{"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/10","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":10,"pages_in_order":17,"rows_per_page":100,"rows":[901,1000],"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/9","next":"/task/code-generation/papers/11","papers":[{"url":null,"slug":"type-constrained-code-generation-with","title":"Type-Constrained Code Generation with Language Models","date":"2025-04-12","arxiv_id":"2504.09246","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-universal-llm-reward-design-through","title":"Boosting Universal LLM Reward Design through the Heuristic Reward Observation Space Evolution","date":"2025-04-10","arxiv_id":"2504.07596","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-token-to-line-enhancing-code-generation","title":"LSR-MCTS: Alleviating Long Range Dependency in Code Generation","date":"2025-04-10","arxiv_id":"2504.07433","repositories_listed":0,"syntology":null},{"url":null,"slug":"pr-attack-coordinated-prompt-rag-attacks-on","title":"PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization","date":"2025-04-10","arxiv_id":"2504.07717","repositories_listed":0,"syntology":null},{"url":null,"slug":"mdit-a-model-free-data-interpolation-method","title":"MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning","date":"2025-04-09","arxiv_id":"2504.07288","repositories_listed":0,"syntology":null},{"url":null,"slug":"prism-dynamic-and-flexible-benchmarking-of","title":"Prism: Dynamic and Flexible Benchmarking of LLMs Code Generation with Monte Carlo Tree Search","date":"2025-04-07","arxiv_id":"2504.05500","repositories_listed":0,"syntology":null},{"url":null,"slug":"ddpt-diffusion-driven-prompt-tuning-for-large","title":"DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation","date":"2025-04-06","arxiv_id":"2504.04351","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-accurately-do-large-language-models","title":"How Accurately Do Large Language Models Understand Code?","date":"2025-04-06","arxiv_id":"2504.04372","repositories_listed":0,"syntology":null},{"url":null,"slug":"opencodeinstruct-a-large-scale-instruction","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","date":"2025-04-05","arxiv_id":"2504.04030","repositories_listed":0,"syntology":null},{"url":null,"slug":"naacl2025-tutorial-adaptation-of-large","title":"NAACL2025 Tutorial: Adaptation of Large Language Models","date":"2025-04-04","arxiv_id":"2504.03931","repositories_listed":0,"syntology":null},{"url":null,"slug":"mg-gen-single-image-to-motion-graphics","title":"MG-Gen: Single Image to Motion Graphics Generation with Layer Decomposition","date":"2025-04-03","arxiv_id":"2504.02361","repositories_listed":0,"syntology":null},{"url":null,"slug":"pel-a-programming-language-for-orchestrating","title":"Pel, A Programming Language for Orchestrating AI Agents","date":"2025-04-03","arxiv_id":"2505.13453","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-self-learning-agent-with-a-progressive","title":"The Self-Learning Agent with a Progressive Neural Network Integrated Transformer","date":"2025-04-03","arxiv_id":"2504.02489","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-code-generation-to-software-testing-ai","title":"From Code Generation to Software Testing: AI Copilot with Context-Based RAG","date":"2025-04-02","arxiv_id":"2504.01866","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-simulation-guided-llm-based-code","title":"On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software","date":"2025-04-02","arxiv_id":"2504.02141","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-difficulty-aware-staged-reinforcement","title":"How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study","date":"2025-04-01","arxiv_id":"2504.00829","repositories_listed":0,"syntology":null},{"url":null,"slug":"srlcg-self-rectified-large-scale-code","title":"SRLCG: Self-Rectified Large-Scale Code Generation with Multidimensional Chain-of-Thought and Dynamic Backtracking","date":"2025-04-01","arxiv_id":"2504.00532","repositories_listed":0,"syntology":null},{"url":null,"slug":"rubric-is-all-you-need-enhancing-llm-based","title":"Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics","date":"2025-03-31","arxiv_id":"2503.23989","repositories_listed":0,"syntology":null},{"url":null,"slug":"carbon-footprint-evaluation-of-code","title":"Carbon Footprint Evaluation of Code Generation through LLM as a Service","date":"2025-03-30","arxiv_id":"2504.01036","repositories_listed":0,"syntology":null},{"url":null,"slug":"ccci-code-completion-with-contextual","title":"CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models","date":"2025-03-29","arxiv_id":"2503.23231","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-and-paths-towards-ai-for-software","title":"Challenges and Paths Towards AI for Software Engineering","date":"2025-03-28","arxiv_id":"2503.22625","repositories_listed":0,"syntology":null},{"url":null,"slug":"robunfr-evaluating-the-robustness-of-large","title":"RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation","date":"2025-03-28","arxiv_id":"2503.22851","repositories_listed":0,"syntology":null},{"url":null,"slug":"malicious-and-unintentional-disclosure-risks","title":"Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation","date":"2025-03-27","arxiv_id":"2503.22760","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-the-potential-of-past-research","title":"Unlocking the Potential of Past Research: Using Generative AI to Reconstruct Healthcare Simulation Models","date":"2025-03-27","arxiv_id":"2503.21646","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-language-models-for-inference-time","title":"Optimizing Language Models for Inference Time Objectives using Reinforcement Learning","date":"2025-03-25","arxiv_id":"2503.19595","repositories_listed":0,"syntology":null},{"url":null,"slug":"vectrans-llm-transformation-framework-for","title":"VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations","date":"2025-03-25","arxiv_id":"2503.19449","repositories_listed":0,"syntology":null},{"url":null,"slug":"assertionforge-enhancing-formal-verification","title":"AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL","date":"2025-03-24","arxiv_id":"2503.19174","repositories_listed":0,"syntology":null},{"url":null,"slug":"modigen-a-large-language-model-based-workflow","title":"ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation","date":"2025-03-24","arxiv_id":"2503.18460","repositories_listed":0,"syntology":null},{"url":null,"slug":"verbal-process-supervision-elicits-better","title":"Verbal Process Supervision Elicits Better Coding Agents","date":"2025-03-24","arxiv_id":"2503.18494","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-the-improvement-of-code-generation","title":"A Study on the Improvement of Code Generation Quality Using Large Language Models Leveraging Product Documentation","date":"2025-03-22","arxiv_id":"2503.17837","repositories_listed":0,"syntology":null},{"url":null,"slug":"every-sample-matters-leveraging-mixture-of","title":"Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM","date":"2025-03-22","arxiv_id":"2503.17793","repositories_listed":0,"syntology":null},{"url":null,"slug":"lamour-leveraging-language-models-for-out-of","title":"LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning","date":"2025-03-21","arxiv_id":"2503.17125","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-love-python-a-study-of-llms-bias-for","title":"LLMs Love Python: A Study of LLMs' Bias for Programming Languages and Libraries","date":"2025-03-21","arxiv_id":"2503.17181","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-explaining-large-language-models-for-code","title":"On Explaining (Large) Language Models For Code Using Global Code-Based Explanations","date":"2025-03-21","arxiv_id":"2503.16771","repositories_listed":0,"syntology":null},{"url":null,"slug":"codereviewqa-the-code-review-comprehension","title":"CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models","date":"2025-03-20","arxiv_id":"2503.16167","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-crowd-sourced-human-feedback-for","title":"Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models","date":"2025-03-19","arxiv_id":"2503.15129","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-aided-customizable-profiling-of-code-data","title":"LLM-Aided Customizable Profiling of Code Data Based On Programming Language Concepts","date":"2025-03-19","arxiv_id":"2503.15571","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-llm-secure-code","title":"A Comprehensive Study of LLM Secure Code Generation","date":"2025-03-18","arxiv_id":"2503.15554","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-milp-model-construction-for-multi","title":"Automatic MILP Model Construction for Multi-Robot Task Allocation and Scheduling Based on Large Language Models","date":"2025-03-18","arxiv_id":"2503.13813","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-enable-verification-in-mainstream","title":"Can LLMs Enable Verification in Mainstream Programming?","date":"2025-03-18","arxiv_id":"2503.14183","repositories_listed":0,"syntology":null},{"url":null,"slug":"speculative-decoding-for-verilog-speed-and","title":"Speculative Decoding for Verilog: Speed and Quality, All in One","date":"2025-03-18","arxiv_id":"2503.14153","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-kolmogorov-test-compression-by-code","title":"The KoLMogorov Test: Compression by Code Generation","date":"2025-03-18","arxiv_id":"2503.13992","repositories_listed":0,"syntology":null},{"url":null,"slug":"xoxo-stealthy-cross-origin-context-poisoning","title":"XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants","date":"2025-03-18","arxiv_id":"2503.14281","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semantic-based-optimization-approach-for","title":"A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation","date":"2025-03-17","arxiv_id":"2503.12899","repositories_listed":0,"syntology":null},{"url":null,"slug":"codet-m4-detecting-machine-generated-code-in","title":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","date":"2025-03-17","arxiv_id":"2503.13733","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-test-generation-via-iterative-hybrid","title":"LLM Test Generation via Iterative Hybrid Program Analysis","date":"2025-03-17","arxiv_id":"2503.13580","repositories_listed":0,"syntology":null},{"url":null,"slug":"vericontaminated-assessing-llm-driven-verilog","title":"VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination","date":"2025-03-17","arxiv_id":"2503.13572","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-formally-reason-as-abstract","title":"Can LLMs Formally Reason as Abstract Interpreters for Program Analysis?","date":"2025-03-16","arxiv_id":"2503.12686","repositories_listed":0,"syntology":null},{"url":null,"slug":"tfhe-coder-evaluating-llm-agentic-fully","title":"TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation","date":"2025-03-15","arxiv_id":"2503.12217","repositories_listed":0,"syntology":null},{"url":null,"slug":"verimind-agentic-llm-for-automated-verilog","title":"VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric","date":"2025-03-15","arxiv_id":"2503.16514","repositories_listed":0,"syntology":null},{"url":null,"slug":"combinatorial-optimization-for-all-using-llms","title":"Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms","date":"2025-03-14","arxiv_id":"2503.10968","repositories_listed":0,"syntology":null},{"url":null,"slug":"capturing-semantic-flow-of-ml-based-systems","title":"Capturing Semantic Flow of ML-based Systems","date":"2025-03-13","arxiv_id":"2503.10310","repositories_listed":0,"syntology":null},{"url":null,"slug":"compute-optimal-scaling-of-skills-knowledge","title":"Compute Optimal Scaling of Skills: Knowledge vs Reasoning","date":"2025-03-13","arxiv_id":"2503.10061","repositories_listed":0,"syntology":null},{"url":null,"slug":"conformal-prediction-sets-for-deep-generative","title":"Conformal Prediction Sets for Deep Generative Models via Reduction to Conformal Regression","date":"2025-03-13","arxiv_id":"2503.10512","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynacode-a-dynamic-complexity-aware-code","title":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","date":"2025-03-13","arxiv_id":"2503.10452","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-learning-for-large-language-models","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","date":"2025-03-13","arxiv_id":"2503.13505","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-understanding-to-excelling-template-free","title":"From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution","date":"2025-03-13","arxiv_id":"2503.10721","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-effectiveness-of-a-socratic","title":"Investigating the Effectiveness of a Socratic Chain-of-Thoughts Reasoning Method for Task Planning in Robotics, A Case Study","date":"2025-03-11","arxiv_id":"2503.08174","repositories_listed":0,"syntology":null},{"url":null,"slug":"resbench-benchmarking-llm-generated-fpga","title":"ResBench: Benchmarking LLM-Generated FPGA Designs with Resource Awareness","date":"2025-03-11","arxiv_id":"2503.08823","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-idea-to-implementation-evaluating-the","title":"From Idea to Implementation: Evaluating the Influence of Large Language Models in Software Development -- An Opinion Paper","date":"2025-03-10","arxiv_id":"2503.07450","repositories_listed":0,"syntology":null},{"url":null,"slug":"automisty-a-multi-agent-llm-framework-for","title":"AutoMisty: A Multi-Agent LLM Framework for Automated Code Generation in the Misty Social Robot","date":"2025-03-09","arxiv_id":"2503.06791","repositories_listed":0,"syntology":null},{"url":"/paper/fea-bench-a-benchmark-for-evaluating","slug":"fea-bench-a-benchmark-for-evaluating","title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","date":"2025-03-09","arxiv_id":"2503.06680","repositories_listed":0,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/fea-bench-a-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2503.06680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06680"}},"official":null}},{"url":null,"slug":"genai-for-simulation-model-in-model-based","title":"GenAI for Simulation Model in Model-Based Systems Engineering","date":"2025-03-09","arxiv_id":"2503.06422","repositories_listed":0,"syntology":null},{"url":null,"slug":"green-prompting","title":"Green Prompting","date":"2025-03-09","arxiv_id":"2503.10666","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-ai-models-in-software","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol","date":"2025-03-07","arxiv_id":"2503.05860","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-large-language-models-in-code","title":"Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index","date":"2025-03-07","arxiv_id":"2503.05852","repositories_listed":0,"syntology":null},{"url":null,"slug":"grammar-based-code-representation-is-it-a","title":"Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?","date":"2025-03-07","arxiv_id":"2503.05507","repositories_listed":0,"syntology":null},{"url":null,"slug":"oransight-2-0-foundational-llms-for-o-ran","title":"ORANSight-2.0: Foundational LLMs for O-RAN","date":"2025-03-07","arxiv_id":"2503.05200","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-reshaping-of-people-processes-products","title":"LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early Adopters","date":"2025-03-06","arxiv_id":"2503.05012","repositories_listed":0,"syntology":null},{"url":null,"slug":"codeif-bench-evaluating-instruction-following","title":"CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation","date":"2025-03-05","arxiv_id":"2503.22688","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-learning-of-diverse-code-edits","title":"Robust Learning of Diverse Code Edits","date":"2025-03-05","arxiv_id":"2503.03656","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-struggle-to-align","title":"Vision-Language Models Struggle to Align Entities across Modalities","date":"2025-03-05","arxiv_id":"2503.03854","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-do-language-models-track-state","title":"(How) Do Language Models Track State?","date":"2025-03-04","arxiv_id":"2503.02854","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterpref-focal-preference-learning-for-code","title":"IterPref: Focal Preference Learning for Code Generation via Iterative Debugging","date":"2025-03-04","arxiv_id":"2503.02783","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorize-or-generalize-evaluating-llm-code","title":"Memorize or Generalize? Evaluating LLM Code Generation with Evolved Questions","date":"2025-03-04","arxiv_id":"2503.02296","repositories_listed":0,"syntology":null},{"url":null,"slug":"pennylang-pioneering-llm-based-quantum-code","title":"PennyLang: Pioneering LLM-Based Quantum Code Generation with a Novel PennyLane-Centric Dataset","date":"2025-03-04","arxiv_id":"2503.02497","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01700","title":"Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation","date":"2025-03-03","arxiv_id":"2503.01700","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-large-language-models-for-code-1","title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","date":"2025-03-03","arxiv_id":"2503.01245","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","date":"2025-03-02","arxiv_id":"2503.00691","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-00767","title":"LLMs are everywhere: Ubiquitous Utilization of AI Models through Air Computing","date":"2025-03-02","arxiv_id":"2503.00767","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-00821","title":"AI Agents for Ground-Based Gamma Astronomy","date":"2025-03-02","arxiv_id":"2503.00821","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-extensive-evaluation-of-pddl-capabilities","title":"An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs","date":"2025-02-27","arxiv_id":"2502.20175","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-natural-language-perplexity-detecting","title":"Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets","date":"2025-02-27","arxiv_id":"2502.20246","repositories_listed":0,"syntology":null},{"url":null,"slug":"convcodeworld-benchmarking-conversational","title":"ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments","date":"2025-02-27","arxiv_id":"2502.19852","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-code-generation-and-validation-for","title":"Automated Code Generation and Validation for Software Components of Microcontrollers","date":"2025-02-26","arxiv_id":"2502.18905","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-planning-for-personal-plans","title":"Conversational Planning for Personal Plans","date":"2025-02-26","arxiv_id":"2502.19500","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-bench-deep-learning-benchmark-dataset","title":"Deep-Bench: Deep Learning Benchmark Dataset for Code Generation","date":"2025-02-26","arxiv_id":"2502.18726","repositories_listed":0,"syntology":null},{"url":null,"slug":"isolating-language-coding-from-problem","title":"Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEval","date":"2025-02-26","arxiv_id":"2502.19149","repositories_listed":0,"syntology":null},{"url":null,"slug":"assistance-or-disruption-exploring-and","title":"Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support","date":"2025-02-25","arxiv_id":"2502.18658","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-llm-paraphrased-code-and","title":"Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features","date":"2025-02-25","arxiv_id":"2502.17749","repositories_listed":0,"syntology":null},{"url":null,"slug":"codeswift-accelerating-llm-inference-for","title":"CodeSwift: Accelerating LLM Inference for Efficient Code Generation","date":"2025-02-24","arxiv_id":"2502.17139","repositories_listed":0,"syntology":null},{"url":null,"slug":"rewardds-privacy-preserving-fine-tuning-for","title":"RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis","date":"2025-02-23","arxiv_id":"2502.18517","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-trusting-trust-multi-model-validation","title":"Beyond Trusting Trust: Multi-Model Validation for Robust Code Generation","date":"2025-02-22","arxiv_id":"2502.16279","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-analysis-of-large-language-models","title":"Comparative Analysis of Large Language Models for Context-Aware Code Completion using SAFIM Framework","date":"2025-02-21","arxiv_id":"2502.15243","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeprtl-bridging-verilog-understanding-and","title":"DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model","date":"2025-02-20","arxiv_id":"2502.15832","repositories_listed":0,"syntology":null},{"url":null,"slug":"mechanistic-understanding-of-language-models","title":"Mechanistic Understanding of Language Models in Syntactic Code Completion","date":"2025-02-20","arxiv_id":"2502.18499","repositories_listed":0,"syntology":null},{"url":null,"slug":"pragmatic-reasoning-improves-llm-code","title":"Pragmatic Reasoning improves LLM Code Generation","date":"2025-02-20","arxiv_id":"2502.15835","repositories_listed":0,"syntology":null},{"url":null,"slug":"beamlora-beam-constraint-low-rank-adaptation","title":"BeamLoRA: Beam-Constraint Low-Rank Adaptation","date":"2025-02-19","arxiv_id":"2502.13604","repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-construct-filter-an-automated","title":"Explore-Construct-Filter: An Automated Framework for Rich and Reliable API Knowledge Graph Construction","date":"2025-02-19","arxiv_id":"2502.13412","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-code-language-models-for-automated","title":"Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis","date":"2025-02-19","arxiv_id":"2502.13921","repositories_listed":0,"syntology":null}],"record_sha256":"326afcbccbb9adaa64b60fc4f0139a87071115bd2745174e9ac7744e51c52831","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}