Language Model Ensembles

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 400% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 93

All topics

TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis
Jul 22, 2026Isabel Xu, Cynthia Xu, Rachel Ren +2Multi-Agent LLM Systems Financial Sentiment Analysis
The Overlake School · 1The Overlake School · Edwards Vacuum Inc. +3
Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift
Jul 19, 2026Junade AliEnsemble Learning Language Model Ensembles
Defence and National Security Programme The Alan Turing Institute London, United Kingdom
Cost-Pragmatic Quality Gating and Selection-Fusion Multi-Model Combiners for BioASQ Phases A+ and B
Jul 15, 2026Dima Galat, Marian-Andrei RizoiuRetrieval-Augmented Generation Biomedical QA
University of Technology Sydney, Australia
Cross-Architecture LLM Ensembles, Feature-Based Reranking and Retrieval-Augmented Prompting for Legal Information Processing
Jul 13, 2026Amal Saad Alshehri, Nelly Bencomo, Amir Atapour-AbarghoueiLegal NLP Legal IR
Durham University · Department of Computer Science · Durham, United Kingdom +2
LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning
Jul 11, 2026Ning LiuLLM Answer Verification Test-Time Scaling
Independent Researcher
When is Routing Meaningful? Diversity and Robustness in Language Model Societies
Jul 10, 2026Fantine Huot, Michael Kaisers, Mirella LapataLLM Routing Language Model Ensembles
Google DeepMind
Collective Intelligence with Foundation Models
Jul 6, 2026J. de Curtò, I. de ZarzàAI Agent Evaluation Multi-Agent Collaboration
Department of Computer Applications in Science & Engineering, BARCELONA Supercomputing Center, 08034 Barcelona, Spain · Escuela Técnica Superior de Ingeniería (ICAI), Universidad Pontificia Comillas, 28015 Madrid, Spain · Human Centered AI, Data & Software, LUXEMBOURG Institute of Science and Technology, L-4362 Esch-sur-Alzette, Luxembourg
Decentralized Aggregation of LLM Predictions via Wagering Mechanisms
Jul 5, 2026Yuhong Luo, David M. Pennock, Xintong WangLanguage Model Ensembles Prediction Markets
Rutgers University · DIMACS, Rutgers University
LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution
Jul 1, 2026Zhao Tian, Yingquan Zhao, Chenyao Suo +2LLM Evaluation Automated Program Repair
School of Computer Software, Tianjin University, Tianjin, China · School of Cybersecurity, Tianjin University, Tianjin, China · School of Computer Science, University of Bristol, Bristol, UK
Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models
Jun 30, 2026Justin Brenne, Christian MeskeLLM Uncertainty Estimation Language Model Ensembles
Ruhr-University Bochum, Bochum, Germany · Ruhr-Universitaet Bochum, Bochum, Germany
Diversity is the Strength of the AI Crowd
Jun 29, 2026Matthew Aitchison, Scott Jeen, Toby Shevlane +1Forecasting Benchmarks Language Model Ensembles
1Mantic Technologies, London, UK.
Categorizing Mathematical Concepts with LLM Voting Ensembles in Mathswitch
Jun 27, 2026Katja Berčič, Slobodan StanojevikjLLM-as-a-Judge Classification
Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia · Institute of Mathematics, Physics and Mechanics, Ljubljana, Slovenia
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
Jun 25, 2026Josef ChenLLM Evaluation LLM Routing
KAIKAKU
The Capability Frontier: Benchmarks Miss 82% of Model Performance
Jun 25, 2026Bradley Fowler, Ryan Smith, Daniel Thi Graviet +8LLM Evaluation Language Model Generation Evaluation
1Martian · 3ThoughtWorks · University of Oxford
Charting the Growth of Social-Physical HRI (spHRI): A Systematic Review Pipeline Augmented by Small Language Models
Jun 24, 2026Mayumi Mohan, Ju-Hung Chen, Alexis E. BlockEvidence Selection Small Language Models
Case Western Reserve University Cleveland, USA
Maestro Order: A Model-Agnostic Orchestration Harness
Jun 22, 2026Hidayet AksuLLM Agent Orchestration LLM Reliability
Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models
Jun 15, 2026Heecheol Yun, Joonhyung Park, Joowon Kim +1Masked Diffusion Models Diffusion Language Model Decoding
1KAIST · 2AITRICS
TeamHerald@CHIPSAL 2026: Hate Speech Detection and Sentiment Analysis of Nepali Memes using Transformer-based Architectures and Ensemble Learning
Jun 7, 2026Ashish Acharya, Anish Khatiwada, Rohit Khadka +1Sentiment Analysis Hate Speech Detection
Herald College Kathmandu, Kathmandu, Nepal
When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference
Jun 6, 2026Yasushi Sakai, Allen Song, Kent LarsonLLM Inference Language Model Ensembles
1MIT Media Lab, Cambridge, MA
Evidence-Grounded Ensemble Diagnosis of 802.11 Packet Captures: A Multi-Stage Pipeline with Deterministic Reliability Scoring
Jun 5, 2026Jerome Henry, Swadhin Pradhan, Miroslav PopovicLLM Evaluation Evidence-Grounded Reasoning
Cisco Systems
Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text Generation
Jun 3, 2026Ahmed Alansary, Molham Mohamed, Ali HamdiMedical QA Curriculum Learning
Faculty of Computer Science MSA University Giza, Egypt
A Multi-Model Metric-based Selection Framework for Abstractive Text summarization
Jun 3, 2026Ahmed Alansary, Ali HamdiText Summarization Language Model Ensembles
Faculty of Computer Science · MSA University · Giza, Egypt
DLLG: Dynamic Logit-Level Gating of LLM Experts
Jun 3, 2026Bingnan Li, Zhaoyang Zhang, Xiaoze Liu +6Ensemble Learning Language Model Ensembles
AWS Agentic AI, Seattle, US · University of California San Diego, La Jolla, US · Purdue University, West Lafayette, US
q0: Primitives for Hyper-Epoch Pretraining
Jun 2, 2026Bishwas Mandal, Shmuel Berman, Akshay Vegesna +1Language Model Pretraining Efficient Language Model Training
Q Labs · Princeton University
CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks
Jun 2, 2026Alexander Apartsin, Yehudit ApersteinModel Selection LLM Evaluation
Holon Institute of Technology, Israel · Afeka Tel Aviv Academic College of Engineering, Israel
A Finite-Calibration Regime Map for LLM Judge Panels
May 31, 2026Bin Zhu, Yanghui RaoLLM-as-a-Judge Language Model Calibration
School of Computer Science and Engineering Sun Yat-sen University
Beyond Agreement: Scoring Panel-Surfaced Biomedical Entity Candidates for Curator Triage
May 29, 2026Shuheng Cao, Ruiqi Chen, Renjie Cao +3Named Entity Recognition LLM-Assisted Annotation
University of California, San Diego · University of Michigan, Ann Arbor · The Hong Kong University of Science and Technology, Guangzhou +2
Design and Evaluation of Multi-Agent AI Oracle Systems for Prediction Market Resolution
May 29, 2026Tarun KotaMulti-Agent LLM Systems Multi-Agent Debate
Yale University
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
May 28, 2026Zhihao Wu, Gracia Gong, Qinglin Zhu +2Watermark Removal LLM Watermarking
Department of Informatics, King’s College London, UK · Department of Mathematics, Imperial College London, UK · Department of Statistics, University of Warwick, UK.
Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels
May 28, 2026Guneet KohliLLM Evaluation LLM-as-a-Judge
Apple

Jul 22, 2026, cs.CLJ/K move · Enter open · S save

TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis

Isabel Xu, Cynthia Xu, Rachel Ren, Cong Guo+1

The Overlake School · 1The Overlake School · Edwards Vacuum Inc.+3

Multi-Agent LLM Systems Financial Sentiment Analysis LLM Routing Language Model Ensembles Finance

Open paper AskPDF arXiv

Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count. We present TriAgent, a multi-agent committee stratified by contextual granularity -- a word-level lexicon (VADER), a sentence-level domain transformer (FinBERT), and a cross-sentence reasoner (Qwen2.5, 0.5B-14B-4bit, with Mistral-7B and Phi-3.5-mini cross-family checks). A three-way Semantic Divergence Index (SDI) measures pairwise disagreement across granularities and routes each query accordingly. Our central finding is the critic plateau: when the LLM is re-tasked as a critic over the smaller agents' outputs, F1 plateaus at ~0.87 across 1.5B-7B Qwen (bootstrap 95% CIs overlap), while a same-size 3-persona vote drops to F1=0.66, which is driven by granularity-stratified diversity. Three corollaries follow from the same SDI signal: (i) a Shared Consensus Dictionary on multilingual sentence-BERT answers 95% of Chinese queries from an English cache at F1=0.99 -- cross-border canonicalization at zero marginal cost; (ii) SDI doubles as a post-hoc LLM-hallucination detector at AUC=0.90; (iii) the SDI single-stage strategy attains the best risk-adjusted return (Sharpe=3.50) on a 20-ticker back-test, dominating both always-FinBERT (1.36) and always-LLM (0.11). At 10M-user scale, TriAgent saves $9.3M/year vs. a GPT-4o-mini baseline. Code, lexicons, and the SCD are released.

Momentum

Related topics

Latest papers 93