LLM Code Generation

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 42% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 196

All topics

Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing
Aug 9, 2026Srinivasan Manoharan, Junhua Zhao, Fangbo Tu +6Cost-Aware Inference LLM Routing
PayPal
Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations
Aug 8, 2026Jiří Klepl, Maty'aš Brabec, Martin KrulišHigh-Performance Computing Large Language Model-Guided Optimization
Charles University, Prague, Czech Republic
DevIntent: How Much Does LLM-Generated Code Violate Developer Intent?
Aug 7, 2026Susana Haing, Natan Vidra, Spurthi SettyLanguage Model Generation Evaluation Code Generation Evaluation
Anote AI
LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs
Aug 6, 2026Lukas Twist, Twm Stone, Helen Yannakoudakis +1LLM Evaluation Language Model Bias Evaluation
King’s College London, London, UK · MATS Research
Large language models for partial differential equation workflows
Aug 4, 2026Han Wan, Rui Zhang, Hao SunPDE Discovery Large Language Model-Guided Optimization
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing 100872, China
Distilling Reasoning Traces into Advisory Prompts for Software Engineering Tasks
Aug 1, 2026Faizan Faisal, Prem Devanbu, Toufique AhmedReasoning Distillation LLM Prompting
University of California, Davis · IBM
Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies
Jul 31, 2026Jan Marius Stürmer, Jascha Knack, Tobias Koch +1LLM Prompting Code Generation Evaluation
German Aerospace Centre (DLR), Institute for the Protection of Terrestrial Infrastructures, Rathausallee 12, 53757, Sankt Augustin, Germany · Algorithms for Computer Vision, Imaging and Data Analysis, Technische Hochschule Würzburg-Schweinfurt, Ignaz-Schön-Straße 11, Schweinfurt, 97421, Germany
RTLCurator: Label-Efficient Data Curation for RTL Generation
Jul 31, 2026Siyang Cai, Cangyuan Li, Wenjing Chang +4Training Data Curation Training Data Selection
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China · CICS, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · Computer Network Information Center, Chinese Academy of Sciences, Beijing, China +1
Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation
Jul 30, 2026Zhibo Hu, Chen Wang, Yanfeng Shu +3Language Model Steering Code Generation
The University of New South Wales · Australia · CSIRO
SecDrift: Measuring Sector-Conditioned Security Drift in AI-Generated Code
Jul 28, 2026Narayanaswami Natraj Bharadwaj, Dhivya ChandramouleeswaranCybersecurity LLM Security
Independent Researcher USA
Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures
Jul 27, 2026Fabian Kreppel, Reza Salkhordeh, Ferdinand Schmidt-Kaler +1Quantum Circuit Compilation LLM-Based Program Synthesis
Institute of Computer Science, Johannes Gutenberg University, Mainz, Germany · Institute of Physics, Johannes Gutenberg University, Mainz, Germany · Department of Computer Science, Saarland University, Saarbrücken, Germany
AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation
Jul 24, 2026Jie "JW" WuCode Generation Code Generation Evaluation
Michigan Technological University, Houghton, MI, USA
Benchmarking LLMs for Verilog Design Flows
Jul 23, 2026Angshuman Chakravertty, Rahul Koshti, Buddhi Prakash Sharma +1Code Generation Code Generation Evaluation
School of Technology Management and Engineering, NMIMS, Hyderabad, India · Department of Electronics and Communication Engineering, Indian Institute of Technology, Roorkee, India · Department of Electrical and Electronics Engineering and the Anuradha and Prashanth Palakurthi Centre for Artificial Intelligence Research (APPCAIR), Birla Institute of Technology and Science, Pilani (BITS Pilani), Pilani 333031, India
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
Jul 23, 2026Mack Nixon, Liam Wright, Yevgeniya Kovalchuk +4AI Agent Benchmarks Open-Weight Language Models
Centre for Advanced Research Computing, University College London, London, UK · Centre for Longitudinal Studies, University College London, London, UK · UK Longitudinal Linkage Collaboration, University of Bristol, Bristol, UK
An LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Process Models
Jul 23, 2026Ari Luna Rueda, Eike Cramer, Klaus Hellgardt +1Language Model-Based Control Feedback Control
Department of Chemical Engineering Imperial College London London, UK · Department of Chemical Engineering University College London London, UK
Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM Agents
Jul 22, 2026Jiale Lao, Immanuel TrummerCode Generation Agentic Code Generation
Cornell University
Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code
Jul 21, 2026Vidyut Sriram, Saatvik Pradhan, Suman SahaAutomated Program Repair Code Generation
The Pennsylvania State University
Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator
Jul 21, 2026Yuxiang JiSynthetic Benchmark Generation Data Contamination in Language Models
Sunway College
Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments
Jul 20, 2026Shuoming Zhang, Ruiyuan Xu, Haofeng Li +7Code Generation LLM Code Generation
SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Leeds, United Kingdom
CommitLLM: A Fine-Tuned Pipeline for Git Commit Message Generation
Jul 20, 2026Md Rafid Haque, Poojan Narendrabhai Patel, Meetkumar Vijaybhai RaychuraLLM Code Generation Text Generation
University of Illinois at Chicago
Can LLMs Build a MaxSAT Solver from Papers? The CoreForge Experience
Jul 16, 2026Ruben MartinsLLM-Based Program Synthesis Combinatorial Optimization
Carnegie Mellon University
Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality
Jul 16, 2026Saima Afrin, Alessandro Midolo, Camilo Escobar-Velásquez +5Multilingual Language Model Evaluation Code Generation
William & Mary, VA, USA · University of Catania, Italy · Universidad de los Andes, Colombia +2
How to Guide LLM Generation: Dual-Surrogate Guided Search for Automated Heuristic Design
Jul 15, 2026Yuhan Wang, Chaoda Peng, Xingyu Wu +2Surrogate-Assisted Optimization Automated Heuristic Design
College of Mathematics and Informatics, South China Agricultural University · Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University · College of Artificial Intelligence, Nankai University
Quantize with Confidence? An Empirical Study of Quantization for Code Generation
Jul 15, 2026Saima Afrin, Md. Zahidul Haque, Antonio MastropaoloLLM Quantization Code Generation Evaluation
AURA Lab · Department of Computer Science · William & Mary +1
Line-Anchored Feedback Cuts Token Costs and Improves Correctness in AI Code Editing
Jul 14, 2026William Franz LambertiCode Generation Evaluation Code Language Models
Computational and Data Sciences College of Science George Mason University Fairfax, VA, United States
The Hitchhiker's Guide to Monoculture: AI Homogenizes Syntax, Not (Necessarily) Semantics
Jul 12, 2026Gordon BurtchAI Coding Agents LLM Code Generation
Boston University
Knowledge-Conditioned, Single-Pass LLM Synthesis of Executable Unity Game Scenes: A Compiler Error Census across 26 Goal Playable Concepts
Jul 11, 2026Hugh Xuechen Liu, Kıvanç TatarLLM-Based Program Synthesis Procedural Content Generation
Chalmers University of Technology and University of Gothenburg, SE-412 96 Göteborg, Sweden
Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database Bypass
Jul 8, 2026Victor Giannakouris, Immanuel TrummerLLM Code Generation Relational Databases
Cornell University Ithaca, NY, USA
Specification Grounding Drives Test Effectiveness for LLM Code
Jul 7, 2026Amin Haeri, Mahdi GhelichiLLM Grounding Automated Software Testing
Model Development Innovation TD Bank, Toronto, Canada
Benchmarking API Drift in LLM-Generated Quantum Code Across Successive SDK Versions
Jul 5, 2026Mohammad Arif Rasyidi, Syahirul FaizCode Generation Benchmarks LLM Code Generation
Department of Computer Science Khalifa University Abu Dhabi, United Arab Emirates

Aug 9, 2026, cs.LGJ/K move · Enter open · S save

Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing

Srinivasan Manoharan, Junhua Zhao, Fangbo Tu, Haifeng Wu+5

PayPal

Cost-Aware Inference LLM Routing LLM Code Generation

Open paper AskPDF arXiv

Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries, escalations, and developer wait time are included. We present Task-to-Model Optimization (T2MO), a data-driven methodology for optimizing model selection in production coding workflows. We treat each developer session as a task that can be discovered, classified, graded for difficulty, benchmarked in a production-like harness, and routed to the cheapest model able to complete it within quality and latency constraints. The framework is a nine-stage pipeline spanning telemetry instrumentation, taxonomy discovery, difficulty grading, benchmark construction, candidate evaluation, optimal mix derivation, forecasting and version planning, staged routing deployment, and continuous governance. Unlike token-centric routing rules, our objective is cost per completed task, with failure escalation priced in explicitly. We show that this expected-completion-cost objective weakly dominates token-cost minimization under escalation, and we derive the routing boundary, the minimum pass rate a cheaper model must reach on a given cell to be worth deploying. Decisions are organized as a two-level hierarchy of task category difficulty tier, and per-cell displacement opportunities are aggregated into a traffic-weighted savings waterfall that ranks replacement candidates by realized dollar impact. The framework supports developer guidance, spend forecasting, and a staged transition from static policies to shadow-mode classifiers, verified cascades, and ultimately an intelligent router. We describe the methodology, optimization objective, evaluation protocol, and governance loop in a form suitable for production deployment and future empirical study.

Momentum

Related topics

Latest papers 196