cs.MANov 10, 2026

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

Authors: Juming Xiong, Weixin Liu, Kevin Guo, Congning Ni, Chongyu Qu, Junchao Zhu, Katherine Brown, Chao Yan, 

Organizations: Vanderbilt University · Vanderbilt University Medical Center

Abstract

Heterogeneous large language models (LLMs) exhibit complementary strengths, motivating routing and multi-model inference methods that seek to identify reliable predictions for each input. However, exploiting this complementarity remains challenging even when a correct prediction is available within the ensemble. We investigate this challenge across heterogeneous LLM ensembles and find that a simple single-round aggregation rule is highly competitive with learned routing methods, yet substantial oracle headroom remains. Further analysis shows that the evaluated single-round response signals provide limited discriminative power for identifying reliable predictions. In contrast, controlled re-presentations of the same question elicit complementary evidence about prediction reliability. Motivated by these findings, we introduce RE-PRESENT, a training-free framework that selectively re-presents disputed questions and directly aggregates candidate-level evidence across alternative views. Across seven multiple-choice benchmarks and two heterogeneous model ensembles, RE-PRESENT improves over strong single-round aggregation while offering a favorable accuracy--cost trade-off compared with self-consistency and multi-model debate.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jul 30, 2026

Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation

Large Language Models (LLMs) reason in free-form chain-of-thought (CoT) without revealing which steps were well supported and which alternatives were rejected. In high-stakes domains, users then cannot judge if an answer rests on sound reasoning. Majority voting and multi-agent debate improve answers using model agreement, but do not expose agreement on individual steps. Reasoning Consensus (RC) extracts a typed reasoning graph from each CoT, merges equivalent steps across graphs from diverse models, and weights every step by how many chains attest to it. RC reveals this step-wise support and the varied justifications behind each answer. On 7 benchmarks across law, science, medicine, narrative reasoning and logic, RC matches majority voting and debate in accuracy (69.4% vs. 69.0-70.3%). An LLM judge prefers RC's best-supported graph to other graphs for the same answer. In a user study, participants read RC graphs faster than debate transcripts or vote tallies, and 14 of 18 preferred them for future use.
Oct 13, 2026

Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation

LLM ensemble gains are often measured against a single baseline, but the value attributed to additional candidates can change with the comparison used. We study an LLM aggregator under four matched conditions: Direct (no candidates), Single-slot (one candidate in a multi-slot interface), Duplicate (one candidate repeated), and Multi-candidate (separately generated candidates). Under either non-diverse control, overall candidate gain (CIV) splits algebraically into an additional-candidate contrast (DSV) and a candidate-context contrast (CCV); the split, but not CIV, depends on the chosen control. On MultiHopRAG model diversity (k=2), the repetition gap Rep=-8.33 pp [-13.25, -3.75] quantifies the difference between gains measured against Duplicate and Single-slot. On a matched FRAMES stronger-panel extension (n=200, k=3, aggregator output limit 4096), paired Delta Rep=+9.67 pp [+6.00, +13.50]; within panels, Rep changes sign (original -6.33; stronger +3.33). In FRAMES evidence aggregation, candidate-context contrasts remain strongly negative under both non-diverse controls. Our results show why ensemble evaluations should state the reference control before attributing gains to additional candidates.
Jul 11, 2026

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution. We study a third signal, free at inference time: cross-model consensus, the degree to which independently trained models, each solving the problem once, agree on a final answer. We treat the panel as an LLM-jury, in which the structure of agreement, not any model's score of another, is the verification signal. Across seven benchmarks it selects correct answers better than self-consistency and far better than a model scoring its own candidates: on competition math it closes the entire gap to an oracle selector, while self-scoring closes almost none. The mechanism is error decorrelation: independently trained models err differently, so their wrong answers scatter while the correct one accumulates agreement. We make this precise with a parameter-free law, derived in closed form, that predicts consensus accuracy from three measured panel statistics to a mean absolute error of 0.030.03 and exposes the method's ceiling: a shared-error floor where models share a misconception, near zero on math but non-trivial on science. Against four trained verifiers spanning discriminative, outcome, and generative reward models, the free LLM-jury matches the strongest inside their math training domain and is the top selector outside it. Cross-model consensus is thus a verifier we can characterize in advance: a law that says when to trust it, and a floor that marks where it cannot.