Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →miosa-osa/lats
Language Agent Tree Search - Monte Carlo planning - 92.7% on HumanEval
Passed 14 of 22 test cases with the skill, and 11 of 22 without it.
and 2 more in the full report
4 fixed11 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
During the expansion phase of tree search reasoning, multiple candidate actions are generated simultaneously. What tool mechanism is specified for executing parallel branch generation?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies the Task tool for parallel candidate generation | Missed | Passed |
The instructions your model reads when the skill loads.
Monte Carlo Tree Search combined with LLM reasoning. Achieved 92.7% pass@1 on HumanEval (SOTA).
Use for:
while not solved and budget > 0:
1. SELECT: Pick best node using UCT formula
2. EXPAND: Generate N candidate actions
3. SIMULATE: Execute actions, get environment feedback
4. REFLECT: Self-evaluate trajectory quality
5. BACKPROPAGATE: Update scores up the tree
UCT(node) = exploitation + C * sqrt(ln(N) / n)
= avg_score + exploration_bonus
Where:
- C = exploration constant (typically 1.41)
- N = parent visit count
- n = node visit count
Generate top-5 candidate actions in parallel using the Task tool.
test cases passed, vs 11 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.