Train Dirty, Recover Reliably: A Controlled Study of Data-Efficient Recovery Tuning for Tool Agents
Yu-Min Lee, Chong-kwon Kim, Y. Choi
· 0 citations
We have 2 of 3 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agents
An action-aware reinforcement learning method that combines a per-turn reward sequence rewarding both the discovery and commitment of gold code regions with an action-level advantage estimation scheme that isolates each action's credit by grouping turns sharing the same exploration context is proposed.
Doyeon Kim, Suyoung Bae, Yu-Min Lee et al.
· 1 citation