Author

Tong-Shuang Wu

h-index 7 View on Semantic Scholar

We have 2 of 18 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.

#artificial intelligence Jun 2026

OdysSim: Building Foundation Models for Human Behavior Simulation

It is shown that LLM-as-judge RL induces reward-hacking patterns, and that LLM-as-judge RL detectors can mitigate them during post-training, suggesting that behavioral foundation models require rethinking the LLM training paradigm.

Xuhui Zhou, Weiwei Sun, Weihua Du et al. · arXiv.org · 8 citations · ⚡1

Jul 2026

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation

This work creates a framework that maps agent failure modes to harness adaptation strategies, and builds a harness optimizer that automatically discovers effective adaptations from failure trajectories, suggesting that harness adaptation can expand the practical deployment range of SLM agents in routine business tasks.

Chenyang Yang, Xin-Ran Zhao, Tongshuang Wu et al. · arXiv.org · 5 citations · ⚡2