mcts-ahd SKILL.md skillA
mcts-ahd from optima-cityu/llm4ad_next is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add optima-cityu/llm4ad_next/mcts-ahd@git:20260825.2005c66Pins git:20260825.2005c66 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- optima-cityu/llm4ad_next
- Path
skills/algo-design/mcts-ahd/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260825.2005c66, committed Aug 25, 2026
- Size
- 3,054 bytes
- Repository stars
- 674
- License
- BSD-3-Clause
Monte Carlo Tree Search for Automatic Heuristic Design (MCTS-AHD) method skill. USE WHEN the user explicitly requests MCTS / Monte Carlo Tree Search for heuristic design, or wants tree-structured search with UCT-based exploration-exploitation balance.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# MCTS-AHD Skill > **Paper**: Zheng et al., "Monte Carlo Tree Search for Comprehensive Exploration in LLM-based Automatic Heuristic Design", ICML 2025. ## 1. Method Essence MCTS-AHD models heuristic search as a **tree**: the root is a template/initial solution, each node is a heuristic implementation, and edges are "mutations producing child nodes". Four-step cycle: 1. **Selection**: From root, select a node using the UCT formula 2. **Expansion**: Use LLM to generate child node variants from the selected node 3. **Evaluation**: Evaluate the child node, obtain reward 4. **Backpropagation**: Update Q-value and visit count for all ancestor nodes along the path UCT formula: ``` UCT = (Q - q_min) / (q_max - q_min) + λ₀ × eval_remain × √(log(parent.visits + 1) / node.visits) ``` - Term 1: Exploitation — normalized Q-value, favoring high-reward nodes - Term 2: Exploration — weighted by λ₀×remaining budget, favoring less-visited nodes - **α and λ₀ jointly control the exploration-exploitation balance** (reference: α=0.5, λ₀=0.1) ## 2. Recommended Parameters See `params.yaml` in this directory for the recommended parameter configuration. **Parameter Guidance**: …
Read the whole file at its exact version.
How to install
mdr add optima-cityu/llm4ad_next/mcts-ahd@sha256:5281c26504234105The line at the top of this page pins the label git:20260825.2005c66, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ugw2hqv6m5sznc4s)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 25, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3054 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
optima-cityu/llm4ad_next · 674 stars · license BSD-3-Clause · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ugw2hqv6m5sznc4s GET https://markdownregistry.com/api/v1/resolve?ref=optima-cityu/llm4ad_next/mcts-ahd GET https://markdownregistry.com/api/v1/blob/5281c26504234105b96ef3beba1fc8ee401c2de8ec683080218974b04b5ddccf
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.