SEVerA uses Formally Guarded Generative Models and a three-stage Search-Verification-Learning process to synthesize self-evolving agents that satisfy hard formal constraints while improving task performance.
Takedown: How it’s done in modern coding agent exploits.arXiv preprint arXiv:2509.24240, 2025
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
ShellSieve, an LLM-driven pipeline, detects command denylist fragility in terminal AI agents and finds 69.0-98.6% of 1,709 GitHub-collected denylists to be bypassable.
Agentic offensive security tools share design flaws enabling API key exfiltration, persistence, and sandbox escape, addressed via a new cyber kill chain and robust architecture principles.
citing papers explorer
-
SEVerA: Verified Synthesis of Self-Evolving Agents
SEVerA uses Formally Guarded Generative Models and a three-stage Search-Verification-Learning process to synthesize self-evolving agents that satisfy hard formal constraints while improving task performance.
-
One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents
ShellSieve, an LLM-driven pipeline, detects command denylist fragility in terminal AI agents and finds 69.0-98.6% of 1,709 GitHub-collected denylists to be bypassable.
-
Red-Teaming the Agentic Red-Team
Agentic offensive security tools share design flaws enabling API key exfiltration, persistence, and sandbox escape, addressed via a new cyber kill chain and robust architecture principles.