mlsanityData to 7 Oct 2026

Advancing Language Models for Code-related Tasks

arXiv 2601.04526 ↗First posted 8 Jan 2026cs.SE cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in language models (LMs) have driven significant progress in various software engineering tasks. However, existing LMs still struggle with complex programming scenarios due to limitations in data quality, model architecture, and reasoning capability. This research systematically addresses these challenges through three complementary directions: (1) improving code data quality with a code difference-guided adversarial augmentation technique (CODA) and a code denoising technique (CodeDenoise); (2) enhancing model architecture via syntax-guided code LMs (LEAM and LEAM++); and (3) advancing model reasoning with a prompting technique (muFiX) and an agent-based technique (Specine). These techniques aim to promote the practical adoption of LMs in software development and further advance intelligent software engineering.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

23 of 40 references.

References · 23

  1. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  2. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  3. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  4. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  5. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  6. 2023Teaching Large Language Models to Self-Debugcited by 963
  7. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  8. 2023Self-collaboration Code Generation via ChatGPTcited by 255
  9. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 191
  10. 2023Software Testing with Large Language Models: Survey, Landscape, and Visioncited by 163
  11. 2023Structured Chain-of-Thought Prompting for Code Generationcited by 136
  12. 2023Self-planning Code Generation with Large Language Modelscited by 121
11 more
  1. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 110
  2. 2025Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scalingcited by 93
  3. 2022Natural Attack for Pre-trained Models of Codecited by 72
  4. 2022An Empirical Study of Deep Learning Models for Vulnerability Detectioncited by 44
  5. 2024Test-Driven Development for Code Generationcited by 32
  6. 2018Learning How to Mutate Source Code from Bug-Fixescited by 13
  7. 2023Code Difference Guided Adversarial Example Generation for Deep Code Modelscited by 8
  8. 2024Large Language Models for Equivalent Mutant Detection: How Far Are We?cited by 6
  9. 2025Aligning Requirement for Large Language Model's Code Generationcited by 4
  10. 2023On-the-fly Improving Performance of Deep Code Models via Input Denoisingcited by 2
  11. 2025On the Effectiveness of Training Data Optimization for LLM-based Code Generation: An Empirical Studycited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence
  2. 2025LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
  3. 2024Improving the Ability of Pre-trained Language Model by Imparting Large Language Model's Experience ↗
  4. 2024Large Language Model Evaluation Via Multi AI Agents: Preliminary results
  5. 2023L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
  6. 2023Augmented Language Models: a Survey
  7. 2024Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?
  8. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents