FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.
Springer Science & Business Media
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
A parametric multi-objective Bayesian optimizer amortizes optimization across continuous task spaces by alternating generative solution sampling and acquisition-driven search to enable direct prediction for unseen problems without re-evaluations.
Frontier AI needs contextual multi-objective optimization to select and balance multiple context-dependent objectives rather than relying on single stable goals.
citing papers explorer
-
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.
-
Amortized Multi-Objective Optimization Across Tasks with Generative Solution Modeling
A parametric multi-objective Bayesian optimizer amortizes optimization across continuous task spaces by alternating generative solution sampling and acquisition-driven search to enable direct prediction for unseen problems without re-evaluations.
-
Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems
Frontier AI needs contextual multi-objective optimization to select and balance multiple context-dependent objectives rather than relying on single stable goals.