Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection
cs.CL, cs.LG, cs.MA
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/ibm-granite/granite-3.0-language-models
Terminology
Sources
- Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
- NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
- InternLM2 Technical Report
- Harnessing Multiple Large Language Models: A Survey on LLM Ensemble
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
- The Llama 3 Herd of Models
- RouterBench: A Benchmark for Multi-LLM Routing System
- Ministral 3
- Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models
- EuroLLM-9B: Technical Report
- Contrastive Decoding Improves Reasoning in Large Language Models
- Olmo 3
- AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
- Gemma 2: Improving Open Language Models at a Practical Size
- Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
- Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems
- Qwen3 Technical Report
- Mixture of Complementary Agents for Robust LLM Ensemble
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering