A Lisp-inspired but language-independent conceptual model is proposed: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments, for semantic persistence in large language model applications.
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.
This work presents PULSE, an Object-Process-Methodology-inspired language that localizes four operational roles and their write effects in one typed runtime, here, modes denote operational roles rather than modal or deontic logic.
Artic is proposed, an artifact-driven workflow compiler that transforms a natural-language workflow into an artifact-driven workflow in which each step declares the artifacts it reads and writes, constraints gate produced artifacts, and explicit control transfers route execution.
Xiangzhe Xu, Hanxi Guo, Guangyu Shen et al.· 0 citations
Large language model (LLM) agents coordinate complex tasks through multi-role and multi-stage workflows. Upstream state is repeatedly transformed into intermediate language artifacts, such as summaries, plans, tickets, memories, and handoff notes, from which downstream components act. For action-constraining state, topical retention is insufficient: an artifact may mention an unresolved condition while changing it from a requirement that must be resolved before execution into information that may merely inform the next action. We study this action-binding role as operational state preservation. Safety blockers provide a controlled instance because each source state has an explicit prerequisite, authority, fallback, and execution consequence. We condition on correct upstream identification, vary the handoff transformation, and evaluate an executor restricted to the resulting artifact. Across 1,296 controlled synthetic episodes, direct-handoff controls preserve every blocker, whereas compression, plan assimilation, convergence, ownership deferral, and precedent substitution repeatedly turn binding state into caveats or non-binding considerations. Normal handoff compression produces 100.0% deactivation and 54.2% forbidden action. Restoring all four state fields raises preservation to 100.0% and reduces forbidden action to 0.0%. Fixed-artifact interventions further separate preservation from containment: downstream verification eliminates forbidden action while artifact deactivation remains 95.3%. These results identify a state-transmission failure between information extraction and action. Handoff transformations can retain state content while weakening its constraints on downstream action. Semantic availability does not guarantee operational preservation.
Yiheng Sun, Huifei Wang, Yancheng Zhu et al.· 0 citations
Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures. However, constructing high-quality agentic workflows remains largely manual and requires substantial domain expertise. Recent studies have explored automatic agentic workflow generation from historical task-solving records, but they mainly produce LLM-centric workflows, where real tool executions are abstracted and simulated by LLM nodes, limiting the usability and stability of generated workflows. To address these limitations, we propose FlowScout, an execution-guided framework for generating tool-integrated agentic workflows from historical task-solving records. Specifically, FlowScout represents an agentic workflow as a directed graph composed of LLM nodes, tool-calling nodes, and dependency edges. It first mines a common tool coordination skeleton from historical records to construct an initial workflow, and then refines the workflow topology through Monte Carlo tree search guided by execution feedback. We evaluate FlowScout on four representative task domains and compare it with three baselines, i.e., PM4Py, ReAct and AFlow. Experimental results show that agentic workflows generated by FlowScout improve tool invocation correctness by at least 92.69% and execution quality by at least 17.66% over the baselines, while achieving lower performance variation across repeated runs.
Generative AI is changing the role of knowledge in organisations. Traditional knowledge management (KM) systems have primarily supported storage, access and retrieval, assuming that knowledge is interpreted and applied by human users. In AI-enabled environments, however, organisational knowledge increasingly becomes a direct input into execution, shaping generated proposals, analyses, summaries, recommendations and other workflow outputs. This shift exposes a limitation of retrieval-oriented KM: fragmented, outdated or weakly governed knowledge can be amplified through AI-generated outputs, reducing consistency, reliability and trust. This paper introduces executable knowledge systems as a conceptual model for structuring organisational knowledge to support reliable human and AI-assisted execution. The term executable is used in a socio-technical sense. Knowledge does not necessarily become code, but is curated, validated and embedded into workflows so that it can guide outputs, decisions and actions. The paper distinguishes this concept from prior work on executable knowledge graphs and executable knowledge bases, which primarily focus on deterministic execution through rules, scripts or formalised representations. The paper further develops a framework of decay and compounding loops to explain how AI-enabled knowledge systems evolve over time. In decay loops, AI-generated outputs re-enter the knowledge environment without sufficient validation, allowing inconsistency and low-quality knowledge to accumulate. In compounding loops, curated knowledge assets are refined through governed feedback, domain ownership and controlled reuse, enabling improvements in reliability over time. The framework is informed by an exploratory case study within a global professional services organisation, where a curated knowledge environment was introduced to support AI-assisted workflows in the Retail, Consumer Products, Travel and Transportation domain. The evaluation compared outputs generated from a controlled, subject matter expert (SME)-validated knowledge dataset with outputs generated from an unconstrained organisational knowledge base. Findings indicate improved retrieval relevance and output quality when AI systems operate on validated knowledge assets. The paper contributes to KM research by reframing KM as a system design challenge for AI-enabled execution and by positioning governance, validation and feedback control as central mechanisms for reliable organisational knowledge use.
Sara Michelazzo, Parmeet Kaur, Saurabh Saxena· European Conference on Knowl...· 0 citations
An AI execution can now outlive the environment in which it began. What once fit inside one model call increasingly unfolds across pauses, retries, branches, subagents, and model-selected tools. Meanwhile, prompts, model aliases, indexes, policies, and tools are deployed independently: stable names can acquire new behavior, and workflows can discover resources only after they start. The workflow can therefore combine saved state with changed assumptions, producing an internally inconsistent result even when every call succeeds. This is an isolation problem: database transactions constrain concurrent data updates, but workflow checkpointing provides no corresponding contract for concurrent changes to an AI workflow's semantic environment. We define four automatically detectable anomalies: semantic read skew, compatibility skew, context escape, and merge skew. To control which anomalies are allowed, we derive a partial order of isolation levels, from Semantic Read Committed to Semantic Snapshot Isolation, by combining three independent guarantees: resource stability, cross-resource compatibility, and continuation inheritance. In a conservative source audit of the 100 most-starred public repositories with executable LangGraph code, we find that 7.4 percent of codebases with durable workflows resolve live or dynamically selected semantic resources within the same workflow, without an evident immutable binding. We show that these guarantees can be checked and enforced efficiently in middleware. Our prototype, SemIso, propagates semantic context and blocks incompatible resources and branch merges with microsecond-scale checks.