Noisy Test-Time Reinforcement Learning for Code LLMs
cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/Xikai97/NTRL-Code
Terminology
Sources
- Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study
- Program Synthesis with Large Language Models
- Adversarial Training of Reward Models
- Evaluating Large Language Models Trained on Code
- Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
- SAGE: A Realistic Benchmark for Semantic Understanding
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
- On the Adversarial Robustness of Instruction-Tuned Large Language Models for Code
- Qwen2.5-Coder Technical Report
- From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
- RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation
- CREME: Robustness Enhancement of Code LLMs via Layer-Aware Model Editing
- On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation
- Maximizing Confidence Alone Improves Reasoning
- Quantifying perturbation impacts for large language models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Qwen3 Technical Report
- Tent: Fully Test-time Adaptation by Entropy Minimization
- Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code
- Certified Robustness for Large Language Models with Self-Denoising
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection