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

arXiv: https://arxiv.org/abs/2602.01797 · HTML: https://mlsanity.com/paper/2602.01797/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [AgentScope: A Flexible yet Robust Multi-Agent Platform](https://mlsanity.com/paper/2402.14034/) (2024)
- [Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge](https://mlsanity.com/paper/2102.03315/) (2021)
- [MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation](https://mlsanity.com/paper/2503.10497/) (2025)
- [Scientific Machine Learning Benchmarks](https://mlsanity.com/paper/2110.12773/) (2021)
- [MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark](https://mlsanity.com/paper/2412.15194/) (2024)
- [Self-Adaptive Large Language Model (LLM)-Based Multiagent Systems](https://mlsanity.com/paper/2307.06187/) (2023)
- [Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems](https://mlsanity.com/paper/2404.14963/) (2024)
- [Calibrating Reasoning in Language Models with Internal Consistency](https://mlsanity.com/paper/2405.18711/) (2024)
- [Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions](https://mlsanity.com/paper/2402.01108/) (2024)
- [LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins](https://mlsanity.com/paper/2405.18092/) (2024)
- [HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning](https://mlsanity.com/paper/2502.11393/) (2025)
- [Large Language Models are Biased Reinforcement Learners](https://mlsanity.com/paper/2405.11422/) (2024)
- [MAS2: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems](https://mlsanity.com/paper/2509.24323/) (2025)
- [PBFT-Backed Semantic Voting for Multi-Agent Memory Pruning](https://mlsanity.com/paper/2506.17338/) (2025)

## Built on by (most cited first, 5 of 5)

- [ATLAS: Agentic Test-time Learning-to-Allocate Scaling](https://mlsanity.com/paper/2606.01667/) (2026)
- [Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts](https://mlsanity.com/paper/2604.00901/) (2026)
- [FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills](https://mlsanity.com/paper/2607.21596/) (2026)
- [Runtime Burden Allocation for Structured LLM Routing in Agentic Expert Systems: A Full-Factorial Cross-Backend Methodology](https://mlsanity.com/paper/2604.01235/) (2026)
- [Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving](https://mlsanity.com/paper/2606.05704/) (2026)

## Abstract (arXiv)

Recent advances in large-scale language models (LLMs) have made multi-agent architectures attractive for challenging reasoning tasks. However, many existing systems rely on stochastic routing or ad-hoc heuristics, making their behavior difficult to reproduce and their decision process hard to interpret. We propose ORCH, a deterministic coordination framework for discrete-choice reasoning that orchestrates heterogeneous LLMs. ORCH follows a ``many analyses, one decision'' paradigm: multiple base models independently produce structured analyses, and a dedicated merge agent outputs the final choice. The framework uses fixed rules for task decomposition and answer aggregation, keeping the pipeline predictable, reproducible, and training-free. Determinism here refers to fixed routing and aggregation rules under a fixed evaluation protocol, rather than strict bit-level reproducibility across deployments. To exploit model complementarity, we optionally introduce an EMA-guided router that updates agent selection using historical accuracy, latency, or cost; since it relies on answer-based feedback, it is mainly intended for benchmarking, controlled evaluation, or delayed-feedback settings. Experiments on MMLU, MMLU-Pro, and GSM8K show that ORCH consistently outperforms single-model baselines and a majority-vote ensemble. On MMLU-Pro, ORCH improves accuracy by over 10 points compared to the strongest baseline, and on GSM8K it yields gains exceeding 50 points; McNemar tests confirm statistical significance. The EMA router provides an additional 0.7--2.0 point accuracy boost, and ablations show that both multi-agent collaboration and routing contribute substantially. Overall, ORCH offers a practical path toward controllable, interpretable, and deployment-ready LLM-based agent systems for discrete-choice reasoning.