{"total":83,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998,"area":null},{"id":"2402.01145","title":"ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution","created":"2024-02-02","cited_by_count":276,"area":null},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203,"area":null},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2406.05590","title":"NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security","created":"2024-06-08","cited_by_count":93,"area":null},{"id":"2403.11322","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","created":"2024-03-17","cited_by_count":65,"area":null},{"id":"2310.03046","title":"EcoAssistant: Using LLM Assistant More Affordably and Accurately","created":"2023-10-03","cited_by_count":49,"area":null},{"id":"2402.10890","title":"When is Tree Search Useful for LLM Planning? It Depends on the Discriminator","created":"2024-02-16","cited_by_count":47,"area":null},{"id":"2403.08604","title":"Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study","created":"2024-03-13","cited_by_count":44,"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":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31,"area":null},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"area":null},{"id":"2312.07413","title":"AI capabilities can be significantly improved without expensive retraining","created":"2023-12-12","cited_by_count":28,"area":null},{"id":"2404.08817","title":"Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance","created":"2024-04-12","cited_by_count":26,"area":null},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2604.25727","title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","created":"2026-04-28","cited_by_count":22,"area":null},{"id":"2510.17797","title":"Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics","created":"2025-10-20","cited_by_count":20,"area":null},{"id":"2309.04316","title":"Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2408.13545","title":"IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering","created":"2024-08-24","cited_by_count":19,"area":null},{"id":"2510.05318","title":"BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions","created":"2025-10-06","cited_by_count":19,"area":null},{"id":"2310.15147","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2505.05602","title":"HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics","created":"2025-05-08","cited_by_count":18,"area":null},{"id":"2504.21751","title":"CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation","created":"2025-04-30","cited_by_count":17,"area":null},{"id":"2503.11917","title":"A Framework for Evaluating Emerging Cyberattack Capabilities of AI","created":"2025-03-14","cited_by_count":16,"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":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2311.07215","title":"Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2506.17644","title":"Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges","created":"2025-06-21","cited_by_count":15,"area":null},{"id":"2510.23564","title":"ReCode: Unify Plan and Action for Universal Granularity Control","created":"2025-10-27","cited_by_count":15,"area":null},{"id":"2502.19852","title":"ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2402.12621","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2402.16181","title":"How Can LLM Guide RL? A Value-Based Approach","created":"2024-02-25","cited_by_count":13,"area":null},{"id":"2406.18294","title":"Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs","created":"2024-06-26","cited_by_count":13,"area":null},{"id":"2404.05449","title":"RoT: Enhancing Large Language Models with Reflection on Search Trees","created":"2024-04-08","cited_by_count":12,"area":null},{"id":"2605.22535","title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks","created":"2026-05-21","cited_by_count":10,"area":null},{"id":"2409.18216","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8,"area":null},{"id":"2609.04148","title":"Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments","created":"2026-09-03","cited_by_count":8,"area":null},{"id":"2403.02528","title":"DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation","created":"2024-03-04","cited_by_count":6,"area":null},{"id":"2402.03130","title":"User Centric Evaluation of Code Generation Tools","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2403.03962","title":"Identify Critical Nodes in Complex Network with Large Language Models","created":"2024-03-01","cited_by_count":5,"area":null},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"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":"2505.16505","title":"Sparse Activation Editing for Reliable Instruction Following in Narratives","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2605.02815","title":"FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2409.17166","title":"ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement","created":"2024-09-12","cited_by_count":3,"area":null},{"id":"2502.14848","title":"GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks","created":"2025-02-20","cited_by_count":3,"area":null},{"id":"2312.04736","title":"Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2507.19399","title":"Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2511.00527","title":"A Hierarchical Imprecise Probability Approach to Reliability Assessment of Large Language Models","created":"2025-11-01","cited_by_count":2,"area":null},{"id":"2604.00491","title":"Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2606.20510","title":"Efficient and Sound Probabilistic Verification for AI Agents","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2410.18312","title":"Countering Autonomous Cyber Threats","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2503.04569","title":"ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2507.03162","title":"MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Multimodal Educational Tasks","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2507.15501","title":"ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2602.16833","title":"VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2605.10966","title":"MMTB: Evaluating Terminal Agents on Multimedia-File Tasks","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.18073","title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2607.15263","title":"Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2608.13547","title":"QuoteBench: How Matched Scores Can Hide Command-Path Failures","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.24368","title":"From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2610.02710","title":"Self-Supervised Scaling of Terminal Environments for Scientific Domains","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2503.15515","title":"Towards Computer-Using Personal Agents","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2503.23053","title":"A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Tasks","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2505.18374","title":"ShIOEnv: A Command Evaluation Environment for Grammar-Constrained Synthesis and Execution Behavior Modeling","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2512.08609","title":"CogMCTS: A Novel Cognitive-Guided Monte Carlo Tree Search Framework for Iterative Heuristic Evolution with Large Language Models","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.13716","title":"ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.06543","title":"Mechanism-Faithful Queueing Simulation Model Translation with Large Language Model Support","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2603.19284","title":"CDEoH: Category-Driven Automatic Algorithm Design With Large Language Models","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.20148","title":"Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.29115","title":"unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.01764","title":"Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.25425","title":"The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.15012","title":"SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.26882","title":"PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.37686","title":"EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02460","title":"CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.20027","title":"LintEval: Benchmarking LLMs on Linter-Guided File Refactoring","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}