AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
KDD 2026 (CCF-A). A benchmark for diagnosing step-level process quality in tool-using agents.
shengda-fan
KDD 2026 (CCF-A). A benchmark for diagnosing step-level process quality in tool-using agents.
KDD 2026 (CCF-A). A benchmark for diagnosing step-level process quality in tool-using agents.
ArXiv 2025. First author. Unified evaluation platform for tool-learning agents.
ArXiv 2025. First author. Unified evaluation platform for tool-learning agents.