Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents

  • 类型：arxiv
  • 标识：2607.22157
  • 链接：http://arxiv.org/abs/2607.22157v1
  • 主分类：agent
  • 形态：application
  • 被引：0
  • 被引来源：Semantic Scholar
  • S2被引：0
  • 影响力被引：0
  • TLDR：It is shown that feedback is a sufficient signal for continual learning when the frozen model is paired with an external memory that distils each episode into retrievable natural-language rules when the frozen model is paired with an external memory.
  • 副分类：engineering
  • 待LLM分类：否
  • 标题中文：Learning on the Job：面向冻结权重 Agent 的部署反馈持续学习
  • TLDR中文：研究表明，当冻结模型与外部记忆配合、且该记忆将每个 episode 提炼为可检索的自然语言规则时，反馈信号足以支撑持续学习。
  • 来源文件：
  • /inbox/tom/_candidates/2026-07-27-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-28-agent-rag-longcontext-candidates.json
  • [S2 enrich]