SRA: Spatial Reasoning Adapter via Evolving Social Interaction Graphs for Trajectory Prediction

Predicting where multiple agents will move next is fundamental to autonomous driving, robotics, and any system that must share space with people safely. Modern stochastic predictors read off inter-agent interactions once from the observed past and keep that view fixed throughout the generative rollout, so the reciprocal geometric constraints that emerge as the joint future sharpens are not re-examined. We address this gap with SRA (Spatial Reasoning Adapter), a modular graph denoiser that plugs into existing diffusion predictors without altering their generative cores. At every reverse step, SRA reads the host's current future estimate, builds a sparse Euclidean interaction graph on the predicted trajectories, and returns a residual correction to the host's decoding path. Our adapter consists of three core components: a sparse top-$N$ neighborhood retrieved with an asymmetric query-key score, a future-conditioned relational feature recomputed on the evolving prediction, and uncertainty-weighted message passing where confident agents act as anchors for uncertain ones. We instantiate SRA on three structurally different hosts - LED, MID, and MoFlow - across four multi-agent benchmarks: SDD, NBA, Soccer, and Football. SRA improves every host on every dataset by 6--7\% on average, indicating that spatial reasoning over the model's own evolving future is broadly useful across denoising architectures. The code will be released upon acceptance.