Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation

• URL: http://arxiv.org/abs/2512.20278v1
• Date: Tue, 23 Dec 2025 11:33:32 GMT
• Title: Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation
• Abstract summary: 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.
• Score: 0.5599792629509229
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: While CodeMem establishes executable code as the optimal representation for agentic procedural memory, the mechanism for autonomously synthesizing this memory from a blank slate remains underexplored. This paper operationalizes the transition of Large Language Models from passive tool-users to active workflow architects. Through a high-fidelity case study of a cross-service orchestration task involving Outlook and OneDrive, we identify and address four structural bottlenecks in automated skill generation: the Discovery Gap involving navigation of large tool registries, the Verification Gap regarding grounding tool response structures, the Decomposition Gap which replaces inefficient search with Linear State Anchoring, and the Scaling Gap focused on concurrency and persistence. We demonstrate that by enforcing a scientific methodology of hypothesize, probe, and code, agents can autonomously write robust, production-grade code skills.

Related papers

• AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery [25.96347096124607]
  AlgoEvo transforms automated algorithm discovery into an interactive, knowledge-accumulating process.<n>A design skill hub decouples paradigm-specific knowledge from the core discovery engine.<n>A hierarchical experience mechanism organizes search trajectories into a task-level tree to guide exploration.
  arXiv  Detail & Related papers  (2026-09-14T16:24:27Z)
• DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations [106.74348504930124]
  We introduce DocOps, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy.<n>Based on DocOps, we systematically evaluate representative closed- and open-source models across various agentic harnesses.<n>Our work exposes the capability boundaries of agents in maintaining global document consistency, shedding light on the future design of robust, non-destructive agents.
  arXiv  Detail & Related papers  (2026-07-22T07:52:59Z)
• AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems [82.01232437066487]
  AgentX is a production-deployed multi-agent system that restructures this production function.<n>It autonomously generates, implements, evaluates, and learns from recommendation experiments.<n>AgentX orchestrates four tightly coupled stages in a closed loop.
  arXiv  Detail & Related papers  (2026-06-25T10:42:28Z)
• The Semantic Training Gap: Ontology-Grounded Tool Architectures for Industrial AI Agent Systems [0.0]
  Large language model (LLM)-based AI agents are increasingly deployed in manufacturing environments for analytics, quality management, and decision support.<n>These agents demonstrate statistical fluency with domain terminology but lack grounded understanding of operational semantics.<n>This paper identifies and formalizes the semantic training gap: a structural disconnect between how AI systems acquire domain vocabulary through training and how manufacturing operations define meaning through ontological relationships.
  arXiv  Detail & Related papers  (2026-05-11T20:48:18Z)
• Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data [52.80567461420316]
  We propose a Memory-Augmented LLM-based Multi-Agent System (textbfMALMAS) for automated feature generation.<n>MALMAS decomposes the generation process into agents with distinct responsibilities, and a Router Agent activates an appropriate subset of agents per iteration.<n>We further integrate a memory module comprising procedural memory, feedback memory, and conceptual memory, enabling iterative refinement that adaptively guides subsequent feature generation.
  arXiv  Detail & Related papers  (2026-04-22T07:09:30Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• El Agente Gráfico: Structured Execution Graphs for Scientific Agents [7.47895130442454]
  We present El Agente Grfico, a single-agent framework that embeds large language models (LLMs)-driven decision-making within a type-safe execution environment.<n>Central to our approach is a structured abstraction of scientific concepts and an object-graph mapper that represents computational state as typed Python objects.<n>We evaluate the system by developing an automated benchmarking framework across a suite of university-level quantum chemistry tasks.
  arXiv  Detail & Related papers  (2026-02-19T23:47:05Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
  ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
  arXiv  Detail & Related papers  (2025-12-18T08:38:44Z)
• Seismology modeling agent: A smart assistant for geophysical researchers [14.28965530601497]
  This paper proposes an intelligent, interactive workflow powered by Large Language Models (LLMs)<n>We introduce the first Model Context Protocol (MCP) server suite for SPECFEM.<n>The framework supports both fully automated execution and human-in-the-loop collaboration.
  arXiv  Detail & Related papers  (2025-12-16T14:18:26Z)
• Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization [69.36509281190662]
  Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck.<n>We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design.<n>We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions.
  arXiv  Detail & Related papers  (2025-12-02T18:42:26Z)
• ScaleCall -- Agentic Tool Calling at Scale for Fintech: Challenges, Methods, and Deployment Insights [0.18643247155980827]
  Large Language Models (LLMs) excel at tool calling, deploying these capabilities in regulated enterprise environments such as toolsets.<n>We present a comprehensive study of tool retrieval methods for enterprise environments through the development and deployment of ScaleCall, a prototype tool-calling framework within Mastercard.
  arXiv  Detail & Related papers  (2025-10-29T14:35:46Z)
• 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)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments [70.42705564227548]
  We propose an automated environment construction pipeline for large language models (LLMs)<n>This enables the creation of high-quality training environments that provide detailed and measurable feedback without relying on external tools.<n>We also introduce a verifiable reward mechanism that evaluates both the precision of tool use and the completeness of task execution.
  arXiv  Detail & Related papers  (2025-08-12T09:45:19Z)
• State and Memory is All You Need for Robust and Reliable AI Agents [29.259008600842517]
  Large language models (LLMs) have enabled powerful advances in natural language understanding and generation.<n>Yet their application to complex, real-world scientific remain limited by challenges in memory, planning, and tool integration.<n>Here, we introduce SciBORG, a modular agentic framework that allows LLM-based agents to autonomously plan, reason, and achieve robust and reliable domain-specific task execution.
  arXiv  Detail & Related papers  (2025-06-30T02:02:35Z)
• ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models [81.12673534903979]
  Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools.<n>We propose ToolCoder, a novel framework that reformulates tool learning as a code generation task.
  arXiv  Detail & Related papers  (2025-02-17T03:42:28Z)
• ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems [80.69865295743149]
  This work attempts to study using LLM-based agents to design collaborative AI systems autonomously.<n>Based on ComfyBench, we develop ComfyAgent, a framework that empowers agents to autonomously design collaborative AI systems by generating.<n>While ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks.
  arXiv  Detail & Related papers  (2024-09-02T17:44:10Z)

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.