# Beyond Consensus: Trace-Level Synthesis in Mixture of Agents

arXiv: https://arxiv.org/abs/2605.29116 · HTML: https://mlsanity.com/paper/2605.29116/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 30 of 39)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [Confidence Improves Self-Consistency in LLMs](https://mlsanity.com/paper/2502.06233/) (2025)
- [Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?](https://mlsanity.com/paper/2508.17536/) (2025)
- [Tailor: Generating and Perturbing Text with Semantic Controls](https://mlsanity.com/paper/2107.07150/) (2021)
- [SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models](https://mlsanity.com/paper/2403.02509/) (2024)
- [Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens](https://mlsanity.com/paper/2505.13775/) (2025)
- [Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!](https://mlsanity.com/paper/2504.09762/) (2025)
- [Boosted Prompt Ensembles for Large Language Models](https://mlsanity.com/paper/2304.05970/) (2023)
- [Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach](https://mlsanity.com/paper/1705.07086/) (2017)
- [Provable Scaling Laws for the Test-Time Compute of Large Language Models](https://mlsanity.com/paper/2411.19477/) (2024)
- [Ranked Voting based Self-Consistency of Large Language Models](https://mlsanity.com/paper/2505.10772/) (2025)
- [How to Correctly do Semantic Backpropagation on Language-based Agentic Systems](https://mlsanity.com/paper/2412.03624/) (2024)
- [Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge](https://mlsanity.com/paper/2602.09341/) (2026)
- [Mirror-Consistency: Harnessing Inconsistency in Majority Voting](https://mlsanity.com/paper/2410.10857/) (2024)

## Built on by (most cited first, 4 of 4)

- [Stage-Replay Divergence Follows the KV Cache: Fixed-Prefix Precision Controls and Bidirectional Cache Transplantation](https://mlsanity.com/paper/2607.28495/) (2026)
- [Decomposing Wrong-Consensus Agreement in LLM Self-Consistency](https://mlsanity.com/paper/2608.18795/) (2026)
- [UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model](https://mlsanity.com/paper/2609.09815/) (2026)
- [Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation](https://mlsanity.com/paper/2610.18786/) (2026)

## Abstract (arXiv)

When multiple LLM agents solve the same problem, standard practice compresses each agent's reasoning into a majority vote or layered synthesis, treating agreement as the finish line. We show this is unnecessarily lossy: an LLM aggregator that reads complete reasoning traces recovers correct solutions even when agents unanimously agree, with beneficial corrections consistently outweighing harmful ones -- the aggregation paradox. Majority voting has a ceiling that perturbation diversity does not raise (error correlations are identical); the aggregator's gain comes from trace-level complementarity, assembling correct intermediate steps from minority chains that voting discards. These findings motivate Self-Consistent Mixture of Agents which generates trace diversity through semantic-preserving input perturbations, safeguards the majority via anchored refinement with provable non-degradation guarantees, and always synthesizes -- never gates on consensus. A single model with perturbation-induced trace variation outperforms heterogeneous model pools across structured reasoning, PhD-level science, competition mathematics, and competitive programming. The unit of aggregation should be the reasoning trace, not the answer.