relative gains of up to 13% on ALFWorld and 11% on WebShop, with consistent leading performance extending to agentic search on HotpotQA. To further enhance this adaptation, we develop STEP-MFT, a Step-wise Memory Fine-Tuning technique that trains the policy to synthesize high-quality strategies from retrieved experiences, yielding additional performance gains. Our work establishes a new scaling dimension for agentic memory, supporting continuous reasoning and self-evolution post-deployment in real-world environments. Our code is available at https://github.com/yunx-z/AdaMEM.

Related papers

• Interactive Memory Learning for Long-Term Conversations [30.375942250315145]
  ICML (InteraCtive Memory Learning) is a multi-agent framework that transforms the memory mechanism from a passive archive into a learnable, interactive memory policy.
  arXiv  Detail & Related papers  (2026-09-15T12:21:41Z)
• UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams [77.52140119830241]
  We propose UniMem, a self-routing framework for autonomous memory management.<n>UniMem uses learnable routing tokens as memory controllers, enabling adaptive coordination between complementary memory pathways.<n>Experiments on long-horizon streaming task sequences show that UniMem consistently outperforms baselines while maintaining execution fidelity.
  arXiv  Detail & Related papers  (2026-07-28T17:28:21Z)
• 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)
• SE-GA: Memory-Augmented Self-Evolution for GUI Agents [17.051355070847166]
  Self-Evolving GUI Agent (SE-GA) is a novel framework that integrates hierarchical memory structures with an iterative self-improvement mechanism.<n>To ensure continuous learning, we introduce Memory-Augmented Self-Evolution (MASE)
  arXiv  Detail & Related papers  (2026-05-16T08:51:57Z)
• Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentation [18.026494321724943]
  We propose a memory-augmented segmentation agent (MemSeg-Agent) that shifts adaptation from weight space to memory space.<n>MemSeg-Agent conditions a fixed backbone with lightweight static, few-shot, and test-time working memories.<n>Experiments on four public datasets demonstrate strong performance and robustness to domain shift.
  arXiv  Detail & Related papers  (2026-03-06T03:49:23Z)
• Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution [18.68532215387754]
  Multimodal Large Language Model (MLLM) agents facilitate Graphical User Interface (GUI) automation but struggle with long-horizon, cross-application tasks.<n>Existing paradigms struggle to adapt to dynamic GUI environments, suffering from a mismatch between high-level intent and low-level execution.<n>We propose the Darwinian Memory System (DMS), a self-evolving architecture that constructs memory as a dynamic ecosystem governed by the law of survival of the fittest.
  arXiv  Detail & Related papers  (2026-01-30T04:01:21Z)
• AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
  We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
  arXiv  Detail & Related papers  (2026-01-28T08:09:49Z)
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents [57.38404718635204]
  Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows.<n>Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components.<n>We propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.
  arXiv  Detail & Related papers  (2026-01-05T08:24:16Z)
• Memp: Exploring Agent Procedural Memory [72.41472703974935]
  Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters.<n>We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions.<n>We show that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks.
  arXiv  Detail & Related papers  (2025-08-08T16:20:56Z)
• SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity [30.260783715373382]
  Test-time adaptation (TTA) has emerged to improve the performance of deep models by adapting them to unlabeled target data online.<n>Yet, the significant memory cost, particularly in resource-constrained terminals, impedes the effective deployment of most backward-propagation-based TTA methods.<n>To tackle memory constraints, we introduce SURGEON, a method that substantially reduces memory cost while preserving comparable accuracy improvements.
  arXiv  Detail & Related papers  (2025-03-26T09:27:09Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)

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.