AgenTracer-v2: Agentic Failure Tracer for LLM Agentic Systems

LLM-powered agentic systems increasingly operate across complex, long-horizon task regimes, yet their growing architectural complexity has intensified system-level fragility and failure rates. The task of agentic failure attribution seeks to identify the specific agent or execution step that causes failure within lengthy traces. However, most existing approaches remain constrained to passive, full-trajectory analysis, which limits their effectiveness in ultra-long and dynamically evolving trajectory attributions. To address this limitation, we introduce AgenTracer-v2, an autonomous, multi-hop failure attribution agent that reconceptualizes tracing as an active, tool-augmented diagnostic process. Concretely, we develop Tracer-Flywheel, a framework-agnostic data synthesis engine with deterministic system rollback, yielding an 8K dataset of precisely annotated failure trajectories. Leveraging this supervision, AgenTracer-v2 is trained to perform token-efficient global summarization, targeted inward inspection, and outward exploration via integrated diagnostic tools. Extensive experiments demonstrate that AgenTracer-v2 (I) consistently surpasses proprietary models such as GPT-5.2 and Gemini-3-Pro, as well as prior specialized tracers, by up to 21.83% in attribution accuracy, (II) maintains robust performance on ultra-long trajectories exceeding 300K tokens and (III) delivering corrective feedback that measurably improves downstream agentic systems and multi-LLM reinforcement training.