Pith. sign in

REVIEW 11 cited by

Execution-based Code Generation using Deep Reinforcement Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2301.13816 v4 pith:KYVQLUQO submitted 2023-01-31 cs.LG cs.AIcs.CLcs.PL

Parshin Shojaee , Aneesh Jain , Sindhu Tipirneni , Chandan K. Reddy This is my paper
classification cs.LGcs.AIcs.CLcs.PL
keywords codegenerationppocodertasksacrosscorrectnessdeepdifferent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The utilization of programming language (PL) models, pre-trained on large-scale code corpora, as a means of automating software engineering processes has demonstrated considerable potential in streamlining various code generation tasks such as code completion, code translation, and program synthesis. However, current approaches mainly rely on supervised fine-tuning objectives borrowed from text generation, neglecting unique sequence-level characteristics of code, including but not limited to compilability as well as syntactic and functional correctness. To address this limitation, we propose PPOCoder, a new framework for code generation that synergistically combines pre-trained PL models with Proximal Policy Optimization (PPO) which is a widely used deep reinforcement learning technique. By utilizing non-differentiable feedback from code execution and structure alignment, PPOCoder seamlessly integrates external code-specific knowledge into the model optimization process. It's important to note that PPOCoder is a task-agnostic and model-agnostic framework that can be used across different code generation tasks and PLs. Extensive experiments on three code generation tasks demonstrate the effectiveness of our proposed approach compared to SOTA methods, achieving significant improvements in compilation success rates and functional correctness across different PLs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. An Iterative Test-and-Repair Framework for Competitive Code Generation

    cs.SE 2026-04 unverdicted novelty 7.0 of 10

    FixAudit improves LLM code generation on competitive programming benchmarks by training a shared model for iterative code-aware test generation and repair, achieving 35%+ gains in Pass@1 over baselines on the same 7B model.

  2. Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning

    cs.LG 2026-07 conditional novelty 6.5 of 10

    Simulation-in-the-loop GRPO on energy-labeled C++ pairs yields 12.63% CARET and beats human energy efficiency on 58.4% of valid held-out outputs, while IPC misranks energy on 67.8% of problems.

  3. From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Using the ALPHA hierarchy penalty as a direct GRPO reward improves CWE prediction under distribution shift, while supervised delivery of the same penalty regresses below zero-shot.

  4. NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation

    cs.LG 2026-07 conditional novelty 6.0 of 10

    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.

  5. Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation

    cs.LG 2026-01 conditional novelty 6.0 of 10

    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.

  6. AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models

    cs.CL 2025-08 conditional novelty 6.0 of 10

    Adversarial teacher-student RL on computationally equivalent narrative rewrites of coding problems yields modest but consistent pass@1 gains on competitive programming benchmarks.

  7. Efficiency of turbulence

    physics.flu-dyn 2025-08 unverdicted novelty 6.0 of 10

    The efficiency of turbulence, the fraction of input energy stored in the flow, appears bounded and may saturate in a power-law manner across several turbulent flows.

  8. Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing

    cs.SE 2025-07 conditional novelty 6.0 of 10

    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.

  9. Rethinking Verification for LLM Code Generation: From Generation to Testing

    cs.CL 2025-07 reject novelty 6.0 of 10

    SAGA, a human-LLM workflow, generates tests that catch 90.62% of known human bugs on a new benchmark, though those bugs also helped create the tests.

  10. D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning

    cs.CR 2025-06 conditional novelty 6.0 of 10

    D-LIFT uses a composite quality score, D-Score, as a reinforcement-learning reward to fine-tune LLMs that rewrite decompiled code, claiming large gains in readability without losing accuracy.

  11. CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review

    cs.SE 2025-05 conditional novelty 5.0 of 10

    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...

Pith tools