{"total":91,"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":"2503.09089","title":"LocAgent: Graph-Guided LLM Agents for Code Localization","created":"2025-03-12","cited_by_count":86,"area":"agents"},{"id":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","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":"2503.12759","title":"RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning","created":"2025-03-17","cited_by_count":30,"area":"rag"},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2510.04905","title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","created":"2025-10-06","cited_by_count":23,"area":"rag"},{"id":"2410.18792","title":"An LLM Agent for Automatic Geospatial Data Analysis","created":"2024-10-24","cited_by_count":21,"area":"agents"},{"id":"2510.01003","title":"Improving Code Localization with Repository Memory","created":"2025-10-01","cited_by_count":20,"area":null},{"id":"2506.15655","title":"cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree","created":"2025-06-18","cited_by_count":17,"area":"rag"},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2506.13589","title":"AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding","created":"2025-06-16","cited_by_count":15,"area":"mllm"},{"id":"2505.17107","title":"CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution","created":"2025-05-21","cited_by_count":14,"area":"agents"},{"id":"2503.07358","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2511.18659","title":"CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning","created":"2025-11-24","cited_by_count":11,"area":"lr"},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10,"area":null},{"id":"2508.16671","title":"Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2601.20789","title":"SERA: Soft-Verified Efficient Repository Agents","created":"2026-01-28","cited_by_count":10,"area":"agents"},{"id":"2502.03233","title":"Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation","created":"2025-02-05","cited_by_count":9,"area":"rag"},{"id":"2603.17829","title":"CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents","created":"2026-03-18","cited_by_count":9,"area":"lr"},{"id":"2508.01959","title":"SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension","created":"2025-08-03","cited_by_count":8,"area":"rag"},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2409.12682","title":"Retrieval-Augmented Test Generation: How Far Are We?","created":"2024-09-19","cited_by_count":7,"area":"rag"},{"id":"2411.19463","title":"Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems","created":"2024-11-29","cited_by_count":7,"area":"rag"},{"id":"2512.18925","title":"Beyond the Prompt: An Empirical Study of Cursor Rules","created":"2025-12-21","cited_by_count":7,"area":null},{"id":"2506.11066","title":"CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2509.07941","title":"ImportSnare: Directed \"Code Manual\" Hijacking in Retrieval-Augmented Code Generation","created":"2025-09-09","cited_by_count":5,"area":"rag"},{"id":"2512.17220","title":"Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding","created":"2025-12-19","cited_by_count":5,"area":"rag"},{"id":"2605.25232","title":"Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2410.11321","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":4,"area":"rag"},{"id":"2410.18251","title":"Context-Augmented Code Generation Using Programming Knowledge Graphs","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2501.18916","title":"LLM Program Optimization via Retrieval Augmented Search","created":"2025-01-31","cited_by_count":4,"area":"rag"},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2503.08398","title":"OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning","created":"2025-03-11","cited_by_count":4,"area":"rag"},{"id":"2505.14394","title":"Knowledge Graph Based Repository-Level Code Generation","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2506.20081","title":"SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization","created":"2025-06-25","cited_by_count":4,"area":"rag"},{"id":"2508.16771","title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2412.18378","title":"RaSeRec: Retrieval-Augmented Sequential Recommendation","created":"2024-12-24","cited_by_count":3,"area":"rag"},{"id":"2505.07768","title":"Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding","created":"2025-05-12","cited_by_count":3,"area":null},{"id":"2505.24715","title":"CoRet: Improved Retriever for Code Editing","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2506.03535","title":"Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation","created":"2025-06-04","cited_by_count":3,"area":"rag"},{"id":"2506.16552","title":"Revela: Dense Retriever Learning via Language Modeling","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2510.22944","title":"Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2601.03378","title":"RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion","created":"2026-01-06","cited_by_count":3,"area":"rag"},{"id":"2601.20615","title":"DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning","created":"2026-01-28","cited_by_count":3,"area":"rag"},{"id":"2603.19281","title":"URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models","created":"2026-03-02","cited_by_count":3,"area":"rag"},{"id":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2410.21591","title":"Can Large Language Models Replace Data Scientists in Biomedical Research?","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2507.15378","title":"AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming","created":"2025-07-21","cited_by_count":2,"area":"lr"},{"id":"2507.19033","title":"SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation","created":"2025-07-25","cited_by_count":2,"area":"rag"},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.02185","title":"FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI","created":"2025-10-02","cited_by_count":2,"area":"agents"},{"id":"2510.08665","title":"RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2511.05533","title":"MCP4IFC: IFC-Based Building Design Using Large Language Models","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2603.22008","title":"On the Challenges and Opportunities of Learned Sparse Retrieval for Code","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2604.18364","title":"Training and Agentic Inference Strategies for LLM-based Manim Animation Generation","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2501.16692","title":"Optimizing Code Runtime Performance through Context-Aware Retrieval-Augmented Generation","created":"2025-01-28","cited_by_count":1,"area":"rag"},{"id":"2505.20182","title":"An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2510.09633","title":"Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security Audits","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2510.15620","title":"On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding","created":"2025-10-17","cited_by_count":1,"area":"rag"},{"id":"2510.24749","title":"Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2511.05626","title":"LLMs as Packagers of HPC Software","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2512.10393","title":"Cross-modal Retrieval Models for Stripped Binary Analysis","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2512.21681","title":"Exploring the Security Threats of Retriever Backdoors in Retrieval-Augmented Code Generation","created":"2025-12-25","cited_by_count":1,"area":"rag"},{"id":"2601.12146","title":"From LLMs to Agents in Programming: The Impact of Providing an LLM with a Compiler","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2602.16069","title":"The Limits of Long-Context Reasoning in Automated Bug Fixing","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2602.20799","title":"Unseen-Codebases-Domain Data Synthesis and Training Based on Code Graphs","created":"2026-02-24","cited_by_count":1,"area":"synth"},{"id":"2604.00167","title":"A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2509.17455","title":"Understanding Benchmark Language Under Weakened Formal Semantics","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.17874","title":"Repairing Tool Calls Using Post-tool Execution Reflection and RAG","created":"2025-10-17","cited_by_count":0,"area":"agents"},{"id":"2512.11509","title":"Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.20810","title":"Context-Augmented Code Generation Using Programming Knowledge Graphs","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.05780","title":"Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.06593","title":"Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation","created":"2026-02-04","cited_by_count":0,"area":"rag"},{"id":"2603.14054","title":"LegacyTranslate: LLM-based Multi-Agent Method for Legacy Code Translation","created":"2026-03-14","cited_by_count":0,"area":"agents"},{"id":"2604.07755","title":"An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.15663","title":"CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval","created":"2026-04-17","cited_by_count":0,"area":"rag"},{"id":"2605.08399","title":"CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.14488","title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)","created":"2026-05-14","cited_by_count":0,"area":"rag"},{"id":"2606.22778","title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","created":"2026-06-22","cited_by_count":0,"area":"rag"},{"id":"2608.19957","title":"Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encoder","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.20195","title":"From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2609.01865","title":"ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval","created":"2026-09-01","cited_by_count":0,"area":"rag"},{"id":"2609.08355","title":"RepoNav: From Snippet Retrieval to File-Centered Repository Navigation for Code Agents","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.09865","title":"Keep Evaluation Fair: Detecting Data Leakage in Code Generation Benchmarks via Membership Inference Attacks","created":"2026-09-09","cited_by_count":0,"area":"safety"},{"id":"2609.32081","title":"Toward Interactive Understanding of Code APIs","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2610.02438","title":"Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}