# AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models Source: [AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models]() Collection index: [llms.txt]() Data updated: 2026-03-11T05:00:11.798Z Authors: Teng Wang, Yanting Lu, Ruize Wang Published: 2026-03-09T05:53:06.000Z ## Abstract We present AutoTraces, an autoregressive vision-language-trajectory model for robot trajectory forecasting in humam-populated environments, which harnesses the inherent reasoning capabilities of large language models (LLMs) to model complex human behaviors. In contrast to prior works that rely solely on textual representations, our key innovation lies in a novel trajectory tokenization scheme, which represents waypoints with point tokens as categorical and positional markers while encoding waypoint numerical values as corresponding point embeddings, seamlessly integrated into the LLM's space through a lightweight encoder-decoder architecture. This design preserves the LLM's native autoregressive generation mechanism while extending it to physical coordinate spaces, facilitates modeling of long-term interactions in trajectory data. We further introduce an automated chain-of-thought (CoT) generation mechanism that leverages a multimodal LLM to infer spatio-temporal relationships from visual observations and trajectory data, eliminating reliance on manual annotation. Through a two-stage training strategy, our AutoTraces achieves SOTA forecasting accuracy, particularly in long-horizon prediction, while exhibiting strong cross-scene generalization and supporting flexible-length forecasting. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Trajectory Prediction on GoStanford (unseen)](): Trajectory Prediction; GoStanford (unseen); L2 Error (m): 1.035. - [Trajectory Prediction on RECON (unseen)](): Trajectory Prediction; RECON (unseen); L2 Error (m): 1.547. - [Trajectory Prediction on SCAND T=5](): Trajectory Prediction; SCAND T=5; L2 Error (m): 0.674. - [Trajectory Prediction on SCAND T=8](): Trajectory Prediction; SCAND T=8; L2 Error (m): 0.923. - [Trajectory Prediction on SCAND T=10](): Trajectory Prediction; SCAND T=10; L2 Error (m): 1.089. ## Original sources and implementation [Original paper]() [PDF]()