Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning

• URL: http://arxiv.org/abs/2607.10836v1
• Date: Sun, 12 Jul 2026 16:58:21 GMT
• Title: Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning
• Abstract summary: GRADE is a hierarchical multi-agent system in which four lightweight learned gates jointly govern agent selection, hierarchy depth, inter-agent communication, and branch pruning.<n>At $sim$17B average active parameters, GRADE outperforms all baselines on GSM8K, MMLUPro, and GPQA.<n>On AIME-2025, where model depth dominates, GRADE remains competitive to existing frameworks.
• Score: 20.207338820226862
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent communication is worth its cost. We present GRADE (Gated Routing and Adaptive Depth for Efficient Reasoning), a hierarchical multi-agent system in which four lightweight learned gates jointly govern agent selection, hierarchy depth, inter-agent communication, and branch pruning. Training uses CoGRPO (Collaborative Group-Relative Policy Optimization), a novel critic-free recipe that adapts GRPO to multi-agent hierarchies and assigns a shared advantage signal to every gate and agent that participated in a rollout. Agent models are drawn from a hot-swappable Expert Registry; per-agent calibration maps allow experts to be replaced at inference time without retraining. At $\sim$17B average active parameters, GRADE outperforms all baselines on GSM8K, MMLUPro, and GPQA, surpassing the strongest baseline by 4.8 points on MMLUPro at half the active compute. On AIME-2025, where model depth dominates, GRADE remains competitive to existing frameworks. Ablations isolate the hierarchy and masked cross-attention as the largest contributors to accuracy, and show that per-agent calibration is necessary for safe hot-swapping.

Related papers

• Scalable Multi-Agent Maze Traversal with Local Communication [1.2875771631391097]
  We propose a distributed algorithm that enables agents to collectively traverse an unknown, possibly cyclic graph.<n>Agents enter sequentially at a designated start node and are tasked to localize and reach an undisclosed goal.<n>At any moment in time, exploration is performed by only one of the agents.
  arXiv  Detail & Related papers  (2026-08-12T10:21:26Z)
• Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning [68.85408801740228]
  We propose textbfAgent Q-Mix, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning problem.<n>Our method learns decentralized communication decisions using Qmix value factorization, where each agent selects from a set of communication actions that jointly induce a round-wise communication graph.<n>Agent Q-Mix achieves the highest average accuracy compared to existing methods while demonstrating superior token efficiency and robustness against agent failure.
  arXiv  Detail & Related papers  (2026-04-01T00:38:24Z)
• MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation [64.2621682259008]
  Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2)<n>We propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2) to integrate policy learning with multi-agent tree search.<n>We show that MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1 on challenging code generation benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T07:28:44Z)
• Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO [24.532870400949424]
  Current training methods train a unified large language model for all agents in the system.<n>This may limit the performances due to different underlying distributions for different agents.<n>We propose M-GRPO, a hierarchical extension of Group Relative Policy Optimization for vertical Multi-agent systems.
  arXiv  Detail & Related papers  (2025-11-17T12:06:30Z)
• AgentAsk: Multi-Agent Systems Need to Ask [26.13279490836716]
  Multi-agent systems built on large language models (LLMs) promise enhanced problem-solving capabilities through collaborative division of labor.<n>We propose AgentAsk, a lightweight and plug-and-play clarification module that treats every inter-agent message as a potential failure point and inserts minimally necessary questions to arrest error propagation.<n>AgentAsk consistently improves accuracy and robustness over public multi-agent implementations while keeping overhead minimal, with latency and extra cost all less than 5%.
  arXiv  Detail & Related papers  (2025-10-08T22:36:05Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [77.62279834617475]
  We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
  arXiv  Detail & Related papers  (2025-06-21T18:34:43Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [67.76186488361685]
  MALT (Multi-Agent LLM Training) is a novel post-training strategy that divides the reasoning process into generation, verification, and refinement steps.<n>On MATH, GSM8K, and CSQA, MALT surpasses the same baseline LLM with a relative improvement of 15.66%, 7.42%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration [55.35849138235116]
  We propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($textDyLAN$) for LLM-powered agent collaboration. We demonstrate that DyLAN outperforms strong baselines in code generation, decision-making, general reasoning, and arithmetic reasoning tasks with moderate computational cost.
  arXiv  Detail & Related papers  (2023-10-03T16:05:48Z)
• Multi-agent Deep Covering Skill Discovery [50.812414209206054]
  We propose Multi-agent Deep Covering Option Discovery, which constructs the multi-agent options through minimizing the expected cover time of the multiple agents' joint state space. Also, we propose a novel framework to adopt the multi-agent options in the MARL process. We show that the proposed algorithm can effectively capture the agent interactions with the attention mechanism, successfully identify multi-agent options, and significantly outperforms prior works using single-agent options or no options.
  arXiv  Detail & Related papers  (2022-10-07T00:40:59Z)

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.