MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System

• URL: http://arxiv.org/abs/2605.05949v2
• Date: Fri, 08 May 2026 06:07:17 GMT
• Title: MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System
• Abstract summary: MAS-Algorithm is a systematic multi-agent workflow for algorithmic problem solving inspired by competitive programmers and algorithm engineers.<n>Our framework decomposes the end-to-end solving process into modular stages, enabling structured reasoning, tool integration, and flexible coordination among agents.
• Score: 15.213043425523287
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's ability to perform structured reasoning in complex scenarios. Existing approaches predominantly rely on model-centric strategies, such as architectural modifications and data scaling, which are costly and offer limited interpretability. Alternative methods leveraging external tools or prompting techniques (e.g., chain-of-thought) are often fragmented and lack a unified framework. In this paper, we propose MAS-Algorithm, a systematic multi-agent workflow for algorithmic problem solving inspired by the practices of competitive programmers and algorithm engineers. Our framework decomposes the end-to-end solving process into modular stages, enabling structured reasoning, tool integration, and flexible coordination among agents. The design emphasizes both rigor and extensibility, allowing it to generalize across diverse problem types. Experimental results on a self-constructed benchmark demonstrate consistent improvements across multiple Qwen series models, achieving an average gain of 6.48% in acceptance rate. In contrast, parameter-efficient fine-tuning on the same data yields only a marginal improvement of 0.89%. We further observe a 4.72% gain on LiveCodeBench-Pro, along with consistent improvements across additional accuracy and efficiency metrics. Beyond performance gains, we conduct comprehensive analyses to better understand the reasoning process within the workflow, including error patterns and cross-scenario behaviors. We further perform customized replacement and ablation studies to explore the upper bound of the framework, showing that individual agents can contribute improvements of up to 27.7%. These results highlight the strong potential of MAS-Algorithm for advancing AI-driven algorithmic reasoning.

Related papers

• A new dual-population constrained multi-objective evolutionary optimization algorithm with repair constraint handling for structural optimization [0.0]
  We introduce a novel constrained evolutionary optimization algorithm for multi-objective engineering applications.<n>The algorithm employs two interacting populations that exchange information, enabling effective global exploration and reducing the risk of convergence to local optima.<n>The proposed algorithm is tested on three engineering problems: the 72-bar truss, the 120-bar truss, and each involving hundreds of nonlinear failure constraints.
  arXiv  Detail & Related papers  (2026-07-14T00:57:07Z)
• OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement [0.0]
  OptiAgent is a multi-agent framework that is able to output a solver-ready mathematical formulation as well as executable code.<n>Our architecture prioritizes the mathematical modeling step, where dedicated agents extract structures.<n>We introduce a novel multi-loop validation architecture with four specialized feedback mechanisms, each targeting a distinct failure mode.
  arXiv  Detail & Related papers  (2026-07-06T17:27:16Z)
• FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization [61.43300970020897]
  Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation.<n>Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity.<n>We introduce FrontierOR, among the first benchmarks to evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems.
  arXiv  Detail & Related papers  (2026-05-24T20:10:42Z)
• Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization [6.428928591765431]
  Operations research with large language models (LLMs) remains limited by hand-crafted reasoning.<n>We propose EvoOR-Agent, a co-evolutionary framework for automated optimization.<n>Case studies and ablation analyses indicate that explicit architecture evolution and graph-supported reasoning-trajectory search contribute to both performance improvement and structural interpretability.
  arXiv  Detail & Related papers  (2026-04-20T01:44:18Z)
• Multi-Action Self-Improvement for Neural Combinatorial Optimization [0.979731979071071]
  Self-improvement models iteratively refine their policies by generating and imitating high-quality solutions.<n>These approaches fail to exploit the structure of problems involving the coordination of multiple agents.<n>We extend self-improvement to operate over joint multi-agent actions.
  arXiv  Detail & Related papers  (2025-10-14T08:26:27Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• DeclareAligner: A Leap Towards Efficient Optimal Alignments for Declarative Process Model Conformance Checking [1.4064491732635231]
  This paper introduces DeclareAligner, a novel algorithm that uses the A* search algorithm, an established AI pathfinding technique, to tackle the problem.<n>The proposed method is evaluated using 8,054 synthetic and real-life alignment problems, demonstrating its ability to efficiently compute optimal alignments.
  arXiv  Detail & Related papers  (2025-03-13T15:49:29Z)
• BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning [78.63421517563056]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks.<n>We present a unified probabilistic framework that formalizes LLM reasoning through a novel graphical model.<n>We introduce the Bootstrapping Reinforced Thinking Process (BRiTE) algorithm, which works in two steps.
  arXiv  Detail & Related papers  (2025-01-31T02:39:07Z)
• A Survey on Inference Optimization Techniques for Mixture of Experts Models [50.40325411764262]
  Large-scale Mixture of Experts (MoE) models offer enhanced model capacity and computational efficiency through conditional computation.<n> deploying and running inference on these models presents significant challenges in computational resources, latency, and energy efficiency.<n>This survey analyzes optimization techniques for MoE models across the entire system stack.
  arXiv  Detail & Related papers  (2024-12-18T14:11:15Z)
• Multi-objective Binary Differential Approach with Parameter Tuning for Discovering Business Process Models: MoD-ProM [2.3423913554158653]
  We consider the Binary Differential Evolution approach in a multi-objective framework for the task of process discovery. It is shown that the process models generated by the proposed approach are superior to or at least as good as those generated by the state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-06-25T16:53:55Z)
• Solution to Advanced Manufacturing Process Problems using Cohort Intelligence Algorithm with Improved Constraint Handling Approaches [0.07989135005592125]
  Cohort Intelligence (CI) algorithm is a socio inspired optimization technique which is successfully applied for solving several unconstrained & constrained real-world problems from the domains such as design, manufacturing, supply chain, healthcare, etc.
  arXiv  Detail & Related papers  (2023-10-16T05:40:23Z)
• Sample-Efficient Multi-Agent RL: An Optimization Perspective [103.35353196535544]
  We study multi-agent reinforcement learning (MARL) for the general-sum Markov Games (MGs) under the general function approximation. We introduce a novel complexity measure called the Multi-Agent Decoupling Coefficient (MADC) for general-sum MGs. We show that our algorithm provides comparable sublinear regret to the existing works.
  arXiv  Detail & Related papers  (2023-10-10T01:39:04Z)
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning [70.65666982566655]
  Permutation flow shop scheduling (PFSS) is widely used in manufacturing systems. We propose to train the model via expert-driven imitation learning, which accelerates convergence more stably and accurately. Our model's network parameters are reduced to only 37% of theirs, and the solution gap of our model towards the expert solutions decreases from 6.8% to 1.3% on average.
  arXiv  Detail & Related papers  (2022-10-31T09:46:26Z)

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.