{"total":150,"rows":[{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426,"area":"lr"},{"id":"2406.14283","title":"Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning","created":"2024-06-20","cited_by_count":97,"area":"lr"},{"id":"2501.10893","title":"Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments","created":"2025-01-18","cited_by_count":95,"area":"agents"},{"id":"2406.14497","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","created":"2024-06-20","cited_by_count":91,"area":"rag"},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61,"area":"agents"},{"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":"2505.21318","title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations","created":"2025-05-27","cited_by_count":49,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2511.07919","title":"Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison","created":"2025-11-11","cited_by_count":44,"area":"alignment"},{"id":"2501.09655","title":"A Survey of Research in Large Language Models for Electronic Design Automation","created":"2025-01-16","cited_by_count":41,"area":null},{"id":"2407.09007","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2410.05318","title":"Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification","created":"2024-10-05","cited_by_count":40,"area":"lr"},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2411.12644","title":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval","created":"2024-11-19","cited_by_count":34,"area":null},{"id":"2410.15756","title":"Automated Proof Generation for Rust Code via Self-Evolution","created":"2024-10-21","cited_by_count":33,"area":null},{"id":"2505.06371","title":"The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization","created":"2025-05-09","cited_by_count":33,"area":null},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30,"area":null},{"id":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28,"area":null},{"id":"2506.08379","title":"Reinforce LLM Reasoning through Multi-Agent Reflection","created":"2025-06-10","cited_by_count":27,"area":"lr"},{"id":"2504.06260","title":"FEABench: Evaluating Language Models on Multiphysics Reasoning Ability","created":"2025-04-08","cited_by_count":22,"area":"lr"},{"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":"2410.18792","title":"An LLM Agent for Automatic Geospatial Data Analysis","created":"2024-10-24","cited_by_count":21,"area":"agents"},{"id":"2410.21157","title":"M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation","created":"2024-10-28","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":"2410.20527","title":"CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming","created":"2024-10-27","cited_by_count":19,"area":null},{"id":"2510.00294","title":"Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models","created":"2025-09-30","cited_by_count":19,"area":"inference"},{"id":"2602.01326","title":"DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas","created":"2026-02-01","cited_by_count":19,"area":"diffusion"},{"id":"2410.01353","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17,"area":"alignment"},{"id":"2504.11109","title":"Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and Optimization","created":"2025-04-15","cited_by_count":17,"area":"agents"},{"id":"2408.02193","title":"CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs","created":"2024-08-05","cited_by_count":15,"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":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2508.10111","title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","created":"2025-08-13","cited_by_count":14,"area":null},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12,"area":null},{"id":"2506.20495","title":"ReCode: Updating Code API Knowledge with Reinforcement Learning","created":"2025-06-25","cited_by_count":12,"area":"alignment"},{"id":"2604.23626","title":"GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs","created":"2026-04-26","cited_by_count":12,"area":"agents"},{"id":"2407.00902","title":"From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning","created":"2024-07-01","cited_by_count":11,"area":"mllm"},{"id":"2407.13739","title":"Scaling Granite Code Models to 128K Context","created":"2024-07-18","cited_by_count":11,"area":null},{"id":"2410.11863","title":"ChatVis: Automating Scientific Visualization with a Large Language Model","created":"2024-10-07","cited_by_count":11,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"area":null},{"id":"2511.05459","title":"SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models","created":"2025-11-07","cited_by_count":11,"area":"agents"},{"id":"2410.01791","title":"DreamGarden: A Designer Assistant for Growing Games from a Single Prompt","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2502.15680","title":"Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2505.23657","title":"Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2504.18116","title":"Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models","created":"2025-04-25","cited_by_count":9,"area":"lr"},{"id":"2507.22063","title":"RedCoder: Automated Multi-Turn Red Teaming for Code LLMs","created":"2025-06-25","cited_by_count":9,"area":"safety"},{"id":"2410.04617","title":"Evaluation of Code LLMs on Geospatial Code Generation","created":"2024-10-06","cited_by_count":8,"area":null},{"id":"2502.07786","title":"Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization","created":"2024-12-19","cited_by_count":8,"area":null},{"id":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2502.12598","title":"Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion","created":"2025-02-18","cited_by_count":8,"area":null},{"id":"2503.18008","title":"Personalized Language Models via Privacy-Preserving Evolutionary Model Merging","created":"2025-03-23","cited_by_count":8,"area":null},{"id":"2505.20630","title":"SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis","created":"2025-05-27","cited_by_count":8,"area":"lr"},{"id":"2508.00033","title":"GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries","created":"2025-07-30","cited_by_count":8,"area":null},{"id":"2512.00020","title":"Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead","created":"2025-10-29","cited_by_count":8,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2503.10452","title":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2504.03871","title":"HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs","created":"2025-04-04","cited_by_count":7,"area":"moe"},{"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":"2505.10838","title":"LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs","created":"2025-05-16","cited_by_count":7,"area":"safety"},{"id":"2408.04660","title":"XMainframe: A Large Language Model for Mainframe Modernization","created":"2024-08-05","cited_by_count":6,"area":null},{"id":"2411.05830","title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2501.09653","title":"The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2502.08923","title":"CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality","created":"2025-02-13","cited_by_count":6,"area":"inference"},{"id":"2503.05507","title":"Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?","created":"2025-03-07","cited_by_count":5,"area":null},{"id":"2504.10557","title":"The Code Barrier: What LLMs Actually Understand?","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2504.12687","title":"Data-efficient LLM Fine-tuning for Code Generation","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2509.01082","title":"RefineStat: Efficient Exploration for Probabilistic Program Synthesis","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2408.14494","title":"Knowledge Graph Modeling-Driven Large Language Model Operating System (LLM OS) for Task Automation in Process Engineering Problem-Solving","created":"2024-08-23","cited_by_count":4,"area":null},{"id":"2410.17736","title":"MojoBench: Language Modeling and Benchmarks for Mojo","created":"2024-10-23","cited_by_count":4,"area":null},{"id":"2412.08859","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2502.06556","title":"MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms","created":"2025-02-10","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":"2506.17125","title":"Large Language Model Unlearning for Source Code","created":"2025-06-20","cited_by_count":4,"area":"safety"},{"id":"2601.12262","title":"Environment-Aware Code Generation: How far are We?","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2406.12326","title":"Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2410.07820","title":"Mitigating Gender Bias in Code Large Language Models via Model Editing","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2503.10737","title":"Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2503.15129","title":"Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models","created":"2025-03-19","cited_by_count":3,"area":"agents"},{"id":"2503.22776","title":"Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2508.10074","title":"Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History","created":"2025-08-13","cited_by_count":3,"area":null},{"id":"2508.13975","title":"ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2509.03117","title":"PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs","created":"2025-09-03","cited_by_count":3,"area":"safety"},{"id":"2509.16275","title":"SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair","created":"2025-09-18","cited_by_count":3,"area":"agents"},{"id":"2510.06738","title":"AWM: Accurate Weight-Matrix Fingerprint for Large Language Models","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.23208","title":"Increasing LLM Coding Capabilities through Diverse Synthetic Coding Tasks","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2412.11699","title":"CoinMath: Harnessing the Power of Coding Instruction for Math LLMs","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2501.04510","title":"CGP-Tuning: Structure-Aware Soft Prompt Tuning for Code Vulnerability Detection","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2503.04241","title":"ThrowBench: Benchmarking LLMs by Predicting Runtime Exceptions","created":"2025-03-06","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":"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":"2601.05770","title":"Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer","created":"2026-01-09","cited_by_count":2,"area":null}],"next_cursor":"100"}