In CybORG CAGE-2, programmatic state abstraction improves mean return up to 76% over raw observations while adding deliberation tools to hierarchies degrades performance up to 3.4x and increases token use.
Optimal defender strategies for CAGE-2 using causal modeling and tree search,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Combines particle filtering, feature-based aggregation, and rollout to produce scalable network security policies with theoretical guarantees that adapt quickly to model changes.
citing papers explorer
-
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
In CybORG CAGE-2, programmatic state abstraction improves mean return up to 76% over raw observations while adding deliberation tools to hierarchies degrades performance up to 3.4x and increases token use.
-
Adaptive Network Security Policies via Belief Aggregation and Rollout
Combines particle filtering, feature-based aggregation, and rollout to produce scalable network security policies with theoretical guarantees that adapt quickly to model changes.