{"total":18,"rows":[{"id":"2604.08523","title":"ClawBench: Can AI Agents Complete Everyday Online Tasks?","created":"2026-04-09","cited_by_count":33,"area":null},{"id":"2604.18543","title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2607.21557","title":"OpenForgeRL: Train Harness-native Agents in Any Environment","created":"2026-07-23","cited_by_count":7,"area":null},{"id":"2605.29253","title":"OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2605.14133","title":"ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2606.03889","title":"RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2604.22577","title":"QuantClaw: Precision Where It Matters for OpenClaw","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2607.23524","title":"Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2608.17319","title":"Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2605.04624","title":"AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.05473","title":"Binocular Gaze Estimation with Single Camera and Single Light Source","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.33772","title":"Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36380","title":"LEGO-Anything: Coding Agents for 3D Scene Reconstruction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38923","title":"GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.14918","title":"SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17670","title":"Cowork-Gym: Synthesizing Interactive Work Environments at Scale","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18330","title":"AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}