Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Requirement Patterns for Engineering Multiagent Interaction Protocols

Authors: Amit K. Chopra, Samuel H. Christie V., Munindar P. Singh

IJCAI 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate Mambo s effectiveness on practical protocols.
Researcher Affiliation Academia 1School of Computing and Communications, Lancaster University, Lancaster LA1 4WA, UK 2Department of Computer Science, North Carolina State University, Raleigh, NC 27695, USA EMAIL, EMAIL, EMAIL
Pseudocode No The paper describes the logic and method in prose, including rule summaries in Figure 2, but does not contain explicitly labeled 'Pseudocode' or 'Algorithm' blocks with structured steps formatted like code.
Open Source Code Yes The appendix and all software, including the protocols mentioned, are available at https://gitlab.com/masr/mambo.
Open Datasets Yes The appendix and all software, including the protocols mentioned, are available at https://gitlab.com/masr/mambo.
Dataset Splits No The paper conducts experiments on different interaction protocols (e.g., Sale, Block-Contra, Create Order) to verify properties like liveness and safety. It does not involve training machine learning models on traditional datasets with specified training/test/validation splits.
Hardware Specification Yes Our experiments were performed on an AMD Ryzen 7 6800U with 16GB of RAM.
Software Dependencies No The paper mentions that its implementation is an extension of Tango and states, 'We used the latest version (taken from its public repository) of the Tango implementation'. However, it does not provide specific version numbers for any other key software components, libraries, or programming languages used.
Experiment Setup Yes We evaluated Mambo s performance using a framework that generates every combination of the setup parameters, including protocol, query, method, and iteration ID (so the experiment runs a specific number of times). ... Table 3: Mean times over 10 runs for safety and liveness checking in ms.