MATEO: A Multimodal Benchmark for Temporal Reasoning and Planning in LVLMs
This provides a new benchmark for evaluating and improving temporal planning in AI agents, addressing a gap in multimodal reasoning for real-world applications, though it is incremental as it builds on existing LVLM research.
The authors tackled the lack of benchmarks for temporal reasoning in Large Vision Language Models by introducing MATEO, a multimodal dataset with graph-based annotations, and found that existing models perform poorly, with accuracy below 50% on complex tasks.
AI agents need to plan to achieve complex goals that involve orchestrating perception, sub-goal decomposition, and execution. These plans consist of ordered steps structured according to a Temporal Execution Order (TEO, a directed acyclic graph that ensures each step executes only after its preconditions are satisfied. Existing research on foundational models' understanding of temporal execution is limited to automatically derived annotations, approximations of the TEO as a linear chain, or text-only inputs. To address this gap, we introduce MATEO (MultimodAl Temporal Execution Order), a benchmark designed to assess and improve the temporal reasoning abilities of Large Vision Language Models (LVLMs) required for real-world planning. We acquire a high-quality professional multimodal recipe corpus, authored through a standardized editorial process that decomposes instructions into discrete steps, each paired with corresponding images. We collect TEO annotations as graphs by designing and using a scalable crowdsourcing pipeline. Using MATEO, we evaluate six state-of-the-art LVLMs across model scales, varying language context, multimodal input structure, and fine-tuning strategies.