# Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias

arXiv: https://arxiv.org/abs/2604.02923 · HTML: https://mlsanity.com/paper/2604.02923/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 18 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)
- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 16 of 16)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [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)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?](https://mlsanity.com/paper/2502.00674/) (2025)
- [Correlated Errors in Large Language Models](https://mlsanity.com/paper/2506.07962/) (2025)
- [LLMs Can Generate a Better Answer by Aggregating Their Own Responses](https://mlsanity.com/paper/2503.04104/) (2025)
- [Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks](https://mlsanity.com/paper/2406.08598/) (2024)
- [DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity](https://mlsanity.com/paper/2602.11685/) (2026)
- [Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs](https://mlsanity.com/paper/2509.00084/) (2025)
- [Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge](https://mlsanity.com/paper/2505.19477/) (2025)
- [Progressive Document-level Text Simplification via Large Language Models](https://mlsanity.com/paper/2501.03857/) (2025)

## Built on by (most cited first, 1 of 1)

- [Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems](https://mlsanity.com/paper/2609.02750/) (2026)

## Abstract (arXiv)

Long-form research questions often require answers that combine complementary details, reconcile conflicting estimates, and retain qualifications across several large language model (LLM) outputs. We present an inspectable LLM Council with two synthesis stages: an analyst organizes three independent candidate answers into a structured textual state, and a separately invoked writer composes the final response from the question and that state. We evaluate the workflow on 100 closed-book tasks from the Deep Research Accuracy, Completeness, and Objectivity (DRACO) benchmark, retaining 600 final answers, 100 analyst states, and 720 whole-answer judgments. Under the primary rubric judge, Council scores 70.98, exceeding GPT and Gemini by 6.18 and 8.34 points; its 0.47-point difference from Claude has a 95% paired interval of [-0.69,1.61]. In the four-arm fusion comparison, Council scores 1.87 points above direct fusion (95% paired interval [0.33,3.48]) and covers 51.1% of positive criteria covered by exactly one candidate, compared with 43.7% for direct fusion. On an exploratory 68-task subset with matching returned model labels, direct fusion scores higher. The full comparison characterizes workflows that differ in structure and generation budget; estimating the analyst stage's effect requires a controlled component study. Traced cases show how selected estimates, provenance qualifications, and selection decisions pass through the saved state into final answers.