Wanjia Zhao
Source-listed: Student Researcher · Google DeepMind
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- ZEBRAARENA: A Diagnostic Simulation Environment for Studying Reasoning-Action Coupling in Tool-Augmented LLMsSaved credit: First author · 2026Explore people connected to this work →
- PRISM-Physics: Causal DAG-Based Process Evaluation for Physics ReasoningSaved credit: First author · 2025Explore people connected to this work →
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal DecompositionSaved credit: Contributor · 2025Explore people connected to this work →
- DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree SearchSaved credit: Contributor · 2025Explore people connected to this work →
- DeepSeek-V3 Technical ReportSaved credit: Contributor · 2024Explore people connected to this work →