{"total":21,"rows":[{"id":"2605.27922","title":"Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows","created":"2026-05-27","cited_by_count":57,"area":"agents"},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2605.14271","title":"Auditing Agent Harness Safety","created":"2026-05-14","cited_by_count":11,"area":"agents"},{"id":"2606.16748","title":"MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents","created":"2026-06-15","cited_by_count":7,"area":"agents"},{"id":"2605.14678","title":"$\\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2605.10779","title":"LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments","created":"2026-05-11","cited_by_count":5,"area":"agents"},{"id":"2604.24696","title":"NeuroClaw Technical Report","created":"2026-04-27","cited_by_count":4,"area":"agents"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2605.06110","title":"On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2605.29893","title":"Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2605.26086","title":"Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2607.26791","title":"SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2607.28037","title":"ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.26546","title":"DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2605.07110","title":"Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2609.06059","title":"DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.33017","title":"Trust and Task Completion in the World of Consumer AI Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.40284","title":"cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.14118","title":"ClawLoop: Self-Improving Agents via Harness-Native Training Loop","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.17378","title":"Get In, Decide, Prove: A Merchant-Side Readiness Benchmark for Agentic Commerce","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17816","title":"Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}