English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Spark-to-Paper: 13 Composable Skills for End-to-End Research Paper Generation

Forum topic · ✨步子哥 · 2026-08-13

Summary

Spark-to-Paper is a 2026 system by Zhuoyang Qian et al. that decomposes the entire research-paper workflow into 13 composable skills running within an existing coding assistant, eliminating the need for a standalone agent platform. Its core design separates model-driven judgment (literature relevance, hypothesis support, revision decisions) from deterministic code operations (citation checks, experiment execution, chart editability, fabrication detection). A key innovation is evidence-before-claim: before any experiment runs, the system freezes a written evidence requirement, then matches results against it and revises claims rather than narrative when results contradict hypotheses. A bounded Self-Refutation Loop prevents infinite retries or silent data manipulation. Charts are generated as editable vector code. Evaluated on 8 controlled research topics, the system achieved 99.5% citation validity, 96.4% chart editability, 92% fabrication detection (up from 14% on a single draft), and 74% adversarial-review precision, at a cost of $8.1 per paper over 3.2 hours.

Overview

Spark-to-Paper is a system proposed by Zhuoyang Qian, Biao Wu, Yiran Wang et al. in their August 2026 paper *Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill*. It decomposes the full research workflow into 13 composable skills executed inside an existing coding assistant, with no dedicated agent platform or orchestration service required.

A representative scenario: a user enters a research topic (e.g., *knowledge degradation in small models under long-context training*). The pipeline then runs through 13 skills covering literature retrieval, experiment design, execution, evidence comparison, claim revision, chart generation, and manuscript assembly.

Core Design Principles

1. Separation of Model Judgment and Deterministic Operations

  • Model handles judgment: literature relevance, hypothesis support, writing clarity, revision decisions.
  • Code handles deterministic tasks: running experiments, verifying citations exist, validating chart editability, detecting fabrication.
  • This split yields a system that is simultaneously flexible (judgment, writing, revision via LLM) and verifiable (checks, validations, executions via deterministic code).

    2. Evidence Before Claim

    The most distinctive design choice. Traditional workflows let results shape the narrative, which encourages selective reporting when evidence contradicts a hypothesis. Spark-to-Paper instead requires the system to write down the evidence required to support or refute a hypothesis before seeing any results. That evidence requirement is frozen, experiments are then run, and the system matches outcomes against the frozen requirements.

    If results do not support the original hypothesis, the system revises the claim, not the narrative. Claims must remain consistent with experimental evidence; "the results were weak so let's rephrase to sound stronger" is structurally blocked.

    This implements the scientific method—hypothesis first, evidence-driven, falsifiable conclusions—at the code level.

    3. Bounded Self-Refutation Loop

    A known failure mode: experiments repeatedly contradict the research goal. Human researchers either abandon the topic or weaken the hypothesis until it is trivially supported. The former wastes effort; the latter is misconduct.

    Spark-to-Paper implements a bounded recovery: the system may revise experimental methods or hypothesis wording a limited number of times, but once a threshold is exceeded it halts and reports *"current evidence does not support the original research goal"*. It neither loops forever nor manipulates data to make results "look good".

    4. Editable Vector Charts

    Instead of exporting PNGs and editing them in presentation tools, Spark-to-Paper generates charts as programmatic, editable vector graphics (matplotlib-style for result plots; reconstructed code for methodology diagrams). Researchers can edit the chart code directly without rerunning the full pipeline.

    Reported Numbers

    Evaluated on 8 controlled research topics:

  • Citation validity: 99.5%
  • Chart editability: 96.4%
  • Fabrication detection: 14% (single draft) → 92% (full integrity stack), a 6.5× improvement
  • Adversarial self-review precision: 74%
  • Cost per paper:

  • 11.9M tokens
  • $8.1 at current API pricing
  • 3.2 hours end-to-end
  • Why the Positioning Matters

    Earlier systems such as AI Scientist and GPT-Researcher already demonstrated AI-generated papers. Spark-to-Paper's contribution is structural rather than functional:

    1. No standalone platform — the 13 skills install into an existing coding assistant, lowering deployment cost. 2. Composable skills — each can be swapped or upgraded independently (e.g., replace the literature retrieval skill without touching the rest). 3. Separation of judgment and verification — the jump from 14% to 92% fabrication detection comes from deterministic checks that catch what the model would otherwise fabricate.

    Relation to the ACE Workflow

    The earlier ACE (Advanced Context Engineering) RPI workflow—Research, Plan, Implement—applies the same underlying principle at a coarser 3-step granularity: each stage is independent, stages connect via deterministic interfaces, and context compression per stage prevents contamination.

    Spark-to-Paper generalizes this to 13 steps. ACE's per-stage context compression corresponds to per-skill context isolation; ACE's "research first" corresponds to Spark-to-Paper's "evidence before claim". The shared pattern is: decompose long agent workflows into independently verifiable steps with explicit input/output contracts.

    A Broader Principle

    Spark-to-Paper illustrates a recurring theme: reliability is a structural property, not a model property.

  • 99.5% citation validity is not because the model is smarter—it is because the structure enforces citation verification.
  • 92% fabrication detection is not because the model is more honest—it is because deterministic checks catch what the model invents.
  • This echoes the same lesson seen in colibrì (1,300 lines of C running a 744B-parameter model): division of labor between what models do well and what code does well outperforms a single monolithic approach. Across papers, a converging consensus is forming: the robustness of agent systems is determined by their architecture, not by the underlying model's capability.

    Paper Details

  • Title: Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
  • Authors: Zhuoyang Qian, Biao Wu, Yiran Wang, et al.
  • arXiv: https://arxiv.org/abs/2608.11924

Tags

#agent-systems#ai-research#spark-to-paper#composable-skills#scientific-workflow#llm-agents#code-generation#research-automation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633432