Pith. sign in

REVIEW 16 cited by

Planning with Large Language Models for Code Generation

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

Shun Zhang , Zhenfang Chen , Yikang Shen , Mingyu Ding , Joshua B. Tenenbaum , Chuang Gan This is my paper
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 16 Pith papers

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

  1. Gradient-Based Program Synthesis with Neurally Interpreted Languages

    cs.LG 2026-04 unverdicted novelty 8.0 of 10

    NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prio...

  2. 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.

  3. POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference

    cs.SE 2026-05 unverdicted novelty 7.0 of 10

    POSTCONDBENCH is a new multilingual benchmark that evaluates LLM postcondition generation on real code using defect discrimination to assess completeness beyond surface matching.

  4. AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search

    cs.SE 2026-04 unverdicted novelty 7.0 of 10

    AdverMCTS frames code generation as a minimax game where an attacker evolves tests to expose flaws in solver-generated code, yielding more robust outputs than static-test baselines.

  5. ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

    cs.AI 2025-10 unverdicted novelty 7.0 of 10

    ToolPRM provides fine-grained intra-call process supervision via a new dataset and reward model, outperforming outcome and coarse-grained alternatives on function-calling benchmarks.

  6. 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...

  7. Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference

    cs.DC 2026-06 unverdicted novelty 6.0 of 10

    SlidingServe achieves up to 30% higher service capacity and 16-53% fewer SLO violations in LLM inference by using dynamic chunking and priority-based batch construction.

  8. 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.

  9. 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.

  10. 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.

  11. 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.

  12. 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.

  13. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

    cs.SE 2024-03 unverdicted novelty 6.0 of 10

    LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.

  14. Bridging the Gap between User Intent and LLM: A Requirement Alignment Approach for Code Generation

    cs.SE 2026-04 unverdicted novelty 5.0 of 10

    REA-Coder improves LLM code generation by iteratively aligning requirements with model understanding and verifying outputs against the aligned spec.

  15. Evaluation of LLM-Based Software Engineering Tools: Practices, Challenges, and Future Directions

    cs.SE 2026-04 unverdicted novelty 4.0 of 10

    LLM-based SE tools lack stable ground truth and deterministic outputs, making standard evaluation assumptions invalid and requiring new approaches for reliable assessment.

  16. 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