The Last Human-Written Paper

In the near future, most CS papers will be written by AI, and most will be read by AI.

When neither the author nor the audience is human, the three-century-old paper format stops making sense. Papers flatten a branching research process into a clean story, and that flattening imposes two taxes.

The Storytelling Tax

Research is inherently branching and exploratory. Scientists try dozens of approaches, hit dead ends, pivot, and iterate. But papers collapse this rich process into a single winning narrative, discarding every failed attempt, rejected hypothesis, and negative result.

The Engineering Tax

Papers describe methods at the precision needed to convince a reviewer, not at the precision needed to reproduce the work. Hyperparameters are underspecified. Warmup schedules live in someone's head. Numerical stability fixes exist in no document. The gap between "sufficient to believe" and "sufficient to execute" is where reproduction breaks down.

The information exists somewhere (a lab notebook, a Slack thread, the original author's muscle memory), but not in any document an AI agent can access. Every reproduction attempt pays the full cost of rediscovering it.

The Solution: Four Interlocking Layers

ARA restructures a paper into four machine-native layers. Together they form a single executable knowledge package: the organized, evolving knowledge produced during research, not the narrative compiled afterward.

PAPER.md                      # Human-readable overview & entry point
│
├── logic/                    # Cognitive Layer
│   ├── claims.yaml           # Falsifiable claims with epistemic status
│   ├── concepts/             # Formal concept definitions
│   ├── experiments/          # Declarative experiment plans
│   └── problem_spec.md       # The "what and why" of the research
│
├── src/                     # Physical Layer
│   ├── kernel/               # Novel algorithm core
│   ├── configs/              # Annotated with search ranges & sensitivity
│   └── environment.yaml      # Exact reproducibility spec
│
├── trace/                   # Exploration Graph
│   ├── graph.json            # Full branching research DAG
│   ├── dead_ends/            # Every failed attempt preserved
│   └── pivots/               # Decision points & lessons learned
│
└── evidence/                # Evidence Layer
    ├── results/              # Machine-readable quantitative outputs
    ├── logs/                 # Raw experiment logs
    └── curves/               # Training curves & metrics

Live Research Manager

ARA doesn't require researchers to manually package their work. The Live Research Manager silently captures the research trajectory during AI-human collaboration: no interruptions, no extra effort. The artifact builds itself in the background.

Collaborate with AI on research, and the trajectory is automatically captured with epistemic provenance: every claim tagged with who proposed it, who verified it, and how strongly the evidence supports it.

Results

A paper shows the path taken. ARA remembers the paths abandoned, and the choices that made the road. We evaluate across three layers: understanding, reproduction, and extension.

Talk

Watch on YouTube

Cite

@article{liu2026ara,
  title   = {The Last Human-Written Paper: Agent-Native Research Artifacts},
  author  = {Liu, Jiachen and Pei, Jiaxin and Huang, Jintao and Si, Chenglei and others},
  year    = {2026},
  journal = {arXiv preprint arXiv:2604.24658},
  url     = {https://arxiv.org/abs/2604.24658}
}