arbor

npx skills add K-Dense-AI/scientific-agent-skills --skill arbor --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# 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 and without overfitting to the feedback 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 the search never optimized against. This is what turns trial-and-error into cumulative, auditable resea

python scripts/tree.py init \
python scripts/tree.py observe
python scripts/tree.py add-node --parent n0 --hypothesis "Verification, not retrieval, is the bottleneck: candidates are found but discarded"
python scripts/tree.py add-node --parent n4 --hypothesis "Decompose the question into atomic constraints and verify each independently"
python scripts/tree.py set-evidence --node n5 --dev-score 70.0 \
python scripts/tree.py propagate --node n5 \
python scripts/tree.py prune --node n7 --reason "search-augmented judge overfits dev questions; no test transfer"
python scripts/tree.py merge --node n5 --test-score 67.67 --branch-ref "wt/n5"