{"total":15,"rows":[{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2602.05843","title":"OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2602.10525","title":"LHAW: Controllable Underspecification for Long-Horizon Tasks","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2510.15966","title":"PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency","created":"2025-10-12","cited_by_count":3,"area":null},{"id":"2604.15715","title":"GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2606.05342","title":"SentinelBench: A Benchmark for Long-Running Monitoring Agents","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2604.02522","title":"Opal: Private Memory for Personal AI","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2607.19865","title":"DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.05263","title":"OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2602.00456","title":"Benchmarking Agents in Insurance Underwriting Environments","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2606.10956","title":"Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.01245","title":"Office Comprehension Benchmark","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.20844","title":"Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2610.18603","title":"AgentStripes: An Evidence-Graded Maturity Model for AI Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}