{"total":117,"rows":[{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130,"area":null},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2503.02240","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","created":"2025-03-04","cited_by_count":91,"area":null},{"id":"2505.11475","title":"HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages","created":"2025-05-16","cited_by_count":75,"area":"alignment"},{"id":"2407.00121","title":"Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks","created":"2024-06-27","cited_by_count":52,"area":"agents"},{"id":"2409.03797","title":"NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls","created":"2024-09-04","cited_by_count":48,"area":"agents"},{"id":"2501.02448","title":"Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap","created":"2025-01-05","cited_by_count":43,"area":"lr"},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2410.05669","title":"ACPBench: Reasoning about Action, Change, and Planning","created":"2024-10-08","cited_by_count":39,"area":"lr"},{"id":"2505.20315","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","created":"2025-05-22","cited_by_count":38,"area":"lr"},{"id":"2406.14712","title":"Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Models","created":"2024-06-20","cited_by_count":30,"area":null},{"id":"2407.09434","title":"Foundation Models for the Electric Power Grid","created":"2024-07-12","cited_by_count":28,"area":null},{"id":"2504.04365","title":"AutoPDL: Automatic Prompt Optimization for LLM Agents","created":"2025-04-06","cited_by_count":27,"area":"agents"},{"id":"2405.19495","title":"Qiskit Code Assistant: Training LLMs for generating Quantum Computing Code","created":"2024-05-29","cited_by_count":25,"area":null},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2407.09726","title":"On Mitigating Code LLM Hallucinations with API Documentation","created":"2024-07-13","cited_by_count":21,"area":null},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","cited_by_count":20,"area":null},{"id":"2502.20432","title":"LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory","created":"2025-02-27","cited_by_count":17,"area":"lr"},{"id":"2503.04378","title":"HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks","created":"2025-03-06","cited_by_count":17,"area":"lr"},{"id":"2503.06689","title":"DependEval: Benchmarking LLMs for Repository Dependency Understanding","created":"2025-03-09","cited_by_count":17,"area":null},{"id":"2407.19619","title":"Enhancing Code Translation in Language Models with Few-Shot Learning via Retrieval-Augmented Generation","created":"2024-07-29","cited_by_count":16,"area":"rag"},{"id":"2410.08385","title":"Language model developers should report train-test overlap","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2406.06575","title":"Ask-EDA: A Design Assistant Empowered by LLM, Hybrid RAG and Abbreviation De-hallucination","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2407.13739","title":"Scaling Granite Code Models to 128K Context","created":"2024-07-18","cited_by_count":11,"area":null},{"id":"2511.10192","title":"Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL","created":"2025-11-13","cited_by_count":11,"area":null},{"id":"2501.03265","title":"Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment","created":"2025-01-04","cited_by_count":10,"area":"lr"},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2510.25510","title":"MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL","created":"2025-10-29","cited_by_count":10,"area":"lr"},{"id":"2407.12281","title":"Turning Generative Models Degenerate: The Power of Data Poisoning Attacks","created":"2024-07-17","cited_by_count":9,"area":"safety"},{"id":"2505.22096","title":"Knowledge Base Construction for Knowledge-Augmented Text-to-SQL","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2507.10583","title":"$\\texttt{Droid}$: A Resource Suite for AI-Generated Code Detection","created":"2025-07-11","cited_by_count":9,"area":null},{"id":"2410.04617","title":"Evaluation of Code LLMs on Geospatial Code Generation","created":"2024-10-06","cited_by_count":8,"area":null},{"id":"2503.24378","title":"ACPBench Hard: Unrestrained Reasoning about Action, Change, and Planning","created":"2025-03-31","cited_by_count":8,"area":"lr"},{"id":"2507.13290","title":"Towards Formal Verification of LLM-Generated Code from Natural Language Prompts","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2601.20679","title":"ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code","created":"2026-01-28","cited_by_count":8,"area":null},{"id":"2603.14360","title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","created":"2026-03-15","cited_by_count":8,"area":null},{"id":"2501.18482","title":"A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models","created":"2025-01-30","cited_by_count":7,"area":"lr"},{"id":"2505.10443","title":"Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?","created":"2025-05-15","cited_by_count":7,"area":null},{"id":"2408.04660","title":"XMainframe: A Large Language Model for Mainframe Modernization","created":"2024-08-05","cited_by_count":6,"area":null},{"id":"2506.21849","title":"The Consistency Hypothesis in Uncertainty Quantification for Large Language Models","created":"2025-06-27","cited_by_count":6,"area":null},{"id":"2507.12308","title":"Chain-of-Descriptions: Improving Code LLMs for VHDL Code Generation and Summarization","created":"2025-07-16","cited_by_count":6,"area":null},{"id":"2602.05695","title":"SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2602.14276","title":"ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2409.02326","title":"Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining","created":"2024-09-03","cited_by_count":5,"area":null},{"id":"2410.14748","title":"ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2506.12072","title":"TRACE: Transparent Web Reliability Assessment with Contextual Explanations","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2412.05159","title":"Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation","created":"2024-12-06","cited_by_count":4,"area":"rag"},{"id":"2503.01022","title":"LLM-Fusion: A Novel Multimodal Fusion Model for Accelerated Material Discovery","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2505.14990","title":"Language Specific Knowledge: Do Models Know Better in X than in English?","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2508.08171","title":"PyVeritas: On Verifying Python via LLM-Based Transpilation and Bounded Model Checking for C","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2407.05467","title":"The infrastructure powering IBM's Gen AI model development","created":"2024-07-07","cited_by_count":3,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2505.02184","title":"Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes","created":"2025-05-04","cited_by_count":3,"area":null},{"id":"2510.08702","title":"Scaling Laws for Code: A More Data-Hungry Regime","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2602.02975","title":"Where Norms and References Collide: Evaluating LLMs on Normative Reasoning","created":"2026-02-03","cited_by_count":3,"area":"lr"},{"id":"2409.18164","title":"Data-Prep-Kit: getting your data ready for LLM application development","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2503.15571","title":"LLM-Aided Customizable Profiling of Code Data Based On Programming Language Concepts","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2503.17811","title":"Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models","created":"2025-03-22","cited_by_count":2,"area":null},{"id":"2505.11441","title":"Is Compression Really Linear with Code Intelligence?","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2505.15469","title":"A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.02182","title":"Enhancing COBOL Code Explanations: A Multi-Agents Approach Using Large Language Models","created":"2025-07-02","cited_by_count":2,"area":"agents"},{"id":"2507.06013","title":"CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation","created":"2025-07-08","cited_by_count":2,"area":"lr"},{"id":"2507.12642","title":"QSpark: Towards Reliable Qiskit Code Generation","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2509.23686","title":"Evaluating Program Semantics Reasoning with Type Inference in System F","created":"2025-09-28","cited_by_count":2,"area":"lr"},{"id":"2510.13836","title":"SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2511.19422","title":"SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2601.02380","title":"LLMs, Reasoning and Plagiarism","created":"2025-12-18","cited_by_count":2,"area":"lr"},{"id":"2602.02079","title":"AICD Bench: A Challenging Benchmark for AI-Generated Code Detection","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.17204","title":"CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization","created":"2026-03-17","cited_by_count":2,"area":"agents"},{"id":"2604.06170","title":"Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2604.17837","title":"Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEs","created":"2026-04-20","cited_by_count":2,"area":"moe"},{"id":"2605.01546","title":"6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence","created":"2026-05-02","cited_by_count":2,"area":"agents"},{"id":"2407.03387","title":"ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2502.15718","title":"Making Sense of Data in the Wild: Data Analysis Automation at Scale","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2505.09610","title":"Customizing a Large Language Model for VHDL Design of High-Performance Microprocessors","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2505.18011","title":"Training with Pseudo-Code for Instruction Following","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.04500","title":"\"Don't Do That!\": Guiding Embodied Systems through Large Language Model-based Constraint Generation","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2506.10989","title":"Prompt engineering and framework: implementation to increase code reliability based guideline for LLMs","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2510.01831","title":"Syntactic Blind Spots: How Misalignment Leads to LLMs Mathematical Errors","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.27532","title":"SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.13590","title":"Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2601.04854","title":"Projected Autoregression: Autoregressive Language Generation in Continuous State Space","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.10436","title":"Development of Ontological Knowledge Bases by Leveraging Large Language Models","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2601.21115","title":"Multi-task Code LLMs: Data Mix or Model Merge?","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2605.14503","title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","created":"2026-05-14","cited_by_count":1,"area":"rag"},{"id":"2606.07017","title":"The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2606.26734","title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2608.11694","title":"The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2608.14303","title":"Detecting Contaminated Code-Generation Prompt Batches via Influence Functions","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2408.09568","title":"MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair","created":"2024-08-18","cited_by_count":0,"area":null},{"id":"2502.15732","title":"Data Wrangling Task Automation Using Code-Generating Language Models","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2503.08815","title":"Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2507.05316","title":"OASBuilder: Generating OpenAPI Specifications from Online API Documentation with Large Language Models","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2507.08037","title":"CRISP: Complex Reasoning with Interpretable Step-based Plans","created":"2025-07-09","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}