The Last Human-Written Paper: Agent-Native Research Artifacts

Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation imposes two structural costs: a Storytelling Tax, where failed experiments, rejected hypotheses, and the branching exploration process are discarded to fit a linear narrative; and an Engineering Tax, where the gap between reviewer-sufficient prose and agent-sufficient specification leaves critical implementation details unwritten. Tolerable for human readers, these costs become critical when AI agents must understand, reproduce, and extend published work. We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with an agent-executable research package structured around four layers: scientific logic, executable code with full specifications, an exploration graph that preserves the failures compilation discards, and evidence grounding every claim in raw outputs.

Introduction. Research produces a rich, branching knowledge object: months of hypotheses tested and rejected, implementation tricks discovered through trial and error, design alternatives weighed against each other, and the full exploration trajectory that explains why the final approach was chosen. Publishing compiles this object into a linear narrative (Medawar, 1963; Canini, 2026), discarding failed experiments, tacit engineering knowledge, and the branching process to satisfy the conventions of human-readable storytelling (Rosenthal, 1979; Franco et al., 2014). This compilation cost, a consequence of the documentation convention rather than any particular file format, was tolerable when every con- The first is the Storytelling Tax: the systematic erasure of research process knowledge imposed by compilation into narrative (Figure 2). Research does not proceed linearly— it branches, backtracks, and accumulates hard-won failure knowledge before converging on a publishable result (Kuhn, 1962; Medawar, 1963).

Discussion / Conclusion. We introduce the ARA protocol and its surrounding ecosystem as a foundation for agent-native scientific communication. Together, they address two structural failures of the PDF format: knowledge that narrative conventions discard (failed attempts, implicit configurations, unexplored branches) and specifications too underspecified to execute. ARA resolves both by restructuring a research contribution as a machine-actionable artifact, one that is navigable, complete, and verifiable without human interpretation. The broader motivation is a shift already underway: AI agents are becoming first-class participants in research workflows, not tools that assist humans but autonomous contributors that read, reproduce, and extend scientific work. That transition demands infrastructure built around agents from the start. ARA is the core abstraction of that ecosystem, a common substrate through which human and machine researchers alike publish, verify, and build on scientific knowledge.