@inproceedings{zheng-etal-2026-training,
    title = "Training-Free Test-Time Contrastive Learning for Large Language Models",
    author = "Zheng, Kaiwen  and
      Zhou, Kai  and
      Hu, Jinwu  and
      Gu, Te  and
      Peng, Mingkai  and
      Liu, Fei",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1482/",
    pages = "29644--29676",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) demonstrate strong reasoning capabilities, but their performance often degrades under distribution shift. Existing test-time adaptation (TTA) methods rely on gradient-based updates that require white-box access and need substantial overhead, while training-free alternatives are either static or depend on external guidance. In this paper, we propose Training-Free Test-Time Contrastive Learning (**TF-TTCL**), a training-free adaptation framework that enables a frozen LLM to improve online by distilling supervision from its own inference experiences. Specifically, TF-TTCL implements a dynamic ``Explore-Reflect-Steer'' loop through three core modules: 1) Semantic Query Augmentation first diversifies problem views via multi-agent role-playing to generate different reasoning trajectories; 2) Contrastive Experience Distillation then captures the semantic gap between superior and inferior trajectories, distilling them into explicit textual rules; and 3) Contextual Rule Retrieval finally activates these stored rules during inference to dynamically steer the frozen LLM toward robust reasoning patterns while avoiding observed errors. Extensive experiments on closed-ended reasoning tasks and open-ended evaluation tasks demonstrate that TF-TTCL consistently outperforms strong zero-shot baselines and representative TTA methods under online evaluation. Code is available at https://github.com/KevinSCUTer/TF-TTCL."
}