paper-with-me

홈 › Papers

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

2026-06-23 · Beining Wu, Zihao Ding, Jun Huang, Yanxiao Zhao arxiv

On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and exposed: it consumes RAM and energy, reaches peers through a thin uplink, and becomes an attack surface because it is writable by what the agent reads. Existing systems each cover one part of this problem: agentic memories grow without a budget, on-device methods keep entries by success alone, and poisoning is studied mainly as an attack rather than as a memory-governance problem. We propose \sys{}, a single net-value-per-byte score that governs an agent's experience-memory lifecycle. The main idea is to let the budget act as the curator: each entry is scored as value minus harm, per byte, so one ruler decides what to keep, share, and trust. \sys{} makes three decisions: (1) \textbf{KEEP} evicts low-value bytes under the RAM and energy budget; (2) \textbf{SHARE} sends an insight only when its value exceeds its uplink cost; and (3) \textbf{TRUST} gates a peer entry by provenance. On language-model-agent task-drift benchmarks and a real heterogeneous Jetson testbed with two robot-arm nodes and a hub, \sys{} reduces memory by $2.7\times$ and uplink by $2.4\times$, drives injection success from 0.75 to zero, and raises accuracy on cases corrupted by poison or stale memory. Curating by net value reduces footprint, energy, uplink, and injection success together without reducing accuracy. In this setting, forgetting by net value improves the agent rather than weakening it.

📄 PDF Abstract BibTeX arXiv:2606.25115

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Online Continual Learning Without the Storage Constraint

2023-05-16 · Ameya Prabhu, Zhipeng Cai, Puneet Dokania, Philip Torr 외

Traditional online continual learning (OCL) research has primarily focused on mitigating catastrophic forgetting with fixed and limited storage allocation throughout an agent's lifetime. However, a broad range of real-wo…

Continual Learning

Few-Shot Continual Active Learning by a Robot

2022-10-09 · Ali Ayub, Carter Fendley

In this paper, we consider a challenging but realistic continual learning (CL) problem, Few-Shot Continual Active Learning (FoCAL), where a CL agent is provided with unlabeled data for a new or a previously learned task …

Active LearningContinual LearningObject

Coordinated Replay Sample Selection for Continual Federated Learning

2023-10-23 · Jack Good, Jimit Majmudar, Christophe Dupuy, Jixuan Wang 외

Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learn…

Continual LearningFederated Learning

Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications

2021-10-25 · Young D. Kwon, Jagmohan Chauhan, Abhishek Kumar, Pan Hui 외

Continual learning approaches help deep neural network models adapt and learn incrementally by trying to solve catastrophic forgetting. However, whether these existing approaches, applied traditionally to image-based tas…

Continual LearningIncremental LearningTime Series Analysis

Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer

2021-01-23 · James Smith, Jonathan Balloch, Yen-Chang Hsu, Zsolt Kira

Rehearsal is a critical component for class-incremental continual learning, yet it requires a substantial memory budget. Our work investigates whether we can significantly reduce this memory budget by leveraging unlabele…

Continual LearningKnowledge DistillationOut of Distribution (OOD) Detection