HyperReason — an MCTS Test-Time Compute Engine That Publishes When It LOSES

---

title: "HyperReason \u2014 an MCTS Test-Time Compute Engine That Publishes When It LOSES" published: true description: "pip install hypermcts: adaptive-entropy Monte Carlo tree search for LLMs across Z.AI, OpenAI, DeepSeek, Groq, Ollama and Transformers \u2014 with an honest eval contract and raw JSONL traces." tags: python, machinelearning, showdev, ai

The honesty problem in test-time compute

A lot of "reasoning engine" repos share two flaws: they never actually call a model, and they publish benchmark tables nobody can reproduce. HyperReason v1 was, by its own README's admission, exactly that.

v2.0.1 is a full honest rebuild: the engine genuinely drives real LLMs and publishes transparent evaluations — including runs where MCTS underperformed greedy decoding. No fake fallbacks; every number traces to code.

What it is

An adaptive-entropy Monte Carlo tree search engine for LLM test-time compute, on PyPI:

pip install hypermcts   # imports as hyper_reason

Supported providers out of the box:

Minimal usage

from hyper_reason import wrap_model, GLMBackend

model = wrap_model(GLMBackend(model="glm-4-flash"))
# run the AE-MCTS search on your problem

There's also a CLI, a live web demo (rudra496.github.io/hyper-reason), and an offline mock backend so you can try the whole pipeline without any API key.

The honest eval contract

• Raw JSONL eval traces are published in the repo (eval/runs/) — wins and losses
• The eval contract (eval/CONFIG.md) documents what was measured and how
• Citable via Zenodo: 10.5281/zenodo.22118810

That's the actual point of the project: if MCTS doesn't beat greedy on your problem, the traces will tell you — which is more than most engines will admit.

Links

• Source (MIT): github.com/rudra496/hyper-reason
• PyPI: pypi.org/project/hypermcts
• Live demo: rudra496.github.io/hyper-reason