{"total":76,"rows":[{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85,"area":"agents"},{"id":"2505.11942","title":"LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners","created":"2025-05-17","cited_by_count":78,"area":"agents"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2409.13082","title":"AutoVerus: Automated Proof Generation for Rust Code","created":"2024-09-19","cited_by_count":49,"area":null},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2410.03131","title":"Code Comprehension then Auditing for Unsupervised LLM Evaluation","created":"2024-10-04","cited_by_count":32,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2408.13001","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","created":"2024-08-23","cited_by_count":31,"area":"lr"},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","cited_by_count":20,"area":null},{"id":"2506.09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","created":"2025-06-10","cited_by_count":20,"area":null},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2505.21577","title":"RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2502.01619","title":"Learning to Generate Unit Tests for Automated Debugging","created":"2025-02-03","cited_by_count":17,"area":null},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16,"area":null},{"id":"2508.16763","title":"WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation","created":"2025-08-22","cited_by_count":16,"area":null},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"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":"2510.21903","title":"TOM-SWE: User Mental Modeling For Software Engineering Agents","created":"2025-10-24","cited_by_count":13,"area":"agents"},{"id":"2404.08877","title":"Aligning the Objective of LLM-based Program Repair","created":"2024-04-13","cited_by_count":12,"area":null},{"id":"2504.19093","title":"CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges","created":"2025-04-27","cited_by_count":11,"area":"lr"},{"id":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2406.01359","title":"R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models","created":"2024-06-03","cited_by_count":9,"area":null},{"id":"2409.19715","title":"Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code","created":"2024-09-29","cited_by_count":9,"area":"alignment"},{"id":"2504.14640","title":"Risk Assessment Framework for Code LLMs via Leveraging Internal States","created":"2025-04-20","cited_by_count":9,"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":"2503.20576","title":"Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Models","created":"2025-03-26","cited_by_count":7,"area":"lr"},{"id":"2504.19277","title":"Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling","created":"2025-04-27","cited_by_count":7,"area":"agents"},{"id":"2606.17056","title":"The Value Axis: Language Models Encode Whether They're on the Right Track","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2404.09356","title":"LLeMpower: Understanding Disparities in the Control and Access of Large Language Models","created":"2024-04-14","cited_by_count":5,"area":null},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2604.08016","title":"Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs","created":"2026-04-09","cited_by_count":5,"area":"lr"},{"id":"2607.02032","title":"PACE: A Proxy for Agentic Capability Evaluation","created":"2026-07-02","cited_by_count":5,"area":"agents"},{"id":"2410.11096","title":"SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2502.16071","title":"Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models","created":"2025-02-22","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":"2504.04372","title":"Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models","created":"2025-04-06","cited_by_count":4,"area":null},{"id":"2504.14681","title":"An LLM-enabled Multi-Agent Autonomous Mechatronics Design Framework","created":"2025-04-20","cited_by_count":4,"area":"agents"},{"id":"2505.15356","title":"NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2507.03156","title":"The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2508.16678","title":"Cognitive Agents Powered by Large Language Models for Agile Software Project Management","created":"2025-08-21","cited_by_count":4,"area":"agents"},{"id":"2510.01409","title":"OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Models","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2606.31511","title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2406.09891","title":"Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2409.04114","title":"Multi-Programming Language Ensemble for Code Generation in Large Language Model","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2506.13824","title":"MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2507.08719","title":"Multilingual Multimodal Software Developer for Code Generation","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2502.10696","title":"Improving Retrieval-Augmented Deep Assertion Generation via Joint Training","created":"2025-02-15","cited_by_count":2,"area":"rag"},{"id":"2509.10436","title":"RefactorCoderQA: Benchmarking LLMs for Multi-Domain Coding Question Solutions in Cloud and Edge Deployment","created":"2025-09-12","cited_by_count":2,"area":"moe"},{"id":"2603.15921","title":"VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2604.17338","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2506.11007","title":"Impact of Comments on LLM Comprehension of Legacy Code","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2601.04540","title":"AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2604.06747","title":"TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.12898","title":"BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design","created":"2026-04-14","cited_by_count":1,"area":null},{"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":"2605.19330","title":"MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2605.30628","title":"The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.24689","title":"Automated Summarization of Software Documents: An LLM-based Multi-Agent Approach","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2610.04184","title":"EvalResearchBench: Can AI Agents Design Their Own Evaluations?","created":"2026-10-03","cited_by_count":1,"area":null},{"id":"2410.02156","title":"The why, what, and how of AI-based coding in scientific research","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2505.17481","title":"MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning","created":"2025-05-23","cited_by_count":0,"area":"lr"},{"id":"2507.12482","title":"Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2510.18911","title":"Prospects for Using Artificial Intelligence to Understand Intrinsic Kinetics of Heterogeneous Catalytic Reactions","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.08052","title":"Dual-Process Scaffold Reasoning for Enhancing LLM Code Debugging","created":"2025-11-11","cited_by_count":0,"area":"lr"},{"id":"2512.18456","title":"SoK: Understanding (New) Security Issues Across AI4Code Use Cases","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2512.21238","title":"Assessing the Software Security Comprehension of Large Language Models","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.06497","title":"Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs During Code Adaptation","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2602.16038","title":"Heuristic Search as Language-Guided Program Optimization","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2605.04624","title":"AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.14539","title":"Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2608.14863","title":"Evaluating Agentic Code Repair Capabilities in Distributed Systems","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2609.01603","title":"Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.29410","title":"Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.18755","title":"PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}