{"total":16,"rows":[{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815,"area":null},{"id":"2602.23166","title":"AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios","created":"2026-02-26","cited_by_count":23,"area":null},{"id":"2605.16679","title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2608.16798","title":"ClawGym II: Exploring Black-Box RL on Agent Harness","created":"2026-08-17","cited_by_count":2,"area":null},{"id":"2608.01604","title":"Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.20634","title":"AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale","created":"2026-08-21","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":"2609.32192","title":"CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2605.14322","title":"Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows","created":"2026-05-14","cited_by_count":0,"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":"2606.20058","title":"Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.27354","title":"PAUSE: A User-Centric Benchmark for Personal AI Assistants in Unified Service Environments","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.12475","title":"Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.01306","title":"DAYJOB: A Benchmark for Long-Horizon Professional Work","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04991","title":"CIPO: Counterfactual Imagination Policy Optimization for Adaptive Tool Granularity Selection","created":"2026-10-04","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}