Pith. sign in

REVIEW 8 cited by

Planning with Large Language Models for Code Generation

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

arxiv 2303.05510 v1 pith:FAWFZF2E submitted 2023-03-09 cs.LG cs.AIcs.CLcs.PL

classification cs.LGcs.AIcs.CLcs.PL
keywords transformergenerateprogramscodedecodinggenerationalgorithmlanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Existing large language model-based code generation pipelines typically use beam search or sampling algorithms during the decoding process. Although the programs they generate achieve high token-matching-based scores, they often fail to compile or generate incorrect outputs. The main reason is that conventional Transformer decoding algorithms may not be the best choice for code generation. In this work, we propose a novel Transformer decoding algorithm, Planning-Guided Transformer Decoding (PG-TD), that uses a planning algorithm to do lookahead search and guide the Transformer to generate better programs. Specifically, instead of simply optimizing the likelihood of the generated sequences, the Transformer makes use of a planner to generate candidate programs and test them on public test cases. The Transformer can therefore make more informed decisions and generate tokens that will eventually lead to higher-quality programs. We also design a mechanism that shares information between the Transformer and the planner to make our algorithm computationally efficient. We empirically evaluate our framework with several large language models as backbones on public coding challenge benchmarks, showing that 1) it can generate programs that consistently achieve higher performance compared with competing baseline methods; 2) it enables controllable code generation, such as concise codes and highly-commented codes by optimizing modified objective.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer

    cs.AI 2026-08 conditional novelty 7.0 of 10

    Solver-aware training of a PBE decomposer with a frozen synthesizer's loss outperforms supervised imitation of ground-truth subgoals, solving tasks that a ground-truth decomposition oracle fails.

  2. MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?

    cs.CL 2025-07 conditional novelty 7.0 of 10

    MOCHA is a benchmark of 10.5K malicious coding prompts, including multi-turn decomposition attacks, showing code LLMs reject these incremental attacks at much lower rates and that fine-tuning on the benchmark improves...

  3. LogiDroid: Individual Functional Test Generation via Business Logic Extraction and Adaptation

    cs.SE 2026-02 conditional novelty 6.0 of 10

    LogiDroid generates functional Android test cases with verification assertions by retrieving similar test cases, fusing their business logic, and adapting it to the target app's real-time GUI state.

  4. Concentration bounds on response-based vector embeddings of black-box generative models

    stat.ML 2025-11 reject novelty 6.0 of 10

    For bounded-variance response distributions, the DKPS embedding error is O_P((n^3/r)^{1/2-delta}) when r grows faster than n^3.

  5. It's Not That Simple. An Analysis of Simple Test-Time Scaling

    cs.LG 2025-07 conditional novelty 6.0 of 10

    The apparent scaling behavior of the s1 model is mostly an artifact of truncating long outputs, while appending 'Wait' does not reliably improve answers.

  6. Breaking the Myth: Can Small Models Infer Postconditions Too?

    cs.SE 2025-07 conditional novelty 6.0 of 10

    Fine-tuning Qwen2.5-Coder-7B on 1.5K reasoning examples yields postcondition generation close to GPT-4o and better than 32B open models on Defects4J.

  7. MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation

    cs.CR 2025-07 conditional novelty 6.0 of 10

    MGC, a two-stage compiler framework, generates functional malware by decomposing malicious intents into benign-appearing MDIR components that strong aligned LLMs will implement, bypassing safety alignment.

  8. BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning

    cs.CL 2025-08 conditional novelty 4.0 of 10

    An updated BLUEX benchmark with 1,422 questions and GPT-4o-generated captions that make image-based questions usable by text-only LLMs.

Pith tools