Volition Elicitation: Operational Semantics for People and Their Machines

2026-07-10

AI Summary

This work addresses the lack of explicit modeling of human intent in existing distributed systems, which hinders effective coordination between users and their personal devices. The paper proposes vGLP (volitional Guarded Language for Programming) along with its operational semantics, formally integrating human intent as a core element of program semantics for the first time and establishing an operational framework for human–machine collaboration. Intent is captured through user interfaces and automatically mapped from abstract transactions to concrete interactions via Communicating Volitional Agents, multi-agent atomic transactions, and AI-driven code generation. A smartphone application incorporating social graphs, social networking features, and a monetary system demonstrates the feasibility and practicality of this intent-driven architecture.

Abstract

The most prevalent distributed systems today include people and their personal machines (smartphones). In such systems, computations are driven by people's volitions: a payment when a person wishes to pay someone, befriending when two people wish to become friends, etc. Volition-Guarded Multiagent Atomic Transactions were proposed as an abstract specification language for such systems, in which each agent consists of a person and their machine, and a transaction can be guarded by both the machine states and the personal volitions of its participating agents. Here, we define the programming language volition-guarded GLP (vGLP), which extends GLP with volition-guarded clauses, and define its operational semantics as an instance of Communicating Volitional Agents. As the semantics requires the person to will a volition-guarded clause reduction, a correct implementation must elicit the person's volitions: finding out ``what's in the person's head'' is the sole rationale for the UI, which is realised accordingly by standard constructs. We demonstrate the approach on the grassroots social graph, social network, and currencies: each platform is a vGLP program, generated by AI from volition-guarded multiagent atomic transactions; the implementation of vGLP, also created by AI, then maps its volition-guarded clauses into the user-interface constructs, resulting in a single working app deployed on a physical smartphone.

Problem

• volition elicitation
• distributed systems
• human-machine interaction
• multiagent transactions
• user intention

Innovation

• volition-guarded programming
• operational semantics
• multiagent atomic transactions
• human-in-the-loop systems
• AI-generated user interfaces