Feed
researchSoftware Engineering / DevTools8d ago

Redesigned SAFE IntelliJ Plugin Uses Agentic Architecture to Improve SAST Vulnerability Explanations

Facts

Researchers have redesigned the SAFE IntelliJ IDEA plugin, introducing an agentic architecture that consults code repositories and detection rules to provide grounded explanations for static analysis vulnerability findings. A study involving 24 participants demonstrated that the agent-based approach significantly improved developer remediation accuracy and perceived usability compared to the previous version.

  • ▸The new SAFE plugin architecture replaces a single-prompt backend with an agent that must query the code repository and detection rules before generating explanations.
  • ▸A crossover study with 24 participants showed that remediation accuracy was 2.6 times higher using the agentic plugin.
  • ▸System Usability Scale scores for the tool improved from 77.3 to 85.0.
  • ▸The agent is compatible with any analyzer reporting in the Static Analysis Results Interchange Format.
  • ▸Despite usability gains, user trust in the tool's findings remained unchanged, highlighting a divide between understanding and belief.
Occurred
2026-11-09 11:40 UTC
First reported
2026-11-09 11:40 UTC
Last updated
2026-11-11 03:15 UTC
Event type
research
Region
Global

Entities

Categories

Source timeline · 1

  • arXivFirst-party2026-11-09 11:40
Community vote

Sign in to vote on importance and sentiment.

Platform Signals

Impact score
70
AI sentiment
Positive
Event significance30%1
Entity importance20%1
Source credibility20%1
Novelty15%1
Corroboration15%1
Confidence1
Novelty1
Corroboration1
Community
ImportanceNo votes
Strategic sentiment
Positive 0%Neutral 0%Negative 0%

Platform signals are algorithmic and community-derived indicators. They are not investment recommendations and do not predict valuation or performance.

Related events

No events yet.