按年被提到
20252025 · 1 次2026
强化学习与智能体›大模型智能体·arXiv:2512.16301 · cs.AI

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi, Zifeng Wang, Luxi He, Yichen Wu, Ming Zhong, Peiyang Song, Qizheng Zhang, Heng Wang, Xueqiang Xu, Hanwen Xu 等 34 人 · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-12-21 · 最近 2026-01-06
2不同的人
2活跃月份
2讨论串
9被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills. Yet the research landscape remains fragmented across post-training, retrieval, memory, and skill systems. This survey studies these developments under a single notion of \emph{adaptation}: improving an agent, its tools, or their interaction after pretraining. We organize the field with a four-paradigm framework spanning agent adaptation and tool adaptation. On the agent side, A1 (tool-execution-signaled) and A2 (agent-output-signaled) improve the agent itself through supervised fine-tuning, preference optimization, and reinforcement learning with verifiable rewards. On the tool side, T1 (agent-agnostic) provides reusable pre-trained modules any agent can call, while T2 (agent-supervised) uses the agent's outputs to train memory systems, skill libraries, or lightweight subagents. Using this framework, we review post-training methods, adaptive memory architectures, and agent skills; compare their trade-offs in cost, flexibility, and generalization; and summarize evaluation practices across deep research, software development, computer use, and drug discovery. We conclude by outlining open problems in agent-tool co-adaptation, continual learning, safety, and efficient deployment.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论steer_dev · 2026-01

“Doing post-mortems on my agent's failures over the holidays made me realize the problem isn't the model. It is the lack of a deterministic inference-time verification layer. I spent the break reading the recent Stanford/Harvard paper on agentic adaptation [1]. Their research provides mathematical proof for what I experienced in Q4: supervising only final…”

The Agent Lobotomy: Inference-time verification for autonomous systems原评论 ↗
被提交为 story · 1 次