Author

Baolin Peng

View on Semantic Scholar

1 paper indexed here

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.

Preprint Jul 2026

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents

On long-horizon complex search, TRACE substantially improves base-model tool-use ability using pure RL, without a cold-start supervised fine-tuning stage, an agentic mid-training stage, or training on live-web data.

Leitian Tao, Baolin Peng, Wenlin Yao et al. · 4 citations