AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs

Bin Li, Ruichi Zhang, Han Liang, Jingyan Zhang, Juze Zhang, Xin Chen, Lan Xu, Jingyi Yu, Jingya Wang

CVPR 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace relative-state exteroception with fully connected interaction graph (ablation)InterAgent 3-stream · InterHuman testFID: 0.676 -> 0.634Improved
add sparse edge attention to the interaction graph (FIG to SIG) (ablation)InterAgent 3-stream · InterHuman testFID: 0.634 -> 0.582Improved
use 3 streams instead of 1 stream in DiT block (ablation)InterAgent with FIG · InterHuman testFID: 0.828 -> 0.634Improved
use 3 streams instead of 2 streams in DiT block (ablation)InterAgent with FIG · InterHuman testFID: 0.662 -> 0.634Improved
use 2 streams instead of 1 stream in DiT block (ablation)InterAgent with FIG · InterHuman testR-precision Top-3: 0.523 -> 0.608Improved
edge-based sparse attention at ratio 1/2 instead of non-sparse (ablation)InterAgent · InterHuman testFID: 0.634 -> 0.582Improved
use a very high sparsity (ratio 1/8) edge-based attention (ablation)InterAgent · InterHuman testFID: 0.634 -> 0.643No clear effect
use joint-based instead of edge-based sparsity at ratio 1/2 (ablation)InterAgent · InterHuman testFID: 0.582 -> 0.619Hurt
train end-to-end physics-based diffusion over interaction graphs instead of generate-then-track (InterGen++)physics-based multi-agent control · InterHuman testFID: 0.943 -> 0.582Improved
use InterAgent instead of InterGen++Multimodality metric · InterHuman testMModality: 2.482 -> 1.903Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy