External pipelines · RISE project catalogue
Arbor
A generalist autonomous research agent (arXiv:2606.11926) from the WebThinker group at Renmin University: given a goal, a benchmark directory, and a metric, a Coordinator grows a persistent hypothesis tree ("Idea Tree") while Executors implement each idea in isolated git worktrees, run real experiments on a dev split, and merge only gains that survive a held-out test split. Sits in the experiment-driven optimization corner of the landscape alongside CORAL and AlphaEvolve rather than the paper-writing corner.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by RUC-NLPIR, Microsoft Research
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 hypothesis tree as first-class research memory: results, failure modes, and distilled insights backpropagate to ancestor nodes so later ideas inherit lessons, and cross-run memory carries findings into future tasks. Ships three ways — native CLI, a Claude Code/Codex markdown skill suite, and a keyless MCP mode where the host harness's model does the reasoning while Arbor supplies deterministic tree/eval/merge/report tools.
- Focus
- end-to-end
- Inputs
- research-goal, codebase, evaluation-script
- Outputs
- optimized-codebase, idea-tree, run-report, session-event-log
- Architecture
- multi-agent, tool-use, iterative-loop, persistent-memory, artifact-versioning
- Maintained by
- RUC-NLPIR (Gaoling School of Artificial Intelligence, Renmin University of China); Microsoft Research
- Started
- 2026
Description
Data model- Discipline
- General
- Method family
- not specified
- Design
- not specified
- Research stage
- HypothesesLiterature discoveryResearch designCode generationData analysis
- Contributors
- RUC-NLPIR; Microsoft Research
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:arbor · 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.