Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows

• URL: http://arxiv.org/abs/2607.08740v1
• Date: Thu, 09 Jul 2026 17:40:46 GMT
• Title: Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
• Abstract summary: Large language model (LLM) applications increasingly use explicit for tool use, retrieval, branching, checkpointing, and human approval.<n>Existing workflow systems already address many execution concerns.<n>This paper proposes a Lisp-inspired but language-independent conceptual model: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This paper proposes a Lisp-inspired but language-independent conceptual model: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments. In this model, workflow definitions, workflow instances, inference records, context snapshots, and dependency relations are represented as persistent knowledge objects in a shared knowledge substrate. Its central semantic distinction is between derive and infer: derive is deterministic computation over available state; infer is mediated LLM judgment under declared context and executor-controlled capability policy. The result is a preliminary conceptual account of semantic persistence: workflows do not merely produce knowledge and leave traces, but can themselves be represented as inspectable, resumable, and reviewable knowledge objects, while formal transition semantics remain future work.

Related papers

• ContextFlow: In-Context Flow Matching for Robot Manipulation [91.60992853468242]
  We introduce ContextFlow, a conditional flow-matching model that learns continuous action distributions for in-context imitation learning.<n>On LIBERO, ContextFlow outperforms ICRT by 35 percentage points in average success rate on unseen task configurations.<n>On real robots, it generalizes to unseen configurations of both single-arm and bimanual tasks, achieving 40% success on a new pen-uncapping configuration.
  arXiv  Detail & Related papers  (2026-09-06T21:53:58Z)
• Knowledge-Centric Agents for Workflow Generation [73.4340391112949]
  We propose a knowledge-centric framework that learns to invert, inject, and infer with knowledge across multiple abstraction levels.<n>Our method produces with richer node diversity, more coherent structures, and higher execution success rates than existing systems.
  arXiv  Detail & Related papers  (2026-07-17T11:03:01Z)
• ATWL: A Formal Language for Representing, Comparing, and Reusing Visual Analytics Workflows [18.606007955432283]
  Visual analytics (VA) are inherently complex, involving data transformation, feature engineering, visual representation, and human interpretation.<n>They are typically described in unstructured prose, hindering systematic comparison, reuse of proven strategies, and training of novices.<n>We present Artifact-Transform Language (ATWL), a domain-agnostic, declarative language that formally represents VA by capturing their structure and underlying analytical intent.
  arXiv  Detail & Related papers  (2026-05-25T06:51:02Z)
• OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering [2.74296307006009]
  Large Language Models (LLMs) are increasingly used in software engineering to automate or assist annotation tasks.<n>Existing studies often lack standardized measures for reliability, calibration, and drift.<n>We argue that LLM-based annotation should be treated as a measurement process rather than a purely automated activity.
  arXiv  Detail & Related papers  (2025-12-17T21:24:07Z)
• Solving Context Window Overflow in AI Agents [0.0]
  Large Language Models (LLMs) have become increasingly capable of interacting with external tools, granting access to specialized knowledge beyond their training data.<n>Existing solutions such as truncation or summarization fail to preserve complete outputs, making them unsuitable for work requiring the full data.<n>This paper introduces a method that enables LLMs to process and utilize tool responses of arbitrary length without loss of information.
  arXiv  Detail & Related papers  (2025-11-27T19:22:20Z)
• Ontology-Driven Model-to-Model Transformation of Workflow Specifications [0.8921166277011348]
  Proprietary languages such as Smart Forms & Smart Flow hamper interoperability and reuse because they lock process knowledge into closed formats.<n>We introduce an ontology-driven model-to-model pipeline that supports domain-specific definitions to Business Process Model and Notation.<n>We instantiated the pipeline for Superior Técnico (IST)'s Smart Forms & Smart Flow and implemented a converter that produces standard-compliant BPMN diagrams.
  arXiv  Detail & Related papers  (2025-11-17T18:16:19Z)
• 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)
• Learning Task Representations from In-Context Learning [67.66042137487287]
  Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL)<n>We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads.<n>The proposed method successfully extracts task-specific information from in-context demonstrations and excels in both text and regression tasks.
  arXiv  Detail & Related papers  (2025-02-08T00:16:44Z)
• 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)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)

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.