# Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning

arXiv: https://arxiv.org/abs/2512.21699 · HTML: https://mlsanity.com/paper/2512.21699/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Survey on Evaluation of LLM-based Agents](https://mlsanity.com/paper/2503.16416/) (2025)
- [Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://mlsanity.com/paper/2309.14348/) (2023)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [Data-efficient Fine-tuning for LLM-based Recommendation](https://mlsanity.com/paper/2401.17197/) (2024)
- [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models](https://mlsanity.com/paper/2404.01230/) (2024)
- [Harnessing Multiple Large Language Models: A Survey on LLM Ensemble](https://mlsanity.com/paper/2502.18036/) (2025)
- [Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments](https://mlsanity.com/paper/1909.11800/) (2019)
- [A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1](https://mlsanity.com/paper/2502.10867/) (2025)
- [Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement](https://mlsanity.com/paper/2508.18765/) (2025)
- [A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows](https://mlsanity.com/paper/2512.08769/) (2025)
- [Agentsway -- Software Development Methodology for AI Agents-based Teams](https://mlsanity.com/paper/2510.23664/) (2025)
- [Standardization of Psychiatric Diagnoses -- Role of Fine-tuned LLM Consortium and OpenAI-gpt-oss Reasoning LLM Enabled Decision Support System](https://mlsanity.com/paper/2510.25588/) (2025)
- [Proof-of-TBI -- Fine-Tuned Vision Language Model Consortium and OpenAI-o3 Reasoning LLM-Based Medical Diagnosis Support System for Mild Traumatic Brain Injury (TBI) Prediction](https://mlsanity.com/paper/2504.18671/) (2025)
- [Model Context Contracts - MCP-Enabled Framework to Integrate LLMs With Blockchain Smart Contracts](https://mlsanity.com/paper/2510.19856/) (2025)
- [LLM Driven Processes to Foster Explainable AI](https://mlsanity.com/paper/2511.07086/) (2025)

## Built on by (most cited first, 14 of 14)

- [A Practical Guide to Agentic AI Transition in Organizations](https://mlsanity.com/paper/2602.10122/) (2026)
- [An Agentic Approach to Generating XAI-Narratives](https://mlsanity.com/paper/2603.20003/) (2026)
- [AI Trust OS -- A Continuous Governance Framework for Autonomous AI Observability and Zero-Trust Compliance in Enterprise Environments](https://mlsanity.com/paper/2604.04749/) (2026)
- [Flowr -- Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains](https://mlsanity.com/paper/2604.05987/) (2026)
- [Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support](https://mlsanity.com/paper/2604.18302/) (2026)
- [Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents](https://mlsanity.com/paper/2604.25684/) (2026)
- [Towards an Agent-First Web: Redesigning the Web for AI Agents](https://mlsanity.com/paper/2606.19116/) (2026)
- [An Agentic AI Control Plane for 6G Network Slice Orchestration, Monitoring, and Trading](https://mlsanity.com/paper/2602.13227/) (2026)
- [MindGap: A Conversational AI Framework for Upstream Neuroplastic Intervention in Post-Traumatic Stress Disorder](https://mlsanity.com/paper/2605.14660/) (2026)
- [Agentic Explainability at Scale: Between Corporate Fears and XAI Needs](https://mlsanity.com/paper/2604.14984/) (2026)
- [Train the Trainers -- An Agentic AI Framework for Peer-Based Mental Health Support in Battlefield Environments](https://mlsanity.com/paper/2605.16269/) (2026)
- [Human-AI Agent Interaction as a Neuroplastic Training Environment](https://mlsanity.com/paper/2607.12823/) (2026)
- [Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents](https://mlsanity.com/paper/2607.15095/) (2026)
- [BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines](https://mlsanity.com/paper/2609.28557/) (2026)

## Abstract (arXiv)

Agentic AI represents a major shift in how autonomous systems reason, plan, and execute multi-step tasks through the coordination of Large Language Models (LLMs), Vision Language Models (VLMs), tools, and external services. While these systems enable powerful new capabilities, increasing autonomy introduces critical challenges related to explainability, accountability, robustness, and governance, especially when agent outputs influence downstream actions or decisions. Existing agentic AI implementations often emphasize functionality and scalability, yet provide limited mechanisms for understanding decision rationale or enforcing responsibility across agent interactions. This paper presents a Responsible(RAI) and Explainable(XAI) AI Agent Architecture for production-grade agentic workflows based on multi-model consensus and reasoning-layer governance. In the proposed design, a consortium of heterogeneous LLM and VLM agents independently generates candidate outputs from a shared input context, explicitly exposing uncertainty, disagreement, and alternative interpretations. A dedicated reasoning agent then performs structured consolidation across these outputs, enforcing safety and policy constraints, mitigating hallucinations and bias, and producing auditable, evidence-backed decisions. Explainability is achieved through explicit cross-model comparison and preserved intermediate outputs, while responsibility is enforced through centralized reasoning-layer control and agent-level constraints. We evaluate the architecture across multiple real-world agentic AI workflows, demonstrating that consensus-driven reasoning improves robustness, transparency, and operational trust across diverse application domains. This work provides practical guidance for designing agentic AI systems that are autonomous and scalable, yet responsible and explainable by construction.