Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems

• URL: http://arxiv.org/abs/2605.12087v1
• Date: Tue, 12 May 2026 13:09:07 GMT
• Title: Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems
• Abstract summary: We argue that such systems should preserve durable, inspectable intermediate artifacts.<n>We distinguish intermediate artifacts from chat transcripts, memory, hidden chain-of-thought, narration, thinking, and final answers.<n>It is that durable intermediate artifacts make AI-generated work more inspectable, revisable, and maintainable over time.
• Score: 0.10312968200748114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many AI systems are organized around loops in which models reason, call tools, observe results, and continue until a task is complete. These systems often produce final artifacts such as memos, plans, recommendations, and analyses, while the intermediate work that shaped those outputs remains ephemeral. For multi-step, revisable AI work, final artifacts are often lossy projections over upstream state. We argue that such systems should preserve durable, inspectable intermediate artifacts: typed, structured, addressable, versioned, dependency-aware, authoritative, and consumable by downstream computation. These artifacts are not the model's private chain-of-thought. They are maintained work products such as evidence maps, claim structures, criteria, assumptions, plans, transformation rules, synthesis procedures, unresolved tensions, and partial products that later humans and agents can inspect, revise, supersede, and improve. The contribution is a systems-level data model. We distinguish intermediate artifacts from chat transcripts, memory, hidden chain-of-thought, narration, thinking, and final answers; formalize additive and superseding update semantics with explicit current-state resolution; describe how artifact lineage supports durable intermediate state across revisions; and argue that evaluation must target maintained-state quality, not only final-output quality. The claim is not that artifacts make models smarter. It is that durable intermediate artifacts make AI-generated work more inspectable, revisable, and maintainable over time.

Related papers

• From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation [49.496216822640974]
  RetroGen is a self-improving framework for retrospective process supervision.<n>It reconstructs latent trajectories from expert artifacts, verifies them against the artifact and supporting evidence, and trains models on their own successful reconstruction data.<n>Experiments show that RetroGen improves grounding, faithful synthesis, and long-form evidence-seeking agent tasks.
  arXiv  Detail & Related papers  (2026-08-31T08:47:39Z)
• Reproducibility is Not Enough: Artifact Verifiability in Decentralized-Build Package Ecosystems [5.670956660842575]
  Artifact verification requires recovering the source state, build environment, dependencies, and build instructions that produced the artifact.<n>Decentralized-build ecosystems make this difficult because artifacts are produced through heterogeneous tools and fragmented metadata.<n>This paper studies artifact verifiability across four popular decentralized-build package ecosystems.
  arXiv  Detail & Related papers  (2026-08-18T02:30:23Z)
• Chained Recursive Language Models for Multi-Iteration Reasoning [46.765013720309064]
  Chained Recursive Language Models (Chained RLM) is an inference-time architecture.<n>Each root receives the original problem and context, but does not inherit the full conversational history.<n>In each staged computation, intermediate artifacts can be inspected, corrected, and extended by a later fresh inference by the same model.
  arXiv  Detail & Related papers  (2026-08-05T17:50:08Z)
• 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)
• From Question Answering to Task Completion: A Survey on Agent System and Harness Design [67.8241530947325]
  This survey examines LLM-based agents through a model-harness lens.<n>We first clarify the functional definition of agents and the implementation view of an LLM-based agent as a foundation model and an execution harness.<n>We then analyze the limits of model-centric scaling, trace four paradigms of agent engineering, and decompose the execution harness into six coupled runtime responsibilities.
  arXiv  Detail & Related papers  (2026-06-14T05:40:16Z)
• From Model Scaling to System Scaling: Scaling the Harness in Agentic AI [4.802305157491253]
  This paper studies the next major bottleneck in agentic AI as system scaling.<n>We refer to this shift as scaling the harness, treating the structured execution layer around a foundation model as a first-class object of design, evaluation, and optimization.<n>Our main claim is that future progress in agentic AI will depend as much on system design as on stronger foundation models.
  arXiv  Detail & Related papers  (2026-05-25T17:59:36Z)
• AI for Auto-Research: Roadmap & User Guide [107.0834449839233]
  We present an end-to-end analysis of AI across the complete research lifecycle.<n>We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy.<n>We show that greater automation can obscure rather than eliminate failure modes.
  arXiv  Detail & Related papers  (2026-05-18T17:08:26Z)
• ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery [58.48859167777581]
  ArtifactLinker is a framework to automatically discover state-of-the-art (SOTA) models for datasets.<n>A benchmark named ArtifactBench with 14,053 artifacts and 51,337 relations is presented.<n>Results show that (1) graph structures between existing artifacts are effective for missing link prediction; (2) end-to-end ranking and verification with ArtifactLinker help discover potential SOTA results and research insights.
  arXiv  Detail & Related papers  (2026-05-16T09:26:08Z)
• From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work [0.10312968200748114]
  We introduce execution lineage: an execution model in which AI-native work is represented as a directed acyclic graph (DAG) of artifact-producing computations.<n>We compare execution-lineage replay against loop-centric update baselines on two controlled policy-memo update tasks.
  arXiv  Detail & Related papers  (2026-05-07T14:39:37Z)
• Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling [183.5907213030813]
  We argue that the field should move beyond appearance synthesis toward intelligent visual generation.<n>We introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation.<n>We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, and sampling acceleration.
  arXiv  Detail & Related papers  (2026-04-30T17:59:02Z)
• Gypscie: A Cross-Platform AI Artifact Management System [0.6784745592354215]
  We introduce Gypscie, a cross-platform AI artifact management system.<n>By providing a unified view of all AI artifacts, Gypscie simplifies the development and deployment of AI applications.
  arXiv  Detail & Related papers  (2026-04-11T18:24:26Z)
• FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios [58.34124792457706]
  The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to transition from simple perception to autonomous execution.<n>Progress is hindered by data scarcity and a lack of fine-grained domain semantics in existing datasets.<n>We first construct a high-quality dataset that combines realworld 2D images and 3D point clouds, annotated with fine-grained domain semantics.<n>We then evaluate 18 state-of-the-art MLLMs across three manufacturing tasks, namely verification, structural surface inspection, and assembly verification, revealing significant performance gaps.
  arXiv  Detail & Related papers  (2026-04-08T12:23:27Z)
• AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model [1.14219428942199]
  Existing automated research systems operate as stateless, linear pipelines.<n>We present textbfAI-Supervisor, a multi-agent orchestration framework.<n>Agents provide end-to-end AI research supervision driven by human interests.
  arXiv  Detail & Related papers  (2026-03-25T15:16:51Z)
• See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis [17.896266572037348]
  ArtiAgent efficiently creates pairs of real and artifact-injected images.<n>It comprises three agents: a perception agent that recognizes entities and subentities from real images, a synthesis agent that introduces artifacts via artifact injection tools, and a curation agent that filters the synthesized artifacts.
  arXiv  Detail & Related papers  (2026-02-24T14:34:13Z)
• Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding [49.26132236798123]
  Vision Language Models (VLMs) have gradually become a primary approach in document understanding.<n>We propose SLEUTH, a multi agent framework that orchestrates a retriever and four collaborative agents in a coarse to fine process.<n>The framework identifies key textual and visual clues within the retrieved pages, filters for salient visual evidence such as tables and charts, and analyzes the query to devise a reasoning strategy.
  arXiv  Detail & Related papers  (2025-11-28T03:09:40Z)
• EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing [170.71134330650796]
  EdiVal-Agent is an object-centric evaluation framework for instruction-based image editing.<n>It is designed to assess not only standard single-turn but also multi-turn instruction-based editing with precision.<n>We build EdiVal-Bench, a benchmark covering 9 instruction types and 13 state-of-the-art editing models spanning in-context, flow-matching, and diffusion paradigms.
  arXiv  Detail & Related papers  (2025-09-16T17:45:39Z)
• Trust at Your Own Peril: A Mixed Methods Exploration of the Ability of Large Language Models to Generate Expert-Like Systems Engineering Artifacts and a Characterization of Failure Modes [0.0]
  We present results from an empirical exploration, where a human expert-generated SE artifact was taken as a benchmark.<n>We then adopted a two-fold mixed-methods approach to compare AI generated artifacts against the benchmark.<n>We find that while the two-material appear very similar, AI generated artifacts exhibit serious failure modes that could be difficult to detect.
  arXiv  Detail & Related papers  (2025-02-13T17:05:18Z)
• TRIAD: Automated Traceability Recovery based on Biterm-enhanced Deduction of Transitive Links among Artifacts [53.92293118080274]
  Traceability allows stakeholders to extract and comprehend the trace links among software artifacts introduced across the software life cycle. Most rely on textual similarities among software artifacts, such as those based on Information Retrieval (IR)
  arXiv  Detail & Related papers  (2023-12-28T06:44:24Z)

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.