activity
20242026
most citedUNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types

1 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

State Representation Shapes Long-Horizon Agent Learning and Transfer: An Empirical Study

Dong Nie, Rui Lan, Yixin Nie +1

An end-to-end success rate alone cannot distinguish failure to learn an action from failure to apply it as task state changes. We study this distinction in deterministic tool workf…