Year: 2026
Type: conference-paper
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 openended evaluation tasks demonstrate that TF-TTCL consistently outperforms strong zeroshot baselines and representative TTA methods under online evaluation.Code is available at https://github.com/KevinSCUTer/TF-TTCL.
Institution: South China University of Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G2884727198
OpenAlex ID: W7166877323