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

arXiv: https://arxiv.org/abs/2607.27783 · HTML: https://mlsanity.com/paper/2607.27783/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 23 of 23)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [FOLIO: Natural Language Reasoning with First-Order Logic](https://mlsanity.com/paper/2209.00840/) (2022)
- [MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning](https://mlsanity.com/paper/2310.16049/) (2023)
- [A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering](https://mlsanity.com/paper/2005.05257/) (2020)
- [Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning](https://mlsanity.com/paper/2412.15797/) (2024)
- [ReasoningFlow: Semantic Structure of Complex Reasoning Traces](https://mlsanity.com/paper/2506.02532/) (2025)
- [Multi-LLM Collaborative Search for Complex Problem Solving](https://mlsanity.com/paper/2502.18873/) (2025)
- [Efficient Dynamic Ensembling for Multiple LLM Experts](https://mlsanity.com/paper/2412.07448/) (2024)
- [HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs](https://mlsanity.com/paper/2601.18753/) (2026)
- [ARGORA: Orchestrated Argumentation for Causally Grounded LLM Reasoning and Decision Making](https://mlsanity.com/paper/2601.21533/) (2026)
- [Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning](https://mlsanity.com/paper/2605.09292/) (2026)

## Built on by (most cited first, 2 of 2)

- [OrchSLM: Probing the Dynamics of Small Language Model Orchestration](https://mlsanity.com/paper/2609.13470/) (2026)
- [Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces](https://mlsanity.com/paper/2610.18606/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) explore problems through chain-of-thought, but this exploration is buried in unstructured prose. On high-stakes tasks, users cannot tell which steps are well-supported, which alternatives were seriously considered, or how the final conclusion compares to those the model discarded. We propose a framework that ensembles the reasoning structure, not just the answers, of multiple LLMs by weighted merging of Directed Acyclic Graphs (DAGs) extracted from reasoning chains. We weight each step by how many traces independently attest to it, to return "Consensus Reasoning". Across six benchmarks spanning statutory interpretation, graduate-level science, narrative multi-hop reasoning, and first-order logic, our ensemble outperforms a matched-budget majority-vote baseline, with a maximum accuracy gain of 3.1% on MuSR-MM (narrative multi-hop reasoning). On a single model, the framework matches or exceeds self-consistency at the same trace budget while additionally exposing an inspectable consensus reasoning graph. Ensemble weights correlate with LLM-judge rankings of reasoning quality at Spearman ρ = 0.30-0.51, and consensus subgraphs are preferred over alternatives leading to the majority-vote answer in 54.4-65.4% of head-to-head comparisons across five of six datasets. We observe that our framework can also be used to analyze diverse reasoning perspectives for a problem.