Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Paper โข 2605.14386 โข Published โข 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 ๐ฅ about 23 hours ago
๐งฌ 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 โ sharing the core ideas below.
๐ Paper: https://huggingface.co/papers/2605.14386
๐ arXiv: https://arxiv.org/abs/2605.14386
๐ 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 โ with zero
gradient-based training โ it reaches frontier-level reasoning.
- ๐ Darwin-28B-Opus: GPQA Diamond 88.89%
- ๐ธ Zero gradient steps โ not a single B200 or H200 hour needed
- ๐งฌ Consistent gains across 4B โ 35B scale
- ๐ Cross-architecture breeding between Transformer and Mamba families
- ๐ Stable recursive multi-generation evolution
#Three Core Mechanisms
โ 14-dim Adaptive Merge Genome โ fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
โก MRI-Trust Fusion โ 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 โ Darwin learns the balance from data.
โข Architecture Mapper โ weight-space breeding across heterogeneous
families. Attention ร SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them โ no gradients required.
Replies and critiques welcome ๐Organizations
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
โข โข 12 reacted to SeaWolf-AI's post with ๐ฅ about 23 hours ago
Post
2248
๐งฌ 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 โ sharing the core ideas below.
๐ Paper: Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning (2605.14386)
๐ arXiv: https://arxiv.org/abs/2605.14386
๐ Model: 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 โ with zero
gradient-based training โ it reaches frontier-level reasoning.
- ๐ Darwin-28B-Opus: GPQA Diamond 88.89%
- ๐ธ Zero gradient steps โ not a single B200 or H200 hour needed
- ๐งฌ Consistent gains across 4B โ 35B scale
- ๐ Cross-architecture breeding between Transformer and Mamba families
- ๐ Stable recursive multi-generation evolution
#Three Core Mechanisms
โ 14-dim Adaptive Merge Genome โ fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
โก MRI-Trust Fusion โ 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 โ Darwin learns the balance from data.
โข Architecture Mapper โ weight-space breeding across heterogeneous
families. Attention ร SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them โ no gradients required.
Replies and critiques welcome ๐
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 โ sharing the core ideas below.
๐ Paper: Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning (2605.14386)
๐ arXiv: https://arxiv.org/abs/2605.14386
๐ Model: 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 โ with zero
gradient-based training โ it reaches frontier-level reasoning.
- ๐ Darwin-28B-Opus: GPQA Diamond 88.89%
- ๐ธ Zero gradient steps โ not a single B200 or H200 hour needed
- ๐งฌ Consistent gains across 4B โ 35B scale
- ๐ Cross-architecture breeding between Transformer and Mamba families
- ๐ Stable recursive multi-generation evolution
#Three Core Mechanisms
โ 14-dim Adaptive Merge Genome โ fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
โก MRI-Trust Fusion โ 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 โ Darwin learns the balance from data.
โข Architecture Mapper โ weight-space breeding across heterogeneous
families. Attention ร SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them โ no gradients required.
Replies and critiques welcome ๐
- 2 replies
liked a
model 23 days ago
liked a
model about 1 month ago
liked a
Space about 1 month ago
upvoted an article about 2 months ago
Article
"The Child That Surpassed Both Parents Through MRI-Guided Evolutionary Merge"
FINAL-Bench
โข โข 14 liked a
Space about 2 months ago
liked a
model about 2 months ago
liked a
Space about 2 months ago
liked a
dataset about 2 months ago
liked 2
Spaces about 2 months ago
liked 2
Spaces 2 months ago
liked a
dataset 2 months ago
liked a
Space 2 months ago
reacted to SeaWolf-AI's post with ๐โค๏ธ๐ฅ 2 months ago
Post
8190
๐ Introducing MARL โ Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning
Now available on PyPI ยท GitHub ยท ClawHub ยท HuggingFace
AI models sense they could be wrong, but they can't actually fix what's broken.
๐ค Live A/B test: VIDraft/MARL
We evaluated 9 SOTA models (GPT-5.2, Claude Opus 4.6, Gemini 3 Pro, etc.) across 1,800 assessments in FINAL Bench and found a 39.2%p gap between "recognizing potential errors (MA=0.694)" and "actually finding and fixing them (ER=0.302)."
MARL (Model-Agnostic Runtime Middleware for LLMs) was built to close this metacognitive gap. It decomposes a single LLM call into a 5-stage expert pipeline (Hypothesis โ Solver โ Auditor โ Adversarial Verifier โ Synthesizer), transforming "answer in one shot" into "think, doubt, correct, and rewrite."
No weight modification โ works instantly with GPT-5.4, Claude, Gemini, Llama, or any OpenAI API-compatible LLM by changing one line: base_url. Ships with 9 domain-specific emergence engines (invention, pharma, genomics, chemistry, ecology, law, and more โ 5,538 expert data items) activated by a simple tag like model="gpt-5.4::pharma".
pip install marl-middleware
MARL is also officially registered on ClawHub, the skill marketplace of OpenClaw โ an AI agent platform with 260K+ developers and 3,200+ skills. It's the first middleware in the Reasoning Enhancement category. One command โ clawhub install marl-middleware โ gives your AI agent a metacognition upgrade.
๐ Technical deep dive: https://huggingface.co/blog/FINAL-Bench/marl-middleware
๐ฆ PyPI: https://pypi.org/project/marl-middleware/
๐ GitHub: https://github.com/Vidraft/MARL
๐ฆ ClawHub: https://clawhub.ai/Cutechicken99/marl-middleware
#MARL #LLM #Hallucination #Metacognition #MultiAgent #AIMiddleware #FINALBench #OpenClaw #ClawHub #PyPI #AGI #HuggingFace #ReasoningAI #SelfCorrection #GlassBoxAI
Now available on PyPI ยท GitHub ยท ClawHub ยท HuggingFace
AI models sense they could be wrong, but they can't actually fix what's broken.
๐ค Live A/B test: VIDraft/MARL
We evaluated 9 SOTA models (GPT-5.2, Claude Opus 4.6, Gemini 3 Pro, etc.) across 1,800 assessments in FINAL Bench and found a 39.2%p gap between "recognizing potential errors (MA=0.694)" and "actually finding and fixing them (ER=0.302)."
MARL (Model-Agnostic Runtime Middleware for LLMs) was built to close this metacognitive gap. It decomposes a single LLM call into a 5-stage expert pipeline (Hypothesis โ Solver โ Auditor โ Adversarial Verifier โ Synthesizer), transforming "answer in one shot" into "think, doubt, correct, and rewrite."
No weight modification โ works instantly with GPT-5.4, Claude, Gemini, Llama, or any OpenAI API-compatible LLM by changing one line: base_url. Ships with 9 domain-specific emergence engines (invention, pharma, genomics, chemistry, ecology, law, and more โ 5,538 expert data items) activated by a simple tag like model="gpt-5.4::pharma".
pip install marl-middleware
MARL is also officially registered on ClawHub, the skill marketplace of OpenClaw โ an AI agent platform with 260K+ developers and 3,200+ skills. It's the first middleware in the Reasoning Enhancement category. One command โ clawhub install marl-middleware โ gives your AI agent a metacognition upgrade.
๐ Technical deep dive: https://huggingface.co/blog/FINAL-Bench/marl-middleware
๐ฆ PyPI: https://pypi.org/project/marl-middleware/
๐ GitHub: https://github.com/Vidraft/MARL
๐ฆ ClawHub: https://clawhub.ai/Cutechicken99/marl-middleware
#MARL #LLM #Hallucination #Metacognition #MultiAgent #AIMiddleware #FINALBench #OpenClaw #ClawHub #PyPI #AGI #HuggingFace #ReasoningAI #SelfCorrection #GlassBoxAI