{"total":77,"rows":[{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"area":null},{"id":"2502.13138","title":"AIDE: AI-Driven Exploration in the Space of Code","created":"2025-02-18","cited_by_count":226,"area":null},{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"id":"2507.09089","title":"Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity","created":"2025-07-12","cited_by_count":101,"area":null},{"id":"2505.13259","title":"From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery","created":"2025-05-19","cited_by_count":93,"area":null},{"id":"2502.02649","title":"Fully Autonomous AI Agents Should Not be Developed","created":"2025-02-04","cited_by_count":45,"area":null},{"id":"2504.10374","title":"Ctrl-Z: Controlling AI Agents via Resampling","created":"2025-04-14","cited_by_count":44,"area":null},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"area":null},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2601.14525","title":"Towards Execution-Grounded Automated AI Research","created":"2026-01-20","cited_by_count":28,"area":null},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"id":"2606.11926","title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","created":"2026-06-10","cited_by_count":22,"area":null},{"id":"2510.26787","title":"Remote Labor Index: Measuring AI Automation of Remote Work","created":"2025-10-30","cited_by_count":20,"area":null},{"id":"2510.22780","title":"How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations","created":"2025-10-26","cited_by_count":19,"area":null},{"id":"2604.24658","title":"The Last Human-Written Paper: Agent-Native Research Artifacts","created":"2026-04-27","cited_by_count":16,"area":null},{"id":"2503.01811","title":"AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2506.22419","title":"The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements","created":"2025-06-27","cited_by_count":15,"area":null},{"id":"2606.05080","title":"AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?","created":"2026-06-03","cited_by_count":13,"area":null},{"id":"2506.08140","title":"AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists","created":"2025-06-09","cited_by_count":11,"area":null},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2605.05724","title":"Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes","created":"2026-05-07","cited_by_count":10,"area":null},{"id":"2605.19156","title":"How Far Are We From True Auto-Research?","created":"2026-05-18","cited_by_count":10,"area":null},{"id":"2607.27191","title":"Can AI agents conduct open-ended AI research? Early evidence from two case studies","created":"2026-07-29","cited_by_count":10,"area":null},{"id":"2505.06108","title":"LLMs Outperform Experts on Challenging Biology Benchmarks","created":"2025-05-09","cited_by_count":9,"area":null},{"id":"2506.03231","title":"NetArena: Dynamic Benchmarks for AI Agents in Network Automation","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2507.11810","title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","created":"2025-07-16","cited_by_count":9,"area":null},{"id":"2603.03992","title":"Measuring AI R&D Automation","created":"2026-03-04","cited_by_count":9,"area":null},{"id":"2606.04455","title":"The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?","created":"2026-06-03","cited_by_count":9,"area":null},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2602.07267","title":"BRIDGE: Predicting Human Task Completion Time From Model Performance","created":"2026-02-06","cited_by_count":6,"area":null},{"id":"2606.30182","title":"MirrorCode: AI can rebuild entire programs from behavior alone","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2510.12826","title":"Scheming Ability in LLM-to-LLM Strategic Interactions","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2608.13417","title":"Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development","created":"2026-08-13","cited_by_count":4,"area":null},{"id":"2608.17271","title":"ASI-Bench: At the Dawn of Artificial Superintelligence","created":"2026-08-18","cited_by_count":4,"area":null},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2604.00010","title":"Can LLMs Perceive Time? An Empirical Investigation","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2605.14445","title":"FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2606.05342","title":"SentinelBench: A Benchmark for Long-Running Monitoring Agents","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2505.02313","title":"What Is AI Safety? What Do We Want It to Be?","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2601.13709","title":"Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2602.17687","title":"IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2607.19321","title":"ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2608.19072","title":"What is Missing from AI Post-Training AI: An Empirical Analysis","created":"2026-08-19","cited_by_count":2,"area":null},{"id":"2609.02749","title":"Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills","created":"2026-09-02","cited_by_count":2,"area":null},{"id":"2609.06396","title":"MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves","created":"2026-09-06","cited_by_count":2,"area":null},{"id":"2505.07846","title":"Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2604.01363","title":"Crashing Waves vs. Rising Tides: Findings on AI Automation from Thousands of Worker Evaluations of Labor Market Tasks","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2606.03544","title":"SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.21891","title":"Learning the ARTS of Search for Automated Discovery","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2606.22866","title":"Discovering Crystal Structure Prediction Algorithms with an AI Co-Scientist","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2608.11341","title":"Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.36054","title":"What if automating AI R&D triggers an intelligence explosion?","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2610.04184","title":"EvalResearchBench: Can AI Agents Design Their Own Evaluations?","created":"2026-10-03","cited_by_count":1,"area":null},{"id":"2512.06006","title":"Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2604.24966","title":"Risk Reporting for Developers' Internal AI Model Use","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2607.24647","title":"Efficiency Matters in Autonomous Research","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.27283","title":"Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.05797","title":"Predicting Task Difficulty Without Rollouts","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.14903","title":"Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.14940","title":"When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.02272","title":"PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.22097","title":"Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.35236","title":"Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.40097","title":"AutoDataBench: A Data-centric Testbed for Accelerating Auto Research","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04976","title":"Priced Guidance: Can Language Models Generate Future Research Ideas?","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05398","title":"MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.06824","title":"TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08781","title":"IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.11877","title":"How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14539","title":"FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16297","title":"SLDBench v2: Active Scaling Law Discovery","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18088","title":"ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18845","title":"The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}