# TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution

arXiv: https://arxiv.org/abs/2505.04480 · HTML: https://mlsanity.com/paper/2505.04480/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 65 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 30 of 34)

- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction](https://mlsanity.com/paper/2002.11927/) (2020)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [Human Motion Trajectory Prediction: A Survey](https://mlsanity.com/paper/1905.06113/) (2019)
- [Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion](https://mlsanity.com/paper/2203.13777/) (2022)
- [Core Challenges of Social Robot Navigation: A Survey](https://mlsanity.com/paper/2103.05668/) (2021)
- [Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap](https://mlsanity.com/paper/2401.10034/) (2024)
- [Remember Intentions: Retrospective-Memory-based Trajectory Prediction](https://mlsanity.com/paper/2203.11474/) (2022)
- [What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction](https://mlsanity.com/paper/1903.07933/) (2019)
- [HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs](https://mlsanity.com/paper/2412.14995/) (2024)
- [A Systematic Survey on Large Language Models for Algorithm Design](https://mlsanity.com/paper/2410.14716/) (2024)
- [MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2108.09274/) (2021)
- [Algorithm Evolution Using Large Language Model](https://mlsanity.com/paper/2311.15249/) (2023)
- [EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting](https://mlsanity.com/paper/2307.09306/) (2023)
- [LLM4AD: A Platform for Algorithm Design with Large Language Model](https://mlsanity.com/paper/2412.17287/) (2024)
- [Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction](https://mlsanity.com/paper/2403.18447/) (2024)
- [MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation](https://mlsanity.com/paper/2503.09950/) (2025)
- [Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches](https://mlsanity.com/paper/2111.06740/) (2021)
- [Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction](https://mlsanity.com/paper/2211.08701/) (2022)
- [Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Models](https://mlsanity.com/paper/2407.10873/) (2024)
- [OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets](https://mlsanity.com/paper/2010.00890/) (2020)
- [What Truly Matters in Trajectory Prediction for Autonomous Driving?](https://mlsanity.com/paper/2306.15136/) (2023)
- [Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions](https://mlsanity.com/paper/2503.03262/) (2025)
- [EvolveHypergraph: Group-Aware Dynamic Relational Reasoning for Trajectory Prediction](https://mlsanity.com/paper/2208.05470/) (2022)
- [Semantics-STGCNN: A Semantics-guided Spatial-Temporal Graph Convolutional Network for Multi-class Trajectory Prediction](https://mlsanity.com/paper/2108.04740/) (2021)
- [Uncovering the human motion pattern: Pattern Memory-based Diffusion Model for Trajectory Prediction](https://mlsanity.com/paper/2401.02916/) (2024)
- [GUIDE-CoT: Goal-driven and User-Informed Dynamic Estimation for Pedestrian Trajectory using Chain-of-Thought](https://mlsanity.com/paper/2503.06832/) (2025)

## Built on by (most cited first, 5 of 5)

- [Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives](https://mlsanity.com/paper/2505.09074/) (2025)
- [What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search](https://mlsanity.com/paper/2604.19440/) (2026)
- [Large Foundation Models for Trajectory Prediction in Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2509.10570/) (2025)
- [Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review](https://mlsanity.com/paper/2506.14831/) (2025)
- [USPR: Learning a Unified Solver for Profiled Routing](https://mlsanity.com/paper/2505.05119/) (2025)

## Abstract (arXiv)

Trajectory prediction is a crucial task in modeling human behavior, especially in fields as social robotics and autonomous vehicle navigation. Traditional heuristics based on handcrafted rules often lack accuracy, while recently proposed deep learning approaches suffer from computational cost, lack of explainability, and generalization issues that limit their practical adoption. In this paper, we introduce TrajEvo, a framework that leverages Large Language Models (LLMs) to automatically design trajectory prediction heuristics. TrajEvo employs an evolutionary algorithm to generate and refine prediction heuristics from past trajectory data. We introduce a Cross-Generation Elite Sampling to promote population diversity and a Statistics Feedback Loop allowing the LLM to analyze alternative predictions. Our evaluations show TrajEvo outperforms previous heuristic methods on the ETH-UCY datasets, and remarkably outperforms both heuristics and deep learning methods when generalizing to the unseen SDD dataset. TrajEvo represents a first step toward automated design of fast, explainable, and generalizable trajectory prediction heuristics. We make our source code publicly available to foster future research at https://github.com/ai4co/trajevo.