MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming

• URL: http://arxiv.org/abs/2505.22967v1
• Date: Thu, 29 May 2025 01:08:36 GMT
• Title: MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
• Abstract summary: We introduce MermaidFlow, a framework that redefines agentic search space through safety-constrained graph evolution.<n>We formulate domain-aware evolutionary operators to preserve semantic correctness while promoting structural diversity.<n>MermaidFlow achieves consistent improvements in success rates and faster convergence to executable plans on the agent reasoning benchmark.
• Score: 31.549367981711686
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the agentic search space through safety-constrained graph evolution. At its core, MermaidFlow represent workflows as a verifiable intermediate representation using Mermaid, a structured and human-interpretable graph language. We formulate domain-aware evolutionary operators, i.e., crossover, mutation, insertion, and deletion, to preserve semantic correctness while promoting structural diversity, enabling efficient exploration of a high-quality, statically verifiable workflow space. Without modifying task settings or evaluation protocols, MermaidFlow achieves consistent improvements in success rates and faster convergence to executable plans on the agent reasoning benchmark. The experimental results demonstrate that safety-constrained graph evolution offers a scalable, modular foundation for robust and interpretable agentic reasoning systems.

Related papers

• AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? [65.05151983193441]
  Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience.<n>We introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components.<n>Our results show that self-evolution reliability varies across streaming scenarios, the benefit of self-evolution is gated by model capability and non-monotonic in model strength.
  arXiv  Detail & Related papers  (2026-07-31T17:50:08Z)
• SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration [40.79922760459963]
  SkillFlow is a flow-based framework that takes a trainable Supervisor as the agent and a structured environment with dynamic skill orchestration.<n>Building on these flow diagnostics, a skill evolution mechanism determines when to evolve, what skills to create or prune, and where decision gaps lie.
  arXiv  Detail & Related papers  (2026-05-13T20:14:44Z)
• Tools as Continuous Flow for Evolving Agentic Reasoning [16.145441371225637]
  We propose Tools as Continuous Flow for Evolving Agentic Reasoning (FlowAgent)<n>FlowAgent reconceptualizes tool chaining as continuous trajectory generation within a semantic space.<n> Empirical evaluations show that FlowAgent achieves superior robustness and adaptability in long-horizon reasoning tasks.
  arXiv  Detail & Related papers  (2026-05-08T06:44:11Z)
• Learning to Compose for Cross-domain Agentic Workflow Generation [56.630382886594184]
  We create an open-source LLM for cross-domain workflow generation.<n>We learn a compact set of reusable workflow capabilities across diverse domains.<n>Our 1-pass generator surpasses SOTA refinement baselines that consume 20 iterations.
  arXiv  Detail & Related papers  (2026-02-11T18:27:22Z)
• Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation [0.5599792629509229]
  This paper operationalizes the transition of Large Language Models from passive tool-users to active workflow architects.<n>We demonstrate that by enforcing a scientific methodology of hypothesize, probe, and code, agents can autonomously write robust, production-grade code skills.
  arXiv  Detail & Related papers  (2025-12-23T11:33:32Z)
• GLOW: Graph-Language Co-Reasoning for Agentic Workflow Performance Prediction [51.83437071408662]
  We propose GLOW, a unified framework for AW performance prediction.<n>GLOW combines the graph-structure modeling capabilities of GNNs with the reasoning power of LLMs.<n>Experiments on FLORA-Bench show that GLOW outperforms state-of-the-art baselines in prediction accuracy and ranking utility.
  arXiv  Detail & Related papers  (2025-12-11T13:30:46Z)
• DyFlow: Dynamic Workflow Framework for Agentic Reasoning [79.19799197382478]
  DyFlow is a dynamic workflow generation framework that adaptively constructs and adjusts reasoning procedures based on task requirements and real-time intermediate feedback.<n>We systematically evaluate DyFlow across diverse domains, including social reasoning, biomedical tasks, mathematical problem solving, and code generation.<n>Results demonstrate that DyFlow significantly outperforms existing baselines, achieving substantial Pass@k improvements and exhibiting robust generalization across diverse domains.
  arXiv  Detail & Related papers  (2025-09-30T10:36:23Z)
• HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution [13.440964262446558]
  Hierarchical Variable Agent (HiVA) is a novel framework modeling agentic as self-organized graphs with the Semantic-Topological Evolution (STEV) algorithm.<n> Experiments on dialogue, coding, Longcontext Q&A, mathematical, and agentic benchmarks demonstrate improvements of 5-10% in task accuracy and enhanced resource efficiency.
  arXiv  Detail & Related papers  (2025-08-29T18:51:18Z)
• Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents [106.04963073116468]
  Flowcharts are a critical tool for visualizing decision-making processes.<n> vision-language models frequently hallucinate nonexistent connections and decision paths when analyzing these diagrams.<n>We introduce Fine-grained Flowchart, which traces specific components grounding a flowchart referring LLM response.<n>We propose FlowPathAgent, a neurosymbolic agent that performs fine-grained post hoc attribution through graph-based reasoning.
  arXiv  Detail & Related papers  (2025-06-02T06:02:41Z)
• Agentic Predictor: Performance Prediction for Agentic Workflows via Multi-View Encoding [56.565200973244146]
  Agentic Predictor is a lightweight predictor for efficient agentic workflow evaluation.<n>By learning to approximate task success rates, Agentic Predictor enables fast and accurate selection of optimal agentic workflow configurations.
  arXiv  Detail & Related papers  (2025-05-26T09:46:50Z)
• Flow: Modularized Agentic Workflow Automation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents [64.1759086221016]
  We present FlowBench, the first benchmark for workflow-guided planning. FlowBench covers 51 different scenarios from 6 domains, with knowledge presented in diverse formats. Results indicate that current LLM agents need considerable improvements for satisfactory planning.
  arXiv  Detail & Related papers  (2024-06-21T06:13:00Z)
• Grammar-based evolutionary approach for automated workflow composition with domain-specific operators and ensemble diversity [0.36832029288386137]
  This paper introduces EvoFlow, a grammar-based evolutionary approach for automatic workflow composition (AWC) EvoFlow enhances the flexibility in designing workflow structures, empowering practitioners to select algorithms that best fit their specific requirements. Our findings show that EvoFlow's specialised genetic operators and updating mechanism substantially outperform current leading methods.
  arXiv  Detail & Related papers  (2024-02-03T11:29:14Z)
• Distributional GFlowNets with Quantile Flows [73.73721901056662]
  Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a policy for generating complex structure through a series of decision-making steps. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. Our proposed textitquantile matching GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty.
  arXiv  Detail & Related papers  (2023-02-11T22:06:17Z)

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.