Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization

• URL: http://arxiv.org/abs/2505.17115v2
• Date: Fri, 30 May 2025 08:59:59 GMT
• Title: Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization
• Authors: Ying Zhu, Heng Zhou, Rui Su, Peiqin Zhuang, Lei Bai,
• Abstract summary: We propose integrating swarm intelligence into the reasoning process by introducing a novel Agent-based Swarm Intelligence (ASI) paradigm.<n>To avoid swarm intelligence getting trapped in local optima, we develop a Swarm Intelligence Enhancing Reasoning framework.
• Score: 18.912255448200888
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, many approaches, such as Chain-of-Thought (CoT) prompting and Multi-Agent Debate (MAD), have been proposed to further enrich Large Language Models' (LLMs) complex problem-solving capacities in reasoning scenarios. However, these methods may fail to solve complex problems due to the lack of ability to find optimal solutions. Swarm Intelligence has been serving as a powerful tool for finding optima in the field of traditional optimization problems. To this end, we propose integrating swarm intelligence into the reasoning process by introducing a novel Agent-based Swarm Intelligence (ASI) paradigm. In this paradigm, we formulate LLM reasoning as an optimization problem and use a swarm intelligence scheme to guide a group of LLM-based agents in collaboratively searching for optimal solutions. To avoid swarm intelligence getting trapped in local optima, we further develop a Swarm Intelligence Enhancing Reasoning (SIER) framework, which develops a density-driven strategy to enhance the reasoning ability. To be specific, we propose to perform kernel density estimation and non-dominated sorting to optimize both solution quality and diversity simultaneously. In this case, SIER efficiently enhances solution space exploration through expanding the diversity of the reasoning path. Besides, a step-level quality evaluation is used to help agents improve solution quality by correcting low-quality intermediate steps. Then, we use quality thresholds to dynamically control the termination of exploration and the selection of candidate steps, enabling a more flexible and efficient reasoning process. Extensive experiments are ...

Related papers

• Reinforcing Question Answering Agents with Minimalist Policy Gradient Optimization [80.09112808413133]
  Mujica is a planner that decomposes questions into acyclic graph of subquestions and a worker that resolves questions via retrieval and reasoning.<n>MyGO is a novel reinforcement learning method that replaces traditional policy updates with gradient Likelihood Maximum Estimation.<n> Empirical results across multiple datasets demonstrate the effectiveness of MujicaMyGO in enhancing multi-hop QA performance.
  arXiv  Detail & Related papers  (2025-05-20T18:33:03Z)
• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System [75.25394449773052]
  Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving.<n>Yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods.<n>We present Optima, a novel framework that addresses these issues by significantly enhancing both communication efficiency and task effectiveness.
  arXiv  Detail & Related papers  (2024-10-10T17:00:06Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• Large Language Model-Aided Evolutionary Search for Constrained Multiobjective Optimization [15.476478159958416]
  We employ a large language model (LLM) to enhance evolutionary search for solving constrained multi-objective optimization problems. Our aim is to speed up the convergence of the evolutionary population.
  arXiv  Detail & Related papers  (2024-05-09T13:44:04Z)
• SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving [64.38649623473626]
  Large Language Models (LLMs) have driven substantial progress in artificial intelligence. We propose a novel framework called textbfSEquential subtextbfGoal textbfOptimization (SEGO) to enhance LLMs' ability to solve mathematical problems.
  arXiv  Detail & Related papers  (2023-10-19T17:56:40Z)
• Federated Multi-Level Optimization over Decentralized Networks [55.776919718214224]
  We study the problem of distributed multi-level optimization over a network, where agents can only communicate with their immediate neighbors. We propose a novel gossip-based distributed multi-level optimization algorithm that enables networked agents to solve optimization problems at different levels in a single timescale. Our algorithm achieves optimal sample complexity, scaling linearly with the network size, and demonstrates state-of-the-art performance on various applications.
  arXiv  Detail & Related papers  (2023-10-10T00:21:10Z)
• Multi-surrogate Assisted Efficient Global Optimization for Discrete Problems [0.9127162004615265]
  This paper investigates the possible benefit of a concurrent utilization of multiple simulation-based surrogate models to solve discrete problems. Our findings indicate that SAMA-DiEGO can rapidly converge to better solutions on a majority of the test problems.
  arXiv  Detail & Related papers  (2022-12-13T09:10:08Z)
• Simulation-guided Beam Search for Neural Combinatorial Optimization [13.072343634530883]
  We propose simulation-guided beam search (SGBS) for neural optimization problems. We hybridize SGBS with efficient active search (EAS), where SGBS enhances the quality of solutions backpropagated in EAS. We evaluate our methods on well-known CO benchmarks and show that SGBS significantly improves the quality of the solutions found under reasonable assumptions.
  arXiv  Detail & Related papers  (2022-07-13T13:34:35Z)
• Multi-Agent Deep Reinforcement Learning in Vehicular OCC [14.685237010856953]
  We introduce a spectral efficiency optimization approach in vehicular OCC. We model the optimization problem as a Markov decision process (MDP) to enable the use of solutions that can be applied online. We verify the performance of our proposed scheme through extensive simulations and compare it with various variants of our approach and a random method.
  arXiv  Detail & Related papers  (2022-05-05T14:25:54Z)
• Multi-Level Evolution Strategies for High-Resolution Black-Box Control [0.2320417845168326]
  This paper introduces a multi-level (m-lev) mechanism into Evolution Strategies (ESs) It addresses a class of global optimization problems that could benefit from fine discretization of their decision variables.
  arXiv  Detail & Related papers  (2020-10-04T09:24:40Z)

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.