AI agents have bad taste in long-term decisions and a new benchmark proves it

Long tasks force an agent to choose which path to try, and a poor choice can look fine until the budget is spent. Researchers at Microsoft and City University of Hong Kong built Taste-Bench by freezing real agent runs where two attempts split, then asking models which branch later worked. The best model, GPT-5.6 Sol, chose correctly just under 60% of the time, and thinking longer did not help.

Summary written with AI by HowTechMoves, based on reporting by The Decoder.