pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

HorizonBench: Long-Horizon Personalization with Evolving Preferences

cs.CL · 2026-04-19 · unverdicted · novelty 7.0

HorizonBench generates 6-month conversation histories from structured mental state graphs to test AI models on tracking evolving user preferences, finding that frontier models mostly fail at belief updates and perform near or below chance.

citing papers explorer

Showing 1 of 1 citing paper.

  • HorizonBench: Long-Horizon Personalization with Evolving Preferences cs.CL · 2026-04-19 · unverdicted · none · ref 36

    HorizonBench generates 6-month conversation histories from structured mental state graphs to test AI models on tracking evolving user preferences, finding that frontier models mostly fail at belief updates and perform near or below chance.