LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents
4.20T1 sourcearXiv cs.HC
arXiv cs.HCoriginal source ↗
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2608.18398.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryLEDGER is a tracing and review system for LLM agents that builds layered trace graphs over agent sessions. It groups trace records into Evidence Nodes and Workflow Nodes, with typed semantic edges connecting claims to supporting actions, artifacts, and validation checks for audit purposes.
Why it mattersAddresses the audit bottleneck as LLM agents take on longer workflows, offering a concrete graph structure that links claims back to the actions and artifacts that support them.
Cited by
No citations on record.