CEDAR pairs an LLM editor with an LLM judge inside tree search to rewrite Python simulations of complex systems toward natural-language goals, and beats a numeric optimizer on one record-fitting benchmark.
maximize population growth
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
CEDAR pairs an LLM editor with an LLM judge inside tree search to rewrite Python simulations of complex systems toward natural-language goals, and beats a numeric optimizer on one record-fitting benchmark.