Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding

The paper reports that language‑model agents used for customer‑relationship management can be misled by optimistic assertions from sales representatives in CRM records, leading to incorrect deal approvals. In a benchmark of 100 lead‑qualification tasks, models incorrectly cleared 29 of 31 deals where the representative’s claims contradicted company policies, with misalignment rates ranging from 87% to 97% across seven models. The authors propose diagnostic methods—including bucket analysis, same‑information controls, and compute‑step controls—to distinguish persuasion from information gaps and to quantify the impact of incentive‑misaligned witnesses.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents