Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

junchenzhi/Awesome-LLM-Ensemble

A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble"

74Apache-2.0HTML

View on GitHub

Stars: 257
Forks: 22
Watchers: 5
Open issues: 1
Contributors: 7

Star history, last 90 days+3 over 16 snapshots

2026-07-31 · 2542026-11-04 · 257

Star history, last 90 days
Date	Stars
2026-07-31	254
2026-08-06	254
2026-08-18	253
2026-08-19	254
2026-08-31	255
2026-09-02	255
2026-09-08	256
2026-09-12	256
2026-09-21	256
2026-09-22	255
2026-09-25	256
2026-10-11	256
2026-10-21	256
2026-10-27	256
2026-10-31	257
2026-11-04	257

Today

— stars today

This week

+1 stars this week

This month

+1 stars this month

Momentum

1.0

growth rate 0.39%/day

From the README

🔥🔥🔥 Awesome-LLM-Ensemble
"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble" (IJCAI Survey 2026)

Zhijun Chen, Xiaodong Lu, Jingzheng Li, Pengpeng Chen, Zhuoran Li, Kai Sun, Yuankai Luo, Qianren Mao, Ming Li, Likang Xiao, Dingqi Yang, Xiao Huang, Yikun Ban, Hailong Sun, Philip S. Yu

If you like our project, please give it a star ⭐ to show your support！Thank you:)

📣 Notices

🔥🔥🔥 This is a collection of papers on LLM Ensemble.

[2026-05] Accepted by IJCAI Survey 2026!

🔥🔥🔥 [2026-04] We have updated our arXiv paper with a new version! Stay tuned for our journal-style paper in recent months.

[Always] [Add your papers in this repo] Thank you to all the papers that have cited our survey.
We will add all related citing papers to this GitHub repo, in a timely manner, to help increase the visibility of your contributions.

[Always] [Maintain] We will make this list updated frequently!
If you found any missed/new paper, please don't hesitate to contact us or Pull requests.

🍀 Citation

If you find this survey useful, please consider citing our paper:

@article{chen2025harnessing,
  title={Harnessing Multiple Large Language Models: A Survey on LLM Ensemble},
  author={Chen, Zhijun and Lu, Xiaodong and Li, Jingzheng and Chen, Pengpeng and Li, Zhuoran and Sun, Kai and Luo, Yuankai and Mao, Qianren and Li, Ming and Xiao, Likang and Yang, Dingqi and Huang, Xiao and Ban, Yikun and Sun, Hailong and Yu, Philip S},
  journal={arXiv preprint arXiv:2502.18036},
  year={2025}
}

Contents

1. LLM Ensemble and Taxonomy

1.1 LLM Ensemble

Paper Abstract:

LLM Ensemble---which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during the downstream inference, to benefit from their individual strengths---has gained substantial attention recently. The widespread availability of LLMs, coupled with their varying strengths and out-of-the-box usability, has profoundly advanced the field of LLM Ensemble. This paper presents the first systematic review of recent developments in LLM Ensemble. First, we introduce our taxonomy of LLM Ensemble and discuss several related research problems. Then, we provide a more in-depth classification of methods under the broad categories of ``ensemble-before-inference, ensemble-during-inference, ensemble-after-inference'', and review all relevant methods. Finally, we introduce related benchmarks and applications, summarize existing studies, and suggest several future research directions. A curated list of papers on LLM Ensemble is available at https://github.com/junchenzhi/Awesome-LLM-Ensemble.

1.2 Taxonomy

Figure 1: Illustration of LLM Ensemble Taxonomy. (Note that for (b) ensemble-during-inference paradigm, there is also a process-level ensemble approach that we have not represented in the figure, mainly because that this approach is instantiated by a single method.)

Figure 2: Taxonomy of All LLM Ensemble Methods. (Please note that this figure may not be fully updated to include all the papers listed below.)

(a) Ensemble before inference.
Since the ensemble-before-inference methods require routing a query to the most suitable LLM before LLM inference, the core of such methods lies in predicting the utility of candidate models for a given query under certain preferences (e.g., performance or cost). Based on how they formulate the utility of candidate LLMs, we divide existing methods into two categories:
- (a1) Discrete utility methods, discretize the model utility into categorical labels;
- (a2) Continuous utility methods model LLM utility as real-valued variables, such as response length or performance scores. This formulation enables a fine-grained characterization of model behavior, capturing subtle performance differences obscured by categorical definitions.
(b) Ensemble during inference.
As the most granular form of ensemble among the three broad categories, this type of approach encompasses:
- (b1) Token-level ensemble methods, which integrate the token-level outputs of multiple models at the finest granularity of decoding;
- (b2) Span-level ensemble methods, which conduct ensemble at the level of a sequence fragment (e.g., a span of four words);
- (b3) Process-level ensemble methods, which select the optimal reasoning process step-by-step within the reasoning chain for a given complex reasoning task. Note that for these ensemble-during-inference methods, the aggregated text segments will be concatenated with the previous text and fed again to models.
(c) Ensemble after inference.
These methods can be classified into two categories:
- (c1) Non cascade methods, which perform ensemble using multiple complete responses contributed from all LLM candidates;
- (c2) Cascade methods, which consider both performance and inference costs, progressively reasoning through a chain of LLM candidates largely sorted by model size to find the most suitable inference response.

2. Papers

2.1 Ensemble Before Inference

Figure 3: Summary analysis of the key attributes of ensemble-before-inference methods. (Please note that this table may not be fully updated to include all the papers listed below.)

2.1.1 (a,1) Discrete utility methods

Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems
2026-11 · Route Anything ·
MARS: Memory-Aware Routing for Session-Level LLM Assistants
2026-10 · MARS ·
Alliance of Stochastic Routing and Reinforcement Fusion for Multi-Model Reasoning
2026-10 · VL-Scout ·
RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing
2026-10 · RouteWeaver ·
CopRoute: Dependence-Aware Conformal Routing for Language Models
2026-10 · CopRoute ·
Prompt-Only LLM Routing with Conformal Regret Control
2026-10 ·
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
2026-09 · RouteFM ·
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
2026-06 · ACRouter ·
From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue
2026-04 · DialRouter ·
DISROUTER: Distributed Self-Routing for LLM Selections
2025-10 · DiSRouter ·
TAGROUTER: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks
2025-06 · TagRouter ·
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
2025-06 · Router-R1 ·
RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing
2025-06 · RadialRouter ·
Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection
2025-05 · RTR ·
Bench-CoE: a Framework for Collaboration of Experts from Benchmark
2024-12 · Bench-CoE ·
GraphRouter: A Graph-based Router for LLM Selections
2024-10 · GraphRouter ·
Eagle: Efficient Training-Free Router for Multi-LLM Inference
2024-09 · Eagle ·
SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models
2024-08 · SelectLLM ·
RouteLLM: Learning to Route LLMs with Preference Data
2024-06 · RouteLLM ·
Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing
2024-05 · LLM Routing Lessons ·
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
2024-04 · Hybrid-LLM ·
An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
2024-03 · ETR ·
Routoo: Learning to Route to Large Language Models Effectively
2024-01 · Routoo ·
RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
2024 · RouterDC ·
Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models
2023-11 · ZOOTER ·
Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling
2023-08 · FORC ·
LLM Routing with Benchmark Datasets
2023 · Benchmark Routing ·

2.1.2 (a,2) Continuous utility methods

Which Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic Workflows
2026-10 · CC-Gittins ·
Breaking the Tie: A Cluster-Aware Routing Framework for Large Language Models
2026-10 · CASLR ·
Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection
2026-09 · C²-MAS ·
FLARE: Fine-Grained Length-Aware Routing for Resource-Efficient Heterogeneous LLM Serving
2026-06 · FLARE ·
Conformal LLM Routing with Distribution-Free Safety Guarantees
2026-06 ·
SCOPE: Cost-Efficient Model Selection for Compound AI Systems under Quality Constraints
2026-06 · SCOPE ·
MonoRouter: Enforcing Monotonicity in Item Response Theory for LLM Routing
2026-03 · MonoRouter ·
ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing
2026-03 · ReLope ·
Multi-LLM Query Optimization
2026-03 ·
RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
2026-02 · RACER ·
Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
2026-02 ·
EPIC: Ensemble Planning with Contrastive learning
2025-11 · EPIC ·
WebRouter: Query-specific Router via Variational Information Bottleneck for Cost-sensitive Web Agent
2025-10 · WebRouter ·
LLMRank: Understanding LLM Strengths for Model Routing
2025-10 · LLMRank ·
The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants
2025-05 · Avengers ·
InferenceDynamics: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling
2025-05 · InferenceDynamics ·
Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers
2025-05 · kNN Router ·
Co-optimizing Recommendation and Evaluation for LLM Selection
2025 · RELM ·
LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing
2025-02 · LLM Bandit ·
PickLLM: Context-Aware RL-Assisted Large Language Model Routing
2024-12 · PickLLM ·
TensorOpera Router: A Multi-Model Router for Efficient LLM Inference
2024-08 · TO-Router ·
MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs
2024-07 · MetaLLM ·
Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario
2024-06 · HomoRouter ·
Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM
2024-01 · Blending ·

2.2 Ensemble During Inference

Figure 4: Summary analysis of the key attributes of ensemble-during-inference methods. (Please note that this table may not be fully updated to include all the papers listed below.)

2.2.1 (b,1) Token-Level Ensemble

DLLG: Dynamic Logit-Level Gating of LLM Experts
2026-06 · DLLG ·
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
2026-05 · WASH ·
Rethinking LLM Ensembling from the Perspective of Mixture Models
2026-05 · ME ·
SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission
2026-04 · SpecFed ·
Token-Level LLM Collaboration via FusionRoute
2026-01 · FusionRoute ·
When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
2025-10 · SAFE ·
Harnessing Consistency for Robust Test-Time LLM Ensemble
2025-10 · CoRe ·
Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
2025-05 · Transformer Copilot ·
Token-level Ensembling of Models with Different Vocabularies
2025-02 · ABE ·
CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
2025-02 · CITER ·
Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
2024-10 · UniTe ·
Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling
2024-06 · GaC ·
Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
2024-04 · DeePEn ·
Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization
2024-04 · PackLLM ·
Bridging the Gap between Different Vocabularies for LLM Ensemble
2024-04 · EVA ·
Purifying large language models by ensembling a small language model
2024-02 ·

2.2.2 (b,2) Span-Level Ensemble

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
2026-01 · AdaFuse ·
RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
2025-06 · RLAE ·
Speculative Ensemble: Fast Large Language Model Ensemble via Speculation
2025-02 · Speculative Ensemble ·
SpecFuse: Ensembling Large Language Models via Next-Segment Prediction
2024-12 · SpecFuse ·
Hit the Sweet Spot! Span-Level Ensemble for Large Language Models
2024-09 · SweetSpan ·
Cool-Fusion: Fuse Large Language Models without Training
2024-07 · Cool-Fusion ·

2.2.3 (b,3) Process-Level Ensemble

Empirical Study of Process Reward-Guided Model Ensemble for Edge Reasoning
2026-05 ·
RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning
2026-03 · RouteGoT ·
Collaborative Beam Search: Enhancing LLM Reasoning via Collective Consensus
2025-11 · CBS ·
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
2024-12 · LE-MCTS ·

2.3 Ensemble After Inference

Figure 5: Summary analysis of the key attributes of ensemble-after-inference methods. (Please note that this table may not be fully updated to include all the papers listed below.)

2.3.1 (c,1) Non Cascade

A Jury, Not an Electorate: Label-Free Reliability Estimation for Ensembles of Language Models
2026-10 · Jury ·
CUSP: Decomposable Collective Uncertainty for Multi-Agent Multimodal Reasoning
2026-09 · CUSP ·
Mixture of Complementary Agents for Robust LLM Ensemble
2026-05 · MCA ·
SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systems
2026-03 · SCoOP ·
Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process
2025-12 · LLM-PeerReview ·
LLMartini: Seamless and Interactive Leveraging of Multiple LLMs through Comparison and Composition
2025-10 · LLMartini ·
Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations
2025-10 ·
Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
2025-10 · OW/ISP ·
Explainable Fault Localization for Programming Assignments via LLM-Guided Annotation
2025-09 · FLAME ·
CARGO: A Framework for Confidence-Aware Routing of Large Language Models
2025-09 · CARGO ·
LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration
2025-07 · LENS ·
EL4NER: Ensemble Learning for Named Entity Recognition via Multiple Small-Parameter Large Language Models
2025-05 · EL4NER ·
Weight Ensembling Improves Reasoning in Language Models
2025-04 · WiSE-FT ·
Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning
2025-03 · Symbolic-MoE ·
DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance
2025-01 · DFPE ·
Balancing Act: Diversity and Consistency in Large Language Model Ensembles
2025-01 · DMoA ·
Smoothie: Label Free Language Model Routing
2024-12 · Smoothie ·
LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation
2024-10 · LLM-Forest ·
LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity
2024-10 · LLM-TOPLA ·
Two Heads are Better than One: Zero-shot Cognitive Reasoning via Multi-LLM Knowledge Fusion
2024-10 · MLKF ·
URG: A Unified Ranking and Generation Method for Ensembling Language Models
2024-08 · URG ·
More Agents Is All You Need
2024-02 · Agent-Forest ·
LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
2023-06 · LLM-Blender ·
Getting MoRE out of Mixture of Language Model Reasoning Experts
2023-05 · MoRE ·

2.3.2 (c,2) Cascade

Who Pays for Efficient Inference? Confidence-Based Small-to-Large LLM Routing Across Tasks and Languages
2026-10 ·
Is Escalation Worth It? A Decision-Theoretic Characterization of LLM Cascades
2026-5 ·
RoBoN: Routed Online Best-of-n for Test-Time Scaling with Multiple LLMs
2025-12 · RoBoN ·
Semantic Agreement Enables Efficient Open-Ended LLM Cascades
2025-09 ·
EMAFusionTM: A Self-Optimizing System for Seamless LLM Selection and Integration
2025-04 · EMAFusionTM ·
Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute
2025-04 · ModelSwitch ·
Dynamic Ensemble Reasoning for LLM Experts
2024-12 · DER ·
A Unified Approach to Routing and Cascading for LLMs
2024-10 · Cascade Routing ·
Language Model Cascades: Token-level uncertainty and beyond
2024-04 ·
AutoMix: Automatically Mixing Language Models
2023-10 · AutoMix ·
Cache & Distil: Optimising API Calls to Large Language Models
2023-10 · neural caching ·
Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning
2023-10 ·
EcoAssistant: Using LLM Assistant More Affordably and Accurately
2023-10 · EcoAssistant ·
FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
2023-05 · FrugalGPT ·
When Does Confidence-Based Cascade Deferral Suffice?
2023-01 ·
Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems
2022-10 · Model Cascading ·

2.4 Others: Benchmarks, Applications, Systems and Related Surveys

2.4.1 Benchmarks

RouterWorld: Scaling Conversational AI with Latency-Aware LLM Routing
2026-10 · RouterWorld ·
LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing
2026-01 ·
Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process
2025-12 ·
RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers
2025-09 ·
FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data
2025-07 ·
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
2025-03 · RouterEval ·
RouterBench: A Benchmark for Multi-LLM Routing System
2024-03 · RouterBench ·
LLM-BLENDER: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
2023-06 · MixInstruct ·

2.4.2 Applications

Beyond the methods presented before, the concept of LLM Ensemble has found applications in a variety of more specialized tasks and domains. Here we give some examples:

Generating MeSH terms using large language models: From individual models to ensemble strategies
2026-10 ·
MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment
2026-09 · MERGE ·
Ensembling LLMs for AI-Augmented Cybersecurity Software Requirements Generation
2026-09 ·
BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration
2026-06 · BEATS ·
Extracting Social Determinants of Health From Electronic Health Records: Development and Comparison of Rule-Based and Large Language Model Methods
2026-05 ·
Scalable code generation with large language models: an open-source ensemble and reinforcement learning-based selector
2026 ·
Pneumonia Detection in Paediatric Chest X-Rays using Ensembled Large Language Models
2026-04 ·
Ensemble Strategies for LLM-based Text Summarization: A Timing-Based Framework
2026-02 ·
Next Generation Active Learning: Mixture of LLMs in the Loop
2026-01 ·
Explainable Fault Localization for Programming Assignments via LLM-Guided Annotation
2025-09 · FLAME ·
Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Large Language Models
2025-05 · Expert Orchestration ·
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
2025-04 · Consensus Entropy ·
Bayesian Calibration of Win Rate Estimation with LLM Evaluators
2024-11 · BWRS ·
FuseGen: PLM Fusion for Data-generation based Zero-shot Learning
2024-06 · FuseGen ·
PromptMind Team at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles
2024-05 ·
LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction
2024-02 ·
On Preserving the Knowledge of Long Clinical Texts
2023-11 ·
Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs
2023-10 · Ensemble-Instruct ·

2.4.3 Systems

A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
2026-06 · SMCS ·
TADEL: Task-Aware Dynamic Ensemble of Lightweight LLMs for Improved Inference Accuracy in Edge AI
2025-12 · TADEL ·
LLMartini: Seamless and Interactive Leveraging of Multiple LLMs through Comparison and Composition
2025-10 · LLMartini ·

2.4.4 Related Surveys

From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models
2026-09 ·
Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey
2026-02 ·
Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration
2025-07 ·
Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques
2025-06 ·
A Survey on Collaborative Mechanisms Between Large and Small Language Models
2025-05 ·
A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well
2025-03 ·
Doing More with Less – Implementing Routing Strategies in Large Language Model-Based Systems: An Extended Survey
2025-02 ·
Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems
2025-02 ·
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
2024-08 ·
A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning
2024-08 ·
Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models
2024-07 ·
Deep Model Fusion: A Survey
2023-09 ·
A comprehensive review on ensemble deep learning: Opportunities and challenges
2023-02 ·

3 Others: Some public implementations of the LLM Ensemble methods

Ensemble-Hub
2025 ·

4 Others: Some other related interesting papers

Here we briefly list some related papers, which are either discovered by us or suggested by the authors to this repository. They mainly focus on LLM Collaboration.

4.1 Test-Time Scaling

Agentic Systems as Boosting Weak Reasoning Models
2026-05 ·
The Law of Multi-Model Collaboration: Scaling Limits of Model Ensembling for Large Language Models
2025-12 ·
Stable LLM Ensemble: Interaction between Example Representativeness and Diversity
2025-10 ·

4.2 LLM Collaboration and Others

Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning
2026-07 · CanonicalMerge ·
Understanding Input-Output Uncertainty in LLM Routing Supervision
2026-06 ·
PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting
2026-06 · PerspectiveGap ·
Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning
2026-04 · Tandem ·
Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
2026-03 · CCPO ·
Adaptive Robust Estimator for Multi-Agent Reinforcement Learning
2026-03 · ARE ·
Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning
2025-12 · Consensus-Driven Reasoning ·
Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models
2025-12 · CogER ·
WISE: Weighted Iterative Society-of-Experts for Robust Multimodal Multi-Agent Debate
2025-12 · WISE ·
Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection
2025-10 · ColMAD ·
Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning
2025-10 · AdCo ·
Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation
2025-10 ·
Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
2025-09 · MoT ·
Best-of-∞ -- Asymptotic Performance of Test-Time LLM Ensembling
2025-09 · Best-of-∞ ·
Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM
2025-08 · SLC ·
An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation
2025-05 ·
Nature-Inspired Population-Based Evolution of Large Language Models
2025-03 · GENOME ·
If Multi-Agent Debate is the Answer, What is the Question?
2025-02 · Heter-MAD ·
LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation
2024-10 · LLM-Forest ·

4.3 Ensemble (or Routing) Methods for Long-Horizon Agent Tasks

Methods that perform ensemble-style selection or routing over closed-set choices during long-horizon agent workflows (e.g., tools, skills, apps, sub-agents, or models at intermediate steps), rather than one-shot query-to-LLM routing before inference.

TabAgent: Distilling LLM Agent Components into Cheap Classifiers
2026-02 · TabAgent ·

4.3.1 Benchmarks / Resources for Long-Horizon Agent Ensemble (or Routing)

Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution
2026-10 · EC2-Bench ·

5 Summarization

Figure 6: Summary analysis of the key attributes of LLM Ensemble approaches.

Rendered by GitHub from the current README

Read on GitHub

Top contributors

No contributor data yet — it is fetched during the contributor sync pass.

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

74/10074

Maintenance: 90%; How recently the default branch was pushed to
Releases: 25%; Recency and cadence of tagged releases
Community: 35%; Contributor breadth and bus factor
Issue backlog: 100%; Open issues measured against the size of the audience
Documentation: 100%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No tagged releases
Usable in commercial products with attribution.

Details

Created: 2 years ago
Last push: 8 days ago
Last release: none
Release tag: —
Releases in the last year: 0
Default branch: main
Size: 9.8k KB
Owner type: User
Owner location: Hong Kong
Discovered via: phrase:language model
First indexed: 3 months ago
Last synced: 8 days ago