iARCS: Iterative Agentic RL for Controllable 3D Scene Generation

• URL: http://arxiv.org/abs/2608.06161v2
• Date: Thu, 13 Aug 2026 12:52:37 GMT
• Title: iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
• Abstract summary: iARCS adapts a pretrained scene generator to natural-language task requirements.<n>Experiments show improved constraint fidelity on walkability, reachability, and clearance-focused tasks.
• Score: 20.98948004289507
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning [95.29291773706224]
  Tool-Integrated Reasoning is a capability for LLM agents to solve complex tasks by interacting with external tools iteratively.<n>Existing approaches typically assign uniform trajectory-level advantages and treat all correct tool calls equally.<n>This can lead to imprecise learning signals that do not adequately distinguish between trivial and challenging tool-use patterns.
  arXiv  Detail & Related papers  (2026-08-22T09:14:15Z)
• The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning [65.67266333751569]
  Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks.<n>We propose a self-supervised reinforcement learning framework that targets the internal reasoning process without requiring ground-truth annotations.<n>We show that this label-free consistency training approaches the accuracy of models trained with ground-truth supervision and achieves similar generalization across diverse tasks and data domains.
  arXiv  Detail & Related papers  (2026-06-10T10:50:06Z)
• Efficient and Adaptive Human Activity Recognition via LLM Backbones [39.42078885809324]
  We propose a paradigm shift that reuses large pretrained language models (LLMs) as generic temporal backbones for sensor-based HAR.<n>We show that this approach enables rapid convergence, strong data efficiency, and robust cross-dataset transfer.
  arXiv  Detail & Related papers  (2026-05-12T12:06:39Z)
• AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning [7.129476412364631]
  We propose AnomalyAgent, an anomaly synthesis agent with self-reflection, knowledge retrieval, and iterative refinement capabilities.<n>Specifically, AnomalyAgent is equipped with five tools: Prompt Generation (PG), Image Generation (IG), Quality Evaluation (QE), Knowledge Retrieval (KR), and Mask Generation (MG)<n>On the MVTec-AD dataset, AnomalyAgent synthesis achieves IS/IC-L of 2.0.33 for anomaly generation, 57.0% classification accuracy using ResNet34, and 99.3%/74.2% AP at the image/pixel level using a simple UNet.
  arXiv  Detail & Related papers  (2026-04-09T07:17:00Z)
• Beyond Quantity: Trajectory Diversity Scaling for Code Agents [51.71414642763219]
  Trajectory Diversity Scaling is a data synthesis framework for code agents that scales performance through diversity rather than raw volume.<n> TDScaling integrates four innovations: (1) a Business Cluster mechanism that captures real-service logical dependencies; (2) a blueprint-driven multi-agent paradigm that enforces trajectory coherence; and (3) an adaptive evolution mechanism that steers toward long-tail scenarios.
  arXiv  Detail & Related papers  (2026-02-03T07:43:03Z)
• ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas [13.919124676472022]
  ASTRA is an end-to-end framework for training tool-augmented language model agents.<n>ASTRA integrates scalable data synthesis and verifiable reinforcement learning.<n> Experiments on multiple agentic tool-use benchmarks demonstrate that ASTRA-trained models achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-01-29T11:22:23Z)
• Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection [71.84636717632206]
  Unmanned aerial vehicles (UAVs) for reliable and energy-efficient data collection from spatially distributed devices holds great promise in supporting Internet of Things (IoT) applications.<n>We propose a joint language model (LLM) to learn effective UAV control policies.<n>LLM-CRDT outperforms benchmark online and offline methods, achieving up to 36.7% higher energy efficiency than current state-of-the-art DT approaches.
  arXiv  Detail & Related papers  (2025-09-17T13:05:08Z)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments [70.42705564227548]
  We propose an automated environment construction pipeline for large language models (LLMs)<n>This enables the creation of high-quality training environments that provide detailed and measurable feedback without relying on external tools.<n>We also introduce a verifiable reward mechanism that evaluates both the precision of tool use and the completeness of task execution.
  arXiv  Detail & Related papers  (2025-08-12T09:45:19Z)
• Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming [37.06543502352577]
  We propose a generator-critic duet-play teaming framework to transform feature spaces efficiently and without supervision.<n>The framework consists of three interconnected steps: (1) Critic agent diagnoses data to generate actionable advice, (2) Generator agent produces tokenized feature transformations guided by the critic's advice, and (3) Iterative refinement ensures continuous improvement through feedback between agents.<n>Extensive experiments demonstrate that the proposed framework outperforms even supervised baselines in feature transformation efficiency, robustness, and practical applicability across diverse datasets.
  arXiv  Detail & Related papers  (2025-04-30T04:26:03Z)
• VIRL: Volume-Informed Representation Learning towards Few-shot Manufacturability Estimation [0.0]
  This work introduces VIRL, a Volume-Informed Representation Learning approach to pre-train a 3D geometric encoder. The model pre-trained by VIRL shows substantial enhancements on demonstrating improved generalizability with limited data.
  arXiv  Detail & Related papers  (2024-06-18T05:30:26Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.