AI Paper Atlas

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

UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation

Longzhong Lin, Xuewu Lin, Kechun Xu, Haojian Lu, Lichao Huang, Rong Xiong, Yue Wang

TPAMI 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 18 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
lengthen prediction horizon from 0.5s to 2s (ablation)anchor-free K=3, open-loop training · WOSAC val subset (150 scenes)Realism Meta: 0.7071 -> 0.7388Improved
lengthen prediction horizon from 0.5s to 4s (ablation)anchor-based K=2048, open-loop training · WOSAC val subset (150 scenes)Realism Meta: 0.7361 -> 0.7570Improved
extend horizon beyond 4s to 8s (ablation)anchor-based K=2048, open-loop training · WOSAC val subset (150 scenes)Realism Meta: 0.7570 -> 0.7489Hurt
increase components from 3 to 6 (ablation)anchor-free, 4s horizon, open-loop · WOSAC val subset (150 scenes)Realism Meta: 0.7382 -> 0.7409Improved
increase components from 6 to 16 (ablation)anchor-free, 4s horizon, open-loop · WOSAC val subset (150 scenes)Realism Meta: 0.7409 -> 0.7343Hurt
increase components from 64 to 2048 (ablation)anchor-based, 4s horizon, open-loop · WOSAC val subset (150 scenes)Realism Meta: 0.7388 -> 0.7570Improved
increase components from 3 to 16 (ablation)anchor-free, 8s horizon · WOMD val open-loop predictionmAP: 0.3356 -> 0.2037Hurt
train on closed-loop samples with closed-loop window equal to 4s horizon (ablation)anchor-free K=6, 4s horizon · WOSAC val subset (150 scenes)Realism Meta: 0.7409 -> 0.7376Hurt
train on closed-loop samples with closed-loop window equal to 4s horizon (ablation)anchor-based K=2048, 4s horizon · WOSAC val subset (150 scenes)Realism Meta: 0.7570 -> 0.7475Hurt
train on closed-loop samples with 0.5s window and 0.5s horizon (ablation)anchor-based K=2048 · WOSAC val subset (150 scenes)Realism Meta: 0.7361 -> 0.7658Improved
train on closed-loop samples with 0.5s window and 0.5s horizon (ablation)anchor-free K=6 · WOSAC val subset (150 scenes)Realism Meta: 0.6948 -> 0.7404Improved
shorten closed-loop window to 0.5s while keeping 4s horizon (ablation)anchor-free K=6 · WOSAC val subset (150 scenes)Realism Meta: 0.7376 -> 0.7624Improved

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