#code generation

try —

41 papers match

cs.SE2026

The Case for Vibe Modeling: A Missing Step in AI-Based Trustworthy Software Development

Shalini Chakraborty, Michael Mittermaier, Judith Michael

The paper proposes "vibe modeling" as a lightweight intermediate abstraction between natural language prompts and code generation by large language models, aiming to improve unders…

#large language models#code generation#trustworthy AI#intermediate representations
cs.SE2026

CoGate: Confidence-Gated Co-Decoding for Secure Code Generation

Minghao Hu, Lannan Luo, Allen Roush +1

The paper introduces CoGate, a method that uses the confidence of a security expert model to gate its influence during co-decoding for generating more secure code with large langua…

#code generation#large language models#security#co-decoding
cs.AI2026

IndustryForge-27B: A Domain-Enhanced Multimodal Foundation Model for Industrial CAD

Nianchen Deng, Jiaxin Ai, Tao Hu +10

The paper introduces IndustryForge-27B, a multimodal foundation model fine‑tuned on diverse industrial CAD data to understand drawings, generate parametric modeling scripts, and co…

#multimodal models#industrial cad#parametric modeling#code generation
cs.CL2026

Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models

Yecheng Wu, Song Han, Han Cai

The paper proposes Lightning OPD 2.0, a method that reduces style‑related bias when using on‑policy distillation across different teacher models, improving performance on mathemati…

#style bias#on-policy distillation#cross-teacher training#reasoning models
cs.SE2026

MRCoder: An Efficient Context Selecting Approach for Repository-Level Code Generation

Peiding Wang, Li Zhang, Fang Liu

The paper introduces MRCoder, a map-reduce based framework that selects and refines repository-specific code context using lightweight draft models, improving the accuracy and effi…

#code generation#large language models#context selection#repository-level programming
cs.LG2026

From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models

Seunggeun Kim, Jaeyeon Kim, Taekyun Lee +4

The paper investigates how to give language models a native ability to reason and generate text in any order, introducing insertion‑based and latent‑space masked diffusion methods…

#any-order inference#masked diffusion models#code generation#insertion-based generation
cs.SE2026

CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development

Peiding Wang, Li Zhang, Fang Liu +2

The paper introduces CodeSpec, a method that creates paired architecture and behavior specifications to guide LLM-based code agents in developing new features across existing codeb…

#code generation#software agents#feature development#executable specifications
cs.LG2026

DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning

Shuhang Wang, Ziming Li, Hui Cheng

The paper introduces DHRCL, a reinforcement‑learning framework for code‑focused large language models that uses a hierarchy of dense rewards (syntax, execution, unit‑test pass, and…

#code generation#reinforcement learning#curriculum learning#dense rewards
cs.SE2026

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

Yihao Chen, Shi Chang, Khaled Chawa +4

MindForge automatically turns open‑source command‑line programs into source‑free environments that expose only compiled executables and documentation, enabling the training of smal…

#source-free program synthesis#software engineering lifecycle#code generation#model fine‑tuning
cs.AI2026

Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants

Zijian Xu, Wenshuo Zhang, Zisen Qin +4

The paper defines personalized ambiguity adaptation for coding assistants, introduces the CAPA benchmark to evaluate how well models use a user's past resolved sessions to handle r…

#code generation#personalized assistance#ambiguity resolution#user history
cs.LG2026

RLPF: Reinforcement Learning from Performance Feedback for Code Generation

Huihao Jing, Haozhe Cui, Wenbin Hu +9

The paper introduces RLPF, a reinforcement‑learning approach that uses staged performance feedback to train code‑generation models to produce not only correct programs but also fas…

#reinforcement learning#code generation#performance optimization#execution feedback
cs.CL2026

VisualPatchWorld: Code World Models as Latent Structured Representations for Planning

Jiaxin Bai, Jiaxuan Xiong

The paper presents VisualPatchWorld, a system that learns compact code programs to model world dynamics from visual observations, enabling inspection, simulation, and use in model-…

#world models#code generation#model predictive control#visual scene graphs
cs.LG2026

Weak-to-Strong On-Policy Distillation

Fangxu Yu, Zinan Lin, Xiaodong Liu +4

The paper proposes Weak-to-Strong On-Policy Distillation (W2S-OPD), a method that improves a large language model by distilling knowledge from multiple weaker models using a constr…

#on-policy distillation#large language models#knowledge distillation#reinforcement learning
cs.AI2026

TraceCoder: Explainable and Auditable Code Generation with Position-Key Snippet Versioning

Rwaida Alssadi, Muntaser Syed, Balaji Kasula +6

The paper introduces TraceCoder, a system that records detailed provenance for each code snippet generated by large language models, visualizes the evolution of code through repair…

#code generation#explainability#auditability#llm-based programming
cs.SE2026

Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories

Prakhar Khatri

The paper investigates whether providing persistent context files (like AGENTS.md) improves the performance of AI coding agents, finding no measurable benefit across Claude Code an…

#coding agents#context files#ablation study#code generation
cs.LG2026

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation

Carlo Di Cicco

The paper shows that the hidden state of a large language model right before it starts generating code contains a linear signal that predicts whether the produced code will be corr…

#code generation#large language models#hidden state analysis#linear probing
cs.SE2026

Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality

Saima Afrin, Alessandro Midolo, Camilo Escobar-Velásquez +5

The paper introduces a curated multilingual benchmark to study how the natural language of prompts influences code generation quality of large language models, evaluating functiona…

#language bias#code generation#multilingual prompts#benchmark
cs.AI2026

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Yubo Wang, Jiarong Liang, Yuxuan Zhang +5

The paper introduces a function-aware fill-in-the-middle (FIM) mid‑training method that masks function calls in code to improve coding agents' ability to incorporate tool outputs,…

#code generation#coding agents#function-aware training#fill-in-the-middle
cs.LO2026

Can LLMs Build a MaxSAT Solver from Papers? The CoreForge Experience

Ruben Martins

The paper describes CoreForge, an effort to use large language models to implement an unweighted MaxSAT solver directly from research papers, detailing the workflow, components bui…

#large language models#maxsat#solver development#unsatisfiability algorithms
cs.SE2026

Capturing and Exploiting Design Pattern Variability in Mobile Application Generation

Ramón Peralta, Jose-Miguel Horcas

The increasing reliance on automatic code generation in mobile application development often leads to code that neglects fundamental design principles and architectural quality. In…

#design patterns#variability modeling#model-driven engineering#code generation
hep-lat2026

LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research

Haofei Gao, Tingjia Miao, Wenkai Jin +12

LQCDMaster is an AI-driven scientific computing agent that translates natural‑language lattice QCD research tasks into fully executable PyQUDA workflows, automating code generation…

#lattice qcd#scientific computing#AI agents#code generation
cs.CL2026

Token Reduction Is Not Cost Reduction

Sarel Weinberger, Amir Hozez

The paper studies whether context‑reduction techniques for API‑based coding agents actually lower the billed cost of using large language models, showing that token reduction often…

#code generation#context reduction#cost evaluation#token compression
cs.SE2026

Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair

Woorim Han, Yeongjun Kwak, Miseon Yu +4

The paper investigates how well fine‑tuned language models can automatically fix unseen software vulnerabilities and critiques common token‑level evaluation metrics, introducing a…

#automated vulnerability repair#language models#code generation#evaluation metrics
cs.SE2026

Design-Specification Tiling for ICL-based CAD Code Generation

Yali Du, San-Zhuo Xi, Hui Sun +1

The paper introduces Design‑Specification Tiling, a method for selecting in‑context learning exemplars that maximizes coverage of CAD design requirements, using a knowledge‑suffici…

#in-context learning#code generation#computer-aided design#exemplar selection

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.