REVIEW 12 cited by
CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
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
Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor performance when solving complex unseen coding tasks. To address the limitations, we propose "CodeRL", a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning (RL). Specifically, during training, we treat the code-generating LM as an actor network, and introduce a critic network that is trained to predict the functional correctness of generated programs and provide dense feedback signals to the actor. During inference, we introduce a new generation procedure with a critical sampling strategy that allows a model to automatically regenerate programs based on feedback from example unit tests and critic scores. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives, larger model sizes, and better pretraining data. Our method not only achieves new SOTA results on the challenging APPS benchmark, but also shows strong zero-shot transfer capability with new SOTA results on the simpler MBPP benchmark.
Forward citations
Cited by 12 Pith papers
-
Self-Improving Large Language Models via Progressive Experience Evolution
SPEE improves LLM math reasoning by explicitly evolving a global pool of transferable experience and distilling it into the policy before applying GRPO reinforcement learning.
-
Embarrassingly Simple Self-Distillation Improves Code Generation
Simple self-distillation—fine-tuning a code model on its own temperature-sampled, truncated outputs—raises LiveCodeBench pass@1 substantially without verifiers, teachers, or RL.
-
Training Language Models to Generate Quality Code with Program Analysis Feedback
REAL trains LLMs with rewards from program analysis and unit tests, improving joint functionality and code quality over prior methods.
-
RLPF: Reinforcement Learning from Performance Feedback for Code Generation
RLPF's staged performance reward lifts Qwen3-32B on PerfCodeBench from 11.1% to 54.6% correct-and-runnable and from 8.1% to 38.6% relative efficiency.
-
NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation
An agent with compile/verify tools reaches 77.3% NKI kernel pass rate on real Trn1 hardware with Opus 4.8, versus 6% single-shot; SFT Qwen3-30B hits 25% at ~1/100th cost, and binary-reward GRPO fails to beat SFT.
-
Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny
A minimal-prior pipeline with automated data curation and verifier-driven RL lets small LLMs generate verifiable Dafny specifications and beat larger proprietary models on a synthetic compositional benchmark.
-
Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing
A bootstrapping algorithm that trains program synthesis models on their own successful outputs and on repaired failures modestly improves pass@k over regular fine-tuning on MBPP, with mixed results on APPS.
-
Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation
An empirical study of 1,023 CoT-code pairs shows that 76.4% of LLM-generated CoTs are low quality and that CoT correctness does not guarantee code correctness.
-
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.
-
Improving LLM-Generated Code Quality with GRPO
Adding a hand-built code-quality score to the GRPO reward makes a 3B model produce code that blind raters prefer, but evidence rests on one model and a synthetic benchmark.
-
CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review
A two-stage SFT+DPO pipeline using linter and code-smell tool outputs plus an LLM judge improves generated code review comments and appears to transfer from Python to Java and JavaScript, though the judge-based evalua...
-
Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing
LLM tutoring modestly accelerates RL convergence on average, with advice reuse saving wall-clock time but reducing stability.
Discussion (0). Sign in to comment.