Orchestration

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 233% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 136

All topics

SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation
Apr 21, 2026Yun He, Kelin Yu, Matthias Zwicker3D Scene Generation Orchestration
University of Maryland, College Park
GraSP: Graph-Structured Skill Compositions for LLM Agents
Apr 20, 2026Tianle Xia, Lingxiang Hu, Yiding Sun +5Unsupervised Skill Discovery Skills
Tencent
Beyond Task Success: An Evidence-Synthesis Framework for Evaluating, Governing, and Orchestrating Agentic AI
Apr 18, 2026Christopher Koch, Joshua Andreas WellbrockArtificial Intelligence Governance Governance
Independent Researcher
Harness as an Asset: Enforcing Determinism via the Convergent AI Agent Framework (CAAF)
Apr 18, 2026Tianbao ZhangAgentic Deployments Safety-Critical Scenarios
Independent Researcher
Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition
Apr 18, 2026Wenzhen Yuan, Wutao Xiong, Fanchen Yu +7Multi-Agent Orchestration Orchestration
Shanghai Jiao Tong University · Sichuan University · Shanghai AI Lab +2
Agentic Frameworks for Reasoning Tasks: An Empirical Study
Apr 17, 2026Zeeshan Rasheed, Abdul Malik Sami, Muhammad Waseem +3Agentic Framework Reasoning Benchmark
*Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland.
Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs
Apr 16, 2026Ziyang Luo, Nian Liu, Junwei HanMultimodal Fusion Modalities
Northwestern Polytechnical University Xi’an, Shaanxi, China
Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems
Mar 23, 2026Hehai Lin, Yu Yan, Zixuan Wang +6Model-Based Multi-Agent Systems Domain-Specific Language
The Hong Kong University of Science and Technology (Guangzhou) · Nanyang Technological University · National University of Singapore +1
Decentralized Orchestration Architecture for Fluid Computing: A Secure Distributed AI Use Case
Mar 12, 2026Diego Cajaraville-Aboy, Ana Fernández-Vilas, Rebeca P. Díaz-Redondo +2Distributed Optimization Orchestration
atlanTTic Research Center – ICLAB – Universidade de Vigo, Vigo, 36310, Spain
Towards Effective Orchestration of AI x DB Workloads
Mar 4, 2026Naili Xing, Haotian Gao, Zhanhao Zhao +6Workload Orchestration
National University of Singapore · Beijing Institute of Technology · Renmin University of China +1
A General Equilibrium Theory of Orchestrated AI Agent Systems
Feb 23, 2026Jean-Philippe GarnierLarge Language Model Agents Artificial Intelligence Agents
Br.AI.K · BrainiaK
OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale
Feb 5, 2026Jingze Shi, Zhangyang Peng, Yizhang Zhu +3Mixture-Of-Expert Inference Mixture-Of-Experts
The Hong Kong University of Science and Technology (Guangzhou) · Beijing Academy of Artificial Intelligence
Disentangling Intrinsic Importance from Emergent Structure in Multi-Expert Orchestration
Feb 4, 2026Sudipto Ghosh, Sujoy Nath, Sunny Manchanda +1Orchestration Interpretability
Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, India · Department of Electrical Engineering, Indian Institute of Technology Delhi, India · DYSL-AI, Defence Research and Development Organisation, India
Monadic Context Engineering
Dec 27, 2025Yifan Zhang, Yang Yuan, Mengdi Wang +1Orchestration Engineering
IIIS, Tsinghua University
AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research
Dec 18, 2025Ignacio Heredia, Álvaro López García, Fernando Aguilar Gómez +28Cloud Orchestration
Instituto de Física de Cantabria (IFCA), CSIC-UC, Avda. los Castros s/n, Santander, 39006, Cantabria, Spain · Instituto de Instrumentación para Imagen Molecular (I3M), Centro Mixto CSIC - Universitat Politècnica de València (UPV), Camino de Vera s/n, Valencia, 46022, Valencia, Spain · Karlsruher Institut für Technologie, Kaiserstraße 12, Karlsruhe, 76131, Germany +7
Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems
Date pendingRakibul Hasan Rajib, Mengxin Zheng, Qian LouMulti-Agent Large Language Model Systems Collaboration
University of Central Florida

Apr 21, 2026, cs.CVJ/K move · Enter open · S save

SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation

Yun He, Kelin Yu, Matthias Zwicker

University of Maryland, College Park

3D Scene Generation Orchestration Chorus Single Trajectory

Open paper AskPDF arXiv

Recent agentic frameworks for 3D scene synthesis have advanced realism and diversity by integrating heterogeneous generation and editing tools. These tools are organized into workflows orchestrated by an off-the-shelf LLM. Current approaches typically adopt an execute-review-reflect loop: at each step, the orchestrator executes a tool, renders intermediate results for review, and then decides on the tool and its parameters for the next step. However, this design has two key limitations. First, next-step tool selection and parameter configuration are driven by heuristic rules, which can lead to suboptimal execution flows, unnecessary tool invocations, degraded output quality, and increased runtime. Second, rendering and reviewing intermediate results after each step introduces additional latency. To address these issues, we propose SceneOrchestra, a trainable orchestration framework that optimizes the tool-call execution flow and eliminates the step-by-step review loop, improving both efficiency and output quality. SceneOrchestra consists of an orchestrator and a discriminator, which we fine-tune with a two-phase training strategy. In the first phase, the orchestrator learns context-aware tool selection and complete tool-call trajectory generation, while the discriminator is trained to assess the quality of full trajectories, enabling it to select the best trajectory from multiple candidates. In the second phase, we perform interleaved training, where the discriminator adapts to the orchestrator's evolving trajectory distribution and distills its discriminative capability back into the orchestrator. At inference, we only use the orchestrator to generate and execute full tool-call trajectories from instructions, without requiring the discriminator. Extensive experiments show that our method achieves state-of-the-art scene quality while reducing runtime compared to previous work.

Momentum

Related topics

Latest papers 136