Author

Jing-Han Wang

2 papers 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.

#artificial intelligence Preprint Mar 2026

The Trace Is the State: Exact Credit Assignment for LLM Agent Teams

C3, credit assignment by counterfactual continuation, substitutes one message at a decision point and continues the run to the terminal reward, so its credit is unbiased, exact up to Monte Carlo error.

Yan-Jun Chen, Yi-Rong Sun, Han-Lin Wang et al. · 8 citations · ⚡1

#artificial intelligence Preprint Sep 2026

Action Shaping: Policies Absorb What They Can Express

Action shaping gains the counterpart of the shaping theorem, a condition for absorption, together with the mechanism behind it and a diagnostic that reads it, together with the mechanism behind it and a diagnostic that reads it.

Yan-Jun Chen, Jing-Han Wang, Xiao-Yu Shen et al. · 0 citations