# Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis

arXiv: https://arxiv.org/abs/2609.31422 · HTML: https://mlsanity.com/paper/2609.31422/

## Key facts

- No citing papers in the map yet (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 17 of its 21 references that are in the map.
- First posted on arXiv 25 Sep 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, 17 of 17)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (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)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [Factuality of Large Language Models: A Survey](https://mlsanity.com/paper/2402.02420/) (2024)
- [PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows](https://mlsanity.com/paper/2508.02866/) (2025)
- [From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization](https://mlsanity.com/paper/2410.13961/) (2024)
- [Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2507.21354/) (2025)
- [TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Education](https://mlsanity.com/paper/2510.17913/) (2025)
- [Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation](https://mlsanity.com/paper/2606.10475/) (2026)

## Abstract (arXiv)

Large language model-based multi-agent debate (MAD) systems are being increasingly used as complex decision pipelines in distributed processes. However, their final synthesis phase still remains inadequately controlled. Even with detailed debate logs, summarizing models are prone to fabricating smoothly written debate consensus that is not grounded in the debate's history. To address this safety gap, this paper presents empirical research and studies if the introduction of active post-debate verification can mitigate the production of such factually unsupported summaries, while still providing valuable information. Furthermore, it is examined whether explicitly signalling divergence is preferable in the absence of a reliable compromise. The Active Provenance Gate (APG) is introduced as a post-debate verification layer that treats the source as a hard constraint, analysing the debate logs, auditing each claim, and applying self-correction. In crisis simulations, the self-healing mechanism more than doubles the average data Provenance Fidelity in difficult condition scenarios, before the strict gate blocks unsupported claims and generates divergence reports. In the human study, a vast majority of the users (over 75%) preferred a report explicitly stating failure in critical scenarios, despite most of them perceiving fabricated consensus from the baseline system as more fluent. Our main contribution is the transition of data origin tracing from passive logging to active conditional blocking before publication.