cs.AINov 9, 2026

Reconfigurable Action Theories: A Formal Foundation for Dynamically Composable Agent Harnesses

Authors: Jianmin Ji

Organizations: University of Science and Technology of China, Hefei, 230026, China

Abstract

Action theories typically fix their vocabulary and causal laws, whereas agent harnesses can change their tools, providers, and policies during execution. We introduce Reconfigurable Action Theories (RAT), in which actions can change the action theory itself. A theory module in RAT contains a vocabulary, causal laws, and an initializer. A RAT configuration records the active modules and the world state. Module loading and unloading are represented by actions governed by ordinary causal laws. RAT retains the standard causal action semantics of its language fragment when the active module set is fixed. We give sufficient conditions for at most one next configuration, preservation of existing behavior when a module is added, and equal results when modules are loaded in either order. We establish the computational complexity of reasoning tasks in RAT and translate finite RAT systems into nonmonotonic causal theories and Answer Set Programming (ASP), preserving bounded executions. Experiments compare finite RAT models with executions of official DeepSeek Harness, Pi, and OpenHands implementations. RAT provides a formal basis for checking how component changes affect a harness's available actions, behavior, and reachable goals.

Figures & tables

Explore similar work

CardsList
  1. HarnessMM: Recursive Self-Improvement for Harness Token Efficiency

    Oct 23, 2026Yuhua Jiang, Chang Xu, Feifei Gao +1Agent Harness OptimizationLLM Agent Efficiency

  2. Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

    Jul 14, 2026Ruhan Wang, Yucheng Shi, Zongxia Li +7Software Engineering AgentsCode Localization

  3. Natural-Language Agent Harnesses

    Mar 26, 2026Linyue Pan, Lexiao Zou, Shuo Guo +2LLM Agent HarnessesLLM Agent Orchestration