{"total":141,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501,"area":"agents"},{"id":"2506.21506","title":"Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge","created":"2025-06-26","cited_by_count":76,"area":"agents"},{"id":"2509.08755","title":"AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning","created":"2025-09-10","cited_by_count":72,"area":"agents"},{"id":"2506.15740","title":"SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents","created":"2025-06-17","cited_by_count":71,"area":"agents"},{"id":"2512.12730","title":"NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents","created":"2025-12-14","cited_by_count":65,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2601.08536","title":"DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports","created":"2026-01-13","cited_by_count":34,"area":"agents"},{"id":"2602.10975","title":"FeatureBench: Benchmarking Agentic Coding for Complex Feature Development","created":"2026-02-11","cited_by_count":34,"area":"agents"},{"id":"2602.11964","title":"Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments","created":"2026-02-12","cited_by_count":33,"area":"agents"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2505.14148","title":"MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem","created":"2025-05-20","cited_by_count":25,"area":"agents"},{"id":"2508.18993","title":"GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging","created":"2025-08-26","cited_by_count":25,"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":"2510.27598","title":"InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research","created":"2025-10-31","cited_by_count":19,"area":"agents"},{"id":"2605.26340","title":"ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence","created":"2026-05-25","cited_by_count":19,"area":"agents"},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2604.13018","title":"Toward Autonomous Long-Horizon Engineering for ML Research","created":"2026-04-14","cited_by_count":17,"area":"agents"},{"id":"2606.07591","title":"ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research","created":"2026-05-28","cited_by_count":17,"area":"agents"},{"id":"2512.07921","title":"DeepCode: Open Agentic Coding","created":"2025-12-08","cited_by_count":16,"area":"agents"},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2603.21489","title":"Effective Strategies for Asynchronous Software Engineering Agents","created":"2026-03-23","cited_by_count":16,"area":"agents"},{"id":"2604.12290","title":"Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization","created":"2026-04-14","cited_by_count":16,"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":"2602.07962","title":"LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth","created":"2026-02-08","cited_by_count":14,"area":"agents"},{"id":"2506.19724","title":"From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking","created":"2025-06-24","cited_by_count":12,"area":"agents"},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2605.30329","title":"SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?","created":"2026-05-28","cited_by_count":12,"area":"agents"},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"id":"2510.24591","title":"ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?","created":"2025-10-28","cited_by_count":11,"area":"agents"},{"id":"2511.08522","title":"AlphaResearch: Accelerating New Algorithm Discovery with Language Models","created":"2025-11-11","cited_by_count":11,"area":"agents"},{"id":"2604.00594","title":"Agent psychometrics: Task-level performance prediction in agentic coding benchmarks","created":"2026-04-01","cited_by_count":11,"area":"agents"},{"id":"2608.09096","title":"Evo-Bench: Can Language Models Improve Agent Harness?","created":"2026-08-10","cited_by_count":11,"area":"agents"},{"id":"2608.20318","title":"AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement","created":"2026-08-20","cited_by_count":11,"area":"agents"},{"id":"2609.26457","title":"Recursive self-improvement of AI research agents","created":"2026-09-22","cited_by_count":11,"area":"agents"},{"id":"2506.01839","title":"Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research","created":"2025-06-02","cited_by_count":10,"area":"agents"},{"id":"2606.24530","title":"NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?","created":"2026-06-23","cited_by_count":10,"area":"agents"},{"id":"2506.06214","title":"Can Theoretical Physics Research Benefit from Language Agents?","created":"2025-06-06","cited_by_count":9,"area":"agents"},{"id":"2601.20613","title":"AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios","created":"2026-01-28","cited_by_count":9,"area":"agents"},{"id":"2605.00803","title":"Can Coding Agents Reproduce Findings in Computational Materials Science?","created":"2026-05-01","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2604.05013","title":"Scaling Coding Agents via Atomic Skills","created":"2026-04-06","cited_by_count":8,"area":"agents"},{"id":"2605.08956","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","created":"2026-05-09","cited_by_count":8,"area":"agents"},{"id":"2606.20659","title":"Skill Coverage: A Test Adequacy Metric for Agent Skills","created":"2026-06-09","cited_by_count":8,"area":"agents"},{"id":"2608.14905","title":"How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks","created":"2026-08-14","cited_by_count":8,"area":"agents"},{"id":"2508.02921","title":"PentestJudge: Judging Agent Behavior Against Operational Requirements","created":"2025-08-04","cited_by_count":7,"area":"agents"},{"id":"2604.17406","title":"EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale","created":"2026-04-19","cited_by_count":7,"area":"agents"},{"id":"2605.13950","title":"Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2606.31651","title":"FARS: A Fully Automated Research System Deployed at Scale","created":"2026-06-30","cited_by_count":7,"area":"agents"},{"id":"2603.17104","title":"When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding Agents","created":"2026-03-17","cited_by_count":6,"area":"agents"},{"id":"2605.14892","title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2605.20563","title":"Multi-agent Collaboration with State Management","created":"2026-05-19","cited_by_count":6,"area":"agents"},{"id":"2606.05238","title":"DeployBench: Benchmarking LLM Agents for Research Artifact Deployment","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2606.11447","title":"AI Coding Agents Can Reproduce Social Science Findings","created":"2026-06-09","cited_by_count":6,"area":"agents"},{"id":"2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","created":"2026-06-16","cited_by_count":6,"area":"agents"},{"id":"2607.12835","title":"Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction","created":"2026-07-14","cited_by_count":6,"area":"agents"},{"id":"2604.17745","title":"HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution","created":"2026-04-20","cited_by_count":5,"area":"agents"},{"id":"2604.21965","title":"Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results","created":"2026-04-23","cited_by_count":5,"area":"agents"},{"id":"2605.15871","title":"Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design","created":"2026-05-15","cited_by_count":5,"area":"agents"},{"id":"2607.20468","title":"InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents","created":"2026-05-20","cited_by_count":5,"area":"agents"},{"id":"2608.25286","title":"BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks","created":"2026-08-26","cited_by_count":5,"area":"agents"},{"id":"2602.08561","title":"Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches","created":"2026-02-09","cited_by_count":4,"area":"agents"},{"id":"2602.17547","title":"KLong: Training LLM Agent for Extremely Long-horizon Tasks","created":"2026-02-19","cited_by_count":4,"area":"agents"},{"id":"2603.22767","title":"Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2605.15846","title":"RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades","created":"2026-05-15","cited_by_count":4,"area":"agents"},{"id":"2606.01961","title":"AutoMedBench: Towards Medical AutoResearch with Agentic AI Models","created":"2026-06-01","cited_by_count":4,"area":"agents"},{"id":"2606.31551","title":"AutoTrainess: Teaching Language Models to Improve Language Models Autonomously","created":"2026-06-30","cited_by_count":4,"area":"agents"},{"id":"2608.11727","title":"Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents","created":"2026-08-12","cited_by_count":4,"area":"agents"},{"id":"2609.04280","title":"EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?","created":"2026-09-03","cited_by_count":4,"area":"agents"},{"id":"2603.00805","title":"NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code","created":"2026-02-28","cited_by_count":3,"area":"agents"},{"id":"2607.07774","title":"ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents","created":"2026-07-08","cited_by_count":3,"area":"agents"},{"id":"2609.20152","title":"MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2507.08038","title":"AblationBench: Evaluating Automated Planning of Ablations in Empirical AI Research","created":"2025-07-09","cited_by_count":2,"area":"agents"},{"id":"2508.16571","title":"LLM-Based Agents for Competitive Landscape Mapping in Drug Asset Due Diligence","created":"2025-08-22","cited_by_count":2,"area":"agents"},{"id":"2603.17216","title":"ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated Environments","created":"2026-03-17","cited_by_count":2,"area":"agents"},{"id":"2603.20101","title":"Pitfalls in Evaluating Interpretability Agents","created":"2026-03-20","cited_by_count":2,"area":"agents"},{"id":"2604.12198","title":"Grounded autonomous scrutiny at scale: emergent critique from reproduction of published computational physics papers","created":"2026-04-14","cited_by_count":2,"area":"agents"},{"id":"2604.20200","title":"Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows","created":"2026-04-22","cited_by_count":2,"area":"agents"},{"id":"2605.28371","title":"From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2606.18237","title":"ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2606.18356","title":"SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2608.13060","title":"VALG: An Agentic System for ML Theory Research","created":"2026-08-13","cited_by_count":2,"area":"agents"},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2608.26195","title":"Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2609.04611","title":"$\\tau^\\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction","created":"2026-09-04","cited_by_count":2,"area":"agents"},{"id":"2609.11117","title":"Overview of the NLPCC 2026 Shared Task 11: Agent-Based Experiment Reproduction from Scientific Papers","created":"2026-09-10","cited_by_count":2,"area":"agents"},{"id":"2609.19801","title":"DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum","created":"2026-09-17","cited_by_count":2,"area":"agents"},{"id":"2602.21480","title":"Both Ends Count! Just How Good are LLM Agents at \"Text-to-Big SQL\"?","created":"2026-02-25","cited_by_count":1,"area":"agents"},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2605.02651","title":"ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-Review","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2605.12808","title":"Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse","created":"2026-05-12","cited_by_count":1,"area":"agents"},{"id":"2606.02006","title":"An Agentic Approach Towards Replication Package Quality Evaluation","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2606.07718","title":"A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2606.10933","title":"Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.11456","title":"AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.19899","title":"Measuring Biological Capabilities and Risks of AI Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2606.31478","title":"One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.27518","title":"Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2608.24252","title":"SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}