Matched MCP and CLI interfaces change language-agent behavior, study finds
DART improved scores by up to 9.0 points and cut MCP cost by up to 27.1k tokens per task.
Stories per day · 30 days
2 RSS
7 stories, newest first · one card per story
Stories tagged #dart
Vijil DART tests AI agents for security flaws and policy violations
Vijil launched DART, automated adaptive red-teaming that probes enterprise AI agents with multi-turn attacks to find security flaws and policy violations.
Beyond source code: A path to the keys to the kingdom
Microsoft DART details how Storm-3068 hijacked an account via self-service password reset, then used Azure DevOps pipelines to harvest Kubernetes credentials across 50+ resources.
1
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
SEAD shows a state-aware defense cutting tool-agent attack success from 48 percent to 4 percent.
Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model
Latent-flow world models lose object motion; decode-augmented training restores it without unfreezing the representation.
Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models
Empirical study finds direct whole-file generation beats iterative diff-based editing for Flutter/Dart code models on about 1,790 held-out tasks.
Cybersecurity IR Workshop: The workshop you shouldn’t miss
Microsoft's DART team promotes a 2-3 day Cybersecurity Incident Response Readiness Workshop that stress-tests IR plans against simulated attacks.
1