A self-evolving runtime defense for LLM agents, HARD, improves security over static handcrafted defenses by updating context policies and action gates from failure traces.
Maddison, and Tatsunori Hashimoto
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
A self-evolving runtime defense for LLM agents, HARD, improves security over static handcrafted defenses by updating context policies and action gates from failure traces.