Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs

• URL: http://arxiv.org/abs/2605.08686v1
• Date: Sat, 09 May 2026 04:51:42 GMT
• Title: Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
• Abstract summary: Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models.<n>We propose a critique-and-routing controller that casts multi-agent coordination as a sequential decision problem.
• Score: 31.34021188099265
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot routing: they select a model once and return its output directly. Such routing-only designs provide no mechanism to critique intermediate drafts or support iterative refinement. To address this limitation, we propose a critique-and-routing controller that casts multi-agent coordination as a sequential decision problem. At each turn, the controller evaluates the current draft, decides whether to stop or continue, and, if needed, selects the next agent for further refinement. We formulate this process as a finite-horizon Markov Decision Process (MDP) with explicit agent-utilization constraints, design a composite reward for controller decisions across turns, and optimize the controller via policy gradients under a Lagrangian-relaxed objective. Extensive experiments across multiple heterogeneous multi-agent systems and seven reasoning benchmarks show that our method consistently outperforms state-of-the-art baselines and substantially narrows the gap to the strongest agent, while using it for fewer than 25% of total calls.

Related papers

• Multi-Objective Agent-Based Model Predictive Controller for Plug-and-Play Vehicle Control [18.92447175833456]
  Functional integration is a growing trend in vehicle control, often involving the coordination of multiple controllers.<n>Agent-based model predictive control (AMPC) has emerged as a distributed solution that treats controllers as agents.<n>We propose a novel, practical distributed control scheme called multi-objective AMPC.
  arXiv  Detail & Related papers  (2026-09-10T18:35:08Z)
• Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making [15.37854161578634]
  We introduce Multi-Head Latent Control, a lightweight layer that reads hidden-state trajectories from a frozen LLM or VLM to produce deployment-time control signals.<n>A Capability Head predicts whether the current model can solve the instance or should defer to a stronger collaborator, while a Resolution Head predicts appropriate resolution decision Clarification, Tool Use, Abstention, or Direct Answering.<n>Both heads are trained only on latent traces from the same frozen LLM backbone, enabling post hoc adaptation without modifying the model.
  arXiv  Detail & Related papers  (2026-07-15T18:36:54Z)
• Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning [87.18590662029432]
  We propose PRP, a Proactive Routing Paradigm that enables early decision-making by jointly evaluating the competence of both the draft and target models.<n>Our draft Rating Learning (DRL) equips the draft model with an internal confidence estimator, while Joint Rating Learning (JRL) predicts how well the target model can handle a given query.<n>These ratings enable fine-grained, instance-level textbfProactive Routing and substantially accelerate inference without compromising overall performance.
  arXiv  Detail & Related papers  (2026-06-29T12:30:24Z)
• Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control [51.92884966472683]
  MSCoT is a multi-scale, coarse-to-fine model for test-time human motion synthesis and control.<n> MSCoT discretizes motion into a multi-scale hierarchical representation and predicts the entire token sequence at each temporal scale.
  arXiv  Detail & Related papers  (2026-05-14T15:09:49Z)
• CAMO: A Conditional Neural Solver for the Multi-objective Multiple Traveling Salesman Problem [13.232337043603161]
  We present CAMO, a conditional neural solver for the Multi-Objective Multiple Traveling Salesman Problem (MOMTSP)<n>It generalizes across varying numbers of targets, agents, and preference vectors, and yields high-quality approximations to the Pareto front (PF)<n>Experiments show that CAMO outperforms both neural and conventionals, achieving a closer approximation of PFs.
  arXiv  Detail & Related papers  (2026-03-19T15:59:45Z)
• Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization [58.59491516762626]
  We propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS)<n>AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms.<n>Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines.
  arXiv  Detail & Related papers  (2026-03-13T12:26:05Z)
• MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning [68.91090643731987]
  Deep reinforcement learning (RL) has been applied extensively to solve complex decision-making problems.<n>Existing approaches are limited to separate fields and can only handle multi-agent decision-making with a single objective.<n>We propose MO-mix to solve the multi-objective multi-agent reinforcement learning (MOMARL) problem.
  arXiv  Detail & Related papers  (2026-02-28T16:25:22Z)
• Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation [50.22481337087162]
  Referring Video Object (RVOS) aims to segment objects in videos based on textual queries.<n>Refer-Agent is a collaborative multi-agent system with alternating reasoning-reflection mechanisms.
  arXiv  Detail & Related papers  (2026-02-03T14:48:12Z)
• ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routing [0.6445605125467574]
  ORCH is a framework for discrete-choice reasoning that orchestrates heterogeneous language models.<n>It uses fixed rules for task decomposition and answer aggregation, keeping the pipeline predictable, reproducible, and training-free.<n>Experiments on MMLU, MMLU-Pro, and GSM8K show that ORCH consistently outperforms single-model baselines and a majority-vote ensemble.
  arXiv  Detail & Related papers  (2026-02-02T08:27:58Z)
• Merge and Guide: Unifying Model Merging and Guided Decoding for Controllable Multi-Objective Generation [49.98025799046136]
  We introduce Merge-And-GuidE, a two-stage framework that leverages model merging for guided decoding.<n>In Stage 1, MAGE resolves a compatibility problem between the guidance and base models.<n>In Stage 2, we merge explicit and implicit value models into a unified guidance proxy, which then steers the decoding of the base model from Stage 1.
  arXiv  Detail & Related papers  (2025-10-04T11:10:07Z)
• Offline Multi-agent Reinforcement Learning via Score Decomposition [51.23590397383217]
  offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts.<n>This work is the first work to explicitly address the distributional gap between offline and online MARL.
  arXiv  Detail & Related papers  (2025-05-09T11:42:31Z)
• PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning [16.523999372817435]
  Action Generation with Plackett-Luce Sampling (AGPS) is a novel mechanism for agent decision order optimization.<n>We propose the Prioritized Multi-Agent Transformer (PMAT), a sequential decision-making MARL algorithm with decision order optimization.<n>Experiments on benchmarks including StarCraft II Multi-Agent Challenge, Google Research Football, and Multi-Agent MuJoCo show that PMAT outperforms state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2025-02-23T08:30:14Z)

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.