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

arXiv: https://arxiv.org/abs/2508.05616 · HTML: https://mlsanity.com/paper/2508.05616/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 80 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Builds on (most cited first, 30 of 40)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [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)
- [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)
- [Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design](https://mlsanity.com/paper/2501.08603/) (2025)
- [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)
- [What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction](https://mlsanity.com/paper/1903.07933/) (2019)
- [Conditional Generative Neural System for Probabilistic Trajectory Prediction](https://mlsanity.com/paper/1905.01631/) (2019)
- [HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs](https://mlsanity.com/paper/2412.14995/) (2024)
- [MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2108.09274/) (2021)
- [EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting](https://mlsanity.com/paper/2307.09306/) (2023)
- [Spectral Temporal Graph Neural Network for Trajectory Prediction](https://mlsanity.com/paper/2106.02930/) (2021)
- [Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking](https://mlsanity.com/paper/2102.09117/) (2021)
- [Shared Cross-Modal Trajectory Prediction for Autonomous Driving](https://mlsanity.com/paper/2011.08436/) (2020)
- [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)
- [CMP: Cooperative Motion Prediction with Multi-Agent Communication](https://mlsanity.com/paper/2403.17916/) (2024)
- [Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction](https://mlsanity.com/paper/2211.08701/) (2022)
- [OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets](https://mlsanity.com/paper/2010.00890/) (2020)
- [Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation](https://mlsanity.com/paper/2401.12275/) (2024)
- [Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting](https://mlsanity.com/paper/2109.14128/) (2021)
- [Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints](https://mlsanity.com/paper/2306.01075/) (2023)
- [EvolveHypergraph: Group-Aware Dynamic Relational Reasoning for Trajectory Prediction](https://mlsanity.com/paper/2208.05470/) (2022)
- [MATRIX: Multi-Agent Trajectory Generation with Diverse Contexts](https://mlsanity.com/paper/2403.06041/) (2024)
- [SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning](https://mlsanity.com/paper/2407.17460/) (2024)
- [Disentangled Neural Relational Inference for Interpretable Motion Prediction](https://mlsanity.com/paper/2401.03599/) (2024)

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

- [Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving](https://mlsanity.com/paper/2603.25740/) (2026)
- [Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models](https://mlsanity.com/paper/2601.01321/) (2026)
- [EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models](https://mlsanity.com/paper/2605.11859/) (2026)
- [Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization](https://mlsanity.com/paper/2605.20249/) (2026)
- [LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagrams](https://mlsanity.com/paper/2609.05327/) (2026)

## Abstract (arXiv)

Trajectory prediction is a critical task in modeling human behavior, especially in safety-critical domains such as social robotics and autonomous vehicle navigation. Traditional heuristics based on handcrafted rules often lack accuracy and generalizability. Although deep learning approaches offer improved performance, they typically suffer from high computational cost, limited explainability, and, importantly, poor generalization to out-of-distribution (OOD) scenarios. 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 propose two key innovations: Cross-Generation Elite Sampling to encourage population diversity, and a Statistics Feedback Loop that enables the LLM to analyze and improve alternative predictions. Our evaluations demonstrate that TrajEvo outperforms existing heuristic methods across multiple real-world datasets, and notably surpasses both heuristic and deep learning methods in generalizing to an unseen OOD real-world dataset. TrajEvo marks a promising step toward the automated design of fast, explainable, and generalizable trajectory prediction heuristics. We release our source code to facilitate future research at https://github.com/ai4co/trajevo.