Annotrace: A Workbench for Step-Level Annotation of Agent Traces

Abstract:Every study of why LLM agents fail begins by labelling traces by hand, and every such study builds its own throwaway tool. Observability platforms record agent traces but offer no structured labelling; annotation tools label text but have no notion of a step, a delegation or a tool call, leaving it unclear what the smallest unit of execution to label should be. Annotrace reads six trace formats, including OpenTelemetry GenAI, LangSmith and Langfuse, and turns each run into an ordered, nested list of steps. The annotator writes their own labelling codebook; a frontier model proposes a starting set from a sample of their own traces, answers first, and is asked exactly the questions the human is asked, making annotation a joint human-AI process. Annotrace measures agreement between any two annotators, human or AI. On a multi-agent question-answering corpus it reproduces a previous manual effort's 235 annotation units exactly, and two models labelling the same traces agree 91% of the time at $\kappa = 0.82$.

4 pages, 4 figures, 1 table. Under review at the AAAI 2027 Demonstration Program

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)

arXiv:2610.23284 [cs.AI]

(or arXiv:2610.23284v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.23284 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.