{"total":17,"rows":[{"id":"2607.20911","title":"Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2608.05013","title":"OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents","created":"2026-08-04","cited_by_count":4,"area":"agents"},{"id":"2608.10875","title":"VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2606.19787","title":"ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2608.17800","title":"StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows","created":"2026-08-18","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":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2606.25836","title":"AI Snitches Get Glitches: Towards Evading Agentic Surveillance","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2608.18050","title":"StagedWorkspace: A Versioned Workspace for Knowledge-Work Agents","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2609.15818","title":"Atria Dawn: The Dawn of Agentic Superintelligence","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.29773","title":"Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32213","title":"HM-ROUTER: Joint Model and Harness Routing for Agentic Systems","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.32616","title":"\"You're Right, Let Me Fix It\": How LLM Agents Damage Correct Work When Falsely Accused","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.00972","title":"VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.10444","title":"RunningTab: Direct Workspace Interaction with Environment-Side Tabs","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.14915","title":"WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.17953","title":"Agent-Reflex: Teaching Language Agents to Act Reflectively","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}