# Self-Consistency for LLM-Based Motion Trajectory Generation and Verification

arXiv: https://arxiv.org/abs/2603.29301 · HTML: https://mlsanity.com/paper/2603.29301/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 18 of 18)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024)
- [Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity](https://mlsanity.com/paper/2510.01171/) (2025)
- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [Visual Programming for Text-to-Image Generation and Evaluation](https://mlsanity.com/paper/2305.15328/) (2023)
- [Breathing Life Into Sketches Using Text-to-Video Priors](https://mlsanity.com/paper/2311.13608/) (2023)
- [LLMR: Real-time Prompting of Interactive Worlds using Large Language Models](https://mlsanity.com/paper/2309.12276/) (2023)
- [The Scene Language: Representing Scenes with Programs, Words, and Embeddings](https://mlsanity.com/paper/2410.16770/) (2024)
- [NeuralSVG: An Implicit Representation for Text-to-Vector Generation](https://mlsanity.com/paper/2501.03992/) (2025)
- [MoVer: Motion Verification for Motion Graphics Animations](https://mlsanity.com/paper/2502.13372/) (2025)
- [Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting](https://mlsanity.com/paper/2410.07839/) (2024)
- [Representation Consistency for Accurate and Coherent LLM Answer Aggregation](https://mlsanity.com/paper/2506.21590/) (2025)
- [Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning](https://mlsanity.com/paper/2508.18395/) (2025)

## Built on by (most cited first, 1 of 1)

- [The Garden of Forking Paths: Threading Narrative Archetype as a Semantic Signal Through Gameplay Planning](https://mlsanity.com/paper/2605.01245/) (2026)

## Abstract (arXiv)

Self-consistency has proven to be an effective technique for improving LLM performance on natural language reasoning tasks in a lightweight, unsupervised manner. In this work, we study how to adapt self-consistency to visual domains. Specifically, we consider the generation and verification of LLM-produced motion graphics trajectories. Given a prompt (e.g., "Move the circle in a spiral path"), we first sample diverse motion trajectories from an LLM, and then identify groups of consistent trajectories via clustering. Our key insight is to model the family of shapes associated with a prompt as a prototype trajectory paired with a group of geometric transformations (e.g., rigid, similarity, and affine). Two trajectories can then be considered consistent if one can be transformed into the other under the warps allowable by the transformation group. We propose an algorithm that automatically recovers a shape family, using hierarchical relationships between a set of candidate transformation groups. Our approach improves the accuracy of LLM-based trajectory generation by 4-6%. We further extend our method to support verification, observing 11% precision gains over VLM baselines. Our code and dataset are available at https://majiaju.io/trajectory-self-consistency .