REVIEW 31 cited by
Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
With the rapid evolution of large language models (LLM), reinforcement learning (RL) has emerged as a pivotal technique for code generation and optimization in various domains. This paper presents a systematic survey of the application of RL in code optimization and generation, highlighting its role in enhancing compiler optimization, resource allocation, and the development of frameworks and tools. Subsequent sections first delve into the intricate processes of compiler optimization, where RL algorithms are leveraged to improve efficiency and resource utilization. The discussion then progresses to the function of RL in resource allocation, emphasizing register allocation and system optimization. We also explore the burgeoning role of frameworks and tools in code generation, examining how RL can be integrated to bolster their capabilities. This survey aims to serve as a comprehensive resource for researchers and practitioners interested in harnessing the power of RL to advance code generation and optimization techniques.
Forward citations
Cited by 31 Pith papers
-
DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning
DHRCL stages syntax, execution, test-pass, and AST-similarity rewards during code-LLM RL and redistributes token credit by stage, yielding about a 1-point average Pass@1 gain across Qwen3 scales.
-
From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software
In OSS repos that commit AI chat logs, AI use is heavier in smaller, less collaborative projects; chats almost always precede commits, quality signals do not broadly worsen, and developers trust their own AI code more...
-
Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation
VeRPO turns partial test-suite success into dense, difficulty-weighted rewards for RL code generation, beating GRPO by up to 8.8 pass@1 points at negligible cost.
-
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
An 8B model trained with SFT and GRPO reinforcement learning generates Triton kernels that match or exceed frontier model performance on TritonBench and KernelBench correctness metrics.
-
VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
A hybrid verifier that combines rule-based code checks and a reasoning-LLM judge enables reinforcement learning to improve LLM instruction following on several benchmarks.
-
Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
Reinforcement learning with execution feedback enables a code model to iteratively improve the efficiency of its own generated code, surpassing supervised and preference-based training methods.
-
$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
Combining a learned Koopman linearization with a learned Kalman filter inside a VAE produces a probabilistic forecaster that beats existing methods on most tested short- and long-horizon datasets.
-
Low-Cost Test-Time Adaptation for Robust Video Editing
Vid-TTA proposes to adapt video editing UNets per test video via motion-aware masked autoencoding and prompt perturbation, with claimed but unquantified improvements.
-
RAST: Reasoning Activation in LLMs via Small-model Transfer
Injecting the logit gap between a small RL-trained model and its base into a larger base model at decoding time improves reasoning accuracy on math and code benchmarks, sometimes matching or exceeding RL training of t...
-
LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data
A lightweight RGB-D cross-attention network is proposed for rail defect detection, but the SOTA accuracy and generalization claims are internally inconsistent and the implementation is not public.
-
A Machine Learning-Based Study on the Synergistic Optimization of Supply Chain Management and Financial Supply Chains from an Economic Perspective
A DML regression on roughly 40,000 firm-year observations reports positive effects of data element marketization on five supply chain resilience indicators, but the abstract's promised operational improvements are not...
-
Leveraging Large Language Model for Intelligent Log Processing and Autonomous Debugging in Cloud AI Platforms
A cloud log debugging framework combining log clustering, LLM reasoning, and reinforcement-learning recovery planning is claimed to improve fault location accuracy by 16.2 percent, but the supporting accuracy experime...
-
Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method
Fine-tuning Stable Diffusion with DreamBooth-style knowledge and hypernetwork-guided crack control maps can synthesize substation meter defect images that boost a YOLOv8 defect detector's mAP when added to the training set.
-
Contextualized Multimodal Lifelong Person Re-Identification in Hybrid Clothing States
CMLReID uses dynamic text prompts and dual-path prototypes to improve lifelong person re-identification in hybrid clothing states, reporting gains of about 5 mAP over four baselines.
-
Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users
A manuscript claims instructional prompt engineering improves LLM-based cold-start recommendation, but provides no reproducible evidence.
-
Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification
The paper proposes a four-stage self-verification prompting method but explicitly labels its experimental results as fabricated, so it cannot support its claimed gains.
-
Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization
LVLM-VAR transforms video into 'semantic action tokens' and uses a LoRA-tuned vision-language model to classify actions and generate explanations, reporting 94.1% on NTU RGB+D X-Sub.
-
Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance
The proposed CAMVR framework is not supported by verifiable evidence, and the manuscript itself labels its experimental results as fabricated.
-
Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms
A standard attention-fusion plus Transformer sequence model is applied to short-video recommendation, with claimed gains over weak baselines and no reproducible artifacts.
-
A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecture
The paper claims a BiLSTM-AM-VMD model achieves AUC 0.963 for early HCC diagnosis, but the evidence is undermined by contradictory dataset descriptions and missing artifacts.
-
Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkers
XGBoost combining MRI radiomics and clinical biomarkers reportedly reaches C-index 0.782 for early brain tumor recurrence, but the paper's methods describe a liver-cancer cohort and no evaluation of its claimed tempor...
-
Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs
A meta-learned prompt-tuning method for cold-start LLM recommendations reports better Hit@10 and nDCG@10 on MovieLens-1M, but with no code, no error bars, and no shown results for Amazon or Recbole.
-
Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation
Hi-SSLVLM combines hierarchical self-captioning, internal sub-prompt planning, and a CLIP-based consistency loss, and reports judged compositional fidelity gains of roughly 0.04 to 0.09 points that no significance tes...
-
Large Language Models for Zero-Shot Multicultural Name Recognition
A prompt-tuned LLM with data augmentation and cultural context prompts reportedly recognizes multicultural names at 93.1% accuracy and unseen names at 89.5%, but the evidence is not reproducible.
-
Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems
A hybrid GNN-LLM recommender with FPGA, DeepSpeed, and LoRA reportedly reaches NDCG@10 of 0.75 at 40-60ms latency while cutting training time by 66%, but the supporting artifacts are absent.
-
LLM-Augmented Symptom Analysis for Cardiovascular Disease Risk Prediction: A Clinical NLP
A small synthetic study reports that Bio_ClinicalBERT embeddings with Random Forest classify CVD risk in about 20 hand-written symptom texts, but the claims of MIMIC-III and CARDIO-NLP evaluation are unsupported.
-
Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems
A hybrid model-plus-data parallel scheme is reported to boost training throughput and GPU utilization for LLM-based recommenders, but the supporting experiments are not reproducible from the paper.
-
Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems
A standard combination of model compression and serving optimization gives 2.4x throughput on a GPU benchmark, but the headline claims of <30% latency and preserved accuracy are not supported by the paper's own data.
-
Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks
A hybrid LLM-plus-GNN recommender is claimed to beat collaborative filtering, LLM-only, and GNN-only baselines on financial product ranking, with NDCG@10 of 0.372.
-
Revolutionizing Radiology Workflow with Factual and Efficient CXR Report Generation
CXR-PathFinder claims to outperform much larger medical vision-language models on chest X-ray reporting, using adversarial fine-tuning with clinician feedback and knowledge graph verification, but the evidence is not ...
-
LLM-Driven E-Commerce Marketing Content Optimization: Balancing Creativity and Conversion
An LLM copywriting pipeline combining fine-tuning, vector search, and weighted reranking reportedly lifts CTR by 12.5% and CVR by 8.3%, but the evidence is unverifiable and internally inconsistent.
Discussion (0). Continue with ORCID to comment.