Skip to content
Demonstrator · items marked Example are invented · what exists today
E2ER

External pipelines · RISE project catalogue

PaperCoder (Paper2Code)

An ICLR 2026 multi-agent system (arXiv:2504.17192) that transforms a machine-learning paper into a working code repository via a three-stage pipeline (planning, analysis, code generation) with specialized agents per stage. Sits at the replication / code- generation block of the RISE pipeline, distinct from referee- simulation or drafting tools.

Indexed in RISE · activeConformance with the standard plannedProject site

What it does

Explicitly targets the *paper-to-implementation* gap rather than paper-from-scratch authoring, and reports outperforming strong baselines on both Paper2Code and PaperBench evaluation suites. Ships its own benchmark datasets alongside the system.

Focus
replication
Inputs
target-paper
Outputs
code-repository, implementation-plan, analysis-report
Architecture
multi-agent, dag-orchestration, tool-use, artifact-versioning
Maintained by
Minju Seo, Jinheon Baek, Seongyun Lee, Sung Ju Hwang (KAIST)
Started
2025

Description

Data model
Discipline
Computer science
Method family
Replication
Design
not specified
Research stage
ReplicationResearch designCode generation
Contributors
Minju Seo; Jinheon Baek; Seongyun Lee; Sung Ju Hwang
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:paper2code · JSON

Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.

Bring it into the standard

A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.

Other pipelines in Computer science