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

---
type: paper
title: "Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory"
authors: Beining Wu, Zihao Ding, Jun Huang, Yanxiao Zhao
year: 2026
venue: arXiv
url: https://arxiv.org/abs/2606.25115
code_url:
source: arxiv
collected_at: 2026-07-08
published_at: 2026-06-23
updated_at: 2026-06-23
status: queued
relevance: high
topics:
  - agent-evaluation
  - embodied-agent
  - memory
methods:
  -
benchmarks:
  -
models:
  -
datasets:
  - cs.LG
  - cs.NI
related_concepts:
  -
related_jobs:
  -
related_experiments:
  -
related_projects:
  -
collection_score: 15
collection_queries: agent-memory
---

## One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

## Why Collected

- matched queries: agent-memory
- inferred topics: agent-evaluation, embodied-agent, memory
- arXiv categories: cs.LG, cs.NI
- collection score: 15

## Review Checklist

- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
- Does it include a benchmark, dataset, code, or reproducible experimental setup?
- Should it be promoted from `queued` to `skimmed` or `summarized`?

## Links

- arXiv: https://arxiv.org/abs/2606.25115