PEARL reduces calendar conflict resolution errors by 55% on a new long-horizon benchmark by adding a preference memory and round-wise RL supervision to LLM agents.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning
PEARL reduces calendar conflict resolution errors by 55% on a new long-horizon benchmark by adding a preference memory and round-wise RL supervision to LLM agents.