SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly

• URL: http://arxiv.org/abs/2601.22623v1
• Date: Fri, 30 Jan 2026 06:26:34 GMT
• Title: SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly
• Authors: Wei Zhu, Zhiwen Tang, Kun Yue,
• Abstract summary: We propose Synergistic Multi-agent Planning with Heterogeneous langauge model assembly (SYMPHONY), a novel multi-agent planning framework.<n>By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration.<n> Empirical results show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware.
• Score: 6.444704310331922
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements have increasingly focused on leveraging large language models (LLMs) to construct autonomous agents for complex problem-solving tasks. However, existing approaches predominantly employ a single-agent framework to generate search branches and estimate rewards during Monte Carlo Tree Search (MCTS) planning. This single-agent paradigm inherently limits exploration capabilities, often resulting in insufficient diversity among generated branches and suboptimal planning performance. To overcome these limitations, we propose Synergistic Multi-agent Planning with Heterogeneous langauge model assembly (SYMPHONY), a novel multi-agent planning framework that integrates a pool of heterogeneous language model-based agents. By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration. Empirical results across multiple benchmark tasks show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware. When enhanced with cloud-based LLMs accessible via API, SYMPHONY demonstrates further improvements, outperforming existing state-of-the-art baselines and underscoring the effectiveness of heterogeneous multi-agent coordination in planning tasks.

Related papers

• 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)
• Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models [41.494768986191104]
  OI-MAS is a novel multi-agent framework that implements an adaptive model-selection policy across a heterogeneous pool of multi-scale models.<n>We show that OI-MAS consistently outperforms baseline multi-agent systems, improving accuracy by up to 12.88% while reducing cost by up to 79.78%.
  arXiv  Detail & Related papers  (2026-01-08T11:56:09Z)
• Multi-Agent Tool-Integrated Policy Optimization [67.12841355267678]
  Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks.<n>Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses.<n>No existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks.
  arXiv  Detail & Related papers  (2025-10-06T10:44:04Z)
• InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios [28.65914611521654]
  InfiAgent is a Pyramid-like DAG-based Multi-Agent Framework that can be applied to textbfinfinite scenarios.<n>InfiAgent achieves 9.9% higher performance compared to ADAS (similar auto-generated agent framework)
  arXiv  Detail & Related papers  (2025-09-26T15:44:09Z)
• Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents [0.0]
  We propose an effective world model for decision-making that models the world's physics and its task semantics.<n>A systematic review of 2024 research in low-resource multi-agent soccer reveals a clear trend towards integrating symbolic and hierarchical methods.<n>We formalize this trend into a framework for Hierarchical Task Environments (HTEs), which are essential for bridging the gap between simple, reactive behaviors and sophisticated, strategic team play.
  arXiv  Detail & Related papers  (2025-09-05T01:03:51Z)
• EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models [64.70546873396624]
  We present the Extremely Complex Instruction Following Benchmark (EIFBENCH) for evaluating large language models (LLMs)<n>EIFBENCH includes multi-task scenarios that enable comprehensive assessment across diverse task types concurrently.<n>We also propose the Segment Policy Optimization (SegPO) algorithm to enhance the LLM's ability to accurately fulfill multi-task workflow.
  arXiv  Detail & Related papers  (2025-06-10T02:39:55Z)
• Heterogeneous Group-Based Reinforcement Learning for LLM-based Multi-Agent Systems [25.882461853973897]
  We propose Multi-Agent Heterogeneous Group Policy Optimization (MHGPO), which guides policy updates by estimating relative reward advantages.<n>MHGPO eliminates the need for Critic networks, enhancing stability and reducing computational overhead.<n>We also introduce three group rollout sampling strategies that trade off between efficiency and effectiveness.
  arXiv  Detail & Related papers  (2025-06-03T10:17:19Z)
• Multi-Agent Collaboration via Evolving Orchestration [55.574417128944226]
  Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving.<n>We propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states.<n> Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs.
  arXiv  Detail & Related papers  (2025-05-26T07:02:17Z)
• Multi-LLM Collaborative Search for Complex Problem Solving [54.194370845153784]
  We propose the Mixture-of-Search-Agents (MoSA) paradigm to enhance search-based reasoning.<n>MoSA integrates diverse reasoning pathways by combining independent exploration with iterative refinement among LLMs.<n>Using Monte Carlo Tree Search (MCTS) as a backbone, MoSA enables multiple agents to propose and aggregate reasoning steps, resulting in improved accuracy.
  arXiv  Detail & Related papers  (2025-02-26T06:31:04Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents [14.08299391695986]
  We propose a sparse mixture-of-agents (SMoA) framework to improve the efficiency and diversity of multi-agent LLMs. SMoA introduces novel Response Selection and Early Stopping mechanisms to sparsify information flows among individual LLM agents. Experiments on reasoning, alignment, and fairness benchmarks demonstrate that SMoA achieves performance comparable to traditional mixture-of-agents approaches.
  arXiv  Detail & Related papers  (2024-11-05T17:33:39Z)
• EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms [55.77492625524141]
  EvoAgent is a generic method to automatically extend specialized agents to multi-agent systems.<n>We show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents.
  arXiv  Detail & Related papers  (2024-06-20T11:49:23Z)
• Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning [14.635361844362794]
  "Smurfs" is a novel multi-agent system that enhances DFSDT with a modular, context-efficient, and training-free design.<n>Smurfs surpasses baseline methods in both the open-ended StableToolBench and the closed-ended HotpotQA tasks.
  arXiv  Detail & Related papers  (2024-05-09T17:49:04Z)

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.