Tag
This paper introduces a taxonomy of 9 model selection algorithms for multi-LLM collaboration, showing that capability-aware selection strategies outperform random or heuristic team assembly by up to 36.1% across math, coding, QA, and reasoning tasks.
This paper introduces scaling participation, a new paradigm for building modular AI systems through contributions from diverse stakeholders, where small models collaborate to outperform monolithic LLMs by up to 15.4% across various tasks, demonstrating emergent capabilities and improved diversity benefits.
This paper proposes TopoPrior, a framework that learns transferable topology priors from offline reference collaboration graphs to generate initial topologies for multi-agent LLM collaboration across domains, significantly reducing online search overhead and token consumption.
Introduces Capability Conditioned Scaffolding, a framework for LLM collaboration that adapts intervention based on user expertise domains to prevent Professional Domain Drift, with pilot evaluation on MMLU subsets.