# PlanLLM: Video Procedure Planning with Refinable Large Language Models

arXiv: https://arxiv.org/abs/2412.19139 · HTML: https://mlsanity.com/paper/2412.19139/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 26 Dec 2024.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis](https://mlsanity.com/paper/1903.02874/) (2019)
- [Cross-task weakly supervised learning from instructional videos](https://mlsanity.com/paper/1903.08225/) (2019)
- [Procedure Planning in Instructional Videos](https://mlsanity.com/paper/1907.01172/) (2019)
- [Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension](https://mlsanity.com/paper/1805.06975/) (2018)
- [CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios](https://mlsanity.com/paper/2403.04640/) (2024)
- [P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision](https://mlsanity.com/paper/2205.02300/) (2022)
- [The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures](https://mlsanity.com/paper/1905.06939/) (2019)
- [PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks](https://mlsanity.com/paper/2109.04869/) (2021)
- [Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions](https://mlsanity.com/paper/2009.14259/) (2020)
- [PDPP: Projected Diffusion for Procedure Planning in Instructional Videos](https://mlsanity.com/paper/2303.14676/) (2023)
- [Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection](https://mlsanity.com/paper/2408.02484/) (2024)
- [Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection](https://mlsanity.com/paper/2404.06194/) (2024)
- [SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos](https://mlsanity.com/paper/2403.01599/) (2024)
- [Who Let The Dogs Out? Modeling Dog Behavior From Visual Data](https://mlsanity.com/paper/1803.10827/) (2018)
- [Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning](https://mlsanity.com/paper/2310.00608/) (2023)
- [Active Object Detection with Knowledge Aggregation and Distillation from Large Models](https://mlsanity.com/paper/2405.12509/) (2024)

## Built on by (most cited first, 10 of 10)

- [Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration](https://mlsanity.com/paper/2508.03207/) (2025)
- [Connector-S: A Survey of Connectors in Multi-modal Large Language Models](https://mlsanity.com/paper/2502.11453/) (2025)
- [AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning](https://mlsanity.com/paper/2508.07626/) (2025)
- [ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videos](https://mlsanity.com/paper/2603.04265/) (2026)
- [OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding](https://mlsanity.com/paper/2604.25276/) (2026)
- [LAP: A Language-Aware Planning Model For Procedure Planning In Instructional Videos](https://mlsanity.com/paper/2603.09743/) (2026)
- [Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models](https://mlsanity.com/paper/2608.20237/) (2026)
- [MMP-A*: Multimodal Perception Enhanced Incremental Heuristic Search on Path Planning](https://mlsanity.com/paper/2601.01910/) (2026)
- [RECIPE: Procedural Planning via Grounding in Instructional Video](https://mlsanity.com/paper/2605.19976/) (2026)
- [Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos](https://mlsanity.com/paper/2608.16457/) (2026)

## Abstract (arXiv)

Video procedure planning, i.e., planning a sequence of action steps given the video frames of start and goal states, is an essential ability for embodied AI. Recent works utilize Large Language Models (LLMs) to generate enriched action step description texts to guide action step decoding. Although LLMs are introduced, these methods decode the action steps into a closed-set of one-hot vectors, limiting the model's capability of generalizing to new steps or tasks. Additionally, fixed action step descriptions based on world-level commonsense may contain noise in specific instances of visual states. In this paper, we propose PlanLLM, a cross-modal joint learning framework with LLMs for video procedure planning. We propose an LLM-Enhanced Planning module which fully uses the generalization ability of LLMs to produce free-form planning output and to enhance action step decoding. We also propose Mutual Information Maximization module to connect world-level commonsense of step descriptions and sample-specific information of visual states, enabling LLMs to employ the reasoning ability to generate step sequences. With the assistance of LLMs, our method can both closed-set and open vocabulary procedure planning tasks. Our PlanLLM achieves superior performance on three benchmarks, demonstrating the effectiveness of our designs.