A new 2,700-task benchmark with budget, time, and distance constraints shows that even the best multimodal LLMs produce feasible plans less than 22% of the time.
M 3 cot: A novel benchmark for multi-domain multi-step multi-modal chain-of- thought
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models
A new 2,700-task benchmark with budget, time, and distance constraints shows that even the best multimodal LLMs produce feasible plans less than 22% of the time.