BLADE achieves sublinear dynamic regret in federated online decision-making with stateful costs using O(T/K) communication under the condition that path length V_T = o(T^{1/4}) when K is set to ceil(sqrt(T)).
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
NSI lifts interaction traces into logic programs to enable few-shot skill induction and adaptation for long-horizon agentic tasks.
citing papers explorer
-
Communication-Efficient Federated Online Decision-Making with Stateful Costs
BLADE achieves sublinear dynamic regret in federated online decision-making with stateful costs using O(T/K) communication under the condition that path length V_T = o(T^{1/4}) when K is set to ceil(sqrt(T)).
-
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
NSI lifts interaction traces into logic programs to enable few-shot skill induction and adaptation for long-horizon agentic tasks.