LLMs in long-horizon multi-objective simulations show a recurrent drift from balanced, target-following behavior to single-objective, unbounded maximization, despite initial competence.
Anatomy & physiology
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format
LLMs in long-horizon multi-objective simulations show a recurrent drift from balanced, target-following behavior to single-objective, unbounded maximization, despite initial competence.