发表机构
School of Systems Science, Beijing Normal University（北京师范大学系统科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出HI-FLOOP分层状态反馈框架，通过多时间尺度分支一致的世界建模和前缀冻结级联恢复，提升多智能体交通仿真长时域生成的一致性，在H-D验证集上取得S1总体得分0.689987。
AI 中文摘要
多智能体交通仿真旨在从地图和观测历史中生成多样化、协调且物理上逼真的未来场景。长时域闭环生成必须在上下文随生成状态演变的同时，协调多个决策时间尺度。现有方法通常从初始场景展开长时域未来，并整体性地解决意图、交互和运动问题，从而削弱了跨尺度一致性和适应性。我们提出了HI-FLOOP，一种分支一致的多时间尺度状态反馈框架。八个场景级世界表示联合假设，所有智能体在8秒的展开过程中共享所选的世界身份。在分支内，一个8秒的目标锚定意图，一个2秒的预览协调交互，1秒的控制产生物理运动。每0.5秒的提交仅将其已执行的前缀作为新事实反馈，而未执行的假设永远不会进入事实记忆。联合预览交互（JPI）从预览中生成稀疏的有向未来图，并使用冲突概率和带符号的到达时间差来门控交互细化。对于生成状态的恢复，前缀冻结的A到B级联允许冻结的模型A生成0-1秒，然后将类型化的物理状态、可接受的上下文和分支索引（但不包含潜在状态）传递给独立的模型B，以重新编码并恢复1-2秒。在包含955个场景的完整H-D公共验证集上，一次完整的S1运行使用官方评估器得到总体得分为0.689987。在智能体中心化的oracle评估下，HI-FLOOP在8秒时域上实现了oracle-minADE@8为1.196636米，在6秒时域上为0.526米。
英文摘要
Multi-agent traffic simulation seeks diverse, coordinated, and physically realistic futures from maps and observed history. Long-horizon closed-loop generation must reconcile multiple decision time scales while its context evolves with generated states. Existing methods often unfold long futures from an initial scene and resolve intent, interaction, and motion monolithically, weakening cross-scale consistency and adaptation. Multimodal rollout poses a further consistency problem: independently reselecting modes across agents or commits can stitch together incompatible futures instead of preserving a coherent joint branch. We present Hi-FLoop, a branch-consistent multi-timescale state-feedback framework. Eight scene-level Worlds represent joint hypotheses; all agents share one selected World identity throughout all 16 commits of an 8-second rollout, while Goal, Preview, and Control states adapt within that branch. An 8-second Goal anchors intent, a 2-second Preview coordinates interactions, and 1-second Control produces physical motion. Every 0.5-second commit feeds back only its executed prefix as new facts, while unexecuted hypotheses never enter factual memory. Joint Preview Interaction induces a sparse directed future graph and uses conflict probabilities and signed arrival-time differences to refine interaction-aware motion. For generated-state recovery, a prefix-frozen A-to-B cascade transfers typed physical state and the branch index--but no latent state--from a frozen prefix model to an independently parameterized recovery model. On the full H-D public-validation split of 955 scenarios, the S2.1 cascade obtains an 8-second scene-joint ADE-at-joint-minFDE@8/joint-minFDE@8 of 2.048/6.384 m when one World must explain all evaluated agents. Agent-centric oracle-minADE@8 is 0.526 m at 6 seconds and 0.875 m at 8 seconds.
Comments12 pages, 2 figures, and 6 tables. Revised abstract, results, and branch-consistency presentation
