Marc Jansen

Marcel Pehlke, Marc Jansen

We present a modular, explainable LLM-agent pipeline for decision support that externalizes reasoning into auditable artifacts. The system instantiates three frameworks: Vester's Sensitivity Model (factor set, signed impact matrix, systemic roles, feedback loops); normal-form games (strategies, payoff matrix, equilibria); and sequential games (role-conditioned agents, tree construction, backward induction), with swappable modules at every step. LLM components (default: GPT-5) are paired with deterministic analyzers for equilibria and matrix-based role classification, yielding traceable intermediates rather than opaque outputs. In a real-world logistics case (100 runs), mean factor alignment with a human baseline was 55.5\% over 26 factors and 62.9\% on the transport-core subset; role agreement over matches was 57\%. An LLM judge using an eight-criterion rubric (max 100) scored runs on par with a reconstructed human baseline. Configurable LLM pipelines can thus mimic expert workflows with transparent, inspectable steps.

Marc Jansen, Marcel Pehlke

This paper introduces an approach to increasing the explainability of artificial intelligence (AI) systems by embedding Large Language Models (LLMs) within standardized analytical processes. While traditional explainable AI (XAI) methods focus on feature attribution or post-hoc interpretation, the proposed framework integrates LLMs into defined decision models such as Question-Option-Criteria (QOC), Sensitivity Analysis, Game Theory, and Risk Management. By situating LLM reasoning within these formal structures, the approach transforms opaque inference into transparent and auditable decision traces. A layered architecture is presented that separates the reasoning space of the LLM from the explainable process space above it. Empirical evaluations show that the system can reproduce human-level decision logic in decentralized governance, systems analysis, and strategic reasoning contexts. The results suggest that LLM-driven standard processes provide a foundation for reliable, interpretable, and verifiable AI-supported decision making.

Aleksei Pupyshev, Dmitry Gubanov, Elshan Dzhafarov et al.

This paper intends to propose the architecture of a blockchain-agnostic protocol designed for communication of blockchains amongst each other (i.e. cross-chain), and for blockchains with the outside world (i.e. data oracles). The expansive growth of cutting-edge technology in the blockchain industry outlines the need and opportunity for addressing oracle consensus in a manner both technologically and economically efficient as well as futureproof. Blockchain-agnosticism is inherently limited if proposing a technological solution involves adding one more architectural layer. As such, Gravity protocol is designed to be a truly blockchain-agnostic protocol. By ensuring parity through direct integration and by leveraging the stability and security of the respective interconnected ecosystems, Gravity circumvents the need for a dedicated, public blockchain and a native token. Ultimately, Gravity protocol intends to address scalability challenges by providing a solid infrastructure for the creation of gateways, cross-chain applications, and sidechains. This paper introduces and defines the concept of Oracle Consensus and its implementation in the Gravity protocol named the Pulse Consensus algorithm. The proposed consensus architecture allows Gravity to be considered a singular decentralized blockchain-agnostic oracle.