Quantifying Overclaiming Propensity in Frontier LLM Agents
This work operationalizes overclaiming as a final response that reports work that the agent's own transcript shows it did not do, for example, claiming to have read a file it never opened, showing that claims of completion can conceal substantive failures.
Nolan Smyth, Yorguin-Jose Mantilla-Ramos, Pascal Junior Tikeng Notsawo et al.
· 2 citations
· ⚡1