Author

Haolang Zhao

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 May 2026

EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation

EmoDistill is introduced, an offline framework for distilling emotional negotiation skills from LLM-LLM interactions into smaller language-model agents and achieves competitive utility and improves over vanilla and IQL-only baselines in most settings.

Yun-Bo Long, Hao-Lang Zhao, Lukas Beckenbauer et al. · arXiv.org · 1 citation

#artificial intelligence May 2026

VeriTrace: Evolving Mental Models for Deep Research Agents

VeriTrace is a cognitive-graph framework that explicitly implements three regulatory loops: interpretive update, deviation feedback, and schema revision, and achieves the strongest reproducible open-source result on DRB.

Haolang Zhao, Yunbo Long, Lukas Beckenbauer et al. · arXiv.org · 0 citations