Imagen de Portada

ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Hanlin, Chan, Huah Yong
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Runtime Burden Allocation for Structured LLM Routing in Agentic Expert Systems: A Full-Factorial Cross-Backend Methodology
por: Hanlin, Zhou, et al.
Publicado: (2026)

ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents
por: Hanlin, Zhou, et al.
Publicado: (2026)

Automatic Adjustment of HPA Parameters and Attack Prevention in Kubernetes Using Random Forests
por: Zhou, Hanlin, et al.
Publicado: (2026)

Dynamic fairness-aware recommendation through multi-agent social choice
por: Aird, Amanda, et al.
Publicado: (2023)

MARS: toward more efficient multi-agent collaboration for LLM reasoning
por: Wang, Xiao, et al.
Publicado: (2025)

Position: agentic AI orchestration should be Bayes-consistent
por: Papamarkou, Theodore, et al.
Publicado: (2026)

Evidence-based diagnostic reasoning with multi-agent copilot for human pathology
por: Weishaupt, Luca L., et al.
Publicado: (2025)

TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection
por: Zeng, Sihang, et al.
Publicado: (2026)

Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient
por: Yu, Xiaoyang, et al.
Publicado: (2025)

EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL
por: Zhang, Lunjun, et al.
Publicado: (2026)

Learning for routing: A guided review of recent developments and future directions
por: Zhou, Fangting, et al.
Publicado: (2025)

SIKeD: Self-guided Iterative Knowledge Distillation for mathematical reasoning
por: Adarsh, Shivam, et al.
Publicado: (2024)

Adaptive routing protocols for determining optimal paths in AI multi-agent systems: a priority- and learning-enhanced approach
por: Panayotov, Theodor, et al.
Publicado: (2025)

Automated legal reasoning with discretion to act using s(LAW)
por: Arias, Joaquín, et al.
Publicado: (2024)

AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery
por: Yin, Yuqi, et al.
Publicado: (2025)

Biomedical reasoning in action: Multi-agent System for Auditable Biomedical Evidence Synthesis
por: Wysocki, Oskar, et al.
Publicado: (2025)

WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis
por: Wu, Yuqi, et al.
Publicado: (2025)

DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning
por: McPheat, Lachlan, et al.
Publicado: (2025)

Reinforcement Learning in hyperbolic space for multi-step reasoning
por: Xu, Tao, et al.
Publicado: (2025)

Learning to reason about rare diseases through retrieval-augmented agents
por: Kim, Ha Young, et al.
Publicado: (2025)

EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes
por: Block, Adam, et al.
Publicado: (2025)

SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning
por: Ghafarollahi, Alireza, et al.
Publicado: (2024)

Retrieval-augmented reasoning with lean language models
por: Chan, Ryan Sze-Yin, et al.
Publicado: (2025)

Is continuous CoT better suited for multi-lingual reasoning?
por: Bashir, Ali Hamza, et al.
Publicado: (2026)

Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics
por: Xu, Cong, et al.
Publicado: (2025)

From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling
por: Lu, Yao, et al.
Publicado: (2025)

Incorporating uncertainty quantification into travel mode choice modeling: a Bayesian neural network (BNN) approach and an uncertainty-guided active survey framework
por: Zheng, Shuwen, et al.
Publicado: (2024)

Configurable multi-agent framework for scalable and realistic testing of llm-based agents
por: Wang, Sai, et al.
Publicado: (2025)

The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents
por: Khan, Rafflesia, et al.
Publicado: (2026)

Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning
por: Sclar, Melanie, et al.
Publicado: (2024)

Causal vs. Anticausal merging of predictors
por: Mejia, Sergio Hernan Garrido, et al.
Publicado: (2025)

Performance Comparison of IBN orchestration using LLM and SLMs
por: Phone, Wai Lwin, et al.
Publicado: (2026)

Adaptive parameter sharing for multi-agent reinforcement learning
por: Li, Dapeng, et al.
Publicado: (2023)

MetaOpenFOAM: an LLM-based multi-agent framework for CFD
por: Chen, Yuxuan, et al.
Publicado: (2024)

Performance of AI agents based on reasoning language models on ALD process optimization tasks
por: Yanguas-Gil, Angel
Publicado: (2026)

Using multi-agent architecture to mitigate the risk of LLM hallucinations
por: Amer, Abd Elrahman, et al.
Publicado: (2025)

Demonstrating specification gaming in reasoning models
por: Bondarenko, Alexander, et al.
Publicado: (2025)

Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably
por: Kang, Enoch Hyunwook
Publicado: (2026)

Causal reasoning in difference graphs
por: Assaad, Charles K.
Publicado: (2024)

Mathematical reasoning and the computer
por: Buzzard, Kevin
Publicado: (2025)