Overview

Language model ensembles study how to combine multiple models so their complementary strengths can improve answers, predictions, or evaluations. Common approaches include majority and weighted voting, learned stacking and calibration, query-level routing, logit fusion, and deliberation or verification across agents. These methods are tested on tasks such as mathematical reasoning, question answering, forecasting, text classification, and evaluation by LLM judges, with attention to accuracy, uncertainty, and inference cost. A central tension is that ensembles help most when models make different errors, yet correlated failures are common and adding models or computation does not reliably outperform the strongest individual model.

Latest papers

CardsList

154 papers17 papers in the last four weeks, down 11% on the four weeks before. 0.1% of all new papers.

  1. Optimal Autoregressive Chain-of-Thought Learning via Bagging

    Nov 16, 2026Awni Altabaa, John Lafferty, Omar MontasserAutoregressive Language ModelingStructured Reasoning in Language Models

  2. Rubric-Based AES with LLM Ensembles: Scoring of Student Responses in Critical Online Reasoning Using Ensembles of LLMs

    Nov 16, 2026Daniel Baumartz, Alexander Mehler, Patrick Schrottenbacher +2Automated Essay ScoringEducational Assessment

  3. Validating LLM-Based Essay Scorers: A Comparative Analysis in Critical Online Reasoning in Medical Education

    Nov 16, 2026Daniel Baumartz, Alexander Mehler, Mevlüt Bagci +1Automated Essay ScoringAutomated Grading

  4. Leakage-aware calibrated decision-level fusion for mental-health text classification

    Nov 14, 2026Wadii Boulila, Giuseppe Varone, Bilel Benjdira +1ClassificationLanguage Model Ensembles

  5. Advancing the Calibration-Compute Frontier of LLM Classifiers via Asymmetric Duos

    Nov 13, 2026Berke Akturk, Ali Can Sahin, Rasit Cem Solatay +3Language Model CalibrationLLM Uncertainty Estimation

  6. Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles

    Nov 13, 2026Wang Ma, Debarun Bhattacharjya, Junkyu Lee +3LLM Uncertainty EstimationUncertainty Decomposition

  7. More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs

    Nov 13, 2026Seyed Mahmoud Sajjadi MohammadabadiMulti-Agent LLM SystemsLLM Agent Evaluation

  8. Small Open-Weight Language Models for Crowd Decision-Making: Capabilities and Limits of Output-Level Fusion and Linguistic Aggregation

    Nov 12, 2026David Herrera-Poyatos, Cristina Zuheros, Carlos Peláez-González +3LLM Decision-MakingOpen-Weight Language Models

  9. Shared Item-Level Error Limits the Aggregation of Small Language Models in Fermi Estimation

    Nov 12, 2026Carolina Fortuna, Blaz BertalanicLanguage Model EnsemblesMulti-Agent LLMs

  10. RE-PRESENT: Evidence Triangulation across Alternative Candidate-Space Views for Efficient LLM Ensemble Inference

    Nov 10, 2026Juming Xiong, Weixin Liu, Kevin Guo +7Language Model EnsemblesMulti-LLM Collaboration

  11. IFRS Compliance Verification: An Open Multi-LLM Benchmark and Content-Conditioned Ensemble Classifier

    Nov 10, 2026Aghoghomena Akasukpe, Li Yang, Xinyao Zhou +2Financial Language Model EvaluationLanguage Model Ensembles

  12. Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference

    Nov 6, 2026Saul Urso, Emanuele Carlini, Patrizio Dazzi +1LLM RoutingCost-Aware Inference

  13. A Scaling Theory of Multi-Epoch Pretraining: Late-Time Overfitting and Ensembling

    Nov 2, 2026Zhen Yang, Yidi Miao, Blake BordelonLanguage Model Scaling LawsLLM Training

  14. How Green Is Your Manifesto? Scoring Environmental Positions in the 2024 EU Elections with an LLM Panel

    Nov 1, 2026Franco Corti, Sajid SirajLanguage Model Ensembles

  15. ReX-GG: a LLM Ensemble Pipeline for Relation-extraction and Graph Generation

    Oct 30, 2026Giacomo Magnifico, Eduard BarbuLanguage Model EnsemblesRelation Extraction

  16. Disparity Laundering: Consensus Without Fairness in Clinical Multi-Agent Systems

    Oct 28, 2026Xiaoyang Wang, Tianrui Wang, Christopher C. YangDemographic Bias in Language ModelsMulti-Agent LLMs

  17. Improving Data-Constrained Scaling with Hyperparameter Transfer and Ensembling

    Oct 27, 2026Ethan Baron, Shmuel Berman, Anirudh Satheesh +3Language Model Scaling LawsHyperparameter Transfer

  18. Multiple Importance Sampling for Guided Speculative Inference

    Oct 23, 2026Joseph Rowan, Ashish J. KhistiLLM Inference AccelerationInference-Time Guidance

  19. Circuits of LLM Classifiers

    Oct 21, 2026Hadi Khalaf, Sajani Vithana, Kunal Talreja +3Large Language Model-Based Text ClassificationLanguage Model Ensembles

  20. Two Sample Sizes in Test-Time LLM Ensembling: Buffered ERM and Minimax Theory

    Oct 15, 2026Zhi Zhang, Arash A. AminiLanguage Model EnsemblesTest-Time Scaling

  21. Judging the Judges: Confidence and Disagreement in Rubrics as Rewards

    Oct 15, 2026Michael Tian-Yue Liu, Anne Harrington, Trevor Darrell +1Rubric-Based RLReward Design for RL

  22. JudgeMoE: Distributional Aggregation for LLM-as-a-Judge

    Oct 5, 2026Yiqi Liu, Joseph James, Yang Wang +3LLM EvaluationLLM-as-a-Judge

  23. Collective Bias Mitigation via Model Routing and Collaboration

    Oct 2, 2026Mingzhe Du, Luu Anh Tuan, Xiaobao Wu +7Social Bias in Language ModelsDemographic Bias in Language Models

  24. Enhancing Biomedical Named Entity Recognition via Multiple Programming Languages Instruction Tuning and Ensemble Method

    Oct 2, 2026Songtao Li, Yijia Zhang, Jianyuan Yuan +3Named Entity RecognitionLLM Fine-Tuning

  25. Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It

    Oct 1, 2026Jonathan Williams, Esin Tureci, Karthik R. NarasimhanRL for Language Model ReasoningLow-Rank Adaptation