If You Want Coherence, Orchestrate a Team of Rivals: Multi-Agent Models of Organizational Intelligence
- URL: http://arxiv.org/abs/2601.14351v1
- Date: Tue, 20 Jan 2026 17:19:09 GMT
- Title: If You Want Coherence, Orchestrate a Team of Rivals: Multi-Agent Models of Organizational Intelligence
- Authors: Gopal Vijayaraghavan, Prasanth Jayachandran, Arun Murthy, Sunil Govindan, Vivek Subramanian,
- Abstract summary: We show that we can achieve reliability without acquiring perfect components, but through careful orchestration of imperfect ones.<n>This paper describes the architecture of such a system in practice: specialized agent teams (planners, executors, critics, experts)<n>We demonstrate the approach achieves over 90% internal error interception prior to user exposure while maintaining acceptable latency tradeoffs.
- Score: 1.1637186977447433
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
arXiv Detail & Related papers (2026-01-21T15:22:21Z) - Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
arXiv Detail & Related papers (2025-12-20T12:06:13Z) - Async Control: Stress-testing Asynchronous Control Measures for LLM Agents [2.7146936326590425]
We investigate asynchronous monitoring, in which a monitoring system reviews agent actions after the fact.<n>Unlike synchronous monitoring, this approach does not impose runtime latency, while still attempting to disrupt attacks before irreversible harm occurs.<n>We treat monitor development as an adversarial game between a blue team (who design monitors) and a red team (who create sabotaging agents)
arXiv Detail & Related papers (2025-12-15T16:56:28Z) - Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning [84.70211451226835]
Large Language Model (LLM) Agents are constrained by a dependency on human-curated data.<n>We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data.<n>Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks.
arXiv Detail & Related papers (2025-11-20T05:01:57Z) - Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents [58.00130492861884]
TraitBasis is a lightweight, model-agnostic method for systematically stress testing AI agents.<n>TraitBasis learns directions in activation space corresponding to steerable user traits.<n>We observe on average a 2%-30% performance degradation on $tau$-Trait across frontier models.
arXiv Detail & Related papers (2025-10-06T05:03:57Z) - Get Experience from Practice: LLM Agents with Record & Replay [16.179801770737892]
This paper proposes a new paradigm called AgentRR (Agent Record & Replay), which introduces the classical record-and-replay mechanism into AI agent frameworks.<n>We detail a multi-level experience abstraction method and a check function mechanism in AgentRR.<n>In addition, we explore multiple application modes of AgentRR, including user-recorded task demonstration, large-small model collaboration and privacy-aware agent execution.
arXiv Detail & Related papers (2025-05-23T10:33:14Z) - When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
arXiv Detail & Related papers (2025-02-21T02:24:43Z) - Preventing Rogue Agents Improves Multi-Agent Collaboration [21.955058255432974]
We propose to monitor agents during action prediction and intervene when a future error is likely to occur.<n>Experiments on WhoDunitEnv, code generation tasks and the GovSim environment for resource sustainability show that our approach leads to substantial performance gains.
arXiv Detail & Related papers (2025-02-09T18:35:08Z) - Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
arXiv Detail & Related papers (2024-06-18T17:32:48Z) - A Zero-Shot Language Agent for Computer Control with Structured
Reflection [19.526676887048662]
Large language models (LLMs) have shown increasing capacity at planning and executing a high-level goal in a live computer environment.
To perform a task, recent works often require a model to learn from trace examples of the task via either supervised learning or few/many-shot prompting.
We approach this problem with a zero-shot agent that requires no given expert traces.
arXiv Detail & Related papers (2023-10-12T21:53:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.