15 Lats banner
ShaheerKhawaja ShaheerKhawaja

15 Lats

Development community

Description

# Layer 15: LATS (Language Agent Tree Search) **Research:** Koh et al. 2024 — "Language Agent Tree Search" (ICML 2024) **Impact:** 94.4% on HumanEval (GPT-4), +14% over baseline ## Technique Monte Carlo Tree Search applied to LLM reasoning. Explores multiple solution paths with backtracking, evaluation, and reflection. The most powerful (and expensive) technique — use only in /omni-plan mode. ## LATS Protocol ```markdown SELECTION: Choose the most promising unexplored path - Use UCB1: sco

Installation

Installs to ~/.claude/skills/shaheerkhawaja-productionos-15-lats/SKILL.md

Terminal
mkdir -p ~/.claude/skills/shaheerkhawaja-productionos-15-lats && curl -fsSL https://raw.githubusercontent.com/ShaheerKhawaja/ProductionOS/HEAD/prompts/15-lats.md -o ~/.claude/skills/shaheerkhawaja-productionos-15-lats/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

Full documentation available on GitHub

View Source Repository