LLMs advance code editing, generation, and bug detection with new techniques
ByPulseAugur Editorial·
Summary by gemini-2.5-flash-lite
from 19 sources
Researchers are exploring various methods to enhance Large Language Models (LLMs) for code-related tasks. One study evaluates locally deployed LLMs like LLaMA 3.2 and Mistral for Python bug detection, finding they can identify bugs but struggle with precise localization. Another paper introduces TreeCoder, a framework to optimize LLM code generation by treating decoding strategies and constraints as optimizable components, improving accuracy on benchmarks like MBPP and SQL-Spider. Additionally, a case study at BMW demonstrates how fine-tuning LLMs like Qwen2.5-Coder and DeepSeek-Coder can generate and modify enterprise domain-specific languages across multiple files. Finally, a new approach called CAT uses call-chain awareness to improve LLM-based unit test generation for Java projects, significantly boosting code coverage.
AI
arXiv:2604.27296v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bottlenecks, posing challenges for interactive coding assistants that demand low l…
arXiv cs.AI
TIER_1·Rongliang Fu, Yi Liu, Qiang Xu, Tsung-Yi Ho·
arXiv:2604.26591v1 Announce Type: cross Abstract: Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimization scripts, their potential for core algorithm enhancement remains untapped. We …
Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bottlenecks, posing challenges for interactive coding assistants that demand low latency and cost. Despite the predominant focus on …
Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimization scripts, their potential for core algorithm enhancement remains untapped. We introduce MappingEvolve, an open-source framework …
arXiv:2604.18245v2 Announce Type: replace Abstract: Large language models are increasingly deployed as protocols: structured multi-call procedures that spend additional computation to transform a baseline answer into a final one. These protocols are evaluated only by end-to-end a…
arXiv cs.AI
TIER_1·Amal Akli, Mike Papadakis, Maxime Cordy, Yves Le Traon·
arXiv:2604.24703v1 Announce Type: cross Abstract: Large language models are widely used for code generation, yet they rely on an implicit assumption that the task descriptions are sufficiently detailed and well-formed. However, in practice, users may provide defective description…
arXiv cs.AI
TIER_1·Sivajeet Chand, Kevin Nguyen, Peter Kuntz, Alexander Pretschner·
arXiv:2604.24678v1 Announce Type: cross Abstract: Large language models (LLMs) perform strongly on general-purpose code generation, yet their applicability to enterprise domain-specific languages (DSLs) remains underexplored, especially for repository-scale change generation span…
arXiv:2604.23361v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance on a wide range of software engineering tasks, including code generation and analysis. However, most prior work relies on cloud-based models or specialized hardware…
Large language models are widely used for code generation, yet they rely on an implicit assumption that the task descriptions are sufficiently detailed and well-formed. However, in practice, users may provide defective descriptions, which can have a strong effect on code correctn…
Large language models (LLMs) perform strongly on general-purpose code generation, yet their applicability to enterprise domain-specific languages (DSLs) remains underexplored, especially for repository-scale change generation spanning multiple files and folder structures from a s…
arXiv:2511.22277v2 Announce Type: replace Abstract: Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most g…
arXiv cs.AI
TIER_1·Guancheng Wang, Qinghua Xu, Lionel C. Briand, Zhaoqiang Guo, Kui Liu·
arXiv:2604.22046v1 Announce Type: cross Abstract: Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approaches primarily rely on execution-path information to guide prompt construction, wh…
Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approaches primarily rely on execution-path information to guide prompt construction, which is often insufficient for complex software sys…
Multi-agent frameworks are widely used in autonomous code generation and have applications in complex algorithmic problem-solving. Recent work has addressed the challenge of generating functionally correct code by incorporating simulation-driven planning and debugging, where lang…
Multi-agent frameworks are widely used in autonomous code generation and have applications in complex algorithmic problem-solving. Recent work has addressed the challenge of generating functionally correct code by incorporating simulation-driven planning and debugging, where lang…
Multi-domain detection of the machine-generated code snippets in various programming languages is a challenging task. SemEval-2026 Task~13 copes with this challenge in various angles, as a binary detection problem as well as attribution of the source. Specifically, its subtasks a…
<p>You might have heard a lot about code generation tools using AI, but could LLMs and generative AI make our existing code better? In this episode, we sit down with Mike from TurinTech to hear about practical code optimizations using AI “translation” of slow to fast code. We lea…
