Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Paper • 2605.14386 • Published • 43
Jojun84
Jojun8403
AI & ML interests
None yet
Recent Activity
upvoted a paper about 15 hours ago
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning reacted to SeaWolf-AI's post with 🔥 about 23 hours ago
🧬 Darwin Family: Zero Gradient Steps, GPQA Diamond 88.89%
How far can we push LLM reasoning *without* training?
Our team at VIDRAFT submitted this paper to Daily Papers yesterday, and it's
currently #3. Huge thanks to everyone who upvoted — sharing the core ideas below.
🔗 Paper: https://huggingface.co/papers/2605.14386
🔗 arXiv: https://arxiv.org/abs/2605.14386
🔗 Model: https://huggingface.co/FINAL-Bench/Darwin-28B-Opus
---
TL;DR
Darwin Family is a training-free evolutionary merging framework.
By recombining the weight spaces of existing LLM checkpoints — with zero
gradient-based training — it reaches frontier-level reasoning.
- 🏆 Darwin-28B-Opus: GPQA Diamond 88.89%
- 💸 Zero gradient steps — not a single B200 or H200 hour needed
- 🧬 Consistent gains across 4B → 35B scale
- 🔀 Cross-architecture breeding between Transformer and Mamba families
- 🔁 Stable recursive multi-generation evolution
#Three Core Mechanisms
① 14-dim Adaptive Merge Genome — fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
② MRI-Trust Fusion — we diagnose each layer's reasoning contribution
via an **MRI (Model Reasoning Importance)** signal and fuse it with
evolutionary search through a **learnable trust parameter**. Trust the
diagnostic too much and search collapses; ignore it and search becomes
inefficient — Darwin learns the balance from data.
③ Architecture Mapper — weight-space breeding across heterogeneous
families. Attention × SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them — no gradients required.
Replies and critiques welcome 🙌Organizations
None yet
upvoted a paper about 15 hours ago
upvoted an article about 23 hours ago
Article
Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step
FINAL-Bench
• • 12 upvoted an article about 2 months ago
Article
"The Child That Surpassed Both Parents Through MRI-Guided Evolutionary Merge"
FINAL-Bench
• • 14 upvoted an article 2 months ago
Article
MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning
FINAL-Bench
• • 16