CostBench is a new travel-planning benchmark showing that leading LLM agents often fail to select cost-optimal tool sequences and drop sharply in performance when facing dynamic events like tool failures or cost changes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
CostBench is a new travel-planning benchmark showing that leading LLM agents often fail to select cost-optimal tool sequences and drop sharply in performance when facing dynamic events like tool failures or cost changes.