Technical Report: Evaluating Goal Drift in Language Model Agents
Rauno Arike, Elizabeth Donoway, Henning Bartsch, Marius Hobbhahn — 2025-05-05 — Apollo Research — arXiv
Summary
Develops and applies a novel evaluation methodology for measuring goal drift in language model agents by exposing them to competing objectives through environmental pressures over extended contexts, testing whether they maintain adherence to originally assigned goals.
Key Result
All evaluated models exhibit some degree of goal drift, with the best-performing agent (scaffolded Claude 3.5 Sonnet) maintaining nearly perfect goal adherence for over 100,000 tokens, and goal drift correlating with increasing susceptibility to pattern-matching behaviors as context length grows.
Source
- Link: https://arxiv.org/abs/2505.02709
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- capability-evals — Evals