CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation

• URL: http://arxiv.org/abs/2504.21751v2
• Date: Sat, 17 May 2025 03:30:11 GMT
• Title: CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation
• Authors: Sizhe Wang, Zhengren Wang, Dongsheng Ma, Yongan Yu, Rui Ling, Zhiyu Li, Feiyu Xiong, Wentao Zhang,
• Abstract summary: We introduce CodeFlowBench, the first benchmark designed to comprehensively evaluate LLMs' ability to perform codeflow.<n>CodeFlowBench comprises 5,258 problems from Codeforces and is continuously updated via an automated pipeline.<n>Extensive experiments on 16 popular LLMs reveal significant performance degradation in multi-turn scenarios.
• Score: 22.74831630054096
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern software development demands code that is maintainable, testable, and scalable by organizing the implementation into modular components with iterative reuse of existing codes. We formalize this iterative, multi-turn paradigm as codeflow and introduce CodeFlowBench, the first benchmark designed to comprehensively evaluate LLMs' ability to perform codeflow, namely implementing new functionality by reusing existing functions over multiple turns. CodeFlowBench comprises 5,258 problems from Codeforces and is continuously updated via an automated pipeline, which decomposes each problem into subproblems with unit tests based on dependency tree analysis and dataflow analysis. We further propose a novel evaluation framework featured dual assessment protocol and structural metrics derived from dependency trees. Extensive experiments on 16 popular LLMs reveal significant performance degradation in multi-turn scenarios. For instance, o1-mini retains only 20.8% Pass@1 in multi-turn scenario versus 37.8% in single-turn scenario. More fine-grained analysis illustrates that model performance inversely correlates with dependency complexity. These findings not only highlight the critical challenges for supporting real-world workflows, but also establish CodeFlowBench as an essential tool for advancing code generation research.

Related papers

• A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback [30.446511584123492]
  Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored.<n>We introduce MultiCodeIF, a comprehensive benchmark designed to evaluate instruction-following in code generation across multiple dimensions.<n>We synthesize and evolve 2,021 code tasks sourced from 14 programming languages, supporting multi-turn evaluation through feedback-driven task variants.
  arXiv  Detail & Related papers  (2025-07-01T11:51:40Z)
• SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving [90.32201622392137]
  We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs)<n>Unlike traditional static benchmarks, SwingArena models the collaborative process of software by pairing LLMs as iterations, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines.
  arXiv  Detail & Related papers  (2025-05-29T18:28:02Z)
• AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation [17.020112052995334]
  A typical multi-agent framework consists of Large Language Model (LLM)-based agents. AdaCoder is a novel adaptive planning, multi-agent framework for function-level code generation.
  arXiv  Detail & Related papers  (2025-04-05T16:14:01Z)
• What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond [32.467437657603604]
  Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts.<n>We propose AllianceCoder, a novel context-integrated method that employs chain-of-thought prompting to decompose user queries into implementation steps and retrieves APIs via semantic description matching.<n>Through extensive experiments on CoderEval and RepoExec, AllianceCoder achieves state-of-the-art performance, improving Pass@1 by up to 20% over existing approaches.
  arXiv  Detail & Related papers  (2025-03-26T14:41:38Z)
• DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation [20.75363011870647]
  DynaCode is a dynamic, complexity-aware benchmark for large language models (LLMs) It evaluates LLMs systematically using a complexity-aware metric, incorporating both code complexity and call-graph structures. Results on 12 latest LLMs show an average performance drop of 16.8% to 45.7% compared to MBPP+, a static code generation benchmark.
  arXiv  Detail & Related papers  (2025-03-13T15:18:56Z)
• FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation [26.14778133391999]
  FEA-Bench is a benchmark designed to assess the ability of large language models to perform incremental development within code repositories.<n>We collect pull requests from 83 GitHub repositories and use rule-based and intent-based filtering to construct task instances focused on new feature development.
  arXiv  Detail & Related papers  (2025-03-09T16:11:57Z)
• EpiCoder: Encompassing Diversity and Complexity in Code Generation [49.170195362149386]
  We introduce a novel feature tree-based synthesis framework inspired by Abstract Syntax Trees (AST)<n>Unlike AST, which captures syntactic structure of code, our framework models semantic relationships between code elements.<n>We fine-tuned widely-used base models to create the EpiCoder series, achieving state-of-the-art performance at both the function and file levels.
  arXiv  Detail & Related papers  (2025-01-08T18:58:15Z)
• Code Review Automation Via Multi-task Federated LLM -- An Empirical Study [4.8342038441006805]
  The study explores five simple techniques for multi-task training, including two sequential methods, one parallel method, and two cumulative methods.<n>The results indicate that sequentially training a federated LLM (FedLLM) for our code review multi-task use case is less efficient in terms of time, computation, and performance metrics, compared to training separate models for each task.
  arXiv  Detail & Related papers  (2024-12-20T08:46:46Z)
• CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models [106.11371409170818]
  Large language models (LLMs) can act as agents with capabilities to self-refine and improve generated code autonomously. We propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions.
  arXiv  Detail & Related papers  (2024-11-07T00:09:54Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• What's Wrong with Your Code Generated by Large Language Models? An Extensive Study [80.18342600996601]
  Large language models (LLMs) produce code that is shorter yet more complicated as compared to canonical solutions. We develop a taxonomy of bugs for incorrect codes that includes three categories and 12 sub-categories, and analyze the root cause for common bug types. We propose a novel training-free iterative method that introduces self-critique, enabling LLMs to critique and correct their generated code based on bug types and compiler feedback.
  arXiv  Detail & Related papers  (2024-07-08T17:27:17Z)
• InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models [56.723509505549536]
  InfiBench is the first large-scale freeform question-answering (QA) benchmark for code to our knowledge. It comprises 234 carefully selected high-quality Stack Overflow questions that span across 15 programming languages. We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings.
  arXiv  Detail & Related papers  (2024-03-11T02:06:30Z)
• LLMDFA: Analyzing Dataflow in Code with Large Language Models [8.92611389987991]
  This paper presents LLMDFA, a compilation-free and customizable dataflow analysis framework. We decompose the problem into several subtasks and introduce a series of novel strategies. On average, LLMDFA achieves 87.10% precision and 80.77% recall, surpassing existing techniques with F1 score improvements of up to 0.35.
  arXiv  Detail & Related papers  (2024-02-16T15:21:35Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation [6.139760107605468]
  Chain-of-thought (CoT) has emerged as a groundbreaking tool in NLP, notably for its efficacy in complex reasoning tasks. We present Code Chain-of-Thought (CodeCoT) that integrates CoT with a self-examination process for code generation.
  arXiv  Detail & Related papers  (2023-08-17T04:58:51Z)
• CodeT5+: Open Code Large Language Models for Code Understanding and Generation [72.1638273937025]
  Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. CodeT5+ is a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning.
  arXiv  Detail & Related papers  (2023-05-13T14:23:07Z)
• Comparative Code Structure Analysis using Deep Learning for Performance Prediction [18.226950022938954]
  This paper aims to assess the feasibility of using purely static information (e.g., abstract syntax tree or AST) of applications to predict performance change based on the change in code structure. Our evaluations of several deep embedding learning methods demonstrate that tree-based Long Short-Term Memory (LSTM) models can leverage the hierarchical structure of source-code to discover latent representations and achieve up to 84% (individual problem) and 73% (combined dataset with multiple of problems) accuracy in predicting the change in performance.
  arXiv  Detail & Related papers  (2021-02-12T16:59:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.