MMA uses LLM agents with RL to rerank candidate pools from first-stage retrievers under missing modalities, reporting 4.0% and 12.7% NDCG@10 gains on OOMA and fixed-pool tasks over baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Meta-Modal Agent: Sequential Evidence Routing for Missing-Modality Candidate Reranking
MMA uses LLM agents with RL to rerank candidate pools from first-stage retrievers under missing modalities, reporting 4.0% and 12.7% NDCG@10 gains on OOMA and fixed-pool tasks over baselines.