# Training-Free Test-Time Contrastive Learning for Large Language Models

arXiv: https://arxiv.org/abs/2604.13552 · HTML: https://mlsanity.com/paper/2604.13552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 32 of its 55 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 30 of 32)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity](https://mlsanity.com/paper/2510.01171/) (2025)
- [AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning](https://mlsanity.com/paper/2406.11200/) (2024)
- [ThetaEvolve: Test-time Learning on Open Problems](https://mlsanity.com/paper/2511.23473/) (2025)
- [Training-Free Group Relative Policy Optimization](https://mlsanity.com/paper/2510.08191/) (2025)
- [MoT: Memory-of-Thought Enables ChatGPT to Self-Improve](https://mlsanity.com/paper/2305.05181/) (2023)
- [M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions](https://mlsanity.com/paper/2405.16420/) (2024)
- [Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers](https://mlsanity.com/paper/2402.17564/) (2024)
- [Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs](https://mlsanity.com/paper/2402.12052/) (2024)
- [COME: Test-time adaption by Conservatively Minimizing Entropy](https://mlsanity.com/paper/2410.10894/) (2024)
- [HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases](https://mlsanity.com/paper/2412.16311/) (2024)
- [SLOT: Sample-specific Language Model Optimization at Test-time](https://mlsanity.com/paper/2505.12392/) (2025)
- [R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory](https://mlsanity.com/paper/2501.12485/) (2025)

## Abstract (arXiv)

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.