{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/code-generation/papers/11","list_of":"/task/code-generation","task":"Code Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":11,"pages_in_order":17,"rows_per_page":100,"rows":[1001,1100],"of":1697,"counts":{"archive_papers_tagged":1697,"with_a_code_link":745,"where_syntology_ran_a_sample":280,"not_listed_spam_title":0,"listed":1697,"listed_where_code_ran":280,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":238,"every_run_a_failure_of_syntologys_instrument":42,"listed_with_a_run_with_no_instrument_failure":238,"listed_every_run_a_failure_of_syntologys_instrument":42,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/code-generation","prev":"/task/code-generation/papers/10","next":"/task/code-generation/papers/12","papers":[{"url":null,"slug":"hidden-darkness-in-llm-generated-designs","title":"Hidden Darkness in LLM-Generated Designs: Exploring Dark Patterns in Ecommerce Web Components Generated by LLMs","date":"2025-02-19","arxiv_id":"2502.13499","repositories_listed":0,"syntology":null},{"url":null,"slug":"boost-disentangle-and-customize-a-robust","title":"Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation","date":"2025-02-18","arxiv_id":"2502.12492","repositories_listed":0,"syntology":null},{"url":null,"slug":"equibench-benchmarking-code-reasoning","title":"EquiBench: Benchmarking Large Language Models' Understanding of Program Semantics via Equivalence Checking","date":"2025-02-18","arxiv_id":"2502.12466","repositories_listed":0,"syntology":null},{"url":null,"slug":"gsce-a-prompt-framework-with-enhanced","title":"GSCE: A Prompt Framework with Enhanced Reasoning for Reliable LLM-driven Drone Control","date":"2025-02-18","arxiv_id":"2502.12531","repositories_listed":0,"syntology":null},{"url":null,"slug":"sens-merging-sensitivity-guided-parameter","title":"Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models","date":"2025-02-18","arxiv_id":"2502.12420","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-github-copilot-on-software","title":"The Role of GitHub Copilot on Software Development: A Perspective on Productivity, Security, Best Practices and Future Directions","date":"2025-02-18","arxiv_id":"2502.13199","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm4effi-leveraging-large-language-models-to","title":"LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness","date":"2025-02-17","arxiv_id":"2502.18489","repositories_listed":0,"syntology":null},{"url":null,"slug":"unitcoder-scalable-iterative-code-synthesis","title":"UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance","date":"2025-02-17","arxiv_id":"2502.11460","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-interpretable-automated-mechanism-design","title":"An Interpretable Automated Mechanism Design Framework with Large Language Models","date":"2025-02-16","arxiv_id":"2502.12203","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversified-sampling-improves-scaling-llm","title":"Diversified Sampling Improves Scaling LLM inference","date":"2025-02-16","arxiv_id":"2502.11027","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-review-on-llm-for-solving","title":"Performance Review on LLM for solving leetcode problems","date":"2025-02-16","arxiv_id":"2502.15770","repositories_listed":0,"syntology":null},{"url":null,"slug":"vispath-automated-visualization-code","title":"Automated Visualization Code Synthesis via Multi-Path Reasoning and Feedback-Driven Optimization","date":"2025-02-16","arxiv_id":"2502.11140","repositories_listed":0,"syntology":null},{"url":null,"slug":"1bit-merging-dynamic-quantized-merging-for","title":"1bit-Merging: Dynamic Quantized Merging for Large Language Models","date":"2025-02-15","arxiv_id":"2502.10743","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-grounded-vision-language-framework-for","title":"3D-Grounded Vision-Language Framework for Robotic Task Planning: Automated Prompt Synthesis and Supervised Reasoning","date":"2025-02-13","arxiv_id":"2502.08903","repositories_listed":0,"syntology":null},{"url":null,"slug":"crane-reasoning-with-constrained-llm","title":"CRANE: Reasoning with constrained LLM generation","date":"2025-02-13","arxiv_id":"2502.09061","repositories_listed":0,"syntology":null},{"url":null,"slug":"refinecoder-iterative-improving-of-large","title":"RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation","date":"2025-02-13","arxiv_id":"2502.09183","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-llm-character-level-manipulation","title":"Enhancing LLM Character-Level Manipulation via Divide and Conquer","date":"2025-02-12","arxiv_id":"2502.08180","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-powerpoint-ui-sketches-to-web-based","title":"From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework","date":"2025-02-12","arxiv_id":"2502.08756","repositories_listed":0,"syntology":null},{"url":null,"slug":"verifying-llm-generated-code-in-the-context","title":"Verifying LLM-Generated Code in the Context of Software Verification with Ada/SPARK","date":"2025-02-11","arxiv_id":"2502.07728","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-replace-human-evaluators-an","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","date":"2025-02-10","arxiv_id":"2502.06193","repositories_listed":0,"syntology":null},{"url":null,"slug":"cardiverse-harnessing-llms-for-novel-card","title":"Cardiverse: Harnessing LLMs for Novel Card Game Prototyping","date":"2025-02-10","arxiv_id":"2502.07128","repositories_listed":0,"syntology":null},{"url":null,"slug":"lessleak-bench-a-first-investigation-of-data","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","date":"2025-02-10","arxiv_id":"2502.06215","repositories_listed":0,"syntology":null},{"url":null,"slug":"snipgen-a-mining-repository-framework-for","title":"SnipGen: A Mining Repository Framework for Evaluating LLMs for Code","date":"2025-02-10","arxiv_id":"2502.07046","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-i-cannot-execute-i-do-not-understand","title":"What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces","date":"2025-02-10","arxiv_id":"2503.05703","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-prompt-engineering-techniques","title":"Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models","date":"2025-02-09","arxiv_id":"2502.06039","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-sensitive-information-leakage-in","title":"Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning","date":"2025-02-09","arxiv_id":"2502.05739","repositories_listed":0,"syntology":null},{"url":null,"slug":"proving-the-coding-interview-a-benchmark-for","title":"Proving the Coding Interview: A Benchmark for Formally Verified Code Generation","date":"2025-02-08","arxiv_id":"2502.05714","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimistic-gradient-learning-with-hessian","title":"Optimistic Gradient Learning with Hessian Corrections for High-Dimensional Black-Box Optimization","date":"2025-02-07","arxiv_id":"2502.04829","repositories_listed":0,"syntology":null},{"url":null,"slug":"refining-integration-by-parts-reduction-of","title":"Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning","date":"2025-02-07","arxiv_id":"2502.05121","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-guided-self-debugging","title":"Large Language Model Guided Self-Debugging Code Generation","date":"2025-02-05","arxiv_id":"2502.02928","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-can-be-easily-confused-by-instructional","title":"LLMs can be easily Confused by Instructional Distractions","date":"2025-02-05","arxiv_id":"2502.04362","repositories_listed":0,"syntology":null},{"url":null,"slug":"path-planning-for-masked-diffusion-model","title":"Path Planning for Masked Diffusion Model Sampling","date":"2025-02-05","arxiv_id":"2502.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-language-models-to-critique-via","title":"Teaching Language Models to Critique via Reinforcement Learning","date":"2025-02-05","arxiv_id":"2502.03492","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-maintain-fundamental-abilities-under","title":"Can LLMs Maintain Fundamental Abilities under KV Cache Compression?","date":"2025-02-04","arxiv_id":"2502.01941","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-student-llm-interaction-in-a","title":"Analysis of Student-LLM Interaction in a Software Engineering Project","date":"2025-02-03","arxiv_id":"2502.01273","repositories_listed":0,"syntology":null},{"url":null,"slug":"next-steps-in-llm-supported-java-verification","title":"Next Steps in LLM-Supported Java Verification","date":"2025-02-03","arxiv_id":"2502.01573","repositories_listed":0,"syntology":null},{"url":null,"slug":"plotgen-multi-agent-llm-based-scientific-data","title":"PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback","date":"2025-02-03","arxiv_id":"2502.00988","repositories_listed":0,"syntology":null},{"url":null,"slug":"process-supervised-reinforcement-learning-for","title":"Process-Supervised Reinforcement Learning for Code Generation","date":"2025-02-03","arxiv_id":"2502.01715","repositories_listed":0,"syntology":null},{"url":null,"slug":"se-arena-benchmarking-software-engineering","title":"SE Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering","date":"2025-02-03","arxiv_id":"2502.01860","repositories_listed":0,"syntology":null},{"url":null,"slug":"security-and-quality-in-llm-generated-code-a","title":"Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis","date":"2025-02-03","arxiv_id":"2502.01853","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-neurosymbolic-program-comprehension","title":"Toward Neurosymbolic Program Comprehension","date":"2025-02-03","arxiv_id":"2502.01806","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-llms-vs-human-experts-in","title":"Analysis of LLMs vs Human Experts in Requirements Engineering","date":"2025-01-31","arxiv_id":"2501.19297","repositories_listed":0,"syntology":null},{"url":null,"slug":"importing-phantoms-measuring-llm-package","title":"Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities","date":"2025-01-31","arxiv_id":"2501.19012","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-adaptive-self-improvement-for-smarter","title":"Towards Adaptive Self-Improvement for Smarter Energy Systems","date":"2025-01-31","arxiv_id":"2501.19340","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-model-efficiencyvia","title":"Enhancing Large Language Model Efficiencyvia Symbolic Compression: A Formal Approach Towards Interpretability","date":"2025-01-30","arxiv_id":"2501.18657","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-multi-metric-evaluation-and","title":"Statistical multi-metric evaluation and visualization of LLM system predictive performance","date":"2025-01-30","arxiv_id":"2501.18243","repositories_listed":0,"syntology":null},{"url":null,"slug":"gllm-self-corrective-g-code-generation-using","title":"GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback","date":"2025-01-29","arxiv_id":"2501.17584","repositories_listed":0,"syntology":null},{"url":null,"slug":"programming-by-examples-meets-historical","title":"Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction","date":"2025-01-27","arxiv_id":"2501.16524","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-generative-artificial-intelligence","title":"Advancing Generative Artificial Intelligence and Large Language Models for Demand Side Management with Internet of Electric Vehicles","date":"2025-01-26","arxiv_id":"2501.15544","repositories_listed":0,"syntology":null},{"url":"/paper/enter-event-based-interpretable-reasoning-for","slug":"enter-event-based-interpretable-reasoning-for","title":"ENTER: Event Based Interpretable Reasoning for VideoQA","date":"2025-01-24","arxiv_id":"2501.14194","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-grounded-objectives-bridging-process","title":"Chain of Grounded Objectives: Bridging Process and Goal-oriented Prompting for Code Generation","date":"2025-01-23","arxiv_id":"2501.13978","repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudocode-injection-magic-enabling-llms-to","title":"Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks","date":"2025-01-23","arxiv_id":"2501.13731","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisit-self-debugging-with-self-generated","title":"Revisit Self-Debugging with Self-Generated Tests for Code Generation","date":"2025-01-22","arxiv_id":"2501.12793","repositories_listed":0,"syntology":null},{"url":null,"slug":"consolidating-tinyml-lifecycle-with-large","title":"Consolidating TinyML Lifecycle with Large Language Models: Reality, Illusion, or Opportunity?","date":"2025-01-20","arxiv_id":"2501.12420","repositories_listed":0,"syntology":null},{"url":"/paper/qualityflow-an-agentic-workflow-for-program","slug":"qualityflow-an-agentic-workflow-for-program","title":"QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks","date":"2025-01-20","arxiv_id":"2501.17167","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-advancing-code-generation-with-large","title":"Towards Advancing Code Generation with Large Language Models: A Research Roadmap","date":"2025-01-20","arxiv_id":"2501.11354","repositories_listed":0,"syntology":null},{"url":null,"slug":"sop-agent-empower-general-purpose-ai-agent","title":"SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs","date":"2025-01-16","arxiv_id":"2501.09316","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-metamemory-mechanisms-for-enhanced","title":"Leveraging Metamemory Mechanisms for Enhanced Data-Free Code Generation in LLMs","date":"2025-01-14","arxiv_id":"2501.07892","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-provider-bias-in-large-language","title":"The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation","date":"2025-01-14","arxiv_id":"2501.07849","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-agent-based-program-repair-at","title":"Evaluating Agent-based Program Repair at Google","date":"2025-01-13","arxiv_id":"2501.07531","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-code-generation-with-llms-a-multi","title":"Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks","date":"2025-01-11","arxiv_id":"2501.06625","repositories_listed":0,"syntology":null},{"url":null,"slug":"bioagents-democratizing-bioinformatics","title":"BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systems","date":"2025-01-10","arxiv_id":"2501.06314","repositories_listed":0,"syntology":null},{"url":null,"slug":"dafny-as-verification-aware-intermediate","title":"Dafny as Verification-Aware Intermediate Language for Code Generation","date":"2025-01-10","arxiv_id":"2501.06283","repositories_listed":0,"syntology":null},{"url":null,"slug":"deriving-coding-specific-sub-models-from-llms","title":"Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning","date":"2025-01-09","arxiv_id":"2501.05248","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-code-llms-understand-design-patterns","title":"Do Code LLMs Understand Design Patterns?","date":"2025-01-08","arxiv_id":"2501.04835","repositories_listed":0,"syntology":null},{"url":"/paper/epicoder-encompassing-diversity-and","slug":"epicoder-encompassing-diversity-and","title":"EpiCoder: Encompassing Diversity and Complexity in Code Generation","date":"2025-01-08","arxiv_id":"2501.04694","repositories_listed":0,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":14,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/epicoder-encompassing-diversity-and#ran","syntology_url":"https://syntology.ai/paper/2501.04694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04694"}},"official":null}},{"url":null,"slug":"robotic-programmer-video-instructed-policy","title":"Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation","date":"2025-01-08","arxiv_id":"2501.04268","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-of-ai-exploring-the-potential-of","title":"The Future of AI: Exploring the Potential of Large Concept Models","date":"2025-01-08","arxiv_id":"2501.05487","repositories_listed":0,"syntology":null},{"url":null,"slug":"chronollm-a-framework-for-customizing-large","title":"ChronoLLM: A Framework for Customizing Large Language Model for Digital Twins generalization based on PyChrono","date":"2025-01-07","arxiv_id":"2501.04062","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-design-and-benchmarking-of","title":"Practical Design and Benchmarking of Generative AI Applications for Surgical Billing and Coding","date":"2025-01-07","arxiv_id":"2501.05479","repositories_listed":0,"syntology":null},{"url":null,"slug":"codevision-detecting-llm-generated-code-using","title":"CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models","date":"2025-01-06","arxiv_id":"2501.03288","repositories_listed":0,"syntology":null},{"url":null,"slug":"rtlsquad-multi-agent-based-interpretable-rtl","title":"RTLSquad: Multi-Agent Based Interpretable RTL Design","date":"2025-01-06","arxiv_id":"2501.05470","repositories_listed":0,"syntology":null},{"url":null,"slug":"cracks-in-the-stack-hidden-vulnerabilities","title":"Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets","date":"2025-01-05","arxiv_id":"2501.02628","repositories_listed":0,"syntology":null},{"url":null,"slug":"toolhop-a-query-driven-benchmark-for","title":"ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use","date":"2025-01-05","arxiv_id":"2501.02506","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-large-language-models-with-some","title":"A Survey on Large Language Models with some Insights on their Capabilities and Limitations","date":"2025-01-03","arxiv_id":"2501.04040","repositories_listed":0,"syntology":null},{"url":null,"slug":"codeelo-benchmarking-competition-level-code","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","date":"2025-01-02","arxiv_id":"2501.01257","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-scaling-of-unit-tests-for-code-reward","title":"Dynamic Scaling of Unit Tests for Code Reward Modeling","date":"2025-01-02","arxiv_id":"2501.01054","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-text-implementing-multimodal-large","title":"Beyond Text: Implementing Multimodal Large Language Model-Powered Multi-Agent Systems Using a No-Code Platform","date":"2025-01-01","arxiv_id":"2501.00750","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-new-hdls-with-agents","title":"Enabling New HDLs with Agents","date":"2024-12-31","arxiv_id":"2501.00642","repositories_listed":0,"syntology":null},{"url":null,"slug":"secbench-a-comprehensive-multi-dimensional","title":"SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity","date":"2024-12-30","arxiv_id":"2412.20787","repositories_listed":0,"syntology":null},{"url":null,"slug":"thinking-before-running-efficient-code","title":"Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement","date":"2024-12-30","arxiv_id":"2502.17442","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-code-llms-with-reinforcement","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","date":"2024-12-29","arxiv_id":"2412.20367","repositories_listed":0,"syntology":null},{"url":null,"slug":"socrates-towards-automated-scenario-based","title":"SocRATES: Towards Automated Scenario-based Testing of Social Navigation Algorithms","date":"2024-12-27","arxiv_id":"2412.19595","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketchfill-sketch-guided-code-generation-for","title":"SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values","date":"2024-12-26","arxiv_id":"2412.19113","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-propense-are-large-language-models-at","title":"How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study","date":"2024-12-25","arxiv_id":"2412.18989","repositories_listed":0,"syntology":null},{"url":null,"slug":"renaissance-of-literate-programming-in-the","title":"Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects","date":"2024-12-25","arxiv_id":"2502.17441","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-ped-multi-prompt-ensemble-decoding-for","title":"M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models","date":"2024-12-24","arxiv_id":"2412.18299","repositories_listed":0,"syntology":null},{"url":null,"slug":"cypress-copilot-development-of-an-ai","title":"Cypress Copilot: Development of an AI Assistant for Boosting Productivity and Transforming Web Application Testing","date":"2024-12-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"emerging-security-challenges-of-large","title":"Emerging Security Challenges of Large Language Models","date":"2024-12-23","arxiv_id":"2412.17614","repositories_listed":0,"syntology":null},{"url":null,"slug":"aigcodeset-a-new-annotated-dataset-for-ai","title":"AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection","date":"2024-12-21","arxiv_id":"2412.16594","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-sum-unlocking-ai-agents-potential","title":"Beyond the Sum: Unlocking AI Agents Potential Through Market Forces","date":"2024-12-19","arxiv_id":"2501.10388","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-consumption-of-code-small-language","title":"Energy consumption of code small language models serving with runtime engines and execution providers","date":"2024-12-19","arxiv_id":"2412.15441","repositories_listed":0,"syntology":null},{"url":null,"slug":"helping-llms-improve-code-generation-using","title":"Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis","date":"2024-12-19","arxiv_id":"2412.14841","repositories_listed":0,"syntology":null},{"url":null,"slug":"hpc-coder-v2-studying-code-llms-across-low","title":"HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages","date":"2024-12-19","arxiv_id":"2412.15178","repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-of-code-a-tree-structured-exploring","title":"Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling","date":"2024-12-19","arxiv_id":"2412.15305","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-we-build-local-large-language-models-an","title":"Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs","date":"2024-12-19","arxiv_id":"2412.14471","repositories_listed":0,"syntology":null},{"url":"/paper/advanced-reasoning-and-transformation-engine","slug":"advanced-reasoning-and-transformation-engine","title":"ARTEMIS-DA: An Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics","date":"2024-12-18","arxiv_id":"2412.14146","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-merging-preserving-specialization-for","title":"Channel Merging: Preserving Specialization for Merged Experts","date":"2024-12-18","arxiv_id":"2412.15283","repositories_listed":0,"syntology":null},{"url":null,"slug":"genx-mastering-code-and-test-generation-with","title":"GenX: Mastering Code and Test Generation with Execution Feedback","date":"2024-12-18","arxiv_id":"2412.13464","repositories_listed":0,"syntology":null},{"url":null,"slug":"syzygy-dual-code-test-c-to-safe-rust","title":"Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis","date":"2024-12-18","arxiv_id":"2412.14234","repositories_listed":0,"syntology":null}],"record_sha256":"c238d7ca64ca3edf06433de1febddf60d0581a32081385aba013eeed7ab28618","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}