ToolACE-MCP: Generalizing History-Aware Routing from MCP Tools to the Agent Web Paper • 2601.08276 • Published 5 days ago • 5
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences Paper • 2601.06789 • Published 7 days ago • 74
RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction Paper • 2601.06966 • Published 7 days ago • 6
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning Paper • 2601.06943 • Published 7 days ago • 202
DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle Paper • 2512.04324 • Published Dec 3, 2025 • 154
InteractComp: Evaluating Search Agents With Ambiguous Queries Paper • 2510.24668 • Published Oct 28, 2025 • 97
ReCode: Unify Plan and Action for Universal Granularity Control Paper • 2510.23564 • Published Oct 27, 2025 • 121
LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries Paper • 2508.15760 • Published Aug 21, 2025 • 46 • 9