{"total":238,"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":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195,"area":"agents"},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564,"area":"agents"},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315,"area":"agents"},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297,"area":"agents"},{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282,"area":"agents"},{"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":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205,"area":"agents"},{"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":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177,"area":"lr"},{"id":"2504.03601","title":"APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay","created":"2025-04-04","cited_by_count":167,"area":"agents"},{"id":"2401.05507","title":"InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks","created":"2024-01-10","cited_by_count":140,"area":"agents"},{"id":"2310.10634","title":"OpenAgents: An Open Platform for Language Agents in the Wild","created":"2023-10-16","cited_by_count":137,"area":"agents"},{"id":"2406.12814","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","created":"2024-06-18","cited_by_count":120,"area":"agents"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"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":"2401.07128","title":"EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records","created":"2024-01-13","cited_by_count":78,"area":"lr"},{"id":"2505.20732","title":"SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution","created":"2025-05-27","cited_by_count":73,"area":"agents"},{"id":"2310.06830","title":"Lemur: Harmonizing Natural Language and Code for Language Agents","created":"2023-10-10","cited_by_count":72,"area":"agents"},{"id":"2311.05657","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","created":"2023-11-09","cited_by_count":72,"area":"agents"},{"id":"2403.11322","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","created":"2024-03-17","cited_by_count":65,"area":null},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61,"area":"agents"},{"id":"2503.14023","title":"Synthetic Data Generation Using Large Language Models: Advances in Text and Code","created":"2025-03-18","cited_by_count":61,"area":"synth"},{"id":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58,"area":"agents"},{"id":"2407.10956","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","created":"2024-07-15","cited_by_count":56,"area":"agents"},{"id":"2410.07706","title":"AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories","created":"2024-10-10","cited_by_count":56,"area":"agents"},{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54,"area":"synth"},{"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":"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":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2506.23719","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning","created":"2025-06-30","cited_by_count":46,"area":"lr"},{"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":"2505.15216","title":"BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems","created":"2025-05-21","cited_by_count":40,"area":"agents"},{"id":"2405.19425","title":"Adaptive In-conversation Team Building for Language Model Agents","created":"2024-05-29","cited_by_count":39,"area":"agents"},{"id":"2407.01511","title":"CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents","created":"2024-07-01","cited_by_count":39,"area":"mllm"},{"id":"2402.12914","title":"Large Language Model-based Human-Agent Collaboration for Complex Task Solving","created":"2024-02-20","cited_by_count":38,"area":"agents"},{"id":"2410.18963","title":"OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning","created":"2024-10-24","cited_by_count":38,"area":"lr"},{"id":"2410.07869","title":"Benchmarking Agentic Workflow Generation","created":"2024-10-10","cited_by_count":37,"area":"agents"},{"id":"2502.00675","title":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration","created":"2025-02-02","cited_by_count":37,"area":"agents"},{"id":"2508.17281","title":"From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users","created":"2025-08-24","cited_by_count":32,"area":"agents"},{"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":"2409.01392","title":"ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems","created":"2024-09-02","cited_by_count":30,"area":"agents"},{"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":"2604.17870","title":"GraSP: Graph-Structured Skill Compositions for LLM Agents","created":"2026-04-20","cited_by_count":26,"area":"agents"},{"id":"2510.06186","title":"RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback","created":"2025-10-07","cited_by_count":25,"area":"alignment"},{"id":"2410.05434","title":"Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback","created":"2024-10-07","cited_by_count":24,"area":"agents"},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2603.03823","title":"SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration","created":"2026-03-04","cited_by_count":23,"area":"agents"},{"id":"2402.12317","title":"EVOR: Evolving Retrieval for Code Generation","created":"2024-02-19","cited_by_count":22,"area":"rag"},{"id":"2604.25727","title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","created":"2026-04-28","cited_by_count":22,"area":null},{"id":"2405.07990","title":"Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots","created":"2024-05-13","cited_by_count":21,"area":"mllm"},{"id":"2411.05651","title":"LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution","created":"2024-11-08","cited_by_count":20,"area":"agents"},{"id":"2502.10931","title":"D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security","created":"2025-02-15","cited_by_count":20,"area":"agents"},{"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":"2512.18950","title":"Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement","created":"2025-12-22","cited_by_count":20,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"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":"2505.00234","title":"Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks","created":"2025-05-01","cited_by_count":19,"area":"agents"},{"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":"2501.16466","title":"Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks","created":"2025-01-27","cited_by_count":17,"area":"safety"},{"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":"2603.21489","title":"Effective Strategies for Asynchronous Software Engineering Agents","created":"2026-03-23","cited_by_count":16,"area":"agents"},{"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":"2507.14201","title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","created":"2025-07-14","cited_by_count":15,"area":"agents"},{"id":"2508.18370","title":"Training Language Model Agents to Find Vulnerabilities with CTF-Dojo","created":"2025-08-25","cited_by_count":15,"area":"agents"},{"id":"2510.23564","title":"ReCode: Unify Plan and Action for Universal Granularity Control","created":"2025-10-27","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":"2412.02776","title":"Hacking CTFs with Plain Agents","created":"2024-12-03","cited_by_count":14,"area":"agents"},{"id":"2502.19852","title":"ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2603.11214","title":"Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios","created":"2026-03-11","cited_by_count":14,"area":"agents"},{"id":"2606.01619","title":"ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL","created":"2026-06-01","cited_by_count":14,"area":"agents"},{"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":"2511.09586","title":"Environment Scaling for Interactive Agentic Experience Collection: A Survey","created":"2025-11-12","cited_by_count":13,"area":"agents"},{"id":"2512.20798","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","created":"2025-12-23","cited_by_count":13,"area":"agents"},{"id":"2310.18239","title":"Fine-Tuning Language Models Using Formal Methods Feedback","created":"2023-10-27","cited_by_count":12,"area":"alignment"},{"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":"2410.09114","title":"Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities","created":"2024-10-10","cited_by_count":12,"area":"agents"},{"id":"2506.10764","title":"OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems","created":"2025-06-12","cited_by_count":12,"area":"agents"},{"id":"2508.05674","title":"Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark","created":"2025-08-05","cited_by_count":12,"area":"agents"}],"next_cursor":"100"}