Mixture-of-Models: Unifying Heterogeneous Agents via N-Way Self-Evaluating Deliberation — HN submission

Wed, 18 Feb 2026 23:21:15 GMT

Show HN: NSED is public – Mixture-of-Models to Hit SOTA using self-hosted AI

Hey HN, We're open-sourcing (source-available, BSL 1.1, patent pending) the orchestrator behind our paper benchmark results. NSED (N-Way Self-Evaluating Deliberation) is a Rust binary that coordinates multiple LLMs through structured rounds of proposals and cross-evaluation, using quadratic voting to prevent any single model from dominating the consensus. The result: Three open-weight models (20B, 8B, 12B) on consumer GPUs — 64GB total VRAM, ~$7K hardware — score 84% on AIME 2025. The same models individually or with naive majority voting score ~54%. That's frontier-model performance on…

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Mixture-of-Models: Unifying Heterogeneous Agents via N-Way Self-Evaluating Deliberation · HackerPapers discussions

Mixture-of-Models: Unifying Heterogeneous Agents via N-Way Self-Evaluating Deliberation — HN submission