FDRP

Manufacturing Quality Control for Complex Project Planning

A self-evolving architecture that treats planning decisions as manufactured artifacts with measurable convergence

Read the Paper (PDF) v14.0 · ~50 pages

Key Numbers

58 Production Runs
1,279 Tracked Decisions
6,052 Antimatter Findings
292 Expert Specialists

Abstract

Planning for complex systems lacks the convergence metrics and defect detection that manufacturing achieved through six decades of statistical process control. FDRP addresses this gap by treating each planning decision as a manufactured artifact with measurable convergence and gate-reviewed quality, applying SPC, 5S, RAMS, Andon, and configuration freeze directly to planning. Applied across 58 production runs (1,279 decisions), the system's strongest empirical contribution is the antimatter building programme: 292 LLM-generated expert specialists across five rounds produced 87,000+ lines of analysis and 6,052 structured findings, discovering expert persistence as an emergent operational pattern. Cross-model verification with 3 independent LLMs revealed 4 systematic bias patterns, suggesting that N≥3 models are needed for blind spot detection. Cross-domain validation on earthquake seismology and power grid data provides preliminary evidence that the sparse-principle thesis generalises. We propose progressive disclosure as the unifying architecture—a hypothesis under test.

FDRP Statistical Process Control Progressive Disclosure Expert Expansion Engineering Review Gates Self-Evolving Systems Cross-Model Verification

How It Works

Convergence Velocity Tensor (CVT)

The CVT measures planning quality as a diamond with four axes: decision stability, coverage completeness, clash resolution rate, and expert consensus. Each axis is independently measurable using SPC control charts, and the composite tensor tracks convergence across gates.

Six-Phase Gate Lifecycle

KICKOFF PDR CDR FDR TRR PQR

Each gate enforces monotonic convergence: decisions can only tighten, never regress. Violations trigger Andon stops and root cause analysis.

Framework Comparison

Framework Convergence Metrics Traceability Clash Detection Grounding Self-Evolution Cross-Model
FDRP
AutoGPT
CrewAI
LangGraph
MAPE-K

Native support Partial Absent

Correction Notice

Cite This Work

BibTeX
@article{olos2026fdrp,
  title   = {FDRP: A Self-Evolving Architecture for Planning Quality},
  author  = {Olos, L.},
  year    = {2026},
  note    = {Preprint},
  url     = {https://fdrp.liviu.ai/paper/FDRP-Paper-v14.pdf}
}