{"total":21,"rows":[{"id":"2604.08523","title":"ClawBench: Can AI Agents Complete Everyday Online Tasks?","created":"2026-04-09","cited_by_count":33,"area":null},{"id":"2510.04491","title":"Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents","created":"2025-10-06","cited_by_count":10,"area":null},{"id":"2605.09636","title":"PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation","created":"2026-05-10","cited_by_count":8,"area":null},{"id":"2604.13064","title":"Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub","created":"2026-03-19","cited_by_count":5,"area":null},{"id":"2604.19657","title":"An AI Agent Execution Environment to Safeguard User Data","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2601.23049","title":"MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2603.15798","title":"CUBE: A Standard for Unifying Agent Benchmarks","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2603.20316","title":"Bypassing Document Ingestion: An MCP Approach to Financial Q&A","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.31308","title":"TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2608.29397","title":"AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2605.16909","title":"TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.04494","title":"Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.20058","title":"Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.26118","title":"The Open Source Economic Index of AI Adoption and Capability","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2607.25891","title":"Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.22510","title":"ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.23925","title":"MCPGen: Benchmarking LLMs on Executable MCPWorkflow Development","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.26927","title":"Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.38914","title":"Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04053","title":"The Cost of a Hop: Benchmarking NLIP and A2A","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}