HyperReason is a real Adaptive-Entropy MCTS engine that drives a live language model — with a genuinely interactive demo, a reproducible GSM8K eval, and KV-cache accounting that's labeled projected when it can't be measured.
No API key, no install — the real AE-MCTS loop executes as you watch. It uses a clearly-labeled deterministic sampler so you can see the search mechanics instantly. The pip package runs the same algorithm against a real model. Click any node to inspect its reasoning.
is_live=false) — a labeled sampler, not a model.
Real reasoning runs in the package. Entropy = sample_diversity_entropy (no logprobs);
FlashKV = projected simulator (no real GPU).
No hidden heuristics, no hardcoded answers. Every signal comes from real model samples or is explicitly labeled.
At each node the model produces K candidate next-steps. Priors and entropy come from those real samples.
AE-PUCT balances value against sample-diversity entropy — a logprob-free uncertainty proxy. Bounded budget: sims × K calls.
The final answer is majority vote (self-consistency) over terminal trajectories the model actually produced.
FlashKV projects CoW paged-cache savings over the real tree — in tokens (model-agnostic) and projected MB.
Run against the live Z.AI GLM gateway. First N problems of the real GSM8K test split, fixed config, raw per-problem JSONL downloadable — aggregated by a separate script that cannot invent numbers.
The honest reading: GLM-4.6 is already near the ceiling on easy GSM8K, so a modest-budget search
underperforms greedy here. Test-time search pays off on harder problems / weaker base models / bigger budgets —
not on a strong model at its ease. Not a claim of SOTA. Re-run it:
python eval/gsm8k_mini.py --n 100 --sims 16 --k 4 · Raw: eval/runs/*.jsonl
v1.x shipped a wrapper that never called a model and a benchmark that was invented. v2 is bound by these rules.
Every number is produced by a runnable command (config given) or explicitly tagged projected / simulated with the assumption stated.
A missing model or daemon makes the backend raise — never return invented text or token counts. (v1.x silently faked Ollama.)
A sample-based uncertainty proxy labeled sample-diversity entropy (no logprobs). The gateway returns no per-token distribution.
Raw per-problem JSONL + a separate aggregator in eval/; a JS↔Python parity test pins the browser demo to the package.