Mixture of Complementary Agents for Robust LLM Ensemble
This paper reframes proposer selection in LLM ensembles as a combinatorial selection problem akin to feature selection, emphasizing complementarity over accuracy or diversity. It explores computationally feasible greedy algorithms that assess complementarity using a small labeled set, validating complementarity as a guiding principle and identifying methods with the best performance-cost trade-offs.
Article intelligence
Key points
- Proposer selection is reformulated as a combinatorial problem focusing on complementarity among models.
- Greedy algorithms are proposed to overcome the prohibitive time complexity of standard feature selection.
- Experiments confirm complementarity as effective for selection and identify optimal performance-cost methods.
Why it matters
This matters because proposer selection is reformulated as a combinatorial problem focusing on complementarity among models.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.24048] Mixture of Complementary Agents for Robust LLM Ensemble
[Submitted on 21 May 2026]
Title:Mixture of Complementary Agents for Robust LLM Ensemble
View a PDF of the paper titled Mixture of Complementary Agents for Robust LLM Ensemble, by Yichi Zhang and 5 other authors
View PDF HTML (experimental)
Abstract:Multi-AI collaboration, such as ensembling or debating large language models (LLMs), is a promising paradigm for aggregating information and boosting performance. A foundational step in these pipelines is to feed the responses of several proposer LLMs into a summarizer LLM, which synthesizes a better answer. However, choosing which proposers to include is non-trivial. Existing approaches primarily focus either on accuracy (picking the strongest models) or diversity (ensuring variety), and often overlook the interactions among proposers and with the summarizer. We reframe proposer selection as a combinatorial selection problem akin to feature selection, where the value of an LLM lies in its complementarity with others. However, directly applying standard feature-selection algorithms is impractical in the LLM setting due to prohibitive time complexity. Motivated by this limitation, we explore an extensive range of computationally feasible, greedy-style selection algorithms that assess complementarity using a small labeled set. Our experiments validate complementarity as a guiding principle for proposer selection and identify methods that achieve the best performance-cost trade-offs in practice.
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.24048 [cs.LG]
(or arXiv:2605.24048v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.24048
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yichi Zhang [view email] [v1] Thu, 21 May 2026 21:29:05 UTC (261 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Mixture of Complementary Agents for Robust LLM Ensemble, by Yichi Zhang and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)