iARCS: 反復エージェント強化学習による制御可能な3Dシーン生成
iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
事前学習済みの3Dシーン生成器を自然言語のタスク要件に適応させる反復エージェント強化学習フレームワークを提案。物理的妥当性とレイアウト品質を向上させつつ、タスク固有の制約（歩行可能性、到達可能性、クリアランス）を満たすシーンを生成する。
著者: Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel
分類: cs.AI
原文アブストラクト
Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably satisfying task-critical functional constraints. This mismatch limits the usefulness of synthetic data for downstream training, where accessibility, traversability, and spatial rule compliance are often essential. We present iARCS, an iterative agentic reinforcement learning framework that adapts a pretrained scene generator to natural-language task requirements. iARCS uses a two-stage strategy: universal-reward pretraining to improve physical plausibility and layout quality, followed by task-specific fine-tuning with LLM-generated reward programs that are iteratively refined from training feedback. Experiments show improved constraint fidelity on walkability, reachability, and clearance-focused tasks, effective task-specific constraint optimization, and competitive scene diversity. We further show that data generated by iARCS improves a base generator, supporting its value as a practical synthetic data generation tool rather than only a controllable scene editing method.