CVFeb 11

ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems

arXiv:2602.11242v1
Originality Synthesis-oriented
AI Analysis

This work addresses the critical question of human identity in the age of AI for artists and researchers interested in embodied AI and socio-cultural critique, though it is incremental as it applies existing methods to a new artistic domain.

The authors tackled the problem of how AI shapes bodily movement by creating ReTracing, a multi-agent performance art that uses LLMs and diffusion models to generate choreographic guides for a human and robot, resulting in a digital archive of motion traces that reveal socio-cultural biases in generative systems.

We present ReTracing, a multi-agent embodied performance art that adopts an archaeological approach to examine how artificial intelligence shapes, constrains, and produces bodily movement. Drawing from science-fiction novels, the project extracts sentences that describe human-machine interaction. We use large language models (LLMs) to generate paired prompts "what to do" and "what not to do" for each excerpt. A diffusion-based text-to-video model transforms these prompts into choreographic guides for a human performer and motor commands for a quadruped robot. Both agents enact the actions on a mirrored floor, captured by multi-camera motion tracking and reconstructed into 3D point clouds and motion trails, forming a digital archive of motion traces. Through this process, ReTracing serves as a novel approach to reveal how generative systems encode socio-cultural biases through choreographed movements. Through an immersive interplay of AI, human, and robot, ReTracing confronts a critical question of our time: What does it mean to be human among AIs that also move, think, and leave traces behind?

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes