计算机科学
适配器(计算)
领域(数学分析)
控制(管理)
人工智能
匹配(统计)
重放攻击
数据挖掘
实时计算
芯(光纤)
面子(社会学概念)
频域
训练集
数据驱动
算法
机器学习
计算机安全
语音识别
控制系统
分布式计算
多智能体系统
在线和离线
出处
期刊:
[SPIE]
日期:2026-10-06
卷期号:: 101-101
被引量:1
摘要
Domain agents often face noisy business data, uncertain post-training gains, offline/application mismatch, and adapter-release risk. This paper presents CLAP (Closed-Loop Agent Post-training), a closed-loop method that converts business data into structured SFT samples, decision-preference samples, holdout sets, risk diagnostics, and release-gate records. CLAP combines data validation, target/evidence normalization, reward/KL diagnosis, offline gates, and application-chain replay to decide whether an adapter is suitable for the target application chain. On five anonymized manufacturing-scenario batches, QLoRA-style LoRA-SFT yields modest average gains: overall score increases by 0.0098, pass rate by 0.0240, and evidence accuracy by 0.0280, while hallucination and wrong facts decrease. Yet only 3 of 5 batches improve, some batches regress, and GRPO exposes high KL risks. Application-chain replay further shows that RAG is necessary for factual extraction; under the same 3B backbone and 100 replay cases, an application-RAG-oriented LoRA-SFT adapter improves value, core fields, and answer-evidence doc/page matching over base+RAG, but increases latency. These results support managing domain-agent post-training through an integrated data-training-evaluation-release loop rather than relying on training completion or a single offline score.
科研通智能强力驱动
Strongly Powered by AbleSci AI