Author

Jia-Yi Zhang

h-index 0 View on Semantic Scholar

We have 3 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories

In long agent executions, an early error can persist through later actions and checks, while evidence needed to trace its origin is dispersed across the history. Short histories offer limited tests of recovering error origins across substantial subsequent execution. We introduce LongRCA Bench: 1,140 complete failed tra...

Yun-Fei Zhang, Bo-Yu Feng, Changhua Pei et al. · 0 citations

#artificial intelligence Preprint Aug 2026

Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems

DUOTRACE follows a detect-before-attribute paradigm: it first detects anomalous executions and then supplies focused trajectory evidence to downstream LLM-based attribution methods, which improves agent-level and step-level attribution accuracy.

Jia-Yi Zhang, Ze-Xin Wang, DecisionMakingRon Sun et al. · 0 citations

Preprint Aug 2026

L ONG RCA B ENCH : D IAGNOSING R ESPONSIBLE R OLES AND R OOT C AUSES IN L ONG -H ORIZON A GENT F AILURES

This work introduces LongRCA Bench, comprising 1,140 failed trajectories across five domains without injected errors, and presents Root-Cause Trajectory Attribution (RCTA), a training-free method that retrieves candidate error steps from segment summaries and traces them to available earlier handoff instructions.

Yun-Fei Zhang, Bo-Yu Feng, Changhua Pei et al. · 1 citation