GitHub's HydraFusion orchestrates multiple AI models to cut coding costs by up to 67%
Project HydraFusion: Frontier quality via multi-model orchestration
GitHub has introduced Project HydraFusion, a research preview for GitHub Copilot that uses runtime orchestration to automatically select and combine models from multiple providers. HydraFusion chooses among three execution patterns—single, cascade, or critique—to balance quality, cost, and latency for each task. In offline evaluations, it matched or exceeded the quality of Claude Opus 5 on three agentic coding benchmarks while reducing estimated costs by 36% to 67%. The system is designed to adapt as new models become available.
We believe the next real gain in coding agents will come from combining frontier intelligence with runtime orchestration.
- gopalv
> One model drafts a result, an independent read-only critic from a different model family reviews it
Multiple model vendors is key here, the cascade pattern doesn't need it, but the critique pattern does.
Last Nov, my team wrote a paper ("Team of Rivals") on the difference between using an OpenAI model to Critique an Anthropic model's output vs running a self-review agent loop on the same vendor.
The ablations [1] proved that neither company alone was better than using both.
The paper was a general response to "What does your company do that Anthropic can't?" but more so a demonstration of how to make something 90%+ good with models which eval at 60% or so (& Gas Town post unblocked our "this is a trade secret" argument about the paper).
- Roark66
I'm questioning their results. It doesn't take much to beat the frontier in single benchmarks if one puts extra software between the model and the harness.
This is also a reason why comparing "naked models" for which weights are available and frontier where providers can do whatever they want behind the scenes is unfair.
Specifically, all it took to boost Qwen3.8-27B to get 10% more points on SWEbench Pro and Terminal Bench 2.0 with a proxy that has just these basics:
- tweaks few decode settings like slightly higher temperature
- detects when model gets stuck and tells it to "go on"
- detects responses cut in the middle, empty responses that contain only reasoning, formats not passing verification etc and tells the model to "try better"
And that is it. 10% more. I admit on a subset of tasks, but results are results, even on a subset.
- guybedo
i've been using adversarial critique and reviews for many planning, solution design and implementation steps inside workflows.
It's so effective and helps catching so many design flaws, implementations misses etc ... that i'm wondering how people manage to build complex/large projects with agents without this kind of process. Well, i actually built this thing because i couldn't get good results so i had to find a way.
I'm gonna open source the whole thing but it needs some cleanup, there's a basic landing page here https://kodfactory.com if anyone wants to be notified when it's released on github. Yeah i know, the world really needs another software factory :-)