S
SKIMIX
Multi-agent framework for inference-time scaling via dynamic skill mixture and retrieval
Open SourceFree
About
SKIMIX is a research framework that enables inference-time scaling through multi-agent collaboration using skill mixture strategies. It combines embedding-based skill retrieval, submodular routing algorithms, and adaptive skill evolution to orchestrate specialized agents for complex reasoning tasks. Designed for researchers exploring scalable multi-agent architectures and dynamic task decomposition.
Details
| Language | |
| Patterns |
Tags
multi-agentopen-sourceframeworkorchestrationautonomous
Quick Info
- Organization
- Research
- Pricing
- open-source
- Free Tier
- Yes
- Updated
- Aug 1, 2026
Also in Frameworks
L
LangChain
Build context-aware reasoning applications with LLMs
OSSFree
LangChain AI
143.1K850.0K/wtoday468
A
AutoGen
Microsoft's framework for building multi-agent AI systems
OSSFree
Microsoft
60.1K15w ago445
C
CrewAI
Multi-agent orchestration framework for collaborative AI workflows
OSSFree
CrewAI Inc
56.4Ktoday299