@inproceedings{mittal-etal-2025-litmus,
    title = "{LITMUS}++ : An Agentic System for Predictive Analysis of Low-Resource Languages Across Tasks and Models",
    author = "Mittal, Avni  and
      Kumar, Shanu  and
      Dandapat, Sandipan  and
      Choudhury, Monojit",
    editor = "Liu, Xuebo  and
      Purwarianti, Ayu",
    booktitle = "Proceedings of The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-demo.6/",
    pages = "47--54",
    ISBN = "979-8-89176-301-2",
    abstract = "We present LITMUS++, an agentic system for predicting language-model performance for queries of the form ``How will a Model perform on a Task in a Language?'', a persistent challenge in multilingual and low-resource settings, settings where benchmarks are incomplete or unavailable. Unlike static evaluation suites or opaque LLM-as-judge pipelines, LITMUS++ implements an agentic, auditable workflow: a Directed Acyclic Graph of specialized Thought Agents that generate hypotheses, retrieve multilingual evidence, select predictive features, and train lightweight regressors with calibrated uncertainty. The system supports interactive querying through a chat-style interface, enabling users to inspect reasoning traces and cited evidence. Experiments across six tasks and five multilingual scenarios show that LITMUS++ delivers accurate and interpretable performance predictions, including in low-resource and unseen conditions. Code is available at https://github.com/AvniMittal13/litmus{\_}plus{\_}plus."
}