Search papers, labs, and topics across Lattice.
The paper introduces SCMAPR, a self-correcting multi-agent prompt refinement framework for text-to-video generation, designed to improve performance in complex scenarios. SCMAPR uses specialized agents for scenario-aware routing, policy-conditioned rewriting, and structured semantic verification, enabling conditional prompt revision. The authors also introduce T2V-Complexity, a new benchmark specifically designed for evaluating T2V models on complex scenarios, and demonstrate that SCMAPR achieves significant gains in text-video alignment and generation quality across multiple benchmarks.
Multi-agent prompt refinement can significantly boost text-to-video generation quality in complex scenarios, exceeding SOTA baselines by up to 3.28% on standard benchmarks.
Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, which are generally exacerbated by the ambiguity and underspecification of text prompts. In this work, we formulate complex-scenario prompt refinement as a stage-wise multi-agent refinement process and propose SCMAPR, i.e., a scenario-aware and Self-Correcting Multi-Agent Prompt Refinement framework for T2V prompting. SCMAPR coordinates specialized agents to (i) route each prompt to a taxonomy-grounded scenario for strategy selection, (ii) synthesize scenario-aware rewriting policies and perform policy-conditioned refinement, and (iii) conduct structured semantic verification that triggers conditional revision when violations are detected. To clarify what constitutes complex scenarios in T2V prompting, provide representative examples, and enable rigorous evaluation under such challenging conditions, we further introduce {T2V-Complexity}, which is a complex-scenario T2V benchmark consisting exclusively of complex-scenario prompts. Extensive experiments on 3 existing benchmarks and our T2V-Complexity benchmark demonstrate that SCMAPR consistently improves text-video alignment and overall generation quality under complex scenarios, achieving up to 2.67\% and 3.28 gains in average score on VBench and EvalCrafter, and up to 0.028 improvement on T2V-CompBench over 3 State-Of-The-Art baselines.
Tsinghua AI