Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
The performance ceiling of an LLM team is constrained not only by individual model capabilities, but also by inter-member error resonance and predictive differences. Although heterogeneous teaming is often observed to be effective in practice, existing approaches lack complementarity metrics that are computable, interpretable, and optimizable, leaving team composition to rely on heuristics. We propose a heterogeneity-driven team selection framework that performs offline profiling to characterize individual capability along with two complementary signals: one captures decorrelation in error patterns to reduce co-failures, while the other measures divergence in predictive behavior to capture strategy diversity. We formulate team selection as a standardized quality--complementarity combinatorial objective and apply an efficient greedy search to select a small team from a candidate pool. Experiments across multiple benchmarks demonstrate that our framework consistently outperforms quality-only baselines under controlled candidate pools and team sizes, establishing reusable selection principles for multi-LLM systems.
BibTeX
@misc{teng2027which,
author = {Liangyu Teng and Hengsong Liu and Juncen Guo and Jingyu Zhang and Yang Liu and Jing Liu and Liang Song},
title = {{Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection}},
year = {2027},
url = {https://openreview.net/forum?id=S7EZ6o4STZ},
howpublished = {OpenReview},
note = {Submitted to ICLR 2027},
}Loading related content...