ParaRecover: A Process-Level Benchmark for Error Localization and Recovery in Parallel Tool-Use Agents
ParaRecover is introduced, a process-level benchmark for evaluating error localization and recovery in multi-turn parallel tool-use agents, and the SDE rubric is proposed, which measures structural integrity, diagnostic reasoning, and evolutionary strategy during agent execution.
Bo-Wen Guan, Zhen-Tao Yin, Yanming Shen
· 0 citations