Execution-security research for AI coding agents is fragmented across 17 mechanism categories with five unaddressed cross-cutting gaps, including missing head-to-head isolation-vs-capability evaluation and untested real-world denylist fragility.
Fault-tolerant sandboxing for ai coding agents: A trans- actional approach to safe autonomous execution,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
DeltaBox achieves 14 ms checkpoint and 5 ms rollback for AI agent sandboxes via layered DeltaFS and incremental DeltaCR mechanisms that exploit similarity between consecutive states.
Introduces taxonomy of agentic failures and four-layer verification architecture; simulation shows HOTL uncertainty thresholds cut privilege-waiver risk by 61% versus autonomous baselines while routing under 25% of documents to humans.
LLM agent security is reframed as an agent-human interaction issue, supported by a survey showing industry preference for human-centric mechanisms over academic favorites and proposing a new research agenda.
citing papers explorer
-
The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities
Execution-security research for AI coding agents is fragmented across 17 mechanism categories with five unaddressed cross-cutting gaps, including missing head-to-head isolation-vs-capability evaluation and untested real-world denylist fragility.
-
DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
DeltaBox achieves 14 ms checkpoint and 5 ms rollback for AI agent sandboxes via layered DeltaFS and incremental DeltaCR mechanisms that exploit similarity between consecutive states.
-
Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery
Introduces taxonomy of agentic failures and four-layer verification architecture; simulation shows HOTL uncertainty thresholds cut privilege-waiver risk by 61% versus autonomous baselines while routing under 25% of documents to humans.
-
Reframing LLM Agent Security as an Agent-Human Interaction Problem
LLM agent security is reframed as an agent-human interaction issue, supported by a survey showing industry preference for human-centric mechanisms over academic favorites and proposing a new research agenda.