Pith. sign in

REVIEW 56 cited by

Magicoder: Empowering Code Generation with OSS-Instruct

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 2312.02120 v2 pith:3J4VEV6A submitted 2023-12-04 cs.CL cs.AIcs.SE

classification cs.CLcs.AIcs.SE
keywords codedatamagicodermodelsopen-sourceoss-instructinstructionllms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce Magicoder, a series of fully open-source (code, weights, and data) Large Language Models (LLMs) for code that significantly closes the gap with top code models while having no more than 7B parameters. Magicoder models are trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets to generate diverse instruction data for code. Our main motivation is to mitigate the inherent bias of the synthetic data generated by LLMs through the wealth of open-source references for the production of more realistic and controllable data. The orthogonality of OSS-Instruct and other data generation methods like Evol-Instruct further enables us to build an enhanced MagicoderS. Both Magicoder and MagicoderS substantially outperform state-of-the-art code models with similar or even larger sizes on a wide range of coding benchmarks. Notably, MagicoderS-CL-7B based on CodeLlama even surpasses the prominent ChatGPT on HumanEval+ (66.5 vs. 65.9 in pass@1 ). Overall, OSS-Instruct opens a new direction for crafting diverse synthetic instruction data for code using abundant open-source references.

Discussion (0). Sign in to comment.

Forward citations

Cited by 56 Pith papers

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

  1. Large Language Diffusion Models

    cs.CL 2025-02 unverdicted novelty 8.0 of 10

    LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.

  2. Repository-Level Solidity Code Generation with Large Language Models: From Prompting to Fine-Tuning

    cs.SE 2026-06 unverdicted novelty 7.0 of 10

    Introduces SolidityBench benchmark and SolidityScore metric for repository-level Solidity code generation, finding supervised fine-tuning outperforms prompting, CoT, ICL, and RAG methods on evaluated LLMs.

  3. CODEBLOCK: Learning to Supervise Code at the Right Granularity

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    CodeBlock partitions code responses into syntactically coherent blocks, scores them with generalized cross-entropy and data-flow signals, and applies sparse supervision to achieve higher pass@1 than full SFT using 1.9...

  4. SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation

    cs.SE 2026-06 unverdicted novelty 7.0 of 10

    SkelDPO improves code generation efficiency by 2-7% over prior DPO methods via joint preference losses on full code and efficiency-critical skeletons.

  5. RogueMerge: Robust and Unified Attacks against LLM Model Merging

    cs.CR 2026-06 unverdicted novelty 7.0 of 10

    RogueMerge is a unified attack method that jointly optimizes task vectors to succeed after merging, using stochastic min-max simulation for unknown merging settings and a Taylor-approximated DRO for prompt generalizat...

  6. Reconstruction of Personally Identifiable Information from Supervised Finetuned Models

    cs.CR 2026-05 unverdicted novelty 7.0 of 10

    PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.

  7. Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation

    cs.SE 2026-05 unverdicted novelty 7.0 of 10

    Many reported failures in LLM-based code translation are false negatives due to evaluation pipeline issues such as improper compilation flags, missing library links, and unconfigured runtime environments rather than i...

  8. Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing

    cs.SE 2026-04 unverdicted novelty 7.0 of 10

    A cascaded large-small model system generates edit sketches with the large model and applies them with the small model to make code editing both accurate and token-efficient.

  9. SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios

    cs.SE 2025-12 unverdicted novelty 7.0 of 10

    SWE-EVO shows GPT-5.4 with OpenHands reaching only 25% success on complex multi-file evolution tasks versus 72.8% on SWE-Bench Verified, and introduces Fix Rate as a partial-progress metric.

  10. Assessing Coherency and Consistency of Code Execution Reasoning by Large Language Models

    cs.SE 2025-10 unverdicted novelty 7.0 of 10

    LLMs achieve 81% coherent execution simulation on HumanEval but show mostly random or weak consistency across tests, with frontier models relying on natural language shortcuts instead of true program analysis.

  11. rStar2-Agent: Agentic Reasoning Technical Report

    cs.CL 2025-08 conditional novelty 7.0 of 10

    A 14B model trained with agentic RL and a resample-on-correct rollout strategy scores 80.6% on AIME24 and 69.8% on AIME25, nearly matching DeepSeek-R1 (671B) in one week on 64 GPUs.

  12. Towards Agentic Runtime Healing

    cs.SE 2024-08 unverdicted novelty 7.0 of 10

    Healer uses LLMs to dynamically generate and execute runtime error-handling code, with GPT-4 recovering from 72.8% of errors across four datasets.

  13. LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation

    cs.LG 2026-08 conditional novelty 6.0 of 10

    LEAP combines difficulty-conditioned pruning with pairwise rank-based rewards to improve multi-turn reinforcement learning for CUDA kernel generation.

  14. MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Routing LoRA adapters with the frozen base router's logits plus a shared cross-layer adapter pool gives the best PEFT accuracy and retention on three MoE backbones.

  15. SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation

    cs.SE 2026-07 conditional novelty 6.0 of 10

    SciCodePile contributes a 128GB scientific code corpus and a 200-task executable benchmark showing that current LLMs still fall far short of reliable scientific code generation.

  16. Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Mid-training on function-aware fill-in-the-middle data improves SWE-Bench by 2.8-5.4 points and reduces post-training capability loss.

  17. Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

    cs.AI 2026-07 unverdicted novelty 6.0 of 10

    Function-aware FIM mid-training on ordinary code improves coding-agent SWE-Bench scores and reduces post-training capability erosion on non-agent benchmarks.

  18. Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs

    cs.LG 2026-07 conditional novelty 6.0 of 10

    The optimal training duration for expert models before merging depends on the merging method; sparsification-based merging benefits from overtrained experts.

  19. LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

    cs.CL 2026-07 conditional novelty 6.0 of 10

    A fine-tuning objective that preserves the base model's local preference among non-label tokens improves pass@1 accuracy and retains more pretrained capability than standard SFT.

  20. Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code

    cs.SE 2026-06 unverdicted novelty 6.0 of 10

    Replication of TCS strategies on 17 LLM instances across three code tasks shows only partial generalization from vision DNN results, with uncertainty features aiding early failure discovery and representation features...

  21. Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks

    cs.SE 2026-06 unverdicted novelty 6.0 of 10

    Empirical study finds instruction tuning on CodeLLMs improves instruction following at the expense of infilling performance, termed the Instruction-Tuning Tax.

  22. BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

    cs.SE 2026-05 unverdicted novelty 6.0 of 10

    BenchEvolver evolves coding problem solutions to generate harder, valid tasks, producing LiveCodeBench-Plus where frontier models score 27.5-62.6% and enabling RL gains on held-out tests.

  23. TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs

    cs.SE 2026-05 unverdicted novelty 6.0 of 10

    TRACER presents a semantic-aware framework and the first benchmark for fine-grained code contamination detection across three levels of overlap, reporting F1 scores of 0.91-0.92 and large gains over prior methods.

  24. Asking Back: Interaction-Layer Antidistillation Watermarks

    cs.CR 2026-05 unverdicted novelty 6.0 of 10

    Interaction-layer antidistillation watermarks use system-prompt-induced behavioral markers like explicit follow-up questions that transfer to distilled student models at 45-89% relative fidelity and can be audited via...

  25. Bayesian Model Merging

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Bayesian Model Merging introduces a bi-level optimization framework that merges task-specific models via closed-form Bayesian regression with an anchor prior and global hyperparameter search, outperforming baselines a...

  26. GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus

    cs.CL 2026-05 conditional novelty 6.0 of 10

    A 303,581-row Korean instruction corpus generated seedlessly from a 1,084-discipline taxonomy, with near-zero duplicates and low measured overlap with KMMLU, KoBEST, and HAE-RAE-Bench.

  27. Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Full finetuning with the pretraining optimizer reduces forgetting compared to other optimizers or LoRA while achieving comparable new-task performance.

  28. Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    Adversarial competition between attacker and defender teams generates diverse multi-turn conversational data that improves LLM performance on secure code generation benchmarks by 18-29%.

  29. Sensitivity-Positional Co-Localization in GQA Transformers

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    In Llama 3.1 8B, task-sensitive layers cluster late while RoPE adaptation is strongest early, yet applying both adaptations only to sensitivity-identified layers outperforms other layer choices by 4-16 points on MMLU,...

  30. Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning

    cs.RO 2026-02 unverdicted novelty 6.0 of 10

    R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.

  31. Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts

    cs.CL 2025-09 unverdicted novelty 6.0 of 10

    EMoE trains MoE models so they maintain performance when the number of activated experts changes at inference, expanding the usable range to 2-3 times the training k with higher peak results.

  32. Modeling Code: Is Text All You Need?

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A GNN-encoded LLVM IR graph, prepended as soft prompts to a frozen code LLM, improves accuracy on device mapping, algorithm classification, vulnerability detection, and code translation tasks.

  33. Turning the Tide: Repository-based Code Reflection

    cs.SE 2025-07 conditional novelty 6.0 of 10

    A new 1,888-case, six-language benchmark and a trained model measure and improve how code LLMs edit and repair code inside multi-file repositories.

  34. BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A ReLU-routed MoE with chunk-level sparsity training objectives and custom kernels combining activation sparsity with speculative decoding achieves over 70% 8-token chunk sparsity and up to 3.67x end-side speedup.

  35. Multilingual Multimodal Software Developer for Code Generation

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A 7B vision-language model trained on synthetic diagram-to-code data outperforms several larger open-weight models on a new 10-language UML/flowchart code-generation benchmark.

  36. Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Long chain-of-thought and RL training on math problems improves general reasoning benchmarks, while short chain-of-thought math fine-tuning often degrades performance.

  37. A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback

    cs.SE 2025-07 conditional novelty 6.0 of 10

    MultiCodeIF introduces a 2,021-task, 14-language benchmark with 27 constraint types to evaluate code instruction following, finding that multi-level constraints sharply reduce model success and iterative feedback subs...

  38. Agentless: Demystifying LLM-based Software Engineering Agents

    cs.SE 2024-07 conditional novelty 6.0 of 10

    Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.

  39. MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

    cs.CL 2024-04 conditional novelty 6.0 of 10

    MiniCPM 1.2B and 2.4B models reach parity with 7B-13B LLMs via model wind-tunnel scaling and a WSD scheduler that yields a higher optimal data-to-model ratio than Chinchilla scaling.

  40. 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.

  41. Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs

    cs.LG 2026-07 unverdicted novelty 5.5 of 10

    Sparsification-based model merging peaks well past expert validation optima, while averaging degrades with overtraining; duration and merge method must be chosen jointly.

  42. Route-Align-Verify for Functional Correctness in Code Generation

    cs.SE 2026-08 reject novelty 5.0 of 10

    RAV combines task-aware prompt routing, aligned LoRA fine-tuning, and public-test-based candidate selection to improve MBPP pass@1, but its verification step leaks evaluation tests.

  43. Quantize with Confidence? An Empirical Study of Quantization for Code Generation

    cs.SE 2026-07 conditional novelty 5.0 of 10

    4-bit quantization of code LLMs mostly preserves pass@1, but AQLM matches or beats full precision while QuIP# degrades most on complex prompts; sensitivity is model-dependent.

  44. LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

    cs.CL 2026-07 conditional novelty 5.0 of 10

    Preserving adaptive non-label local structure from the base model during SFT improves the pass@1 vs pass@k trade-off and reduces catastrophic forgetting versus vanilla cross-entropy and recent SFT variants.

  45. ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards

    cs.CL 2026-06 unverdicted novelty 5.0 of 10

    ROSUM-MCTS applies MCTS-inspired hierarchical candidate expansion and a composite reward balancing functional correctness, local content adequacy, and fluency to improve LLM summaries of VHDL and Verilog code, outperf...

  46. Lossless Anti-Distillation Sampling

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalizati...

  47. Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation

    cs.SE 2026-05 unverdicted novelty 5.0 of 10

    A large-scale study finds that many LLM code translation failures are false negatives due to improper evaluation configurations rather than incorrect translations.

  48. A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data

    cs.AI 2026-01 conditional novelty 5.0 of 10

    A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.

  49. SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment

    cs.CL 2025-09 conditional novelty 5.0 of 10

    Adding a KL penalty between fine-tuned and original model logits on input tokens during RAG fine-tuning reduces catastrophic forgetting while preserving downstream performance.

  50. Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    Grove MoE uses unequal-size adjugate experts with complexity-based activation to run 33B-parameter models at roughly 3.1 to 3.3B active parameters while matching larger open models in benchmarks.

  51. Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes

    cs.CL 2026-08 conditional novelty 4.0 of 10

    Statistical classifiers built on LLM activation norms and coordinates match or beat trained MLP heads on coarse intent routing and resist camouflage better, while MLPs win on fine-grained subfield distinctions.

  52. Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation

    cs.SE 2026-06 unverdicted novelty 4.0 of 10

    Empirical study on five LLMs finds pretrained-to-aligned paths yield bigger gains over baseline than finetuned-to-aligned paths, though absolute accuracy remains lower for pretrained starts.

  53. Context-Instrumental Data Distillation for Kubernetes Manifest Generation: Method and Experimental Evaluation

    cs.LG 2026-05 unverdicted novelty 4.0 of 10

    Context-instrumental data distillation allows a 1.5B SLM to generate valid Kubernetes manifests at 91.5% pass@1 rate, with strict output formatting proving more impactful than additional training data.

  54. Large Language Models for Multilingual Code Intelligence: A Survey

    cs.SE 2026-04 unverdicted novelty 4.0 of 10

    A survey of methods, benchmarks, and open challenges for large language models in multilingual code generation and translation.

  55. Position: Intelligent Coding Systems Should Write Programs with Justifications

    cs.SE 2025-08 conditional novelty 4.0 of 10

    A position paper advocating that intelligent coding systems should accompany code with justified explanations that are cognitively aligned and semantically faithful.

  56. A Survey on Large Language Models for Code Generation

    cs.CL 2024-06 unverdicted novelty 3.0 of 10

    A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark...

Pith tools