Skip to main content
HyperReason v2 — an honest Adaptive-Entropy MCTS test-time-compute engine.

v1.x of this project shipped an engine that never called a model and an invented
benchmark table. v2 is a full honest rebuild: it genuinely drives a real LLM
(Z.AI GLM by default; Ollama / HuggingFace supported), runs Adaptive-Entropy
MCTS over model-generated candidates, picks the answer by self-consistency, and
projects KV-cache savings from real per-node token counts.

Quickstart:
pip install hypermcts
export ANTHROPIC_BASE_URL=https://api.z.ai/api/anthropic
export ANTHROPIC_API_KEY=...
python -c "from hyper_reason import wrap_model, GLMBackend; \
print(wrap_model(GLMBackend()).reason('What is 17 + 25?')['boxed_answer'])"

Real benchmark (GSM8K-mini, N=20, GLM-4.6):
greedy (T=0) : 95.0%
self-consistency (K=4) : 90.0%
AE-MCTS (sims=6,k=2,d3) : 85.0%

We publish the run where AE-MCTS UNDERPERFORMS greedy: GLM-4.6 is already near
the ceiling on easy GSM8K, so modest-budget search does not pay off there. This
is the opposite of a SOTA claim. Re-run and scale it:
python eval/gsm8k_mini.py --n 100 --sims 16 --k 4

Entropy is labeled "sample_diversity_entropy (no logprobs)". KV savings are a
projected simulator (no real GPU). Backends RAISE when offline — they never
fabricate a response. Raw per-problem traces: eval/runs/*.jsonl.

Full docs: https://github.com/rudra496/hyper-reason (README.md)
Live demo: https://rudra496.github.io/hyper-reason
License: MIT. Author: Rudra Sarker.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hypermcts-2.0.1.tar.gz (36.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hypermcts-2.0.1-py3-none-any.whl (35.0 kB view details)

Uploaded Python 3

File details

Details for the file hypermcts-2.0.1.tar.gz.

File metadata

  • Download URL: hypermcts-2.0.1.tar.gz
  • Upload date:
  • Size: 36.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for hypermcts-2.0.1.tar.gz
Algorithm Hash digest
SHA256 28815bfe9d80f8a9300f6c006c2f05409770ec6b1b6788903f9767c269b0107a
MD5 566ffedec670153881a15b3663c36720
BLAKE2b-256 4983ce5ae63d7481ed850755fc19d5de0be3a8ade7c727aba56f86790524f93b

See more details on using hashes here.

Provenance

The following attestation bundles were made for hypermcts-2.0.1.tar.gz:

Publisher: publish.yml on rudra496/hyper-reason

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file hypermcts-2.0.1-py3-none-any.whl.

File metadata

  • Download URL: hypermcts-2.0.1-py3-none-any.whl
  • Upload date:
  • Size: 35.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for hypermcts-2.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 c71d2440277added8148dfa0cca9f84b8ce8ef678b0eed525a6c436a83dedffc
MD5 db5ef6118868a33d1a7e8fa6b3ae9771
BLAKE2b-256 04b27a7cf5ca62b76b6cc4468b6b16a1dfed539b9e7539e3e9cd9d6bddcec2c8

See more details on using hashes here.

Provenance

The following attestation bundles were made for hypermcts-2.0.1-py3-none-any.whl:

Publisher: publish.yml on rudra496/hyper-reason

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page