Adaptive Multi-Agent Reasoning for Text-to-Video Retrieval

TL;DR

This paper introduces an adaptive multi-agent framework for zero-shot text-to-video retrieval that dynamically orchestrates specialized agents to improve reasoning and retrieval accuracy, significantly outperforming existing methods.

Contribution

It proposes a novel multi-agent reasoning framework with dynamic coordination and communication mechanisms for improved zero-shot text-to-video retrieval.

Findings

Twofold improvement over CLIP4Clip

Significant outperformance of state-of-the-art methods

Effective handling of complex temporal and logical queries

Abstract

The rise of short-form video platforms and the emergence of multimodal large language models (MLLMs) have amplified the need for scalable, effective, zero-shot text-to-video retrieval systems. While recent advances in large-scale pretraining have improved zero-shot cross-modal alignment, existing methods still struggle with query-dependent temporal reasoning, limiting their effectiveness on complex queries involving temporal, logical, or causal relationships. To address these limitations, we propose an adaptive multi-agent retrieval framework that dynamically orchestrates specialized agents over multiple reasoning iterations based on the demands of each query. The framework includes: (1) a retrieval agent for scalable retrieval over large video corpora, (2) a reasoning agent for zero-shot contextual temporal reasoning, and (3) a query reformulation agent for refining ambiguous queries and recovering performance for those that degrade over iterations. These agents are dynamically coordinated by an orchestration agent, which leverages intermediate feedback and reasoning outcomes to guide execution. We also introduce a novel communication mechanism that incorporates retrieval-performance memory and historical reasoning traces to improve coordination and decision-making. Experiments on three TRECVid benchmarks spanning eight years show that our framework achieves a twofold improvement over CLIP4Clip and significantly outperforms state-of-the-art methods by a large margin.