Hot eventLive
CLEAR:基于因果上下文的多智能体漏洞检测框架
1 reports1 sources3 hr ago updated
Get the story
AI overview
2026年10月7日,研究者在 arXiv(Software Engineering 类别)发表论文,提出 CLEAR,一个结合因果知识图谱的多智能体漏洞检测框架。该框架构建漏洞因果知识图谱(VCKG),用于建模入口点、前置条件、根因与修复意图之间的因果链。CLEAR 由 Collector、Claim、Critic、Judge 四个专门智能体协作组成,通过检索到的因果上下文验证漏洞假设。目前公开信息仅包含该论文报道,框架的实际效果、评测数据与后续进展尚无进一步报道。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
Oct 7, 2026
- arXiv · Software EngineeringCLEAR:基于因果上下文的智能体推理漏洞检测框架
研究者提出 CLEAR,一个结合因果知识图谱的多智能体漏洞检测框架,构建漏洞因果知识图谱(VCKG)建模入口点、前置条件、根因与修复意图之间的因果链。框架由 Collector、Claim、Critic、Judge 四个专门智能体协作,通过检索到的因果上下文验证漏洞假设。
Heat trend
Current heat 9·Comparable peak 10(Oct 7)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.