Authors

Andrew Paverd

Publications 2

Preprint Open access

Planarian: Managing Agent State with Statepoints

Jinnan Guo, Hao Mark Chen, Kapil Vaswani et al. · 2026

LLM agents solve complex tasks by iteratively changing files, invoking local tools, and interacting with remote services, which modifies state across their local environment and remote services. Today, agents and users must manage these changes explicitly, whether reverting exploratory actions or recovering from errone …

Preprint Open access

Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents

Anastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner et al. · 2026

AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for legal compliance, governance, accountability, and security; current frameworks must be adapted to the unique characteristics of AI agents. In …

Co-authors