Skip to content

Repository files navigation

MRRA: An Auditable Reasoning Control Architecture for Role-Specialized LLM Ensembles

DOI License: CC BY 4.0

From Consensus to Audit — Transforming multi-LLM reasoning from answer optimization into auditable decision evidence.

Overview

While current multi-agent reasoning frameworks (Multi-Agent Debate, ReConcile, ECON) focus on maximizing accuracy and driving agents toward consensus, high-stakes decisions require a different objective. Under risk, a definitive answer is less valuable than an auditable decision trace that explicitly surfaces hidden assumptions, conflicts, and minority warnings.

MRRA is a state-machine-based reasoning control architecture (S0–S7) that permits non-convergence, limits overconfidence, and prioritizes audit trail generation over forced consensus.

This repository contains the technical report, specification, analysis, and case studies for MRRA v0.1.1. The framework is implemented as the MRRA Core v0.8.0 skill for Hermes Agent.


Core Architecture

MRRA operates across three tightly integrated layers:

                  S0 [User Query]
                         │
              ┌──────────▼──────────┐
              │ 1. Problem Reframer │ ◄─── (S1 Heuristics)
              └──────────┬──────────┘
                         │ Surfaced Assumptions
              ┌──────────▼──────────┐
              │ 2. Triangulated     │ ◄─── (S3 Solver/Skeptic/Alternative)
              │    Evaluator        │ ───► Interference Layer (4-Axis Analysis)
              └──────────┬──────────┘
                         │ Competing Perspectives
              ┌──────────▼──────────┐
              │ 3. Revision         │ ◄─── (S4/S5 Persistent Registry)
              │    Controller       │ ───► Confidence Cap & Stopping Rules
              └──────────┬──────────┘
                         │
             S7 [Auditable Decision Evidence] (Conditional Recommendation)

Core 1: Problem Reframer

Deconstructs and reframes questions using six cognitive heuristics (abstraction, decomposition, lateral reframing, estimation, projection, assumption elicitation) to surface implicit assumptions before evaluation begins.

Core 2: Triangulated Evaluator

Employs three role-specialized agents — Solver (constructs the strongest solution), Skeptic (detects risks and contradictions), and Alternative (proposes reframings) — to evaluate candidate directions. Uses the Interference Layer to classify cross-role outputs into four categories:

Classification Definition Downstream Action
Agreement Independent convergence across roles Accepted as high-confidence evidence
Conflict Contradictory conclusions Triggers Revision Controller return
Complement Each role addresses different facets Integrated to strengthen conclusion
Absence / Absent Warning A high-impact concern raised by only one role or absent from dominant consensus Preserved and must be reviewed before final aggregation (protects minority views from majority pressure)

When comparative decision-making is needed, candidates are scored via MCDA (six axes: independent agreement, evidence strength, logical consistency, implementability, risk controllability, originality).

Core 3: Revision Controller

Maintains a persistent Assumption Registry (audit trail of every assumption with confidence, importance, and verification status) and applies structural confidence governance:

  • Confidence Cap: Critical + Low assumptions cap final confidence at Medium.
  • Stopping Conditions (clean termination): all critical assumptions verified, conflicts within threshold, absent warnings reviewed, MCDA margin satisfied (when active).
  • Conditional Termination: when clean conditions fail, recommendation is conditional on resolving residual uncertainties. MRRA permits non-convergence rather than forcing an unverified conclusion.

Key Contributions

  1. C1: Reasoning Control Architecture — A structured, recursively-controlled state machine (S0–S7) designed for traceability rather than simple conversational debate.

  2. C2: Interference Analysis & Absent Promotion — A structured evaluation primitive that prevents minority warnings (Absence) from being erased by majority pressure.

  3. C3: Conservative Confidence Governance — A mechanism that caps final confidence based on unverified assumptions, conflicts, and absent warnings, producing conditional recommendations under residual risk.


Repository Structure

File Description
MRRA-Technical-Report-v0.1.1.pdf Compiled technical report published on Zenodo (v0.1.1, June 10, 2026).
MRRA-Technical-Report-v0.1.1.md Markdown source of the Technical Report / Extended Abstract.
MRRA-Technical-Report-v0.1.1-package.zip Complete snapshot bundle for reproducibility.
case-study-zero23w-v0.1.md Case Study 2: Web access-control design evaluation (domain contrast against crypto trading).
related-work-matrix-v0.1.md 13-paper × 10-dimension positioning matrix, mapping MRRA against the SOTA.
related-work-structure-v0.1.md Literature review section structure, contribution mapping, and 7-element uniqueness table.
extended-abstract-v0.1.md Extended abstract summarizing the MRRA framework.
references.bib Comprehensive BibTeX database of surveyed literature, including the MRRA Zenodo DOI.

Positioning Against Related Work

Among surveyed works, MRRA is designed with a focus on auditability and structural uncertainty control rather than benchmark-optimized convergence:

Dimension Debate Frameworks (MAD / DMAD / ReConcile) Game-theoretic (ECON) Calibration (UQ / FermiEval) MRRA (This Work)
Primary Goal Accuracy / consensus Equilibrium / efficiency Statistical coverage Auditability / decision trace
Assumption Tracking None None None Persistent Registry (Audit Trail)
Minority Protection Weak None None Absent Promotion (Mandatory Review)
Confidence Handling Self-reported or calibrated Implicit (belief) Probabilistic calibration Structural Capping under Unresolved Risk
Evaluation Target Benchmark accuracy Benchmark performance CI coverage Assumption coverage / risk detection

"Among surveyed works, we did not identify prior work that jointly treats these mechanisms as first-class components of a reasoning-control architecture."

The full 13-paper comparative matrix with explicit MRRA positioning is available in related-work-matrix-v0.1.md.


Case Studies

Case 1: Trading Strategy Evaluation (bitflyerbot)

A L2.5 strategy change for a crypto trading bot was evaluated through MRRA Deep mode. The Interference Layer detected 3 Conflicts, 1 Agreement, 2 Complements, and 4 Absence warnings. MCDA scored the best candidate at 4.4/10. The Solver's proposal was rejected — Confidence Cap activated due to Critical+Low assumptions about market regime persistence.

Case 2: Web Access-Control Decision (zero23w)

A proposed policy change (retroactively restricting publicly accessible magazine issues to premium-only) was evaluated. The Interference Layer identified a key Absent Warning — the notification process design was missing from all perspectives. Two Critical+Low assumptions triggered the Confidence Cap. Final recommendation was conditional on three preconditions.

Metric bitflyerbot zero23w
Assumptions surfaced 9 (Deep) 9 (Deep)
Critical risk detected 3 2
Absent warnings preserved 4 1
Confidence Cap activated Yes Yes
Recommendation type Conditional Conditional

Citation

If you use MRRA in your research, please cite the Technical Report as follows:

@techreport{maruko2026mrra,
  title={MRRA: An Auditable Reasoning Control Architecture for Role-Specialized LLM Ensembles},
  author={Maruko, Yoshifumi},
  institution={Zenodo},
  year={2026},
  number={v0.1.1},
  doi={10.5281/zenodo.20618374},
  url={https://doi.org/10.5281/zenodo.20618374}
}

Implementation

MRRA is implemented as a production-grade skill set for Hermes Agent. The core implementation includes:

  • mrra-core (v0.8.0) — Full S0–S7 state machine, Assumption Registry, CLI tools
  • triangulated-reasoning (v4.2.0) — Role-specialized Solver/Skeptic/Alternative evaluation
  • marukoshiki-reasoning — Six-cognitive-heuristic problem reframing
  • Interference Layer — 4-axis structured cross-perspective analysis
  • MCDA Module — 6-axis multi-criteria decision scoring with observation preset profiles

Implementation source is available under the MRRA Core Skill repository.


Related Publications


License

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


For detailed specifications, refer to the MRRA Technical Report PDF or contact the author through the repository issues.

About

Monju Reasoning Core — MRRA Technical Report. Auditable Reasoning Control Architecture for Role-Specialized LLM Ensembles.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors