Song Wang

Soumit Kanti Saha, Fazle Rabbi, Song Wang et al.

Large Language Models (LLMs) are increasingly being applied across various domains, including code-related tasks such as code translation. Previous studies have explored using LLMs for translating code between different programming languages. Since LLMs are more effective with natural language, using natural language as an intermediate representation in code translation tasks is an intuitively appealing approach. However, whether this benefit is general or highly context-dependent remains unclear. In this work, we investigate using NL-specification as an intermediate representation for code translation. We evaluate our method using three datasets, five popular programming languages, and 29 language pair permutations. Our results show that using NL-specification alone does not lead to performance improvements. However, when combined with source code, it provides gains in certain language pairs (notably with Python and C++ as source languages), while offering no consistent improvement overall. Besides analyzing the performance of code translation, we also investigate the quality of the translated code and provide insights into the issues present in the translated code.

Melika Sepidband, Hamed Taherkhani, Song Wang et al.

Automatic code generation has gained significant momentum with the advent of Large Language Models (LLMs) such as GPT-4. Although many studies focus on improving the effectiveness of LLMs for code generation, very limited work tries to understand the generated code's characteristics and leverage that to improve failed cases. In this paper, as the most straightforward characteristic of code, we investigate the relationship between code complexity and the success of LLM generated code. Using a large set of standard complexity metrics, we first conduct an empirical analysis to explore their correlation with LLM's performance on code generation (i.e., Pass@1). Using logistic regression models, we identify which complexity metrics are most predictive of code correctness. Building on these findings, we propose an iterative feedback method, where LLMs are prompted to generate correct code based on complexity metrics from previous failed outputs. We validate our approach across multiple benchmarks (i.e., HumanEval, MBPP, LeetCode, and BigCodeBench) and various LLMs (i.e., GPT-4o, GPT-3.5 Turbo, Llama 3.1, and GPT-o3 mini), comparing the results with two baseline methods: (a) zero-shot generation, and (b) iterative execution-based feedback without our code complexity insights. Experiment results show that our approach makes notable improvements, particularly with a smaller LLM (GPT3.5 Turbo), where, e.g., Pass@1 increased by 35.71% compared to the baseline's improvement of 12.5% on the HumanEval dataset. The study expands experiments to BigCodeBench and integrates the method with the Reflexion code generation agent, leading to Pass@1 improvements of 20% (GPT-4o) and 23.07% (GPT-o3 mini). The results highlight that complexity-aware feedback enhances both direct LLM prompting and agent-based workflows.

Mian Zhang, Shujian Liu, Sixun Dong et al. · microsoft-research

Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agentic behaviors. As tasks grow more challenging, the logic structures embedded in natural language instructions becomes increasingly intricate. However, how well LLMs perform on such logic-rich instructions remains under-explored. We propose LogicIFGen and LogicIFEval. LogicIFGen is a scalable, automated framework for generating verifiable instructions from code functions, which can naturally express rich logic such as conditionals, nesting, recursion, and function calls. We further curate a collection of complex code functions and use LogicIFGen to construct LogicIFEval, a benchmark comprising 426 verifiable logic-rich instructions. Our experiments demonstrate that current state-of-the-art LLMs still struggle to correctly follow the instructions in LogicIFEval. Most LLMs can only follow fewer than 60% of the instructions, revealing significant deficiencies in the instruction-following ability. Code and Benchmark: https://github.com/mianzhang/LogicIF

Haoran Xue, Gias Uddin, Song Wang

Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these reasoning chains remains underexplored. We present a comprehensive empirical study examining the reasoning process and quality of thinking LLMs for code generation. We evaluate six state-of-the-art reasoning LLMs (DeepSeek-R1, OpenAI-o3-mini, Claude-3.7-Sonnet-Thinking, Gemini-2.0-Flash-Thinking, Gemini-2.5-Flash, and Qwen-QwQ) across 100 code generation tasks of varying difficulty from BigCodeBench. We quantify reasoning-chain structure through step counts and verbosity, conduct controlled step-budget adjustments, and perform a 21-participant human evaluation across three dimensions: efficiency, logical correctness, and completeness. Our step-count interventions reveal that targeted step increases can improve resolution rates for certain models/tasks, while modest reductions often preserve success on standard tasks, rarely on hard ones. Through systematic analysis, we develop a reasoning-problematic taxonomy, identifying completeness as the dominant failure mode. Task complexity significantly impacts reasoning quality; hard problems are substantially more prone to incompleteness than standard tasks. Our stability analysis demonstrates that thinking LLMs maintain consistent logical structures across computational effort levels and can self-correct previous errors. This study provides new insights into the strengths and limitations of current thinking LLMs in software engineering.