# If You Want Coherence, Orchestrate a Team of Rivals: Multi-Agent Models of Organizational Intelligence

arXiv: https://arxiv.org/abs/2601.14351 · HTML: https://mlsanity.com/paper/2601.14351/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 16 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Harnessing Multiple Large Language Models: A Survey on LLM Ensemble](https://mlsanity.com/paper/2502.18036/) (2025)
- [Probabilistic Consensus through Ensemble Validation: A Framework for LLM Reliability](https://mlsanity.com/paper/2411.06535/) (2024)
- [Multi-LLM Collaboration for Medication Recommendation](https://mlsanity.com/paper/2512.05066/) (2025)

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

- [From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company](https://mlsanity.com/paper/2604.22446/) (2026)
- [Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents](https://mlsanity.com/paper/2608.15008/) (2026)

## Abstract (arXiv)

AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues are rarely written down. We did not come to fire them for their mistakes, but to hire them and provide a safe productive working environment. We posit that we can reuse a common corporate organizational structure: teams of independent AI agents with strict role boundaries can work with common goals, but opposing incentives. Multiple models serving as a team of rivals can catch and minimize errors within the final product at a small cost to the velocity of actions. In this paper we demonstrate that we can achieve reliability without acquiring perfect components, but through careful orchestration of imperfect ones. This paper describes the architecture of such a system in practice: specialized agent teams (planners, executors, critics, experts), organized into an organization with clear goals, coordinated through a remote code executor that keeps data transformations and tool invocations separate from reasoning models. Rather than agents directly calling tools and ingesting full responses, they write code that executes remotely; only relevant summaries return to agent context. By preventing raw data and tool outputs from contaminating context windows, the system maintains clean separation between perception (brains that plan and reason) and execution (hands that perform heavy data transformations and API calls). We demonstrate the approach achieves over 90% internal error interception prior to user exposure while maintaining acceptable latency tradeoffs. A survey from our traces shows that we only trade off cost and latency to achieve correctness and incrementally expand capabilities without impacting existing ones.