# LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos

arXiv: https://arxiv.org/abs/2603.14468 · HTML: https://mlsanity.com/paper/2603.14468/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 23 of 23)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [VideoAgent: Long-form Video Understanding with Large Language Model as Agent](https://mlsanity.com/paper/2403.10517/) (2024)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [A Survey of Multimodal Large Language Model from A Data-centric Perspective](https://mlsanity.com/paper/2405.16640/) (2024)
- [Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning](https://mlsanity.com/paper/2506.13654/) (2025)
- [UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens](https://mlsanity.com/paper/2505.14671/) (2025)
- [Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark](https://mlsanity.com/paper/2510.26802/) (2025)
- [Let's Verify Math Questions Step by Step](https://mlsanity.com/paper/2505.13903/) (2025)
- [LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts](https://mlsanity.com/paper/2505.13928/) (2025)
- [GENIUS: Generative Fluid Intelligence Evaluation Suite](https://mlsanity.com/paper/2602.11144/) (2026)
- [Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL](https://mlsanity.com/paper/2511.10192/) (2025)
- [Synth-Empathy: Towards High-Quality Synthetic Empathy Data](https://mlsanity.com/paper/2407.21669/) (2024)
- [PAS: Data-Efficient Plug-and-Play Prompt Augmentation System](https://mlsanity.com/paper/2407.06027/) (2024)

## Built on by (most cited first, 4 of 4)

- [OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning](https://mlsanity.com/paper/2607.29401/) (2026)
- [Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents](https://mlsanity.com/paper/2607.11433/) (2026)
- [VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding](https://mlsanity.com/paper/2608.14718/) (2026)
- [VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents](https://mlsanity.com/paper/2609.38119/) (2026)

## Abstract (arXiv)

Long video question answering (Long-Video QA) increasingly relies on agentic tool use to retrieve evidence from long videos. In realistic settings, this process often requires multi-hop retrieval, where agents must iteratively gather multiple discontinuous evidence clips. However, existing long-video benchmarks are largely static: they rarely enforce strict multi-hop retrieval and typically lack a standardized evidence-access interface, making it difficult to separate failures in retrieval planning from those in answer generation. To address this gap, we introduce LongVidSearch, a benchmark for evaluating agentic multi-hop evidence retrieval planning in long videos under standardized access constraints. LongVidSearch enforces retrieval necessity: a Hop-k question requires exactly k necessary evidence clips, and removing any single clip renders the question unsolvable. The benchmark contains 3,000 questions over 447 long videos (average length 26 minutes), covering four reasoning categories: State Mutation, Causal Inference, Global Summary, and Visual Tracking, with 2-hop, 3-hop, and 4-hop evidence requirements. To ensure fair and controlled evaluation, all agents interact with LongVidSearch through a unified tool interface, which fixes the retrieval backend and isolates the agent's ability to formulate queries and plan iterative retrieval. In addition to answer accuracy, we measure tool-call cost to analyze the accuracy-efficiency trade-off under identical access conditions. We evaluate VideoAgent-style QA agents with multiple backbone LLMs using three-judge majority voting. GPT-5 achieves the highest accuracy (42.43), outperforming Gemini 3 Pro (30.97) and GPT-4o (19.20), yet remaining below 50 %, highlighting the difficulty of multi-hop retrieval planning. With gold evidence clips, performance becomes near-perfect, confirming retrieval planning as the primary bottleneck.