Challenge: Modern software development demands code that is maintainable, testable, and scalable by organizing the implementation into modular components with iterative reuse of existing codes.
Approach: They propose a benchmark to evaluate LLMs' ability to perform codeflow by reusing existing functions over multiple turns.
Outcome: The proposed benchmarks show that LLMs perform significantly worse in multi-turn codeflow scenarios and that their performance inversely correlates with dependency complexity.

Similar Papers

StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluation benchmarks focus on fine-grained constraint satisfaction and domain-specific capability assessment, yet overlook the crucial structural dependencies between dialogue turns that distinguish multi-turn from single-turn interactions.
Approach: They propose a multi-turn instruction following benchmark with structural flow modeling that defines an innovative structural flow framework with six fundamental inter-turn relationships.
Outcome: The proposed model is based on a framework with six fundamental inter-turn relationships and is able to analyze and generate specific dialogue flows tailored to specific scenarios.
TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks focus on single-turn or single-step tasks, failing to capture iterative reasoning in real-world settings.
Approach: They propose a benchmark that evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by the "Turing Machine Board Game" the best model achieves 84% accuracy in Classic mode, but performance drops to 18% in Nightmare mode.
Outcome: The new benchmark evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by the "Turing Machine Board Game" the best model achieves 84% accuracy in Classic mode, but performance drops to 18% in Nightmare mode.
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for evaluating the code understanding and generation capacities of Large Language Models are insufficient . existing benchmarks focus on a narrow range of popular programming languages and specific tasks .
Approach: They propose an execution-based, multilingual, multitask evaluation benchmark for LLMs . they evaluate coding performance from three dimensions: length, difficulty, efficiency .
Outcome: The proposed benchmark covers 43 programming languages and eight coding tasks.
DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing code benchmarks for large language models remain static, resulting in data contamination and unreliable evaluation results.
Approach: They propose a dynamic, complexity-aware benchmark that overcomes the limitations of static datasets and provides a memorization-advantaged benchmark.
Outcome: DynaCode generates 189 million unique nested code problems across 4 units of code complexity and 16 types of call graphs.
Turning the Tide: Repository-based Code Reflection (2025.findings-emnlp)

Copied to clipboard

Challenge: Code large language models (LLMs) enhance programming by understanding and generating code across languages.
Approach: a new benchmark evaluates code understanding and generation in repositories using code large language models.
Outcome: The proposed model improves code understanding and generation in repositories by evaluating 1,888 test cases across 6 programming languages.
EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks focusing on single-task environments with limited constraints lack the complexity required to fully reflect the evolution of large language models (LLMs).
Approach: They propose to use a Segment Policy Optimization algorithm to enhance the LLM's ability to accurately fulfill multi-task workflows.
Outcome: The proposed benchmarks show that existing benchmarks lack the complexity required to fully reflect the evolution of large language models.
XCodeEval: An Execution-based Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.
Approach: They propose to use a multilingual multitask benchmark to evaluate large language models that can generate codes from natural language descriptions, repair buggy codes, and translate between languages.
Outcome: The proposed model performs 7 tasks covering up to 11 languages with execution-level parallelism and 25 M document-level coding examples (16.5 B tokens)
CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly used to judge code, but their reliability remains poorly understood.
Approach: They propose a benchmark to evaluate Large Language Models as code judges . they find that small reasoning models outperform larger non-reasoning models .
Outcome: The proposed benchmark evaluates LLM-as-a-Judge models across three coding tasks.
LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking (2024.eacl-demo)

Copied to clipboard

Challenge: Recent development and success of Large Language Models necessitate evaluation of their performance across diverse NLP tasks in different languages.
Approach: They propose a framework that can be customized to evaluate LLMs for any NLP task, regardless of language.
Outcome: The LLMeBench framework can be customized to evaluate LLMs for any NLP task, regardless of language.
FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on standalone programming problems, such as HumanEval, MBPP, and LiveCodeBench.
Approach: They propose to use large language models to evaluate their ability to perform incremental development within code repositories by collecting pull requests from 83 GitHub repositorias and using rule-based and intent-based filtering to construct task instances focused on new feature development.
Outcome: The proposed benchmarks show that large language models perform significantly worse in the FEA-Bench, highlighting considerable challenges in repository-level incremental code development.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations