Across five LLMs and three benchmarks, orchestration adds up to 4.6 points over optimized single-call CoT at 2-4x token cost, with no difficulty-scaled benefit but strong method-by-backbone interactions.
pgn": SAN in standard algebraic notation **without any annotation symbols** (no ’+’ for check, no ’##’ for checkmate). Use uppercase letters for pieces. Example:
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
-
When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty
Across five LLMs and three benchmarks, orchestration adds up to 4.6 points over optimized single-call CoT at 2-4x token cost, with no difficulty-scaled benefit but strong method-by-backbone interactions.