From Agent Traces to Trust: Evidence Tracing and Execution Provenance in LLM Agents 事件

From Agent Traces to Trust: Evidence Tracing and Execution Provenance in LLM Agents arXiv:2606.04990v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly solve complex tasks by interacting with external tools, retrieval systems, memory modules, environments, and other agents. These capabilities expand agent autonomy, but also make agent behavior harder to verify, debug, and audit. Final-answer accuracy alone cannot explain how an output was produced, which evide