mlsanityData to 14 Oct 2026

Requirement-Based Testing: Enhancing Reinforcement Learning with Game Theory

arXiv 2407.18994 ↗First posted 26 Jul 2024cs.AI cs.GT cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

We consider the automatic online synthesis of black-box test cases from functional requirements specified as automata for reactive implementations. The goal of the tester is to reach some given state, so as to satisfy a coverage criterion, while monitoring the violation of the requirements. We develop an approach based on Monte Carlo Tree Search, which is a classical technique in reinforcement learning for efficiently selecting promising inputs. Seeing the automata requirements as a game between the implementation and the tester, we develop a heuristic by biasing the search towards inputs that are promising in this game. We experimentally show that our heuristic accelerates the convergence of the Monte Carlo Tree Search algorithm, thus improving the performance of testing.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 3 of its 50 references that are in the map. First posted on arXiv 26 Jul 2024.

Builds on

3 of 50 references.

References · 3

  1. 2021Deep Reinforcement Learning for Black-Box Testing of Android Appscited by 10
  2. 2014AbsSynthe: abstract synthesis from succinct safety specificationscited by 2
  3. 2024Reusable Formal Verification of DAG-based Consensus Protocolscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2019Automated Video Game Testing Using Synthetic and Human-Like Agents
  2. 2026CA2: Code-Aware Agent for Automated Game Testing
  3. 2026Test-time Reinforcement Learning in Imperfect Information Games
  4. 2024Enhancing Reinforcement Learning Through Guided Search
  5. 2026ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation
  6. 2025Adaptive Reinforcement Learning for Dynamic Configuration Allocation in Pre-Production Testing
  7. 2025Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning
  8. 2025Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning