GraphEcho: Structural Redundancy and Evidence Provenance in LLM Graph Agents
arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without acquiring more independent evidence. GraphEcho tests whether agents mistake these repeated encounters for additional...
Read more: https://arxiv.org/abs/2609.17695
Scan with your phone
Scan with your phone