# Arbor

Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable...

- Repository: https://github.com/K-Dense-AI/scientific-agent-skills (55651 stars)
- Category: Data and ML
- License: MIT license
- Last updated: 2026-10-26
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add K-Dense-AI/scientific-agent-skills --skill arbor -g -a claude-code -y`
Codex: `npx skills add K-Dense-AI/scientific-agent-skills --skill arbor -g -a codex -y`
Cursor: `npx skills add K-Dense-AI/scientific-agent-skills --skill arbor -g -a cursor -y`
Gemini CLI: `npx skills add K-Dense-AI/scientific-agent-skills --skill arbor -g -a gemini-cli -y`

## Description

Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Arbor, Autonomous Optimization via Hypothesis Tree Refinement

## Overview

This skill runs an **Autonomous Optimization (AO)** loop: starting from an existing artifact and a measurable objective, improve it through many rounds of experiment and evaluation, without step-by-step human supervision, while checking for overfitting to the development signal. It's the right tool when the bottleneck isn't writing one good change, but *organizing dozens of trials* so that lessons accumulate instead of evaporating.

It implements **Hypothesis Tree Refinement (HTR)** from *Arbor* (Jin et al., 2026). The key idea: keep the research state in a persistent **hypothesis tree** rather than in conversation history. Each node binds a hypothesis, the distilled insight it produced, and a pointer to the artifact version that realizes it. You play the long-lived **coordinator** that owns this tree and decides where to search; short-lived **executor** subagents test one hypothesis each in isolated git worktrees and report back. A **held-out merge gate** admits a change only when it improves on a *test* evaluator executors do not optimize against. This is what turns trial-and-error into cumulative, auditable research.

Use the `scripts/tree.py` state manager for all the bookkeeping (creating nodes, writing evidence, propagating insights, pruning, the merge gate, the Observe projection). It records scores and decisions; it does **not** run evaluators, create worktrees, verify Git refs, or merge Git branches. Only the coordinator writes shared state, serially; executors return evidence. The helper has no multi-writer locking. Its JSON schema is separate from upstream Arbor checkpoints.

## When to use this skill

The rest: https://github.com/K-Dense-AI/scientific-agent-skills/blob/HEAD/skills/arbor/SKILL.md