External pipelines · RISE project catalogue
EconCS Bench
A benchmark suite of open research challenges in Economics and Computation (EconCS), associated with the AI-Driven Research in EconCS workshop at EC 2026. 24 open problems — mechanism design, fair division (EFX, MMS, PMMS), prophet inequalities, information design, complexity of equilibria — each a markdown PROBLEM.md with YAML metadata, contributor attribution, known results, and an optional difficulty rating (Approachable / Challenging / Hard). Sits in the RISE evaluation-infrastructure layer alongside AstaBench, Aviary, and MLGym, but targets formal *theory* research rather than empirical, coding, or literature tasks.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by AI-driven Research in EconCS workshop organizers
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
What it does
The first community-curated open-problem benchmark aimed at AI-driven theory research: problems are contributed via pull requests by many of the field's leading researchers (Nisan, Papadimitriou, Procaccia, Conitzer, Feldman, Mirrokni, Weinberg, Dobzinski, Chen, Babaioff, Rubinstein, Duetting, Lucier, Branzei, Paes Leme), making it both a live registry of what experts consider genuinely open and a difficulty-graded target set for proof-capable research agents. Success has no harness: a solved benchmark problem is a publishable research result.
- Focus
- end-to-end
- Inputs
- open-problem-submissions
- Outputs
- problem-statements, difficulty-ratings
- Maintained by
- AI-driven Research in EconCS workshop organizers (EC 2026)
- Started
- 2026
Description
Data model- Discipline
- Economics
- Method family
- not specified
- Design
- not specified
- Research stage
- Formal modeling
- Contributors
- AI-driven Research in EconCS workshop organizers
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:econcs-bench · 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.