REVIEW 16 cited by
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
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
The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpreter across key benchmarks such as HumanEval, MBPP, and their enhanced versions from EvalPlus reveals its exceptional performance. Notably, OpenCodeInterpreter-33B achieves an accuracy of 83.2 (76.4) on the average (and plus versions) of HumanEval and MBPP, closely rivaling GPT-4's 84.2 (76.2) and further elevates to 91.6 (84.6) with synthesized human feedback from GPT-4. OpenCodeInterpreter brings the gap between open-source code generation models and proprietary systems like GPT-4 Code Interpreter.
Forward citations
Cited by 16 Pith papers
-
\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating
Selecting the top 50% of LoRA weight matrices by condition number halves trainable parameters and cuts fine-tuning time by about 16% while roughly matching full-LoRA accuracy.
-
Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality
Prompt language affects LLM code generation, but English is not consistently best: Chinese prompts improve Python correctness on CoderEval, while quality and lexicon effects vary by model and programming language.
-
Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines
Disguising unsafe operations as routine software-engineering tests makes coding agents execute them at high verified rates, revealing a gap between language-layer refusal and execution-layer harm.
-
Synthetic Interaction Data for Scalable Personalization in Large Language Models
PersonaGym simulates noisy multi-turn user–assistant interactions to build PersonaAtlas, and PPOpt learns to rewrite user prompts from interaction history, improving judged personalization on synthetic benchmarks.
-
MACD: Model-Aware Contrastive Decoding via Counterfactual Data
MACD reduces Video-LLM hallucination by masking model-identified critical objects/frames via gradient ascent and using the masked video as a contrastive decoding reference.
-
Diving into Kronecker Adapters: Component Design Matters
Kronecker adapter performance depends on the dimensions and number of its Kronecker components, and component design with small r1, large r2, and moderate r improves alignment with full fine-tuning.
-
LAMDAS: LLM as an Implicit Classifier for Domain-specific Data Selection
LAMDAS selects domain-relevant training data via an LLM likelihood ratio with a learned domain prefix, beating full-data training and nine baselines on code and math.
-
Multilingual Multimodal Software Developer for Code Generation
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.
-
Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
Trans-PEFT uses random FFN masking and layer dropping during fine-tuning so PEFT modules trained on an old base model transfer to a continually updated base model without retuning.
-
ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests
ICPC-Eval benchmarks LLMs on 118 recent ICPC contest problems with local test suites and a Refine@K metric that quantifies iterative refinement, showing even the best models solve only about 29% of problems.
-
A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search
LLM embeddings plus Bayesian optimization find better LoRA hyperparameters in ~30 proxy trials than standard published settings.
-
ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding
ReST-RL pairs reward-variance-filtered self-training (ReST-GRPO) with value-model-guided MCTS decoding (VM-MCTS) to improve LLM code reasoning.
-
ChatVis: Large Language Model Agent for Generating Scientific Visualizations
A retrieval-augmented LLM assistant with iterative error correction nearly doubles the rate of generating executable ParaView visualization scripts compared with unassisted models.
-
A Comparative Study of Specialized LLMs as Dense Retrievers
Specialized Qwen2.5 7B models differ in dense retrieval quality: math and long-reasoning variants degrade performance, while coder and vision-language variants improve zero-shot text and code retrieval.
-
Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
CorDA++ uses data-driven SVD to initialize LoRA adapters, adding per-layer covariance selection and rank allocation that reduce forgetting and speed convergence compared to LoRA, PiSSA, QLoRA, and other baselines.
-
MiniCPM4: Ultra-Efficient LLMs on End Devices
MiniCPM4-8B reportedly matches Qwen3-8B on standard benchmarks while using about 22% of the training tokens, and achieves large long-context speedups on edge devices.
Discussion (0). Sign in to comment.