Awesome Auto Research Hub Papers · Datasets · Projects
← Back to papers

Scaling Scientific Discovery Environments for Turn-Level Agentic RL

arXiv 2026 58.7 method

TLDR

SciDisco: a scalable framework for training scientific discovery agents using process-verifiable environments and turn-level reinforcement learning.

Reasoning

The paper introduces a well-structured framework (SciDisco) with clear components (SciThèque, DAG trajectory synthesis, DiscoPO) and achieves SOTA on benchmarks, demonstrating strong methodology. However, the abstract lacks details on the specific datasets and real-world applicability, and the scope is limited to hypothesis-driven data analysis rather than full scientific discovery.

Read-first score

Read-first score 58.7, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 60.

Recency 8%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%
80

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=analysis,benchmark,dataset,experiment

Topical relevance 42%
50

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Reproducibility 25%
38

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=dataset

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 21.

Keyword Scores

automated scientific discovery
9
scientific discovery agent
9
AI for scientific research
8
AI scientist
7
automated research
7
autonomous research agent
6
research automation
6
automated experimentation
3
experiment design agent
2
literature review agent
1
survey generation
1
paper writing agent
1

Deep Analysis

Innovations

  • SciDisco framework for training scientific discovery agents in process-verifiable environments
  • SciThèque: compilation of hypotheses, datasets, hidden evidence graphs, and verifiers into task environments with progress checks
  • DAG-grounded trajectory synthesis to construct verifier-filtered multi-turn demonstrations
  • DiscoPO: turn-level credit assignment using environment as training signal, rewarding actions that produce verifiable analytical evidence

Methodology

The paper proposes SciDisco, a framework that uses SciThèque to create process-verifiable environments with hidden evidence graphs and verifiers. DAG-grounded trajectory synthesis generates multi-turn demonstrations filtered by verifiers, and DiscoPO assigns turn-level credit for actions that yield verifiable evidence. A 14B model is trained and evaluated on hypothesis-driven scientific data analysis benchmarks.

Key Results

SciDisco-14B achieves state-of-the-art performance on hypothesis-driven scientific data analysis benchmarks.

Tags